Dr. K. Yogeswara Rao Mobile: 9963265836 Email:[email protected]Key Highlights: MCA, M. Tech-IT, Ph.D.(CSE) with 18+ Years of IT & Academic exposure Professional strengths: ➢ Possess good communication and team spirit. ➢ Extensive Knowledge of Data Mining and graph theory, DBMS, OOP, Artificial Intelligence and Machine Learning, IoT, WSN(Wireless Sensor Networks). ➢ Strong urges to learn new technologies. ➢ Ability to complete assigned course within limited time period. Summary of Skills & Experience (18+ years) Work Experience: Organization : AITAM Tekkali, Designation : Associate Professor. Duration* : June 2017 to tilldate. Organization : GIET, Rajahmundry. Designation : Assistant Professor. Duration* : June 2015 to July 2016. Organization : ANITS, VISAKHAPATNAM. Designation : Assistant Professor. Duration* : May 2008 to April 2013. Organization : RAGHU Engineering College, Visakhapatnam Designation : Assistant Professor. Duration* : May 2007 to April 2008. Organization : Sri Gowri Degree & P.G. College, Visakhapatnam Designation : HOD. Duration* : June 1999 to April 2007 Qualifications: Ph.D. : Awarded (CSE) from GITAM University, Visakhapatnam in January 2017. PG : M. Tech (IT) from AU, Visakhapatnam in 2010. UG : MCA from Madras University in 1997 BOI : M.P.C from Board of Intermediate Education, Hyderabad in 1991. SSC : A.P secondary board of Education, Hyderabad in 1989.
32
Embed
Dr. K. Yogeswara Rao Mobile: 9963265836 … · 2020-02-22 · Dr. K. Yogeswara Rao Mobile: 9963265836 Email:[email protected] Key Highlights: MCA, M. Tech-IT, Ph.D.(CSE) with
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
MCA, M. Tech-IT, Ph.D.(CSE) with 18+ Years of IT & Academic exposure
Professional strengths: ➢ Possess good communication and team spirit.
➢ Extensive Knowledge of Data Mining and graph theory, DBMS, OOP, Artificial
Intelligence and Machine Learning, IoT, WSN(Wireless Sensor Networks). ➢ Strong urges to learn new technologies. ➢ Ability to complete assigned course within limited time period.
Organization : Sri Gowri Degree & P.G. College, Visakhapatnam
Designation : HOD.
Duration* : June 1999 to April 2007
Qualifications: Ph.D. : Awarded (CSE) from GITAM University, Visakhapatnam in January 2017. PG : M. Tech (IT) from AU, Visakhapatnam in 2010. UG : MCA from Madras University in 1997 BOI : M.P.C from Board of Intermediate Education, Hyderabad in 1991. SSC : A.P secondary board of Education, Hyderabad in 1989.
International Conferences/Grants/Publications:
International Conferences:
Metric-Driven Load Balancing System in WMS on Distributed computing
platform, IEEE 3rd International Conference on Machine Learning and
Computing(ICMLC-2011) organized at Singapore in the month of Feb-2011 ISBN
No: 978-1-4244-9253-4
Paper Publications:
Published a paper in IJAER 2016 with title is “Topic Ontology Assisted Multi-
Document Summary Generation” International Journal of Applied Engineering
Research ISSN 0973-4562 Volume 10, Number 23 (2015) pp 43501-43508(Scopus
Indexed).
Published a paper in IJCIR 2016 with title in “Ontology and Query-Focused Multi-
Document Summarization System” International Journal of Computational
Published a paper in IJIRCCE 2016 with title is “User Plan Recommendation
using Mobile Call Log Analysis” Vol. 4, Issue 9, September 2016, ISSN(Online):
2320-9801, ISSN (Print): 2320-9798.
Published a paper in IJIRCCE 2016 with title is “A Study on Tools of Big Data Analytics”Volume 4, Issue 10, October 2016, ISSN (Online): 2320 – 9801, ISSN (Print): 2320– 9798.
Published a paper in IJIRCCE 2016 with title is “Product Recommendation System
from Users Reviews using Sentiment Analysis” International Journal of Computer
Applications (0975 – 8887) Volume 169 – No.1, July 2017
Published a paper in IICTT2017 with title is” An Automated Traffic Surveillance
Control system by using STC algorithm”Volume 2, Issue 4, December 2017, ISSN (Online): 2231-2803
Professional Activities:
Memberships Attained
➢ Member in Computer Society of India(CSI).
Workshops/ Seminars Participated ➢ I attended for Faculty Development Program which is conducted by
NITTTER CHENNAI, ANITS.
➢ I attended for Staff development program which is organized by CSE
department of ANITS and sponsored by AICTE.
➢ I am attended the workshop at ISI Kolkata in “TEXT MINING”.
Academic Activities:
➢ B.Tech Question Paper Setter for AUTONMOUS Institutions.
➢ External Examiner for Project Viva Voce in AUTONMOUS Institutions.
➢ Attendance Committee Member in ANITS Engineering College. ➢ Uploaded AICTE Research Promotion Scheme Proposal for the Academic year
2017-18 at AITAM Teekkali. ➢ Completed NPTEL Courses on DATA ANALYTICS , OPERATING SYSYEMS
Department of Computer Since and Engineering, GITAM University, Visakhapatnam, Andhrapradesh. yogiindusisu@gmail. com
P. V. Nageswara Rao
Department of Computer Since and Engineering, GITAM University, Visakhapatnam, Andhrapradesh. nagesh@gitam. in
Abstract
An effective Multiple Document Summarization (MDS) system is a sound method to provide concise and comprehensive information in a short-form. The conventional summarization techniques exploit the machine learning techniques based sentence extraction and sentence position hypothesis to summarize the huge document collection under the same topic. However, these techniques may lead the redundant and less informative sentences in the summary due to the lack of semantic analysis. To tackle this constraint, this paper attempts to exploit the ontology and word
position hypothesis. This paper proposes multi-document SummarY generatioN with the tOPic ontology asSIStance (SYNOPSIS) approach. The core aim of this approach is to balance the objective function that refers to improve the coherence, and salience of the summary and diminish the redundancy of the sentences. To achieve this aim, the SYNOPSIS model investigates, the two phases, namely optimal sentence ranking and sentence selection in MDS system. Initially, the SYNOPSIS uses Yago ontology to identify the context of the keyword semantically and employs the word position hypothesis to discover the importance of the sentence by ranking the document sentences. To
further reduce the document content, the SYNOPSIS approach focuses on shortening the sentence length by applying the structure analysis of the original sentences. Finally, it selects the key sentences based on the most relevant information on sentence rank and constructs the summary based on the satisfaction of the objective function. The experimental results demonstrate that the SYNOPSIS approach achieves better performance than the conventional summarization method.
Keywords: Ontology, summary, word position, document summarization, coherence, salience, and redundancy
1. Introduction
Due to emerging usability of online information, the attention of effective result provisioning according to the user queries is an important process in Information Retrieval (IR) system. As exponential growth of a number of textual documents on the web, discovering the hidden information is often an arduous task in real-world applications. With the aim of addressing this constraint, Multiple Document Summarization (MDS) model creates a greater impact on the web searching field that facilitates the users to obtain the core information within a short time [1, 2]. MDS focuses on providing the succinct and informative summaries from the larger document collections.
This task is achieved by reducing the irrelevant sentences from the collection of documents to generate essential text summary in IR system. It is the extraction based MDS method that generates the summary by only omitting the sentences from the original text sentences not constructing the novel sentences. MDS is a non-trivial process in real time applications instead of summarizing a single document. For instance, News aggregation application in IR process: when multiple news feeds are submitted about a particular news topic, an IR system is forced to provide a short and comprehensive summary to users for improving the user convenience. It has the responsibility to create an understandable summary. Hence, an automatic multi-document summarization is necessary for IR system to summarize the multiple documents into an extractive summary.
To provide the accurate summarization, Ontology is the most valuable source that captures the hidden semantic information and comprises the abundant concepts and domain-related information [3]. It deals with either questions or input texts to identify the entities and its similarity based hierarchical structure. Most of the conventional researchers exploit the ontology to measure the semantic similarity [4] and to improve the document
clustering [5] in text mining. Comparatively, some of the researchers are focused on the ontology-assisted document summarization. However, the extraction based MDS approaches to meet the redundancy problem since the top-ranked sentences of the multiple documents convey the similar information. Some of the existing methods resolve the redundancy issue while summarizing the multiple documents. The main contribution of multi-document SummarY generatioN with tOPic ontology asSIStance (SYNOPSIS) approach includes two phases such as identification of sentence importance in the document set and optimal summarization of the
document set. • The SYNOPSIS approach summarizes the
multiple documents under the same topic using Yago ontology and word position hypothesis, beneficial in effective IR process.
• The SYNOPSIS approach recognizes the entity of each keyword in the document sentences using Yago ontology after performing the preprocessing steps. Applying entity score, and word position, frequency and distance factors on the sentences enables the SYNOPSIS to assign the score to each sentence semantically.
Due to the increasing growth of online information on the specific topic, Multiple Document Summarization (MDS) has become a non-trivial task. The MDS facilitates the
user to understand the large volume of information in a short time by creating a concise and comprehensive summary. In addition, user’s query based MDS system provides a
consistent summary, including the core of the information. The conventional summarization techniques focus on the dynamic query based summary generation.
However, it lacks in providing the entire user’s information in a single convenient
summary according to the particular topic. As a result, it leads to the complexity of the numerous summary generation process to each query. Hence, ensuring the effective query
relevant information in extractive summary is a crucial task in MDS system. To address this constraint, this paper introduces oNtology and query focused muLti documEnt
sUmmarization System (NUCLEUS). It incorporates the two essential steps such as query based summary type detection and summary generation. In the first step, NUCLEUS
analyzes the document set as well as queries using ontology and Web Search Query Log (WSQL) to determine the summary type. To identify the proper context of the summary,
it categorizes the document sentences based on the entities of the words in a sentence. In
the second step, the NUCLEUS generates the score to each relevant query sentence using the Vector Space Model (VSM) and then, the sentences are compressed by linguistic
structure analysis. Eventually, it measures the edge weight between the sentences to order coherently the sentences which having high salience and information diversity in the final
summary. The evaluation results show that the NUCLEUS system can obtain significant improvement over the conventional summarization method.
Keywords: Multi-document summarization, Query-focused, sentence score, WSQL, and ontology