PROGRAMME DETAILS BOTH W/O AND WITH ABSTRACT …fyp.upm.edu.my/icicse2018/Programme_Details.pdf · Nur Azaliah Abu Bakar and Surya . ... Nurfadhlina Mohd Sharef, Iskandar Ishak, Maslina

The International Conference on Innovations in Computer Science and Engineering, 2018(ICiCSE2018) 1

PROGRAMME DETAILS – BOTH W/O AND WITH ABSTRACT INFORMATION

(UPDATED ON 26/7/2018 – 4.15PM)

(1)PROGRAMME DETAILS WITHOUT ABSTRACT

SPEAKERS

30th July 2018

Time Activity Event

8:00 – 8.45 am Registration

Ballroom Foyer

8.45 – 9:30 am Opening Ceremony Ballroom 1

9.30– 10:00 am Photo Session and Coffee Break Ballroom Foyer

10:00 – 10:50 am Keynote speaker 1 Prof. Dr. Jemal H. Abawajy

Deakin University, Australia

Ballroom 1

10:50 – 11:30 am Industry Talk Tengku Shahrizam bin Tengku Abdullah

Sulaiman Cisco System (Malaysia)

Ballroom 1

11:30 – 1:00 pm Parallel Session 1 Session 1A: Ballroom 1 Session 1B : Kenyalang Session 1C: Engseng

1:00 – 2:00 pm Lunch Waterfront The

2:00 – 5.00pm Tutorial Deep Learning

Ballroom 1

5.00pm Tea Break

Ballroom Foyer

7.00pm Dinner Ballroom 3

31st July 2018

8.00 – 8.40am Registration Ballroom Foyer

8.40-10.40am

Parallel Session 2

Session 2A: Ballroom 1 Session 2B : Kenyalang

Session 2C: Engseng

10.40 – 10.50am Break

Ballroom Foyer

10.50-11.40am Keynote speaker 2 Prof. Dr. Sung-Bae Cho

Yonsei University, Seoul, Korea

Ballroom 1

11.40 – 1.00pm

Parallel Session 3 Session 3A: Ballroom 1 Session 3B : Kenyalang

Session 3C: Enseng

PROGRAMME


1.00 – 2.00pm Lunch Waterfront Café

2.00 -5.00pm Parallel Session 4 Session 4A: Ballroom 1 Session 4B : Kenyalang

Session 4C: Engseng

5.00pm Tea Break

Ballroom Foyer

Session 1A, 11:30 – 1:00 pm (30 July 2018)

Ballroom 1 (SEIS)

Session Chair : Dr. Masnida Hussin No. Paper ID Title of Paper Author

1

8 Comparing Web Vulnerability Scanners with

a New Method for SQL Injection

Vulnerabilities Detection and Removal

EPSQLiFix

Kabir Umar, Abu Bakar Md Sultan,

Hazura Zulzalil, Novia Admodisastro

and Mohd Taufik Abdullah

2 131 A Study of Web Design for Customer Billing

Telephony System Using User Experience

(UX) Approach

Noraini Che Pa, Raziera Bidin and

Azrina Kamaruddin

3 21 Real Time Productivity Monitoring System

for Small and Medium Size Manufacturing

Industry

Wong Phaik-Ean, Nasuha Lee

Abdullah, Rosnah Idrus and Pantea

Keikhosrokiani

4 23 Towards Employing Metrics in Measuring

the Quality of Software Safety Critical

Systems and Managing Their Development

Jamilah Din, Rodziah Atan, Yusmadi

Yah Jusoh and Muhammed Basheer

Jasser

5 25 Design and Development of Topic-Based

Students’ Knowledge Modelling System

using Fuzzy Set Theory and Visual Analytics

Wen Thing Ng, Chee Siong The and

Chwen Jen Chen

6 33 Enhanced Bring Your Own Device (BYOD)

Environment Security Based On Blockchain

Technology

Fara Jamal, Mohd Taufik Abdullah,

Azizol Abdullah and Zurina Mohd

Hanapi

Session 1B, 11:30 – 1:00 pm (30 July 2018)

Kenyalang (AIBD)

Session Chair : Dr. Hazlina Hamdan No. Paper ID Title of Paper Author

DETAILS SESSION PROGRAMME


1 7 Identifying the most effective feature

category in machine learning-based

phishing website detection

Choon Lin Tan, Kang Leng Chiew,

Nadianatra Musa and Dayang

Hanani Abang Ibrahim

2 9 Building standard offline anti-phishing

dataset for benchmarking

Kang Leng Chiew, Ee Hung Chang,

Choon Lin Tan, Johari Abdullah and

Kelvin Sheng Chek Yong

3 14 Solving Classification Problem Using

Ensemble Binarization Classifier

M.N. Shah Zainudin, Md. Nasir

Sulaiman , Norwati Musapha,

Thinagaran Perumal1 and Raihani

Mohamed

4. 15 Case Study of UPNM Students Performance

Classification Algorithms

Syarifah B. Rahayu, Nur D.

Kamarudin and Zuraini Zainol

5 35 Role Minimization as An Optimization

Metric in Role Mining Algorithms: A

Systematic Review

Nazirah Abd Hamid, Rabiah Ahmad

and Siri Rahayu Selamat

6. 45 Evaluation of Weighted Based Algorithm for

Android Malware Detection

Nurul Hidayah Mazlan and Isredza

Rahmi A Hamid

Session 1C, 11:30 – 1:00 pm (30 July 2018)

Engseng (CNDS)

Session Chair : Dr. Abdullah Muhammed

No. Paper ID Title of Paper Author

1. 22 Replication Strategies For Big Data In Cloud

Environment Fazlina Mohd Ali and Rohaya Latip

2. 28 Load Management Evaluation of Hbase and Cassandra Databases Using YCSB

Ali Y. Aldailamy, Abdullah Muhammed, Waidah Ismail and Abduljalil Radman

3. 71 A Super-Peer Approach for Scalable Collaborative Intrusion Detection Network (CIDN)

Yousef Bakhdlaghi, Nur Izura Udzir, Azizol Abdullah and Nor Fazlida Mohd Sani

4. 91 Optimizing the Space Utilization in Real-time Flash Translation Layer Mapping Scheme

Mohd Bazli Ab. Karim, Amir Rizaan Abdul Rahiman, Rohaya Latip and Hamidah Ibrahim


5. 119 An Empirical Study of the Performance Analysis Between Quantum Computers and Silicon Computers

Mohd Aisar M.M.I, Dr Shukor Sanim Mohd Fauzi, Dr Hanif Baharin, Wan Asma Wan Mohammad Sobri, Anjila .J. Suali, Ray Adderley Jm Gining, Muhammad Nabil Fikri Jamaluddin and Mohd Helmy Abdul Wahab

6. 128 Efficient Energy Management in Cloud Data Center: An Analysis of DVFS towards Cloud Applications

Joshua Samual and Masnida Hussin

Session 2A, 8:40 – 10:40am (31 July 2018)

Ballroom 1 (SEIS)

Session Chair : Dr. Noraini Che Pa


1. 38 An Automated Test Case Generating Tool

Using UML Activity Diagram

Md Abdul Monim and Rozi Nor

Haizan Nor

2. 73 Educators’ Readiness in Using Mobile Phone

as a Pedagogical Tool for Teaching

Siti Nur’ain Hamsan and Maslina

Abdul Aziz

3. 52 Applying Agile Concepts from Software

Development into the Design of Flood

Disaster Management Framework

Mohamad Firdaus Mat Saad, Aliza

Abdul Latif, Marini Othman and

Mohd Saiful Anuar Mohd Noor

4. 57 The Enterprise Resource Planning System

and Human Influences on Perceived

Business Benefits

Jiansi Lim, Norshidah Mohamed

and Nor Shahriza Abdul Karim

5. 62 An Iris Image Thresholding Based on

Binarization Threshold in Black Hole Search

Method

Muktar Danlami, Sofia Najwa

Ramli, Zahraddeen Pindar, Sapiee

Jamel and Mustafa Mat Deris

6. 120 The Role of Employee in Information

Security Risk Management

David Lau Kiat Jin, Noor Hafizah

Hassan, Nurazean Maarop,

Ganthan Narayana Samy and

Rasimah Che Mohd Yusoff

7. 68 A model on multiple perspectives of citizens’

trust in using social media for e-government

services

Sohrab Khan, Nor Zairah Ab. Rahim

and Nurazean Maarop

8. 70 Understanding the Factors that Affect

Information Technology Outsourcing of

Government Shared Services

Fadzilah Ahmad, Nurazean Maarop

and Nurulhuda Firdaus Mohd Azmi


Session 2B, 8:40 – 10:40 am (31 July 2018)

Kenyalang (AIBD)

Session Chair : Assoc. Prof. Dr. Nurfadhlina Mohd Sharef No. Paper ID Title of Paper Author

1. 44 Systematic review on ear identification Ahmed Alemran, Dr. Bahbibi Binti

Rahmatullah and Ali Hadi

2. 49 Multi-objective PSO-fuzzy Optimization

Approach to Improve Interpretability and

Accuracy in Medical Data

Alwatben Batoul Rashed, Hazlina

Hamdan, Md Nasir Bin Sulaiman,

Nurfadhlina Binti Mohd Sharef and

Razali Bin Yaakob

3. 58 An Artificial Immune System Approach For

Type E Assembly Line Balancing Problem

Mohd Nor Akmal Khalid, Umi

Kalsom Yusof and Zarul Fitri Zaaba

4. 59 A Hybrid Feature Selection Technique for

Classification of Group-based Holy Quran

verses

A. Adeleke and N. Samsudin

5. 60 A Review on Z-numbers Saeed Bahrami, Razali Bin Yaakob,

Azreen Azman and Rodziah Atan

6. 138 Know Your Hotel well!- An online Review

Analysis using Text Analytics

Angela Lee, Zaharin Yusoff and

Zuraini Zainol

7. 67 A Study on Detecting Misleading Online

News Using Bigram

Normala Che Eembi Jamil, Iskandar

Ishak, Fatimah Sidi and Lilly Suriani

Affendey

8. 69 A Two Dimensional Facial Analysis for Sex

Comparison Using Morphometrics Approach

Olalekan Agbodale, Azree Shahrel

Ahmad Nazri

Session 2C, 8:40 – 10:40am (31 July 2018)

Engseng (IDMA)

Session Chair : Dr. Alfian Abdul Halin


1. 11 Speckle Filtering Method in the Gonad

Ultrasound Image for Mahseer’s fish (Tor

Tombroides)

Nurul Asmaa Abd Razak,

Hizmawati Madzin, Fatimah Khalid

and Mas Rina Mustaffa

2. 85 Fusion CLAHE-Based Image Enhancement

with Fuzzy in enhancing the quality of Field

Image

Elmaliana Albahari, Hizmawati

Madzin and Mohamad Roff Mohd

Noor


3. 65 Elderly Experience Evaluation through

Medication

Nuha Alnabit and Evi Indriasari

Mansor

4. 107 iLung: Interactive Holographic Medical

Application for Lung CT Scans using

HoloLens

Aala Al Khayer and Evi Indriasari

Mansor

5. 56 Fruits Recognition Based on Texture

Features and k-Nearest Neighbour

Nur Izzani Kamal Ariffin, Mas Rina

Mustaffa, Lili Nurliyana Abdullah

and Nurul Amelina Nasharuddin

6. 39 Using Continuous Spatial Configuration for

Bezels Issues in a Multi-mobile System

Beng Liang Ong, Rhun Ming Teo,

Noris M Norowi and Azrul Hazri

Jantan

7. 100 A Usability Evaluation of Image and Emojis in

Graphical Password

Nur Syabila Zabidi, Noris M Norowi

and Rahmita Wirza

8. 53 Designing an Expressive Virtual Kompang on

Mobile Device with Tri-axial Accelerometer

Hoo Yong Leng, Noris M Norowi

and Azrul Hazri Jantan

9 96 Designing Engaging Community Learning

Application with Children using Gamification

Norshikin Zainal Abidin, Aslina

Baharum, Syed Mohd Fairuz Syed

Mohd Dardin, Nur Shahida Ab

Fatah, Ismassabah Ismail and

Nurhafizah Moziyana Mohd Yusop

Session 3A, 11:40 – 1:00 pm (31 July 2018)

Ballroom1 (SEIS)

Session Chair : Dr. Jamilah Din No. Paper ID Title of Paper Author

1. 74 Industry Involvement to Enhance the HCI

Project-Based Learning Experience Using

User-Centered Approach

Azrina Kamaruddin , Evi Indriasari Mansor, Novia Indriaty Admodisastro, Noris Mohd Norowi and Salfarina Abdullah

2. 75 Accessibility Design Issues with Malaysian News Websites: A Case Study Using Achecker and WAVE

Mariam Azwa Yazid, Azrul Hazri Jantan, Abdul Azim Abd Ghani, Azrina Kamaruddin and Novia Admodisastro

3. 83 Enterprise Integration of Employee Onboarding Process Using Zachman Framework

Wan Faezah Abbas, Siti Hajar Ismail, Haryani Haron and Wan Nor Amalina Wan Hariri

4. 88 The Effectiveness of an Enhanced Weighted Method with a Unique Priority Value for Test Case Prioritization in Regression Testing

Asmaa Ammar, Salmi Baharom, Abdul Azim Abd Ghani and Jamilah Din


5. 97 The Significant Effect of People Factors on Enterprise Architecture Implementation

Nur Azaliah Abu Bakar and Surya Sumarni Hussein


Session 3B, 11.40 – 1.00pm (31 July 2018)

Kenyalang (AIBD)

Session Chair : Assoc. Prof. Dr. Nurfadhlina Mohd Sharef No. Paper ID Title of Paper Author

1. 76 Scoring Matrix Framework for Threat Factor Profiling Model

Maslina Daud, Sabariah Ahmad, Syafiqa Anneisa Abdullah, Naqliyah Zainuddin, Fatimah Sidi, Marzanah A. Jabar, Lilly Suriani Affendey, Nurfadhlina Mohd Sharef, Iskandar Ishak, Maslina Zolkepli, Fatin Nur Majdina Nordin, Nur Zahirah Md Noor, Norazlin Yusof, Hashimah Amat Sejani, Saiful Ramadzan Hairani, and Azizi Sabron

2. 78 Comparison of Different Feature Selection Techniques in Attribute Selection of Learning Style Prediction

Haziqah Shamsudin, Umi Kalsom Yusof and Maziani Sabudin

3. 79 A Study of Diabetic Retinopathy Classification using Support Vector Machine

Nur Izzati Ab Kader, Umi Kalsom Yusof, and Syibrah Naim

4. 93 Mobile Malware Classification Zolidah Kasiran, Norkhushaini Awang and Fatin Nurhanani Rusli

5. 95 ResQ Banjir: A mMbile Apps for Emergency Rescue, Evacuation and Relief Center Management

Muhammad Rafie Mohd Arshad

Session 3C, 11:40 – 1:00 pm (31 July 2018)

Engseng (IDMA)

Session Chair : Dr. Mas Rina Mustaffa No. Paper ID Title of Paper Author

1. 37 Improved Segmentation for Intravascular Ultrasound (IVUS) Modality

Suhaili Beeran Kutty, Rahmita Wirza O.K Rahmat, Sazzli Shahlan Kassim, Hizmawati Madzin and Hazlina Hamdan

2. 54 Design Models for Mobile Augmented Reality Exergames: State-of-the-Art Review

Hasdina Lynn Hashim, Azrina Kamaruddin, Rahmita Wirza O.K. Rahmat and Azrul Hazri Jantan

3. 50 User Behavior Towards Video Content in Mobile Devices for Designing Individualistic Prefetching Algorithm

Shuria Saaidin and Zolidah Kasiran

4. 72 Integration of Gamification Mechanics and Dynamics to the Authentic Learning Environment (ALE) in Non-Game Context

Sharifah Nafisah Syed Muhammad, Rosnah Idrus, Nasuha Lee Abdullah and Pantea Keikhosrokiani


5. 87 Musafir Ilmu Application Development Using Mobile Application Development Life Cycle

Zan Azma Nasruddin, Irwan Mazlin, Maslina Abd Aziz, Mohd Shukor Abd Rahman and Wan Adilah Wan Adnan

Session 4A, 2.00 – 5.00pm (31 July 2018)

Ballroom1 (SEIS)

Session Chair : Dr. Azrul Hazri Jantan No. Paper ID Title of Paper Author

1. 111 Dynamic Service Adaptation Framework for Context Aware Mobile Cloud Learning Using Semantic Based Approach

Muhammad Sufri, Novia Admodisastro, Norhayati Mohd Ali and Hafeez Osman

2. 112 Exploring Design Opportunities of Tangible Interaction in Learning for Children with Dyslexia using Secondary Data

Novia Admodisastro, Siti Nurliana Jamali, Azrina Kamaruddin, Abdul Azim Abd Ghani, Sa’adah Hassan and Siti Suhaila Abdul Hamid

3. 116 A Domain Ontology for Eliciting Usability Features

Too Chian Wen, Sa’adah Hassan, Abdul Azim Abdul Ghani and Jamilah Din

4. 118 A Success Model for Semantic Technology Based – Knowledge Management Systems: An Empirical Investigation

Abdulmajid Babangida Umar, Azmi Ja’afar, Marzanah A. Jabar and Masrah Azrifah Azmi Murad

5. 64 Improving the governance of software maintenance process for agile software development team

Salfarina Abdullah, Mangaiarasi Subramaniam and Sazly Anuar

6. 125 Automated Code Optimizer as an Energy Assistant in Green Computing Applications

Jamilah Din, Chiew Wei Ooi and Muhammed Basheer Jasser

7. 101 Enhancing Scrum Framework: A Case at a Multinational Semiconductor Company in Malaysia

Shalini Mariyappan, Nasuha Lee Abdullah and Rosnah Idrus

8. 106 Goal-directed approach and design principle approach: a comparative study

Meei Hao Hoo, Azizah Jaafar and Hooi Ching Beh

9. 110 Cognitive-Behaviour Intervention in Developing an Adaptive Learning Model for Students with Dyslexia

Novia Admodisastro, Siti Suhaila Abdul Hamid, Azrina Kamaruddin, Abdul Azim Abd Ghani and Noridayu Manshor

10. 40 Applying ITIL Framework to Analyze Problem Management Key Performance Indicator (KPI): A Case Study of Malay Owner Company (Mesiniaga Berhad)

Mudiana Mokhsin, Amer Shakir Zainol, Siti Nordianah Haihom, Mohd Husni Mohd Som and Abdul Jalil Abdul Rahim


Session 4B, 2.00 – 5:00 pm (31 July 2018)

Kenyalang (AIBD and SEIS)

Session Chair : Assoc. Prof. Dr. Rohaya Latip No. Paper ID Title of Paper Author

1. 98 Recognition of Food with Monotonous Appearance using Speeded-Up Robust Feature (SURF)

Mohd Norhisham Razali, Noridayu Manshor, Alfian Abdul Halin, Razali Yaakob and Norwati Mustapha

2. 108 Parameter Tuning of Groceries Scheduling by Genetic Algorithm

M-Nazmi N-S, Shuzlina Abdul-Rahman and Nurzeatul Hamimah A.H

3. 109 Case-Based Reasoning Approach to Map Similar Cases for Accident Injury Claims

Shuhaizan Sulaiman, Nurzeatul Hamimah Abdul Hamid, Nur Huda Jaafar and Shuzlina Abdul-Rahman

4. 115 Multistage Genetic Algorithm and Q-learning for Flexible Ligand-protein docking

Erzam Marlisah, Razali Yaakob, Md. Nasir Sulaiman , Mohd Basyaruddin Abdul Rahman , M.N. Shah Zainudin

5. 98 Recognition of Food with Monotonous Appearance using Speeded-Up Robust Feature (SURF)

Mohd Norhisham Razali, Noridayu Manshor, Alfian Abdul Halin, Razali Yaakob and Norwati Mustapha

6. 66 A library for articulating the measurement streams with columnar data

Mario Diván and María Laura Sánchez Reynoso

7. 17 Knowledge Management Strategy and Initiative for Development of Digital Energy Hub

Hairoladenan Kasim

8. 31 Near Field Communication (NFC) Technology Security Vulnerabilities and Countermeasures

Manmeet Mahinderjit Singh, Ku Aina Afiqah Ku Adzman , Rohail Hassan

9. 32 Privacy Preserving Technique for Mitigating Anonymity Attack in Pervasive Social Networking Applications

Nur’Ayuni binti Adnan, Manmeet Mahinderjit Singh, Aman Jantan

10. 99 Price Changes Analysis Using Association Rule Mining on Online Shopping Portals

Aini Atikah Baharudin, Sofianita Mutalib, Nurzeatul Hamimah Abd Hamid and Nor Hayati Abdul Hamid


Session 4C, 2.00 – 5.00pm (31 July 2018)

Engseng (CNDS & IDMA)

Session Chair : Dr. Abdullah Muhammed No. Paper ID Title of Paper Author

1. 130 Channel Estimation in OFDM Multipath Fading Channel Systems according to Modulation Schemes

Alaa Abdullah Al-Saadi, Rohaya Latip, Abdullah Muhammed and Mohd Helmy Abd Wahab

2. 133 Enhanced Congestion Control Algorithms for LEO Satellite Networks

Fahrul Hakim and Shamala Subramaniam

3. 134 Performance Evaluation of Load Balancing Algorithm for Virtual Machine in Data Center in Cloud Computing

Yuganes Parmesivan and Sazlinah Hasan

4. 94 Ease of Use and Usefulness Evaluation of Medical Family Tree Data Visualization

Siti Fatimah Bokhare, Wan Mohd Nazmee Wan Zainon, Mohd Azam Osman and Abdullah Zawawi Talib

5. 24 Uncovering the Satisfying MOOC Gamification Elements via Fuzzy Analytic Hierarchy Process

Nie Hui Ling, Chwen Jen Chen and Chee Siong The

6. 48 Head Gesture Recognition and Interaction Technique in Virtual Reality: A Review

Nurul Nasuha Zolkefly, Ismahafezi Ismail, Suhailan Safei, Syadiah Nor Wan Shamsuddin, and Mohd Azhar M. Arsad

7. 121 IOT-Based Battery Monitoring System Nur Imanina Mohamed Anuar, Mohd Helmy Abd Wahab, Radzi Ambar, Shukor Sanim Mohd Fauzi, Aslina Baharum, and Hafizul Fahri Hanafi


(2) PROGRAMME DETAILS WITH ABSTRACT

SPEAKERS

30th July 2018

Time Activity Event

8:00 – 8.45 am Registration

Ballroom Foyer

8.45 – 9:30 am Opening Ceremony Ballroom 1

9.30– 10:00 am Photo Session and Coffee Break Ballroom Foyer

10:00 – 10:50 am Keynote speaker 1 Prof. Dr. Jemal H. Abawajy

Deakin University, Australia

Ballroom 1

10:50 – 11:30 am Industry Talk Tengku Shahrizam bin Tengku Abdullah

Sulaiman Cisco System (Malaysia)

Ballroom 1

11:30 – 1:00 pm Parallel Session 1 Session 1A: Ballroom 1 Session 1B : Kenyalang Session 1C: Engseng

1:00 – 2:00 pm Lunch Waterfront Cafe

2:00 – 5.00pm Tutorial Deep Learning

Ballroom 1

5.00pm Tea Break

Ballroom Foyer

7.00pm Dinner Ballroom 3

31st July 2018

8.00 – 8.40am Registration Ballroom Foyer

8.40-10.40am

Parallel Session 2

Session 2A: Ballroom 1 Session 2B : Kenyalang

Session 2C: Engseng

10.40 – 10.50am Break

Ballroom Foyer

10.50-11.40am Keynote speaker 2 Prof. Dr. Sung-Bae Cho

Yonsei University, Seoul, Korea

Ballroom 1

11.40 – 1.00pm

Parallel Session 3 Session 3A: Ballroom 1 Session 3B : Kenyalang

Session 3C: Enseng

1.00 – 2.00pm Lunch Waterfront Café

PROGRAMME


2.00 -5.00pm Parallel Session 4 Session 4A: Ballroom 1 Session 4B : Kenyalang

Session 4C: Engseng

5.00pm Tea Break

Ballroom Foyer

Session 1A, 11:30 – 1:00 pm (30 July 2018)

Ballroom 1 (SEIS)

Session Chair : Dr. Masnida Hussin No. Paper

ID Title of Paper / Author

Abstract

1

8 Comparing Web

Vulnerability Scanners

with a New Method

for SQL Injection

Vulnerabilities

Detection and

Removal EPSQLiFix

Kabir Umar, Abu Bakar

Md Sultan, Hazura

Zulzalil, Novia

Admodisastro and

Mohd Taufik Abdullah

Web vulnerabilities have become a major threats to the security of

information and services accessible via the internet. Web Vulnerability

Scanners (WVS) have been employed to facilitate testing of web

applications for detection of vulnerabilities. Clear understanding of the

workflow of these scanners is very essential in designing more

improved scanners. However, current literature does not provide

comprehensive presentation on workflow of WVSs. This paper presents

thorough description of generic WVS through synthesis and aggregation

of knowledge. In addition, the paper propose evolution programming

based static analysis method for detection and removal of

vulnerabilities called EPSQLiFix, and highlights how its’ functions goes

beyond WVSs.

2 131 A Study of Web

Design for Customer

Billing Telephony

System Using User

Experience (UX)

Approach

Noraini Che Pa,

Raziera Bidin and

Azrina Kamaruddin

User Experience (UX) is about technology that realizes the instrumental

needs as a subjective, situated, complex and dynamic encounter which

concern on user’s internal state, the characteristics of the designed

system and the context within which the interaction occurs. Obviously,

this creates innumerable design and experience opportunities which

represent the holistic view with of the pragmatic aspect and hedonic

aspect. Nowadays, UX is become important issue in developing web

based system and that has been discussed by many researchers.

Telecommunications industry has gone through series of development

efforts to make services available to consumers and to provide quality

services. While, telecommunications billing system consists on various

processes such as collect consumption data, calculate charging and

billing information, produce bills to customers, process their payments

and manage debt collection. The hardest challenge in

telecommunications industry is to meet the customer satisfaction in

billing system such as the accurate billing, easy to understand and

resolving billing issue, the billing problem resolution speed, the service

cost performance, rate discount degree, and rate communication.

DETAILS SESSION PROGRAMME


Hence, the improvement of these issues can enhance the customer

satisfaction. This research is focus on a study of customer billing

telephony system in order to decrease the challenges in

telecommunications industry. A survey conducted to collect data from

the customers of telecommunication industry. The result shows that

the improvement of billing system is needed to improve the efficiency

and correctness in billing process. It is expected that by implementing

this approach, it will improve the customer billing telephony system. In

addition, it gives the positive perceptions and experiences of a service

lead to high customer satisfaction with the service and will result the

customer loyalty to the service provider.

3 21 Real Time Productivity

Monitoring System for

Small and Medium

Size Manufacturing

Industry

Wong Phaik-Ean,

Nasuha Lee Abdullah,

Rosnah Idrus and

Pantea Keikhosrokiani

This paper attempts to propose a real time knowledge management system to monitor productivity for production lines of small and medium size enterprises (SME). The proposed system hopes to empower managers in meeting the target of daily production output. The uniqueness is it provides real time productivity level to enhance visibility and control in the production lines. The system automates the process of data collection by using bar code scanners at the input and output station. Productivity is calculated based on cycle time of each product and display in real time. Colour coded display indicating productivity level enables the line foreman to take immediate action. Apart from that, it can also send alert in the form of Whatsapps messages to relevant personnel in case of loss time issues. The system consists of two main modules, which are, data collection module and reporting module. It is developed as a web-based knowledge management system to ease setup, access, maintenance and facilitate future upgrade into mobile application. The system can be implemented in any production line to monitor the line performance and helps to reduce loss time by providing an instantaneous response to solve issues.

4 23 Towards Employing

Metrics in Measuring

the Quality of

Software Safety

Critical Systems and

Managing Their

Development

Jamilah Din, Rodziah

Atan, Yusmadi Yah

Jusoh and

Muhammed Basheer

Jasser

Failures in safety critical systems have a high impact on the

environment in which they are used. For that, developers usually follow

specific development standards and techniques to avoid and reduce

failures in such systems. Developers have to build safety critical systems

considering the quality, complexity, and size factors in all the

development phases beginning with the requirement gathering and

ending with the maintenance and verification. In this paper, some

quality models and some metrics for measuring the quality, complexity,

and size of systems are explored. The metrics are classified to the

development phases so that the classification indicates the degree of

metrics usage in measuring the quality, complexity, and size factors in

relation to the development phases. We are now working on relating

the studied metrics in this paper with their impact on the development

of the software safety critical system. We expect to use these metrics in

the management of the development phases and processes of software

safety critical systems so that a decision making could be performed


based on the measurements of these metrics.

5 25 Design and

Development of

Topic-Based Students’

Knowledge Modelling

System using Fuzzy

Set Theory and Visual

Analytics

Wen Thing Ng, Chee

Siong Teh and Chwen

Jen Chen

To the field of education, advances in technology raise opportunities

and challenges in delivering personalised learning to heterogeneous

group of learners, while monitoring their learning progress and learning

outcomes. In this paper, a students’ knowledge modelling system was

proposed to address the ultimate goal of personalized learning. In

addition, how instructor-oriented topic-based approach, fuzzy set

theory, and visual analytics was applied into the proposed system for

modelling, analysing and reporting knowledge level of individual

learners was presented. The implementation of the proposed system is

presented and discussed through a real-world case study at the end of

this paper.

6 33 Enhanced Bring Your

Own Device (BYOD)

Environment Security

Based On Blockchain

Technology

Fara Jamal, Mohd

Taufik Abdullah, Azizol

Abdullah and Zurina

Mohd Hanapi

BYOD is a practice by many organizations where employees can use

their personal devices for work purpose. BYOD may bring a lot of

advantages, but it also leads to security issues such as data leakages.

Data leakage can come from many sources such as stolen devices,

malware, security attack and also an insider threat. Data can be leaked

because of the weak authentication technique used to verify the user

and the device. A secure authentication technique is what the

organization needs that equip with high security features. Blockchain is

the answer to this because blockchain used cryptographic technology

that’s not easy for hacker to break. This research proposes a user trust

model that includes multifactor authentication combining with public

and private key generated by blockchain and an agentless device trust

model that can scan for malware and detect the device location. In

order to secure the record and sensitive data, the record keeping model

is built using blockchain technology where every activity related to the

record is recorded in the digital ledger. This ledger can be used as

evidence collection for further investigation. It is hoped the proposed

BYOD trust model solution can help organizations to minimize the

number of cases in data leakage while allowing BYOD concept.

Session 1B, 11:30 – 1:00 pm (30 July 2018)

Kenyalang (AIBD)

Session Chair : Dr. Hazlina Hamdan No. Paper


Abstract

1 7 Identifying the most

effective feature

category in machine

learning-based

phishing website

This paper proposes an improved approach to categorise phishing features into precise categories. Existing features are surveyed from the current phishing detection works and grouped according to the improved categorisation approach. The performances of various feature sets are evaluated using the C4.5 classifier, whereby the content URL obfuscation category is found to perform the best,


detection.

Choon Lin Tan, Kang

Leng Chiew,

Nadianatra Musa and

Dayang Hanani

Abang Ibrahim

achieving an accuracy of 95.97%. Additional benchmarking is conducted to compare the performance of the winning feature set against other feature sets utilised in existing phishing detection techniques. Results suggest that the winning feature set is indeed an effective feature category which has contributed significantly to the performance of existing machine learning-based phishing detection systems.

2 9 Building standard

offline anti-phishing

dataset for

benchmarking.

Kang Leng Chiew, Ee

Hung Chang, Choon

Lin Tan, Johari

Abdullah and Kelvin

Sheng Chek Yong

Anti-phishing research is one of the active research fields in information security. Due to the lack of a publicly accessible standard test dataset, most of the researchers are using their own dataset for the experiment. This makes the benchmarking across different anti-phishing techniques become challenging and inefficient. In this paper, we propose and construct a large-scale standard offline dataset that is downloadable, universal and comprehensive. In designing the dataset creation approach, major anti-phishing techniques from the literature have been thoroughly considered to identify their unique requirements. The findings of this requirement study have concluded several influencing factors that will enhance the dataset quality, which includes: the type of raw elements, source of the sample, sample size, website category, category distribution, language of the website and the support for feature extraction. These influencing factors are the core to the proposed dataset construction approach, which produced a collection of 30,000 samples of phishing and legitimate webpages with a distribution of 50 percent of each type. Thus, this dataset is useful and compatible for a wide range of anti-phishing researches in conducting the benchmarking as well as beneficial for a research to conduct a rapid proof of concept experiment. With the rapid development of anti-phishing research to counter the fast evolution of phishing attacks, the need of such dataset cannot be overemphasised.

3 14 OVA-RF with Self-

Tuning Tree

Parameter in Solving

Classification

Problem

M.N. Shah Zainudin,

Md. Nasir Sulaiman ,

Norwati Musapha,

Thinagaran Perumal1

and Raihani

Mohamed

Binarization strategy is broadly applied in solving various multi-class classification problems. However, classifier model complexity tends to increase when expending the number of problems into several replicas. One-Versus-All (OVA) is one of the strategies which transforming the ordinal multi-class classification problems into a series of two-class classification problems. The final output from each classifier model is combined in order to produce the final prediction. This binarization strategy has been proven as superior performance in accuracy than ordinal multi-class classifier model. However, training model complexity (eg. Random forest ensemble decision trees) tends to increase when employing a large number of trees. Even though a large number of trees might produce decent accuracy, generating time of the learning model is significantly longer. Hence, self-tuning tree parameter is introduced to tackle this matter. In such circumstances, a number of trees in the random forest is defined according to the number of class problem. In this paper, we evaluate OVA with self-tuning parameter initialization in the context of random forest ensemble decision tree. We also evaluate the performance of the proposed method with J48 and boosting forseveral well-known datasets.


4. 15 Case Study of UPNM

Students

Performance

Classification

Algorithms

Syarifah B. Rahayu,

Nur D. Kamarudin

and Zuraini Zainol

Data mining is one of the steps in the knowledge discovery in database that extract hidden information and useful patterns using various algorithms from large amount of data. In this study, three classification techniques are applied on educational datasets to predict the students’ performance. The prediction results may help lecturers and students to improve their teaching and learning process. The selected classification algorithms applied in this study such as J48 Decision Tree, Naïve Bayes and kNN. WEKA is used as an experimental tool. The selected algorithms are applied on a data of student database of Data Mining subject. Findings shows Naïve Bayes outperforms other classification algorithms with above 80% prediction rate. As a conclusion, the classification algorithms can predict students’ performance on a particular subject.

5 35 Role Minimization as

An Optimization

Metric in Role Mining

Algorithms: A

Systematic Review

Nazirah Abd Hamid,

Rabiah Ahmad and

Siri Rahayu Selamat

A recent access control model that could accommodate a dynamic structure such as cloud computing can be recognized as role based access control and the role management process of this access control can be identified as role mining. The current trend in role based access control is the role mining problem that can be described as the difficulty to uncover an optimum set of roles from the user- permission assignment. To solve this problem, the researchers have proposed role mining algorithms to produce role set and among the existing algorithms there is an intrinsic topic of the common perception to evaluate the goodness of the generated role set. Eventually, the value of the identified roles could be measured by the preferred metric of optimality namely the number of roles, sizes of user- assignment and permission-assignment and Weighted Structural Complexity. Until now, there is some disagreement on the optimization metric but notably many researchers have agreed on the minimization of the number of roles as a solid metric. This paper discusses an overview of the current state-of-the-art on the recent role mining algorithms that focus on role minimization as an optimization metric to evaluate the goodness of the identified roles.

6. 45 Evaluation of

Weighted Based

Algorithm for

Android Malware

Detection

Nurul Hidayah

Mazlan and Isredza

Rahmi A Hamid

This paper synthesizes an evaluation of weighted based algorithm by utilizing Term Frequency Inverse Document Frequency (TF-IDF) as the main algorithm in Android malware detection. The Android features were filtered before detection process using TF-IDF algorithm. However, IDF is unaware to the training class labels and give incorrect weight value to some features. Therefore, the proposed approach modified the TF-IDF algorithm where the algorithm focused on both sample and feature. We then applied weighted based algorithm that considers the feature based on its level of importance. These experiments are conducted on a sample collected from DREBIN data set. The comparison between existing TF-IDF algorithm and modified TF-IDF (MTF-IDF) algorithm have been tested in various conditions such as different number of sample, different number of feature, different types of feature and different types of machine learning algorithm. The experimental results show that the MTF-IDF algorithm gives promising result with accuracy value of 97.6%, 96.8% and 98.9% when tested on Bagging, Decision Table and Random Forest respectively


Session 1C, 11:30 – 1:00 pm (30 July 2018)

Engseng (CNDS)

Session Chair : Dr. Abdullah Muhammed

No. Paper


Abstract

1. 22 Replication Strategies For Big Data In Cloud Environment

Fazlina Mohd Ali and Rohaya Latip

Big Data technology is emerging around the globe to provide better insight and decision making for every organization. As the nature of Big Data is providing variety and huge volume of data with complex data computation, cloud environment is the best choice to resolve storage issues. However, the challenge remain in this technology is data availability due to heterogeneity of Big Data systems. Data must be always accessible and available for user regardless of time. The most essential option to satisfy this desire is providing best replication strategies which able to afford business continuity without interruption. Hence, this paper delivers better perceptions on the data replications strategies for Big Data systems in cloud environment. Critical review concerning replication strategies is discussed and presented with imperative details from numerous researchers. Additionally, this work contributes thorough discussion on advantages and gaps for each study. This study also explores algorithms and performance metrics that has been improved by researchers. The methodology used to conduct this paper was using qualitative research approach. Ultimately, this paper would be helpful for future researchers in understanding and selecting the best strategy to fit their research scope and goals.

Submitted: Mar 28, 03:29 GMT

2. 28 Load Management Evaluation of HBase and Cassandra Databases Using YCSB

Ali Y. Aldailamy, Abdullah Muhammed, Waidah Ismail and Abduljalil Radman

The advancement in cloud computing, the increasing size of databases and the emergence of big data have made traditional data management system to be insufficient solution to store and manage such large-scale data. Therefore, there has been an emergence of new mechanisms for data storage that can handle large-scale of data. NoSQL databases are used to store and manage large amount of data. They are intended to be open source, distributed and horizontally scalable in order to provide high performance. Scalability is one of the important features of such systems, it means that by increasing the number of nodes, more requests can be served per unit of time. Scalability is always companied with load management, which provides load balancing of work among multiple nodes. In this study, HBase and Cassandra load management with scalability will be evaluated as they are the most popular NoSQL databases modeled based on BigTable. In particular, this paper will compare and analyze the distributed performance of HBase and Cassandra using standard benchmark tool named Yahoo! Cloud Serving Benchmark (YCSB). The experiments will measure the performance of database operations with a different number of connections using different numbers of operations, database size, and processing nodes. The experimental results showed that HBase can provide better performance as the number of connections increase in the presence of horizontal scalability.


3. 71 A Super-Peer Approach for Scalable Collaborative Intrusion Detection Network (CIDN)

Yousef Bakhdlaghi, Nur Izura Udzir, Azizol Abdullah and Nor Fazlida Mohd Sani

Collaborative intrusion detection systems (CIDSs) have the ability to correlate suspicious activities from various CIDSs in different networks to maximize the efficiency of the intrusion detection in addition to sharing the knowledge and resources among them. Current consultation-based CIDNs do not honor the scope variations of CIDSs (area of expertise). Evaluating collaborators’ knowledge regardless of their scope variations could degrade the efficiency of the CIDN, while in reality CIDSs have different platforms and strengths in various areas that could affect the overall scalability and efficiency of the architecture negatively. Additionally, many architectures in the literature built under information-based settings, while few architectures have the consultation-based capabilities. An architecture that combines both information-based and consultation-based capabilities has not been proposed yet. This paper proposes a scope-aware super-peer collaborative intrusion detection network (CIDN) architecture that takes CIDS scope into consideration when consulting, by organizing CIDSs into groups based on their scope regardless of their physical locations as well as incorporating the information-based into the consultation-based architecture to benefit from consultation-based capabilities while limiting the information being distributed to fast-spreading attacks that are discovered from consultation requests. However, the proposed architecture can strengthen the efficiency of the CIDN as well as reducing the overload of the communications among collaborators and contributes to enhance the overall scalability of the architecture.

4. 91 Optimizing the Space Utilization in Real-time Flash Translation Layer Mapping Scheme

Mohd Bazli Ab. Karim, Amir Rizaan Abdul Rahiman, Rohaya Latip and Hamidah Ibrahim

Solid-State Disk (SSD) is a semiconductor storage device and it has

become a preferred choice for many storage sub-systems solutions to

replace the classical hard drives due to its high performance and

durability. Moreover, NAND flash memory has become cheaper in

costs. However, this flash memory type has its own limitations due to

its erase-before-write operations nature. This limitation will cause the

memory to wear faster and consuming higher cost when initiating the

cleaning process. To overcome the limitation, an address mapping in

NAND flash memory namely Flash Translation Layer (FTL) plays

important role in handling I/O operations. Several studies on the FTL

have been carried out to manage the IO operations in NAND flash

device efficiently. This paper proposed an optimized address-mapping

scheme called Optimized Real-Time Flash Translation Layer (ORFTL). In

order to increase the NAND flash space utilization, the proposed

scheme reduces idle buffer blocks and reassigns the blocks as new

Logical Block Addressing (LBA) in order to optimize blocks in flash

memory for more space utilization. In addition, the scheme introduces

a pool of buffer blocks with the same bandwidth throughput size of IO

interface that connects the SSD to the host system in order to

guarantee available free spaces to serve write operations. By optimizing

both types of blocks, the proposed scheme has shown significant

increases in the NAND flash memory space utilization as compared to

the existing FTL schemes.


5. 119 An Empirical Study of the Performance Analysis Between Quantum Computers and Silicon ComputersMohd Aisar M.M.I, Dr Shukor Sanim Mohd Fauzi, Dr Hanif Baharin, Wan Asma Wan Mohammad Sobri, Anjila .J. Suali, Ray Adderley Jm Gining, Muhammad Nabil Fikri Jamaluddin & Mohd Helmy Abdul Wahab

The purpose of this study was to demonstrate the computational capabilities of quantum computers to a wider audience, including students and professionals working in computer-related fields. Several tests were conducted using various programming control statements to differentiate the completion times based on performance analyses of a high-performance silicon computer and a quantum computer. Three types of experimental performance analysis scenarios were conducted of basic programming statements, including for loop, while, and if-else control statements. The experiments were repeated five times to obtain the average completion times. The obtained results suggest that the silicon computers outperformed the quantum processing capabilities.

6. 128 Efficient Energy Management in Cloud Data Center: An Analysis of DVFS towards Cloud Applications

Joshua Samual and Masnida Hussin

Cloud data center contains various resources which are utilized continuously without any break. The data centers consumed large energy to keep the components to run 24/7 for achieving certain performances. Such energy usage becomes one of the major issues in the Cloud data center. It is due to the Cloud availability is highly demanded in network community. In this study, we formed an analysis on the energy consumption by considering the CPU usages through the existing Dynamic Voltage and Frequency Scaling (DVFS) techniques that proposed in existing researches. The aim of this work is to investigate and identify Cloud services application factors that can be employed on the DVFS for better energy management in Cloud data center. Our study expresses the areas of the Cloud service applications such as Business Application-as-a-Services, Consumer Application-as-a-Services and Scientific Application as-a Service that embedded in DVFS where it can be part of the energy saving contributors. We also analyzed the two main factors in DVFS are proportional to time and frequency that can be adjusted towards energy efficient in the data center. The survey is also investigated on how far such functions can be manipulated for energy saving while investigating potential solutions for further enhancement.

Session 2A, 8:40 – 10:40am (31 July 2018)

Ballroom 1 (SEIS)

Session Chair : Dr. Noraini Che Pa

No. Paper ID

Title of Paper / Author

Abstract

1. 38 An Automated Test

Case Generating Tool

Using UML Activity

Diagram

Md Abdul Monim

Software or application testing is a process of executing a program with

the goal of finding defect to make better system. In software testing

phase, writing test cases is one of the important activities. Manually

writing test cases approach is lengthy of time period and need more

effort to accomplish the process. On the other hand, automated test


and Rozi Nor Haizan

Nor

case generation technique is the way to solve this issue and Model-

Based Test case generation approach would be the appropriate for this

automation process. Usually, a model is required in Model-Based

Testing approach to generate the test cases and UML activity diagram is

the model in our research. In this paper, we explained our proposed

Model-Based Test case generating approach and we successfully

developed a tool based on our proposed technique that could generate

test cases automatically using UML activity diagram as an input. Finally,

we conducted an experiment on a real life simple application of a

system using the tool and successfully able to show that our tool can

produce same test cases as manually writing test cases of the same

system but this tool can save a lot of time and effort as well.

2. 73 Educators’ Readiness

in Using Mobile

Phone as a

Pedagogical Tool for

Teaching

Siti Nur’ain Hamsan

and Maslina Abdul

Aziz

Owing to the rapid growth of technology, most higher educational

institutions are looking for new learning systems that can improve their

curriculum. The preliminary study has identified four problems which

are lack of understanding on the level of technology acceptance among

educators, how mobile phone can be used for learning, the benefits of

m-learning to student learning and lack of confidence among educators

in integrating technology in the teaching process. This study is an

adoption of Parasuraman’s study on Technology Readiness Index (TRI).

The objective of this study is to identify the level of technology

readiness among educators in Higher Education towards the

implementation of mobile phone as pedagogical tools in the teaching

and learning process. Besides that, this study also aims to identify the

relationship between the dimensions of technology belief and

educator’ readiness and which dimensions influenced the most to their

readiness level. In order to achieve this objective, quantitative

approach and questionnaire instrument are used to gather data from

the respondents. The findings show that there is a high level of

technology readiness among educators (mean=3.87) with a positive and

significant relationship between the dimensions of technology belief

and educators’ readiness (p<0.05). Optimism has influenced the most

to educators’ readiness (β = 0.834). Since the respondents of this study

were limited on educators, it is recommended this study would be

expanded to students. The comprehensive findings may provide some

key consideration to the higher education institutions to determine the

greatest solution in ensuring the successful of m-learning post-

implementation.

3. 52 Applying Agile

Concepts from

Software

Development into

Managing complex environment often require flexibility in its

processes. This is evident in flood management where the factors that

determine the success of it is uncertain. A flexible flood management

require an agile frame-work that allows flexibility to respond to any


the Design of Flood

Disaster

Management

Framework

Mohamad Firdaus

Mat Saad, Aliza Abdul

Latif, Marini Othman

and Mohd Saiful

Anuar Mohd Noor

possible event during a disaster. The concept of agile methods used in

software development help to provide values that is used a basis in

offering agility in managing flood complexity. These values are observed

during field studies of Standard Operating Procedures (SOP)

implementation in managing flood impact at selected flood sites in

Malaysia. This study aim to identify the key values of agility in

developing a framework based on the review of agile methods

combined with factors identified from study of successful flood

management. The developed framework is aligned with uncertainties

mitigation by dividing the disaster areas into small sub-areas, improving

communication, and empowering on-site response team with clear

leadership.

4. 57 The Enterprise

Resource Planning

System and Human

Influences on

Perceived Business

Benefits

Jiansi Lim, Norshidah

Mohamed and Nor

Shahriza Abdul Karim

Strategic information systems are designed to support business

processes for firms to achieve competitive advantage in the market

place. Enterprise Resource Planning (ERP) system is one such example

of a strategic information system. While there have been many

researches on ERP systems, evidence about ERP systems business

benefits from user’s perspective still remains to be known. The

research, therefore, aims at exploring and determining the influences of

ERP systems on business benefits. The influences encompass the user

satisfaction with the ERP system itself (system factor) and the human

factor of service provider as perceived by users. The human factor is

made up of the perceived service quality of provider as consultant and

the relationship quality between the user and the provider. Data was

collected using a survey research instrument from three different

organizations in Malaysia. A total of 120 users provided responses to

the survey. The research provides support for the ERP system and

human influences on user’s perceived business benefits. Implications of

the research are discussed herein.

5. 62 An Iris Image

Thresholding Based

on Binarization

Threshold in Black

Hole Search Method

Muktar Danlami,

Sofia Najwa Ramli,

Zahraddeen Pindar,

Sapiee Jamel and

Mustafa Mat Deris

In iris recognition system, the segmentation stage is one of the

important stages where the iris is located and then further segmented

into outer and lower boundary of iris region. Several algorithms have

been proposed in order to segment the outer and lower boundary of

the iris region. This aim of this work research is to identify the suitable

threshold value in order to locate the outer and lower boundaries using

Black Hole Search Method. The experiment was conducted using three

data set; UBIRIS, CASIA and MMU. Given that different iris databases

have different file formats and quality the images used for this work are

jpeg and bmp. Based on the experimentation, most suitable threshold

values for identification of iris aboundaries for different iris databases

have been identified. Values of 0.3, 0.4 and 0.1 for database UBIRIS,

CASIA and MMU respectively. The study concludes that threshold

values vary depending on the database.


6. 120 The Role of Employee in Information Security Risk Management David Lau Kiat Jin,

Noor Hafizah Hassan,

Nurazean Maarop,

Ganthan Narayana

Samy and Rasimah

Che Mohd Yusoff

Information security risk management (ISRM) is become essential for establishing safe and reliable environment for online and e-transactional activities. With the coming Industrial Revolution 4.0, there is a huge interest of the organization for involving user in their risk management activity to minimize any security incidents. Limited research has been conducted in investigating involvement of user in ISRM. Therefore, this paper examines the involvement of user in ISRM in financial organization. Besides, this paper discusses the existing theories of risk management use in assessing ISRM. This paper investigates user participation in ISRM implemented in the organization using mixed-method approach. This study use questionnaire survey and follow-up with interview in one financial organization. Besides, Strength, Weakness, Opportunities and Threat (SWOT) analysis is presented based on the result found for the organisation to focus on their improvements needed. This study shows that a well-known procedure and standards must be implemented in the organisation to ensure that employee participate more in the ISRM process and activities.

7. 68 A model on multiple

perspectives of

citizens’ trust in using

social media for e-

government services

Sohrab Khan, Nor

Zairah Ab. Rahim and

Nurazean Maarop

The lack of trust has a critical role in discouraging citizens to use social

media for e-government services. Therefore, developing trust is an

essential need for making citizens’ comfortable to participate in

government social media services. Majority of previous studies on the

relationship with trust between government and people have been

conducted on e-government websites. Those studies are quite narrow

in terms of their scope to address multiple aspects of citizens trust. On

the contrary, the context of using social media for e-government

services has not received much attention by previous researchers. This

study proposes an integrated model of trust from multiple perspectives

with an objective to identify those factors that can influence citizens’

trust in context of using social media as a technology for e-government

services. The constructs in the proposed model were integrated from

the trust literature and Technology Acceptance Model (TAM). The

findings reveal individual characteristics, government factors, risk

factors and social media characteristics as multiple antecedents of

citizen’s trust to use social media for e-government services. A research

instrument was developed and validated to examine the proposed

model. A pilot study was conducted, and the instrument was refined

based on its results.

8. 70 Understanding the

Factors that Affect

Information

Technology

Outsourcing of

Government Shared

Services

One of the Public Sector Information Communication Technology

Strategic Directions for 2016 – 2020 is to optimize shared services

through a centralized and structured initiative. Due to some identified

problems and challenges in managing the IT outsourcing arrangement,

this study aims to explore the factors that could influence the success

implementation of Information Technology (IT) outsourcing of

government shared services (GSS) in the case of Malaysian public


Fadzilah Ahmad,

Nurazean Maarop

and Nurulhuda

Firdaus Mohd Azmi

sector. This paper is presented based on qualitative case study entailing

interviews with key informants to gather information and the data

analysis was performed based on the content analysis. Subsequently,

nine factors that potentially influence the successful arrangement of IT

outsourcing of government shared services were identified to be

further used in our next stage of study in developing maturity model of

IT outsourcing

Session 2B, 8:40 – 10:40 am (31 July 2018)

Kenyalang (AIBD)

Session Chair : Assoc. Prof. Dr. Nurfadhlina Mohd Sharef

No. Paper


Abstract

1. 44 Systematic review on

ear identification

Ahmed Alemran, Dr.

Bahbibi Binti

Rahmatullah and Ali

Hadi

Context: The topic is permitted from modern topics of interest for

researchers to find logical solutions to problems of detection and

recognition for ear identification. Therefore, we are looking for a

solution to the problem of occlusion, detection and recognition of the

person create an integrated system based on the latest research and to

find new results in terms of accuracy and time and be comprehensive

for everything. Objective: To survey researchers’ efforts in response to

the new and disruptive technology of ear identification systems,

mapping the research landscape form the literature into a coherent

taxonomy. Method: We use a systematic review as the basis for our

work. a systematic review builds on 249 peer-reviewed studies,

selected through a multi-stage process, from 1960 studies published

between 2005 and 2017. Results: We develop a taxonomy that

classifies the ear identification systems. The results of these articles are

divided into three main categories, namely review and survey article,

studies conducted on ear biometrics and development of ear biometric

applications. Conclusion: The paper is, to our knowledge, the largest

existing study on the topic of ear identification. This typically reflects

the types of available systems. Researchers have expressed their

concerns in the literature, and many suggested recommendations to

resolve the existing and anticipated challenges, the list of which opens

many opportunities for research in this field.

2. 49 Multi-objective PSO-

fuzzy Optimization

Approach to Improve

Interpretability and

Accuracy in Medical

Data

Alwatben Batoul

Rashed, Hazlina

Today, Decision Support Systems (DSS) plays an important role in a

medical and healthcare domain. Designing an Automatic Fuzzy Rule-

based Classification Systems (FRBCSs) can be considered an

optimization problem associated to a result of high interpretability and

accuracy. Interpretability and accuracy are the two main objectives to

be improved in the optimization measurement of FRBCSs. However,

improving these objectives is found to be difficult in most of the

existing systems due to the conflicting issues between interpretability


Hamdan, Md Nasir

Bin Sulaiman,

Nurfadhlina Binti

Mohd Sharef and

Razali Bin Yaakob

and accuracy. In this paper, we proposed an approach that can

effectively handle accuracy- interpretability trade-off in constructing

FRBCSs. We designed automated FRBCSs in the form of Multi-objective

Particle Swarm Optimization with Crowding Distance. In the approach,

there will be a collection of solutions to FRBCSs that deem best global

minimum or global maximum with respect to interpretability and

accuracy. Our method is evaluated on three well-known benchmark

data sets from the medical domain, publicly available in the

evolutionary learning data repository. These datasets are Liver

Disorders (BUPA), Pima Indians Diabetes and Thyroid Disease (New

Thyroid). The result obtained shows that the proposed method yields

an optimum solution in handling the accuracy-interpretability trade-off.

Moreover, the result of the comparison shows that our approach

outperforms the alternate techniques in terms of accuracy of the

FRBCSs and also exhibits good result in terms of interpretability

objective.

3. 58 An Artificial Immune

System Approach For

Type E Assembly Line

Balancing Problem

Mohd Nor Akmal

Khalid, Umi Kalsom

Yusof and Zarul Fitri

Zaaba

The manufacturing industry has evolved in the past decades, due to the

competition of the global economy, where the market demands high

quality and customized products, and meeting lowest possible costs are

paramount. One of the many processes in manufacturing is the

assembly line operation, namely the assembly line balancing (ALB)

problem. ALB problem is dependent on optimum resource utilization in

order to improve production output, reduces costs, and shortens

production lead times. In these recent years, various approaches have

been proposed to solve the complexity of assembly line balancing

operations, which composed of exact, heuristic, and meta-heuristic

approaches. However, little work had been done to solve the type E

assembly line balancing problem. This paper proposed an approach

using artificial immune system (AIS) algorithm, namely as the swarm of

immune cell (SIC) approach, for solving type E assembly line balancing

problem. An initialization mechanism through the bone marrow model

and probabilistic clonal selection mechanism had encouraged efficient

exploration and exploitation of the solution space. The computational

results over 242 instances of 24 datasets had demonstrated the

efficiency of the proposed SIC approach by achieving high-quality

solutions (up to 85.94% optimum solutions was obtained). Also, the

results were statistically justified by comparing with approaches from

the literature.

4. 59 A Hybrid Feature

Selection Technique

for Classification of

Group-based Holy

Quran verses

Text classification problem is primarily applied in document labeling.

However, the major setbacks with the existing feature selection

techniques are high computational runtime associated with wrapper-

based FS techniques and low classification accuracy performance

associated with filter-based FS techniques. In this paper, a hybrid

feature selection technique is proposed. The proposed hybrid


A. Adeleke and N.

Samsudin

technique is a combination of filter-based information gain(IG) and

wrapper-based CFS algorithms. The specific purpose for this

combination is to achieve both high classification accuracy performance

(associated with wrapper) at lower computational runtime (associated

with filter). The proposed IG-CFS technique is then applied to label

Quranic verses of al-Baqara and al-Anaam from two major references,

the English translation and commentary (tafsir). StringToWordVector

with weighted TF-IDF method were used for preprocessing the textual

data while four classifiers: naive bayes,libSVM,k-NN,and decision trees

(J48) were experimented. The overall highest classification accuracy of

94.5% was achieved at 3.89secs runtime with the proposed IG-CFS

technique.

5. 60 A Review on Z-

numbers

Saeed Bahrami,

Razali Bin Yaakob,

Azreen Azman and

Rodziah Atan

Decisions are based on information and reliable information is very

important to make accurate and rational decisions. The concept of a Z-

number as an adequate concept for the description of real-world

information is relates to the issue of reliability of information. This

concept has a potential for many application such as Engineering,

Management, Education, Mathematics, and also in many other fields.

The purpose of this paper is to review systematically the applications

and methodologies of the Z-numbers. Based on the study, articles are

grouped into four categories: the concepts papers, new approach

papers, develop methods, and application papers.

6. 138 Know Your Hotel

well!- An online

Review Analysis using

Text Analytics

Angela Lee, Zaharin

Yusoff and Zuraini

Zainol

Online travel forums have become an extremely popular platform for sharing travel information, with a large number of reviews being posted daily. Travel websites such as TripAdvisor and Booking.com have turned into very important resources for hotel operators and travellers alike, for promoting hotel rooms, choosing hotels as well as for soliciting and sharing feedback. Criti-cisms, compliments, dissensions, etc., are now accessible anytime and anywhere on the web, and can be readily amassed, while opinion mining techniques have developed rapidly. Together they provide the opportunity and capability to analyse and deduce factors that influence travellers in their choice of hotels. In this paper, we apply opinion mining on data collected from Tripad-visor websites. In total, 11,130 reviews on 4 hotels within the four-star and five-star categories in Kuala Lumpur are crawled, collected, and mined to identify the top-k most predominant information based on the most frequent and most related terms used in describing each of the chosen hotels. The results of this study would allow travellers to see the opinions of other travel-lers on these hotels, and hotel operators would be able to receive feedback to improve their services and in turn promote their hotels. This study is also carried out in view of future improvements in the techniques used and the analysis performed.

7. 67 A Study on Detecting

Misleading Online

Fake news can impact negatively in terms of creating negative perception towards business, organization, and government. One of the ways that fake news is created is through deceptive news writing. Many


News Using Bigram

Normala Che Eembi

Jamil, Iskandar Ishak,

Fatimah Sidi and Lilly

Suriani Affendey

researchers have developed approaches in detecting deceptive news con-tent using machine-learning approach and each of the approach has its own focus. Previous researches emphasis on the components of the news content such as in detecting grammar, humor, punctuation, body-dependent and body-independent features. In this paper, a new approach in detecting deceptive news based on misleading news has been developed which is focusing on the similarity between the content and its headlines using bigram and cosine similarity. Based on the experiments, the proposed approach has better performance in terms of detecting deceptive news.

8. 69 A Two Dimensional

Facial Analysis for Sex

Comparison Using

Morphometrics

Approach

Olalekan Agbodale,

Azree Shahrel Ahmad

Nazri

Making a gender comparison between male and female is not a difficult task for human beings but the science of gender comparison of faces by humans is completely unfathomable due to commonality of gender comparison in both humans and other animal species. Significant gender differences between masculine and feminine exist in many facial regions such as eyes, nose, mouth, cheek and chin; which have not been critically looked into. This research characterizes and analyzes the gender comparison in the human face as a function of face features and identifies the features which contribute significantly to the uniqueness of the face using morphometrics techniques such as Principal Component Analysis (PCA), Thin-Plate Spline (TPS) Warping and Procrustes Superimposition (PS). The results demonstrate that the male face is significantly different from that of female based on the analysis of the selected facial features which provides the basis for gender-based comparison of faces.

Session 2C, 8:40 – 10:40am (31 July 2018)

Engseng (IDMA)

Session Chair : Dr. Alfian Abdul Halin

No. Paper


Abstract

1. 11 Speckle Filtering

Method in the Gonad

Ultrasound Image for

Mahseer’s fish (Tor

Tombroides)

Nurul Asmaa Abd

Razak, Hizmawati

Madzin, Fatimah

Khalid and Mas Rina

Mustaffa

In the context of breeding and seed production of Mahseer species, understanding and control of the Mahseer gonad maturation level have given strong interest for scientific and commercial purposes. Possible use of ultrasound for monitoring of gonad maturation in Mahseer fish is investigated. From previous studies, ultrasound image can be affected by many speckle noise. Subtle differences between speckle noise and the Mahseer eggs lead to difficulties in identifying the eggs in the gonad ultrasound image. To eliminate these speckle noise, speckle filtering method is required. There will be experimenting in comparing which speckle filtering method is suitable for the gonad’s ultrasound image. From the result, the best speckle filtering method will be chosen for eliminating the speckle noise in the image. So, it will be easier to identify the eggs in the gonad ultrasound image later. This noninvasive tool can then obviously be utilized to improve and monitor the maturation level of Mahseer fish. Ultrasound thus has great potential for use in Mahseer fish both for conservation and aquaculture field.


2. 85 Fusion CLAHE-Based

Image Enhancement

with Fuzzy in

enhancing the quality

of Field Image

Elmaliana Albahari,

Hizmawati Madzin

and Mohamad Roff

Mohd Noor

In this paper, a new fusion CLAHE-based method is proposed to enhance the field image. This field image considered as low resolution images are taken by normal camera or device as smartphones with poor quality compared to the lab image with proper setup. This field image has low contrast, blurred and unsharp due to inconsistent setting or environment exposes. Image enhancement is to enrich the perception of images for better quality and reduce impulsive noise, sharpen the edges with the help of different image enhancement techniques. The main attraction towards this enhancement research area is because of the additional knowledge and hidden information provided by the results of this procedure which will further be used for many different useful purposes. This research proposed to fusion CLAHE-based with Fuzzy set theory. An optimization technique is applied to increase the enhancement ratio. The result of the proposed fusion method is compared with the standard method as benchmark. The obtained value was compared by using image quality measurement techniques. The proposed fusion method produced better quality enhanced image and required minimum processing time than the other methods.

3. 65 Elderly Experience

Evaluation through

Medication

Nuha Alnabit and Evi

Indriasari Mansor

Technology advancement has been providing innovative solutions to assist elderly to overcome many challenges they face when learning about their medication due to their declining abilities. However, due to the lack of proper understanding of elderly experience and poor representation of their requirements, many of these solutions are rejected. Natural and simple interactions are one of the main features elderly require to adopt technology which can be supported through the integration of augmented reality technology with these solutions. This paper focused on studying elderly interaction with an augmented reality medication learning application and evaluating their experiences as a user from the perspective of visceral, behavioral and reflective levels at an early stage of the development process. The results indicated positive feedbacks with considerations when developing similar application for the future

4. 107 iLung: Interactive

Holographic Medical

Application for Lung

CT Scans using

HoloLens

Aala Al Khayer and

Evi Indriasari Mansor

This research aims to design a holographic medical application for lung CT scans using Microsoft HoloLens. iLung application offers users the possibility to interact with the actual lung of a patient in a mixed reality and 3D environment. A prototype of the iLung was developed based on raw CT scans data and converted into 3D model generation. This paper reports the earlier stage in designing the application. Based on the application’s overview with a group of users, the findings gathered showed that iLung prototype facilitates interactive manipulation and exploring of the 3D lung object. Feedback and comments were recorded for future improvements such as air taping interaction method and voice command.

5. 56 Fruits Recognition

Based on Texture

Features and k-

Nearest Neighbour

Malaysia is well-known for its variety of fruits available in the country such as pineapple, guava, durian, apple, and watermelon. Therefore, it is important for us to get to know more about fruits so that we can take advantage of all the benefits that each fruit can offer. However, problems may arise where a person may know nothing about a particular fruit apart from only having an image of it. Most of the fruit


Nur Izzani Kamal

Ariffin, Mas Rina

Mustaffa, Lili

Nurliyana Abdullah

and Nurul Amelina

Nasharuddin

encyclopedias nowadays still rely on text as search input. Furthermore, various features are commonly utilised for representation which can lead to high computational complexity. Therefore, to overcome these problems, we proposed a content-based texture-only fruits recognition that accepts an image as input instead of text. We propose a framework which extracts five texture features (homogeneity, energy, entropy, correlation, and contrast) based on Gray-level Co-occurrence Matrix (GLCM) descriptor. k-Nearest Neighbour (k-NN) is used at the classifier model to determine the type of fruits. The conducted empirical study has shown that the proposed work has the ability to effectively recognise fruit images with 100% accuracy.

6. 39 Using Continuous

Spatial Configuration

for Bezels Issues in a

Multi-mobile System

Beng Liang Ong,

Rhun Ming Teo, Noris

M Norowi and Azrul

Hazri Jantan

With the fast moving technology and innovation, the current digital technology such as smartphones and tabletop system have become vital necessities to accommodate people’s daily activities. As a more robust alternative to tabletop system, the multi-mobile system is also benefiting humans’ interaction by combining multiple mobile devices to become a shared and larger touch surface display. This paper presents a study on the effects of bezels on a multi-mobile system that allows users to come together with their mobile devices in an ad-hoc manner, and integrates together as one seamless display surface with multi-touch capabilities. Unfortunately, gaps and bezels between the mobile displays cause inherent design problems to the multi-display structure. Before conducting the experiments, two prototypes have been designed; high-fidelity prototype (without solution) and iterative prototype (with the continuous spatial configuration). Two user studies have been conducted with the prototypes by observing groups of students performing an interactive drawing task and the findings were compared. Results from the first user study show gaps and disjointed objects were observed in the drawing outcomes, while in the second user study, where the Continuous Spatial Configuration was implemented as a solution to this bezel issue, the gaps and spaces between the screens were eliminated by 94.8%. From this study, it is believed that implementing the Continuous Spatial Configuration in the prototype designs can provide the next step in the evolution of collaboration beyond the use of expensive tabletops systems.

7. 100 A Usability Evaluation

of Image and Emojis

in Graphical

Password

Nur Syabila Zabidi,

Noris M Norowi and

Rahmita Wirza

This paper presented user preferences in applying image and emojis use in graphical password authentication application. There is generally lack of two-factor authentication (2FA) approach in mobile devices. A preliminary study and a user study (N=30) have been conducted to investigate on usability and security issues. Both of the studies revealed the method of applying picture superiority effect to enhance memorability of graphical password.

8. 53 Designing an

Expressive Virtual

Kompang on Mobile

Device with Tri-axial

The paper presents an expressive virtual percussion instrument for Kompang on mobile devices that closely replicates the actual instrument. In nowadays, most available applications are lacking expressiveness control as these applications only use trigger-type event to play corresponding sound. This paper is therefore implemented a


Accelerometer

Hoo Yong Leng, Noris

M Norowi and Azrul

Hazri Jantan

simple extraction method by extracting percussive features from embedded sensors to map with the output sound with minimum delay. Multiple features related to the shape of the drum hit are extracted by using tri-axis accelerometer sensors of the mobile device. These features provide an expressive percussion experience that closely imitates playing an actual instrument. An application of the virtual Kompang is described with an evaluation of the system with ideas for future developments.

9 96 Designing Engaging

Community Learning

Application with

Children using

Gamification

Norshikin Zainal

Abidin, Aslina

Baharum, Syed Mohd

Fairuz Syed Mohd

Dardin, Nur Shahida

Ab Fatah, Ismassabah

Ismail and Nurhafizah

Moziyana Mohd

Yusop

This research presents an approach to engage the children with a learning mobile application. The interest in education and learning pro-cess are increasing significantly due to the emerging of digital technologies. The use of e-learning in particularly for children to improve the learning process has been an issue as educators are facing problems on how to promote and to stay engaged with them.. Due to the new technology that applies the new method into the e-learning process they able to overcome the problem. The aim of this study is to identify the features and guidelines for designing engaging for community learning with children using gamification technique. Hopefully, the proposed community learning application can engage the children using the proposed technique. The research finding revealed that the gamification technique could help the student to engage with the learning material effectively.

Session 3A, 11:40 – 1:00 pm (31 July 2018)

Ballroom1 (SEIS)

Session Chair : Dr. Jamilah Din

No. Paper


Abstract

1. 74 Industry Involvement

to Enhance the HCI

Project-Based

Learning Experience

Using User-Centered

Approach

Azrina Kamaruddin ,

Evi Indriasari Mansor,

Novia Indriaty

Admodisastro, Noris

Mohd Norowi and

Alfarina Abdullah

Human-computer interaction (HCI) is one of the courses that require in-depth involvement with the end-user to build usable and useful software. The course consists of both theory and practical aspects. One element in this course is doing project work. Throughout the semester, the project has been about a lecturer assigning groups of students with project topics for them to complete by the end of the semester. It is a common practice and has led the students to stagnant learning experience throughout the semester. In order to make students’ learning experience more challenging and engaging, the project has included the industry as part of its 14 weeks duration. The industry was involved in giving the project title, persona, and conducted formative and summative assessments. Finally, an interview session was conducted with the students to obtain information about their learning experiences with the industry involvement while doing their project. The study received both positive and negative feedback from students about this approach


2. 75 Accessibility Design Issues with Malaysian News Websites: A Case Study Using Achecker and WAVE Mariam Azwa Yazid, Azrul Hazri Jantan, Abdul Azim Abd Ghani, Azrina Kamaruddin and Novia Admodisastro

The objective of this research is to provide public society and web developers with a higher level of awareness on web accessibility is-sues in Malaysian websites. The finding is extremely crucial to avoid discrimination among the disable community to use Information and Communication Technologies (ICT) in their daily lives. Accessibility evaluation has been performed on four Malaysian broadsheet news websites using two online automated tools. The analysis is based on the compliance level of the WCAG (Web Content Accessibil-ity Guidelines) 2.0 standard. The research also identified the common accessibility design issues found in most of Malaysian news websites. The result of this study shows that none of the Malaysian news website conformed with WCAG 2.0 standard. The websites fail to provide an alternative text to convey the information for non-text content in their websites. Therefore, serious improvement is needed to improve the accessibility of the websites with the aim to provide the universal access websites.

3. 83 Enterprise Integration of Employee Onboarding Process Using Zachman Framework Wan Faezah Abbas, Siti Hajar Ismail, Haryani Haron and Wan Nor Amalina Wan Hariri

Onboarding is the process of getting newly hired employee to adjust to the social and performance aspects of their new jobs quickly and smoothly. It is important to the organization to maximize the employee retention and productivity and increase their satisfaction and loyalty where it could reduce cost of hiring employee by reducing the turnover rate. Studies have shown there is a requirement to integrate the business process between the enterprise entities to make the onboarding processes run smoothly and effectively. Therefore, the main objective of this study is to analyze the business processes to be integrated in the enterprise organization. Using qualitative methods, interview and document review, analysis was conducted to understand the current onboarding practices and processes in a case study. As a result, this research proposes a business process driven modelling for analysing enterprise integration requirements by using Zachman framework.

4. 88 The Effectiveness of an Enhanced Weighted Method with a Unique Priority Value for Test Case Prioritization in Regression Testing Asmaa Ammar, Salmi Baharom, Abdul Azim Abd Ghani and Jamilah Din

Regression testing is an important and expensive strategy in software testing. To reduce its cost, many methods have been proposed including the test case prioritization methods. The aim of the prioritization methods is to define an ideal order of test cases that allows for higher coverage and early fault detection with minimal number of executed test cases. However, the problem with most of the existing test case prioritization methods is the random sorting of test cases when two or more test cases record equal priority values. In this paper, an enhanced weighted method using a unique priority value, UniVal, is proposed. Unival prioritizes test cases based on code coverage criteria with information from history of previous executions. In addition, a controlled experiment was executed, and the results were statistically analyzed to evaluate the effectiveness of the proposed method. The results show an improved performance in terms of prioritizing test cases and achieving higher APFD values.


5. 97 Association of People Factors with Successful Enterprise Architecture Implementation Nur Azaliah Abu Bakar and Surya Sumarni Hussein

Many organizations are facing problem in Enterprise Architecture Implementation as it fails to meet expectations. While much has been written about the success factors related to EA framework, EA tools, and business-IT alignment process, there are few empirical investigations focusing on the people factors. Therefore, this paper aims to investigate the association of people factors with successful EA implementation by identifying seven people factors from the literature. A quantitative survey was conducted to assess the hypothesis that this seven people factors are associated with the successful EA implementation. The analysis reveals that only five factors are associated with the success of EA implementation, while two are not. Based on the result, this study highlighted that it is important to analyze the people factors in details rather than one whole factor because each of the people factors identified has their own uniqueness and success elements

Session 3B, 11.40 – 1.00pm (31 July 2018)

Kenyalang (AIBD)

Session Chair : Assoc. Prof. Dr. Nurfadhlina Mohd Sharef No. Paper

ID Title of Paper /

Author

Abstract

1. 76 Scoring Matrix Framework for Threat Factor Profiling Model Maslina Daud, Sabariah Ahmad, Syafiqa Anneisa Abdullah, Naqliyah Zainuddin, Fatimah Sidi, Marzanah A. Jabar, Lilly Suriani Affendey, Nurfadhlina Mohd Sharef, Iskandar Ishak, Maslina Zolkepli, Fatin Nur Majdina Nordin, Nur Zahirah Md Noor, Norazlin Yusof, Hashimah Amat Sejani, Saiful Ramadzan Hairani, and Azizi Sabron

One of the important requirements in preparing for an information security risk management system is to construct a threat profiling model that can be used to identify and classify threats. Threat profiling model provides organization a complete set of information including pattern of threat scenarios and analysis on the threat they encountered. However, an organization must set goals and outcome of a threat profiling, as well as metrics in order to measure, understand and counter the potential threats. The main contribution of this paper is the framework of the threat scoring which extends of our previous finding on combinations of components found in referred threat models. Furthermore, to the best of our knowledge, threat scoring framework has not been investigated by any previous approaches. In fact, the computed threat score enables the quantification of the degree of threat severity which is an important benchmark for an organizations to plan their countermeasure actions. Therefore, a scoring matrix framework for Threat Factor Profiling (TFP) model that includes identification and classification of threat is proposed. The purpose of this framework is to identify threats based on activity within an information system of an organization. The Threat Profile Report presents the collected data of threat based on the predetermined matrix

2. 78 Comparison of Different Feature Selection Techniques in Attribute Selection of Learning Style

Learning style of specific users on an online learning system is determined based on their interaction and behaviour towards the system. The most common online learning theory used in determining the learning style is the Felder-Silverman’s Theory. Many researchers have proposed machine learning algorithms to establish learning style


Prediction Haziqah Shamsudin, Umi Kalsom Yusof and Maziani Sabudin

by using the log file attributes. Due to many attributes in predicting the learning style, the performance and efficiency of the classification and prediction are still poor; so far it is only between 58%-85%. This research is conducted to determine the most relevant attributes in predicting the learning style. First, three different feature selection methods are used to select the most relevant number of attributes, which are Rank by Importance (RbI), Recursive Feature Elimination (RFE) and Correlation. Next, five different classifiers are used to evaluate those selected feature selection methods. The classifiers are Support Vector Machine (SVM), Random Forest (RF), k-Nearest Neighbour (KNN), Linear Discriminant Analysis (LDA) and Classification and Regression Tree (CART). From the experiments, RbI has proven to be the most effective feature selection method, with the accuracy improvement from87% to 91%.

3. 79 A Study of Diabetic Retinopathy Classification using Support Vector Machine Nur Izzati Ab Kader, Umi Kalsom Yusof, and Syibrah Naim

Diabetic Retinopathy (DR) is a diabetic complication which can cause blindness. As DR cases keep increasing, ophthalmologists are forced to diagnose a large number of retinal images daily. Generally, the diabetic eye screening is done manually using qualitative scale to detect abnormalities on the retina. Although this approach is useful, the detection is not accurate; and create a need for a tool that can help the experts to classify the severity of DR to establish adequate therapy. Previous researchers have studied machine learning to propose an automatic DR classification. However, it needs to be improvised especially in terms of accuracy. Hence, this paper aimed to find classifier with optimal performance in the study of DR classification. This study considered three classes of diabetic patients which were patients who do not have DR (NODR), patients with non-proliferative DR (NPDR) and patients with proliferative DR (PDR), instead of focusing only on two classes (NO DR, DR). Support Vector Machine was used in this research due to the success of many classification problems that had been proposed which produced good result. The results obtained showed that SVM gave the best accuracy, 76.62% with average sensitivity of 0.8081 and average specificity of 0.8376 respectively.

4. 93 Mobile Malware Classification Zolidah Kasiran, Norkhushaini Awang and Fatin Nurhanani Rusli

Android malware is growing at such an exponential pace which lead out to automated tools that can aid the malware analyst in analyzing the behaviors of new malicious applications. This project had proposed clustering in intrusion detection method using hybrid learning approaches combining K-Means clustering and Naïve Bayes classification had been proposed. The result had shown the improved false rate alarm in malware detection.

5. 95 ResQ Banjir: A mMbile Apps for Emergency Rescue, Evacuation and Relief Center Management Muhammad Rafie Mohd Arshad

A quick response to urgent relief needs after a natural disaster is vital to the alleviation of a disaster’s impact in the affected areas. Flood victims had difficulties in sending emergency relief requests as they had limited phone battery life to highlight their current location. Such limitation led to the difficulty in locating the victims, which affected the effectiveness of coordinating a rescue and evacuation operation. In this research, we develop ResQ Banjir application which consist of Flood Rescue & Evacuation Operation Management (FREOM) and Flood Relief Centre Management (FRCM) to assist in flood disaster management. In these


system, we exploits the existing and emerging technologies on smart phones and tablet such as sensors, cameras, GPS, SMS, Location Based System (LBS) and Augmented Reality (AR). The FREOM system is a web and mobile apps based system consist of the Rescue & Evacuation Management System (server) for rescue and evacuation operation monitoring & management at the flood operation center; SOS/SMS Flood apps for sending SOS help by victims; ResQ Banjir Skuad Penyelamat apps which is used by rescue teams to locate and rescue flood victims, and an Augmented Reality (AR) guidance system for location direction navigation guide. FRCM is a web based system which integrates a number of features such as flood relief center registry, shelter activation and management, inventory management and disbursement, and relief aid and goods supplies management. We conducted a simulation testing that involves the overall capability of the applications. Both systems seem to be working in an efficient manner although there are some issues that exists.

Session 3C, 11:40 – 1:00 pm (31 July 2018)

Engseng (IDMA)

Session Chair : Dr. Mas Rina Mustaffa No. Paper

ID Title of Paper /

Author Abstract

1. 37 Improved Segmentation for Intravascular Ultrasound (IVUS) Modality Suhaili Beeran Kutty, Rahmita Wirza O.K Rahmat, Sazzli Shahlan Kassim, Hizmawati Madzin and Hazlina Hamdan

IVUS is the modality to investigate the internal structure of the coronary artery. This paper presents the process to segment catheter shape, inner and outer layer of the artery that appears on the IVUS modality. The new algorithm is proposed to detect the catheter shape and percentage of the accuracy is 100. We also provide information on detection of lumen and media-adventitia border and area using parametric deformable model algorithm with gradient vector flow as the external force. The PAD value for the segmentation is below than one, indicate that this proposed method is encouraging for IVUS segmentation process. Based on the inner border detected, media-adventitia boundaries also can be detected without manual initialization points. This work is important to facilitate the process of the 3D reconstruction of the coronary artery.

2. 54 Design Models for Mobile Augmented Reality Exergames: State-of-the-Art Review Hasdina Lynn Hashim, Azrina Kamaruddin, Rahmita Wirza O.K. Rahmat and Azrul Hazri Jantan

The sedentary lifestyle is common in this digital age and a cause of concern as it encourages individuals to elicit sedentary behaviour i.e. lower instances to being physically active. This lifestyle affects the major portion of the population; with obesity being a major risk and a factor for many cardiovascular diseases such as coronary heart rate disease, heart failure, stroke etc. Use of mobile devices may be linked to the increase of sedentary individuals, however its usage could also be utilised to encourage fitness awareness among its users. Incorporating interactive digital applications such as exergames, a combination of exercise and games, to mobile devices could provide the means to encourage fitness activity for sedentary individuals through physical gameplay. This paper explores the current design models of exergames and how their usage can affect changes to the psychological and physiological states of the players as well as the


promising directions for adapting their usage for the mobile environment through augmented reality immersion

3. 50 User Behavior Towards Video Content in Mobile Devices for Designing Individualistic Prefetching Algorithm Shuria Saaidin and Zolidah Kasiran

Prefetching content in mobile network environment are meant to shorten users perceive waiting time. Different approaches have been taken by various literature to provide an algorithm that are able to predict user request ahead of time. A questionnaire was design and distributed to verify approaches taken by those research using new respondents. Base on the response analyzed it is found that the most important aspect that influenced user behavior towards video content is the relevancy of the topics and WiFi is the most preferred type of connections to be used to download video content. Another behavior observed is that users who are willing to watch prefetched video also tends to download a new video. The analysis also confirm that user could be categorized to heavy and light users and they behave differently during weekdays and weekends. Findings from this survey would hopefully become a guidance in designing a prefetching algorithm that suited individual needs.

4. 72 Integration of Gamification Mechanics and Dynamics to the Authentic Learning Environment (ALE) in Non-Game Context Sharifah Nafisah Syed Muhammad, Rosnah Idrus, Nasuha Lee Abdullah and Pantea Keikhosrokiani

In educational environment, one of the most important factors for students development and achievement is their engagement level with the learning activities. However, some students are lacking in essential 21st century skills that are important for their working life and daily activities. The essential skills are associated with high level thinking skill. Authentic learning environments promote the environment for high-level thinking skills. This study is proposed to engage students and confront motivational problem by using the gamification mechanics and dynamics in the authentic learning environment. Gamification uses game mechanics and dynamics in a non-game context to motivate, engage and reward user for completing tasks. This paper had identified the commonly used gamification mechanics and dynamics in the gamified learning environment. The identified gamification mechanics are badges, leaderboards, clear goals, fast feedback and points; while the gamification dynamic are achievements, rewards and competitions. From this, a conceptual framework is proposed according to the guideline and the characteristics of authentic learning and integrates it with the gamification mechanics and dynamics identified in this study. Time management skills are chosen as an example of the non-game context of high order thinking skills structured into a system design based on the proposed conceptual framework. An application prototype named Time+ (Time Plus), is developed to foster students motivation and engagement in acquiring effective time management skills. This study aims to help students improve their engagement positively in the gamified learning environment. This research is able to improve the educational experiences for the current millennial students by adapting the gamification concept. Furthermore, it can encourage students to learn and engage with the gamified learning environment and enhance the modern teaching and learning methods.


5. 87 Musafir Ilmu Application Development Using Mobile Application Development Life Cycle Zan Azma Nasruddin, Irwan Mazlin, Maslina Abd Aziz, Mohd Shukor Abd Rahman and Wan Adilah Wan Adnan

The presence of mobile wireless technology has changed the current learning culture environment. Today, smartphone has become an essential device for effective learning. Many mobile apps have been developed covering digital contents for all sorts of disciplines. This paper presents the development of mobile application for Muslims which is focusing on Hijaiyyah pronunciation.This application is named Musafir Ilmu Application with aims to help improve the learning process of Hijaiyyah pronounciation. The Mobile Application Development Life Cycle is employed in the development of the apps. This application has been tested on 32 UiTM students by observation method. Performance of the application is measured using Confusion matrix which calculated the precision and recall rates. The results have indicated the app is an effective learning tool.

Session 4A, 2.00 – 5.00pm (31 July 2018)

Ballroom1 (SEIS)

Session Chair : Dr. Azrul Hazri Jantan No. Paper

ID Title of Paper /

Author

Abstract

1. 111 Dynamic Service Adaptation Framework for Context Aware Mobile Cloud Learning Using Semantic Based Approach Muhammad Sufri, Novia Admodisastro, Norhayati Mohd Ali and Hafeez Osman

Current developments in IT field such as mobile technology and cloud computing have offered modern way of teaching and learning. Effective learning methodologies that meet the learners' requirement as well as support learning resources (LR) with high flexibility, mobility and accessibility are most important aspects. Hence, Mobile Cloud Learning (MCL) has been introduced to boost up the feature of m-learning already provided. MCL comprises of services that integrated with each other. These services are monitored and need enhancement and evolvement based on new learner's requirements for upgrading the services or maintaining the Quality of Services (QoS). Service-oriented systems need to be enhanced through dynamic adaptation process during runtime to sense and react to learner’s context or device’s context known as context awareness to provide a better user experience. This is where ontologies and rule-based approaches used for context representation, descriptions, and reasoning mechanisms to support discovery and matching of services semantically. QoS consideration is important to ensure the efficiency and correctness of the services during adaptation process. Thus, this paper describes dynamic adaptation framework that leverages on semantic based approach for context aware mobile cloud learning. This framework aims to support in service adaptation by considering contextual information and QoS using ontologies and rule-based approaches.

2. 112 Exploring Design Opportunities of Tangible Interaction in Learning for Children with Dyslexia using Secondary Data

Tangible Interaction (TI) have received tremendous attention and become mature in research perspective whereby TI provides efficacy to support in learning. Despite active research in TI, nevertheless there is still a lack of exploring design learning that associated with tangible interaction (TI) for children with dyslexia. To better understand how TI works for children with dyslexia, a secondary data analysis is conducted which obtained from semi-structured interviews with dyslexia teachers


Novia Admodisastro, Siti Nurliana Jamali, Azrina Kamaruddin, Abdul Azim Abd Ghani, Sa’adah Hassan and Siti Suhaila Abdul Hamid

from Dyslexia Association Malaysia (DAM) organizations in Selangor. In this paper, we investigate the study material,and study approach which being adopted in school to support children with dyslexia in learning. Based on data gathered, we identify the study approaches, study materials and how study activity being performed in school. We then derived a design guideline which obtained from this study. The result from this study will be used to develop a tangible interaction system for children with dyslexia in learning.

3. 116 A Domain Ontology for Eliciting Usability Features Too Chian Wen, Sa’adah Hassan, Abdul Azim Abdul Ghani and Jamilah Din

One of the crucial factors that can influence user preferences of software is usability. It assesses the extent of which software able to facilitate user and use the software easily and effectively. Typically, usability requirements are specified at the design stage of software development due to its characteristic that is subjective in nature and hard to be elicited at the early stage. Essentially, it suggested that usability need to be specified at the requirements engineering stage to complement the software functional requirements. This paper presents a study on current efforts to support the activities in identifying usability attributes in the software functional requirements. The potential of adopting pattern and ontology for identifying usability features are also presented. The development of domain ontology is proposed to fill the gap of the current efforts where there is lack of usability driven semantic knowledge model to support the usability elicitation tasks. The designed domain ontology is expected to overcome the problems resulted from software developer that lack of sufficient knowledge or expertise in eliciting usability features at requirements engineering level.

4. 118 A Success Model for Semantic Technology Based - Knowledge Management Systems: An Empirical Investigation Abdulmajid Babangida Umar, Azmi Ja’afar, Marzanah A. Jabar and Masrah Azrifah Azmi Murad

This paper is an attempt to predict on the success of Semantic Knowledge Management Systems (KMS) through the analysis of empirical data. The study proposed a model that shows the relationship between the effectiveness dimensions of Semantic KM Systems, based on knowledge management systems success literature. The proposed model includes two quality dimensions namely, knowledge quality and system quality. Relationship between these measures and two dependent constructs, net benefit and user satisfaction were examined. A total of 5 hypothesis were formulated around the model, and a questionnaire survey conducted to collect data for the model validation. 265 valid responses were received from academicians in Malaysian public higher institutions, and used for the analysis. Although no direct relationship was found between knowledge quality, search-ability, and user satisfaction, result from the study indicated that user satisfaction with semantic KM systems is positively associated with user perceived benefit of the system, which is strongly associated with the search-ability of the system. Also, a weak association between knowledge quality and perceived benefit was revealed.

5. 64 Improving the

governance of

software

maintenance process

Software maintenance is one of the most debated phases in software development process for so many years. Having reputed as the most expensive phase of software development life cycle (SDLC), it utilizes the maximum share of the overall project costs as well as time. Agile


for agile software

development team

Salfarina Abdullah, Mangaiarasi Subramaniam and Sazly Anuar

software development provides opportunities to assess the direction of a project throughout the development lifecycle. However, it does not ideally map with the existing software maintenance process. One of the highlighted issues is the difficulty for searching of information as well as lack of knowledge to solve the maintenance problems within certain time frame. Thus, the main objective of this study is to improve the governance of software maintenance process in an Agile development team. In doing so, a tool named Axita is developed to assist the software maintenance team for storing of information in central data repository and managing projects in more efficient and timely manner. Based on the literature review as well as mapping between the agile software development and the existing ISO software maintenance process, we also proposed six best practices to better govern the software maintenance process in an Agile development team, to overcome the difficulty of information finding and reduce the time spent to solve the maintenance issues. We believe that our study and findings complement the efforts that have been put forth in improving the way we manage software maintenance thus enhance the efficiency of the software development process.

6. 125 Automated Code Optimizer as an Energy Assistant in Green Computing Applications Jamilah Din, Chiew Wei Ooi and Muhammed Basheer Jasser

In the rise of green computing, researchers are looking for more energy efficient software solutions. One of the approaches is optimizing the software design patterns. Studies have shown that adopting certain design patterns (especially Decorator, Observer) leads to a higher energy consumption. Fortunately, there are studies for proposing optimization rules to reduce the energy consumption of such patterns. However, due to the lack of guidance, designers do not adopt these optimization rules. This research aims to identify the factors that cause energy inefficiency during the implementation of software design patterns and to provide a tool to automate the optimization of software design patterns. Based on the experimental results, the adopted automated optimization rules in the proposed tool reduce the energy consumption of the design pattern of interest meeting the research objective in automating the design pattern optimization, which makes it easier to adopt design patterns in green computing.

7. 101 Enhancing Scrum Framework: A Case at a Multinational Semiconductor Company in Malaysia Shalini Mariyappan, Nasuha Lee Abdullah and Rosnah Idrus

Many organizations today are adopting Scrum, an Agile methodology for handling complex software project. Despite all the benefits, there are still issues and challenges in adapting to Agile and some refusals to move from traditional method. This research aims to assess the perception of effectiveness of implementation of Scrum and identify the challenges after adopting Scrum in an information technology (IT) department of company X, a multinational manufacturing company in Malaysia. The findings of this study revealed that after one year of adopting Scrum, the perceptions from the staff is there is no significant improvement made. Five challenges were identified: team members unaware of each other’s tasks, difficulty in handling daily task priorities, no work synchronization among management and delivery team, too many tasks at the middle of sprints and poor attendance during daily stand up meeting. An enhanced Scrum framework that uses Scrum and Kanban is proposed to address the identified challeng-es. The insights gained from this research hope to provide practitioners with useful


reference for adopting scrum.

8. 106 Goal-directed approach and design principle approach: a comparative study Meei Hao Hoo, Azizah Jaafar and Hooi Ching Beh

Uncertainty arises from intuitive design, prioritize usability goal, trade-off among usability attributes, choose usability patterns, conflict opinion during evaluation are putting more difficulties for novice designers in design tasks. As previous studies focused on the effectiveness of novice designers through the use of design patterns, we extended the use of usability pattern to look into the delivery of prototype design. Furthermore, in the aspect of usability analysis, Analytical Hierarchical Process (AHP) technique was applied in the prioritization of usability criteria and usability problems. In this study, AHP is used to prioritize the usability goals and integrated with usability testing and cognitive walkthrough to affirm the result for better judgement. We developed the approach to guide novice designers for the achievement of the targeted usability goal and supported with a tool to capture the collective decisions in providing convinced result during comparative evaluation. We built the approach and compared it using an experimental study with the undergraduate students. Our results suggested that prototype designed by novice designers followed usability pattern approach has more usability patterns applied into and was preferred by experts than using design principle approach.

9. 110 Cognitive-Behaviour Intervention in Developing an Adaptive Learning Model for Students with Dyslexia Novia Admodisastro, Siti Suhaila Abdul Hamid, Azrina Kamaruddin, Abdul Azim Abd Ghani and Noridayu Manshor

Cognitive-Behaviour Intervention (CBI) is to design suitable intervention for students by identifying cognitive as well behaviour conditions. Through CBI, the students' learning goals are easier to establish and the skills of particular conditions can be developed. For students learning difficulties like dyslexia, current interventions were mostly developed to tackled cognitive or behaviour condition separately. While the students with dyslexia suffer from cognitive deficiencies as well as behaviour challenges, both the conditions are interrelatedly. In addition, there were very limited works allowing adaptability in addressing dynamic states of student's learning such as engagement. A study has shown students’ engagement could be a predictor of a good academic performance. Therefore, in this paper, we present the adaptive learning model that considers both cognitive and behaviour conditions for the students with dyslexia. The learning model utilising machine learning model to address engagement states of the students. The results showed a promising new way to assists the students with dyslexia in their learning.

10. 40 Applying ITIL

Framework to

Analyze Problem

Management Key

Performance

Indicator (KPI): A

Case Study of Malay

Owner Company

(Mesiniaga Berhad)

Problem Management (PM) is one of the components in the Information Technology Infrastructure Library (ITIL) Service Support area. The primary focus of Problem Management is to identify causes of service issues and commission corrective work to prevent recurrences. To address this practice and make it more effective, the project tends to identify the specific Key Performance Indicator (KPI) for Problem Management process in a Malay owner company named as Mesiniaga Berhad. The identification of Problem Management KPI is based on the previous research which is using ITIL as a framework. The interview session has been conducted in Mesiniaga with Problem Manager


Mudiana Mokhsin, Amer Shakir Zainol, Siti Nordianah Haihom, Mohd Husni Mohd Som and Abdul Jalil Abdul Rahim

working at that company with more than 10 years’ experience in Problem Management process. The method of interview is using qualitative approach which is using the design question with the lists of KPI. The expert will select or decide which KPI are related with the current report in Mesiniaga. The result showed that 6 KPIs are related and come out with analysis on how the outcome of KPI behavior matched with the Incident report in Mesiniaga. To enhance on how the identification of KPI, instead of using manual to capture the Problem Management KPI, the automation of selected KPI from Incident to Problem Management can be implement in the systems. Most technologies are intelligent enough for data analytic to decide which suitable KPI of Problem Management follow the current business and client environment.

Session 4B, 2.00 – 5:00 pm (31 July 2018)

Kenyalang (AIBD)

Session Chair : Assoc. Prof. Dr. Rohaya Latip No. Paper


Abstract

1. 98 Recognition of Food with Monotonous Appearance using Speeded-Up Robust Feature (SURF) Mohd Norhisham Razali, Noridayu Manshor, Alfian Abdul Halin, Razali Yaakob and Norwati Mustapha

Food has become one of the most photographed objects since the inceptions of smart phones and social media services. Recently, the analysis of food images using object recognition techniques have been investigated to recognize food categories. It is a part of a frame-work to accomplish the tasks of estimating food nutrition and calories for health-care purposes. The initial stage of food recognition pipe-line is to extract the features in order to capture the food characteristics. A local feature by using SURF is among the efficient image detector and descriptor. It is using fast hessian detector to locate interest points and haar wavelet for descriptions. Despite the fast compu-tation of SURF extraction, the detector seems ineffective as it obviously detects quite a small volume of interest points on the food ob-jects with monotonous appearance. It occurs due to 1) food has texture-less surface 2) image has small pixel dimensions, and 3) image has low contrast and brightness. As a result, the characteristics of these images that were captured are clueless and lead to low classifica-tion performance. This problem has been manifested through low production of interest points. In this paper, we propose a technique to detect denser interest points on monotonous food by increasing the density of blobs in fast hessian detector in SURF. We measured the effect of this technique by performing a comparison on SURF interest points detection by using different density of blobs detection. SURF is encoded by using Bag of Features (BoF) model and Support Vector Machine (SVM) with linear kernel adopted for classification. The findings has shown the density of interest point detection has prominent effect on the interest points detection and classification performance on the respective food categories with 86% classification accuracy on UEC100-Food dataset.


2. 108 Parameter Tuning of Groceries Scheduling by Genetic Algorithm M-Nazmi N-S, Shuzlina Abdul-Rahman and Nurzeatul Hamimah

This paper investigates the importance of parameter tuning for an optimization problem. The experiments are performed on different values of mutation operator, crossover operator and a number of iterations on groceries scheduling problem. The knowledge representation and the architecture of the problem are presented. The improvements of the search ability are verified by a series of experiments.

3. 109 Case-Based Reasoning Approach to Map Similar Cases for Accident Injury Claims Shuhaizan Sulaiman, Nurzeatul Hamimah Abdul Hamid, Nur Huda Jaafar and Shuzlina Abdul-Rahman

The procedures of getting compensation from a legal claim are time-consuming. Lawyers spend time to retrieve the similar or relevant past cases to support their claim for a case. The process to map the past similar cases to get the best claim is even more challenging. Thus, this study aims to help the lawyers in their work to speed-up the process of claiming for compensation in an accident case. Consequently, it helps those who need and worthy of the compensated money. This study developed a Legal Advisor of Accident Cases system using a CBR approach which outlines three primary objectives; (i) to identify features of past cases that indicate the similarity of facts to the current case; (ii) to design an intelligent system to assist lawyers in finding similar cases to back up an injury claim case; (iii) to develop a prototype of the legal advisor system that can be used by lawyers to speed-up the case settlement. We interviewed lawyers and collected data from a law firm cases. It reuses the past cases and aligned with the legal procedures. A satisfactory performance was obtained with an efficiency rate of 75%. It has a potential to be extended to cover a wide area of legal claims.

4. 115 Multistage Genetic Algorithm and Q-learning for Flexible Ligand-protein docking Erzam Marlisah, Razali Yaakob and Md Nasir Sulaiman

Protein-ligand docking is an optimization task involving translation and rotation of orientation and torsional angles of a small molecule (ligand) with respect to a target protein. Traditional genetic algorithm can be used to find the optimal conformation, however it often found poor structure with high docked energy due to premature convergence and its weakness in performing precision search. The proposed algorithm is a multistage genetic algorithm with Q-learning agent to overcome the limitations inherent in genetic algorithm and reinforcement learning algorithm. The idea is to combine the explorative speed of genetic algorithm in finding promising area in the search space and the ability of the reinforcement learning agent to do fine-grained search. Docking of ten ligands to thermolysin as the target protein shows the proposed algorithm is more efficient in finding the lowest docked energies and more reliable in finding similar structure every run compared to traditional genetic algorithm and AutoDock Vina in docking highly flexible ligand. The algorithm almost matches AutoDock Vina in docking less flexible ligands and outperforms it in docking highly flexible ligands.

5. 98 Recognition of Food with Monotonous Appearance using Speeded-Up Robust Feature (SURF) Mohd Norhisham

Food has become one of the most photographed objects since the inceptions of smart phones and social media services. Recently, the analysis of food images using object recognition techniques have been investigated to recognize food categories. It is a part of a frame-work to accomplish the tasks of estimating food nutrition and calories for health-care purposes. The initial stage of food recognition pipe-line is to extract the features in order to capture the food characteristics. A local


Razali, Noridayu Manshor, Alfian Abdul Halin, Razali Yaakob and Norwati Mustapha

feature by using SURF is among the efficient image detector and descriptor. It is using fast hessian detector to locate interest points and haar wavelet for descriptions. Despite the fast compu-tation of SURF extraction, the detector seems ineffective as it obviously detects quite a small volume of interest points on the food ob-jects with monotonous appearance. It occurs due to 1) food has texture-less surface 2) image has small pixel dimensions, and 3) image has low contrast and brightness. As a result, the characteristics of these images that were captured are clueless and lead to low classifica-tion performance. This problem has been manifested through low production of interest points. In this paper, we propose a technique to detect denser interest points on monotonous food by increasing the density of blobs in fast hessian detector in SURF. We measured the effect of this technique by performing a comparison on SURF interest points detection by using different density of blobs detection. SURF is encoded by using Bag of Features (BoF) model and Support Vector Machine (SVM) with linear kernel adopted for classification. The findings has shown the density of interest point detection has prominent effect on the interest points detection and classification performance on the respective food categories with 86% classification accuracy on UEC100-Food dataset.

6 66 A library for articulating the measurement streams with columnar data Mario Diván and María Laura Sánchez Reynoso

The CINCAMI/Measurement Interchange Schema (MIS) organizes jointly data and metadata generated from the heterogeneous measurement devices under the same data stream. The Processing Architecture based on Measurement Metadata (PAbMM) is a data stream engine which processes the data streams organized under the CINCAMI/MIS schema. PAbMM is able to replicate in real-time each measurement stream but limited to C-INCAMI/MIS. This constitutes a use limitation of CINCAMI/MIS because the reading, using and writing of the measures was previously performed just by PAbMM. The CINCAMImisConversor library extracts this functionality with the aim of fostering the using along with any measurement project who need it. The functionality extraction was guided by PAbMM´s internal behavior, which is documented through SPEM metamodel. This allowed defining to the CincamimisConversor’s object model, its implementation and carry forward a discrete simulation for having an associated time reference. As a contribution, the library allows the data format conversion from the CINCAMI/MIS streams to the columnar organization. The library could translate 4900 measures in approximately 11 ms.

7. 17 Knowledge Management Strategy and Initiative for Development of Digital Energy Hub Hairoladenan Kasim

This article revised several Knowledge Management (KM) strategies and initiatives, in order to develop the digital energy hub. This digital platform employs robust computers and network technology to cater for a wide-range exchange of information and knowledge, which eventually supports new businesses, collaboration and globalization for the energy players. The objective of this article is to analyze KM strategy and initiative for the purpose of developing a digital energy hub. Thus, by accurately identifying the relevant KM strategies and initiatives, the probability for future development and deployment of this KM platform to be successful can be enhanced.


8. 31 Near Field Communication (NFC) Technology Security Vulnerabilities and Countermeasures Manmeet Mahinderjit Singh, Ku Aina Afiqah Ku Adzman , Rohail Hassan

NFC operates on low-range 13.56 MHz frequency within distance from 4cm to 10cm and the applications can be categorized as touch and go, touch and confirm, touch and connect, and touch and explore. NFC applications are vulnerable to various security and privacy attacks such due to its physical nature; unprotected data stored in NFC tag and unsecure communication between its applications. This paper aims to determine the likelihood of security risks happening in an NFC technology and application. We present an NFC technology taxonomy covering NFC standards, types of application and various security and privacy attack. Based on observations and the survey presented to evaluate the risk assessment within the touch and go application demonstrates two security attacks that are high risks namely data corruption and DOS attacks. After the risks are determined, risk countermeasures by using AHP is adopted. The guideline and solutions to these two high risks, attacks are later applied to a secure NFC-enabled Smartphone Attendance System.

9. 32 Privacy Preserving Technique for Mitigating Anonymity Attack in Pervasive Social Networking Applications Nur’Ayuni binti Adnan, Manmeet Mahinderjit Singh, Aman Jantan

Pervasive Social Networking (PSN) applications become more popular in the last few years. The uses of PSN applications through mobile devices such as smartphones, tablets will lead to the security and privacy issues. This is because users tend to share their personal information with the third party organizations such as applications in mobile devices. Due to the development of social network, the security and privacy need to be improved as well as others to make sure that all the user’s information is protected securely in social network (SN). In this study, we will focus more on the privacy issues on how to preserve the privacy of user’s data from being known by the third party. The dataset of PSN application will be tested using data mining tool, which is Weka, in order to identify the optimal technique and classifier that can be applied to conceal the information. Then, a new enhanced base learner will be proposed, which is masking technique algorithms will be implemented into the dataset of PSN application at the end of this research.

10. 99 Price Changes Analysis Using Association Rule Mining on Online Shopping Portals Aini Atikah Baharudin, Sofianita Mutalib, Nurzeatul Hamimah Abd Hamid and Nor Hayati Abdul Hamid

In the recent years, the growth of online marketplace explodes and has become the new norm of shopping. Access to the internet allows consumers to visit local and global online marketplace. By using online shopping, consumers can view the latest products and comparing products' prices. Online marketplace offers flexibility and eases consumers in so many ways. On the contrary, it also has some limitations. Dynamic pricing allows sellers to enhance their marketing strategy by ensuring price competitive with other sellers. The frequent occurrence of real-time price changing limits the user to get the best deal. This paper discusses the analysis of price changes using Association Rule Mining. Price-ChARM finds a frequent pattern of price changes in corresponding to different timelines. On the online marketplace, due to multiple sellers can sell the same item with different offers such as delivery speed and dynamic pricing, the comparison can be quite tricky. We collected data from two well-known portals and we represent the dataset as set of prices for different products for the purpose of frequent itemset mining. We implement the Apriori algorithm and use a total amount of 3,960 records. We


generate association rules from the frequent itemsets found in the records and visualize the confidence of 0.9 rules. The association rules represent the pattern of price changes in the portals. This study eases consumer shopping experiences by understanding the trend of price changes to provide a better decision in making a purchase.

Session 4C, 2.00 – 5.00pm (31 July 2018)

Engseng (CNDS & IDMA)

Session Chair : Dr. Abdullah Muhammed No. Paper


Abstract

1. 130 Channel Estimation in OFDM Multipath Fading Channel Systems according to Modulation Schemes Alaa Abdullah Al-Saadi, Rohaya Latip, Abdullah Muhammed and Mohd Helmy Abd Wahab

Orthogonal Frequency Division Multiplexing system (OFDM) is a very popular communication technique is applied nowadays in several wireless network modern systems. Wireless communication system has some limitations, one of them is Multi Path Fading Channel. Therefore, our paper is specifically focused on study of the importance of applying channel estimation in OFDM system which leads to be close to an accurate data. Basically, There are many types of channel estimation techniques, e.g., Least Square Error Estimation (LSE) and Minimum Mean-Square (MMSE). In our study, we utilized LSE and proved the necessity of applying channel estimation in multi path fading channel by verification that with simulation codes in Matlab and make a comparison by sending data, e.g., Baboon image with and without channel estimation technique. Our study is very useful for new researchers to get a clear image for the importance of channel estimation with multi path fading channel in OFDM technique.

2. 133 Enhanced Congestion Control Algorithms for LEO Satellite Networks Fahrul Hakim and Shamala Subramaniam

Since TCP WestwoodNew is designed to be implemented in wired and wireless network environment, there are few drawbacks found when TCP WestwoodNew is implemented in the satellite network environment. For examples, the sender cannot fully utilize the available bandwidth because the rate of the congestion window increment in Slow Start phase of TCP WestwoodNew is rather slow. The other problem is, since packets losses often occur due to link errors in satellite environment, TCP WestwoodNew tends to decrease its throughput drastically without committing proper available bandwidth estimation. In this research, there is a potential for TCP WestwoodNew to be improved by increasing its throughput and implemented in satellite networks. In this research, we suggest that the congestion avoidance algorithm of TCP WestwoodNew to be modified. This modification aims to improve the performance of TCP flows by increasing its throughput while attempting to maintain packet delay and the percentage rate of packet drops from getting worse.

3. 134 Performance Evaluation of Load Balancing Algorithm for Virtual

Cloud computing is moving towards new era, has merged into a new opportunity to further enhance way of hosting data center and provide services. Cloud computing is a huge and comprehensive scale distributed computing model, which it is depends on financial size of


Machine in Data Center in Cloud Computing Yuganes Parmesivan and Sazlinah Hasan

the cloud services. The primary substance of cloud computing is to deal the computing power, storage, different sort of stages and services which assigned to the external users on demand through the internet. Task scheduling in cloud computing is vital role optimization and effective dynamic resource allocation for load balancing. Thus, load balancing is to assign tasks to the individual nodes of the shared system so that no single node is overloaded or under loaded. A Hybrid approach of Honey Bee (HB) and Particle Swarm Optimization (PSO) load balancing algorithm is combined in order to get effective response time. The proposed hybrid algorithm has been experimented by using CloudSim simulator. The result shows that the hybrid load balancing algorithm improves the cloud system performance by reducing the response time compared to the Honey Bee (HB) and Particle Swarm Optimization (PSO) load balancing algorithm.

4. 94 Ease of Use and Usefulness Evaluation of Medical Family Tree Data Visualization Siti Fatimah Bokhare, Wan Mohd Nazmee Wan Zainon, Mohd Azam Osman and Abdullah Zawawi Talib

Ease of use and usefulness are two of the evaluation methods that are used frequently to evaluate software or visualization tools. It is used to investigate user acceptance and usually requires a model explaining people's attitudes and behavior as well as reliable and valid measurement instruments. Family trees on the other hand have many potentials to be explored for research purposes, especially medical family tree data or genogram. However, some limitations exist while using family tree or genogram, namely problems in visualizing the wealth and complexity of the information represented once a family tree gets bigger and more complex. Hence, a framework for exploring medical family tree data is proposed. This paper focus on the evaluation part that has been done in order to evaluate the ease of use and usefulness of the proposed visualization framework. The results will be helpful in understanding the potential and limitations of the proposed approach

5. 24 Uncovering the Satisfying MOOC Gamification Elements via Fuzzy Analytic Hierarchy Process Nie Hui Ling, Chwen Jen Chen and Chee Siong Teh

The constantly high drop-out rate in MOOCs remains as a concern of many MOOC providers. Gamification elements in MOOCs are seen to be able to alleviate this problem. As satisfaction is crucial to sustain learners’ engagement in MOOCs, this study aims to uncover the satisfying gamification elements for MOOC via Fuzzy Analytical Hierarchy Process (FAHP) approach. The study reveals learner-learner interaction as a significant criterion to provide a sense of satisfaction among MOOC learners and the most satisfying gamification elements are leaderboard, badge and opponent and thus, should be considered to be incorporated into MOOCs.

6. 48 Head Gesture Recognition and Interaction Technique in Virtual Reality: A Review

Nurul Nasuha Zolkefly, Ismahafezi Ismail, Suhailan Safei, Syadiah Nor Wan

This paper presents a review of head gesture recognition using specific models by year timeline. The related topics of this project also mainly discuss (a) Virtual reality interaction technique, (b) Virtual Reality head gesture interaction, and (c) Mobility Impairments using virtual reality (VR) System. This study contributes to an exploration of a different body part of the gestural input, which is the head gesture as the main interaction approach in virtual reality (VR). This review also prepares new insights of head gestures on how the model theoretically recognises the gesture and implemented as input modality and interaction in virtual reality (VR) environment.


Shamsuddin, and Mohd Azhar M. Arsad

7. 121 IOT-Based Battery Monitoring System Nur Imanina Mohamed Anuar, Mohd Helmy Abd Wahab, Radzi Ambar, Shukor Sanim Mohd Fauzi, Aslina Baharum, and Hafizul Fahri Hanafi

This paper described the application of Internet-of-things (IoT) applied in monitor the performance of vehicle battery. As the trend is clear that electric vehicle is totally depend on the source of energy from a battery. However, the amount of energy supplied to the vehicle is decreasing gradually that lead to the performance degradation. As the battery manufacture concern on this problem, the idea is proposed to monitor the performance of the vehicle using IoT techniques so that the monitoring can be done directly. An IoT application consists of two major parts i) sensors and processor ii) the monitoring system. Finally, the system has been successfully tested. The system was capable to detect degraded battery performance and send the notification to the battery manufacturer for further action

PROGRAMME DETAILS BOTH W/O AND WITH ABSTRACT …fyp.upm.edu.my/icicse2018/Programme_Details.pdf · Nur Azaliah Abu Bakar and Surya . ... Nurfadhlina Mohd Sharef, Iskandar Ishak, Maslina

Documents