A Cloud-Based DSS Model for Driver Safety and Monitoring on Australian Roads

Int. J. Emerg. Sci., 1(4), 634-648, December 2011 ISSN: 2222-4254

© IJES

634

A Cloud-Based DSS Model for Driver Safety and

Monitoring on Australian Roads

Shah Jahan Miah and Rakib Ahamed

Informatics Group, Faculty of Business, University of the Sunshine Coast, Australia

School of Accounting and Information Systems, Australian National University, Canberra, Australia

Email(s): [email protected], [email protected]

Abstract. There is a need to balance the requirements of new application

design and technology provisioning platforms to meet both the demands of

clients and new technological environments. This paper introduces a cloud

computing provision for a new decision support systems (DSS) solution

design. The proposed DSS is based on an intelligent method in which

decision/policy makers of the Australian road safety authorities can obtain on-

demand monitoring records regarding the behavior of provisional license

holding drivers. The study proposes a conceptual framework and possible

benefits for deploying a cloud-based DSS service.

Keywords: cloud computing, decision support systems, road safety

1. INTRODUCTION

… We change the tools and then tools change us, and that cycle continues.

--JEFF BEZOS, CEO & Founder amazon.com [45]

Over recent years cloud computing has been touted as a modern architecture of

shared computing service, especially for the provision of various on-demand

services for clients. This service is based on utility rental by different cloud

computing service providers. After the introduction of web-based utility services by

Amazon.com, many service providers became increasingly interested in the cloud

computing platform for launching new services and for meeting a client‘s demand

with minimal labor and expense. Many recent studies provide examples of the

proliferation of cloud computing. For instance, Nurmi, Wolski and Grzegorczyk

[32] describe an open source software framework for cloud computing in which

cloud computing resources are considered as an ―Infrastructure as a Service‖. For

similar services, a study addresses requirements of confidentiality and integrity in

data access and process, and deliberately proposed a trusted cloud computing

platform for facilitating a ―closed box execution and storage‖ in a virtual

environment [39]. Cloud providers such as Amazon, Flexiscale and GoGrid offer

mailto:[email protected]

mailto:[email protected]


635

Infrastructure as a Service for clients to access a virtual machine (VM). These

providers allow businesses to host services at lower layers. Additionally, cloud

providers such as Google offer application layers provision such as Software as a

Service [39]. While there has been little attempt to formalize the growing

requirements of new application design for problem solving, we identify

requirements of designing decision support systems (DSS) service for the clients as

an open source—‗Software as a Service‘ on cloud.

This paper introduces a new requirement of DSS solution design in cloud

computing and describes the possible benefits from both the client and service

provider‘s perspective. The study intends to particularize a hypothetical problem in

which a new DSS solution, based on an intelligent method, is important to develop.

This solution will allow decision makers from Australian road safety authorities to

obtain on-demand monitoring records regarding the behavior of provisionally-

licensed drivers while on the road. A number of recent studies have suggested that

there are detrimental effects in using mobile devices while driving [17][26]. This

affects driving behavior and can be measured in four ways, including reduced

sensitivity to road conditions, increased mental workload, reduction in headway,

and slower responses to events and stimuli [11][42]. Previous studies [6][10]

[15][30] analyze hand-held mobile phone use while driving and suggested that

usage of hand-held devices has a positive relationship with motor vehicle crashes. It

is reported that 84% of Australian drivers own a mobile phone and, more

importantly, 47% of them use their mobile phones while driving [22]. Not only are

these risky driving practices, but also illegal in Australia and in many other

countries (e.g., Canada) [22]. The findings clearly demonstrate the overall

ineffectiveness of the educational campaigns and approaches for law enforcement to

stop mobile phone usage while driving [9][21].

We aim to address this contemporary issue through the use of current

computing infrastructure capabilities. Therefore, this study discusses the

requirement of developing a new on-demand based service framework using cloud-

based provisioning with DSS technology. We propose a conceptual approach that is

comprised of hardware, software, and network components that provide automatic

monitoring support for the relevant road safety stakeholders. The proposed

monitoring solution can automatically detect hand-held device usage while driving,

especially targeting provisionally-licensed drivers. In our proposed conceptual

approach, a small device will be mounted in the vehicle for capturing the/a driver‘s

sequential movement and transmitting information to the cloud so that the road

safety authority can obtain relevant data anywhere. Vouk [44] describes the key

concepts of cloud computing as a service-oriented architecture that can be seen to

reduce IT overheads both for the client and service owners/providers. In a recent

white paper [47], three founders (of Amazon web services, Right Scale, and Path)

identify benefits of cloud-based solutions from the application provider‘s point of

view. These benefits include: control in scaling up and down; quick recovery from

failure; offers an environment for development and testing; quick roll-out of new

solutions to the clients; and efficient load-testing for applications. Further, the latter

authors also described various architectural considerations for successful ‗Software

International Journal of Emerging Sciences, 1(4), 634-648, December 2011

636

as a Service‘ deployment. It is also significant to explore the architectural

considerations within the requirements of our proposed approach.

Design science research methods address various IT artifacts design. In the

literature of socio-technical context of design science, a study identifies multiple

viewpoints of artifacts design such as design as a product, process, intention,

planning, communication, user experience, value, professional practice, and service

[27]. As part of design as planning, McKay et al. [27] include the key qualities such

as modeling, representation, and method. Regarding planning as design, our study

offers a high level of analysis on initial requirements of DSS solution design. As

such, the research question is outlined as: To explore how a cloud-based DSS can

be designed for driver safety and monitoring purposes.

As a subset of information systems (IS), DSSs are classified based on purpose

and used technologies. Carlsson and Turban [4] described the DSS scholarship as

having/moving in four different directions: methods and instruments for addressing

unstructured or semi-structured decision making problems, interactive computer-

based systems for decision support, user-oriented systems for decision support, and

the separation of data and models in DSS applications. According to [4] the first

direction is related to an improvement in management science and operations

research methodology. The second direction involves an advanced DSS solution-

building platform for managers, which has additional features out of descriptive

systems theory and traditional decision approaches. The third direction is related to

forming an effective decision-making platform that functions better than traditional

management information systems (MIS) applications and the fourth direction is

related to forming a foundation for more effective DSS modeling. Our research is

relevant to both the first and second directions for two reasons. First, we attempt to

analyze designing an improved management tool in terms of a monitoring system

that can offer a new operations research methodology. Our second aim is to outline

a conceptual DSS approach that would enhance the traditional DSS system by

enabling provision of customization for decision support.

The remainder of the paper is organized as follows: a relevant background of

the proposed study is outlined in the next section, while the methodological

foundation of the research is detailed subsequently. In the following section, a full

analysis of the proposed cloud-based smart DSS framework is presented, with some

discussions and conclusion given in the final section.

2. PROBLEM BACKGROUND AND KEY CONCEPTS

This section presents the problem background of the target decision making and

also highlights the key technologies for reasoning our conceptual understanding in

the cloud computing environment.

2.1 Target problem domain


637

Recent literature suggests that the use of mobile phones and other in-vehicle

portable devices while driving could cause significant cognitive and physical driver

distraction, increasing the risk of crashes [17] [26]. The number of crashes due to

mobile phone usage has increased significantly in recent times due to the popularity

of mobile phone usage all over the world, especially among young people. It is

reported [3] that 25% of car accidents were caused from talking on mobile phones.

The use of mobile devices while driving is treated as the number one cause for car

accidents. Consequently, it is regarded as being as dangerous as drink driving. So

far, no previous research has been found in the literature to address the requirements

for developing an automatic systematic solution that could offer possible decision

support for the relevant authority. A recent study [43] suggests that in-vehicle visual

display may increase mental workload causing distractions while driving. On the

other hand, in-vehicle notification of safety information can add substantial value to

increase driving attention. In the Australian road transport department, there is

legislation set for ensuring appropriate driving behavior that helps qualify drivers

from their provisional license period to fully professional license holders.

2.2 Cloud computing platform

The term ―cloud computing‖1 has become popular since October 2007 when Google

and IBM jointly announced their collaboration (IBM website) [44]. The service

design in cloud computing has become increasingly accepted within the web

community, because it offers reduced IT overhead and flexibility for users. At the

same time, from the service provider‘s point of view, it offers reduced service

costing for providing on-demand services [44]. FitzGerald and Dennis [13] describe

cloud-based design as a ―circuit-switched service architecture‖ that is easier to

implement for organizations because ―they move the burden of network design and

management inside the cloud‖ (p. 297).

The heart of cloud computing is the virtual machine (VM) and its mechanism

for providing resources and support services to the users [32]. Alternatively, in

service-oriented architecture, cloud computing ―refers to both the applications

delivered as services over the Internet and the hardware and systems software in

the data centres that provide those services‖ [2] (p.1). In terms of the purpose of

software application, the ―machine virtualisation‖ is even more useful as a service

for its enhanced capability. Thus, this becomes an interesting research area. The

study identifies three significant aspects of cloud computing as Software as a

Service over the traditional service [2]. Firstly, cloud computing offers computing

resources on demand for end users to plan their long term provisioning. Secondly, it

eliminates up-front commitment by the end users on the computing infrastructure,

and finally, cloud computing enables use of computing resources on a short-term

1 Cloud computing refers to a computing platform in which users have options to

use lease connection points into a network for establishing a temporary operation

between computers [13]. Hayes [18] describes cloud computing as a software

application migration from local PCs ―to distant Internet servers, users and

developers alike go along for the ride‖ (p. 9).


638

basis of services as needed. The last aspect reinforces the requirement for end-user

enabled service provision. This service provision can be viewed as a DSS

application through the cloud-based platform for facilitating end users‘ decision

making.

2.3 Previous Intelligent DSS

For significant real-world application design, many intelligent DSSs have been

introduced both for stand-alone and network-based platforms in previous studies.

Examples of applications in stand-alone platforms are: manufacturing systems [8],

urban infrastructure management [37], family financial planning [14], nuclear

emergencies [34], operational decision making in rural industry [28] and service

network planning [7]. Network-based platforms can be seen in the traditional

methods of road safety and monitoring purposes. For instance, Fernandez-Caballero

et al. [12] present an image-analysis approach for monitoring road traffic to ensure

safer behavior. However, this approach is unable to identify driver behavior as the

image is taken from outside the car.

Muntermann [29] proposes a mobile DSS, so-called MoFiN DSS, that combines

software and hardware components to support individual investors reacting to

unforeseen market events. The DSS model utilizes a forecasting model based on

quantitative metrics that is used for identifying those company announcements for

which significant effects can be expected on the capital markets. Then the

forecasting model is used for estimating the period of time for which abnormal price

effects can be expected, for example time duration. The hardware infrastructure

then provides access to the data sources and communication channels needed to

implement the required functionality. The appealing innovation in this solution is

that there is a GSM/GPRS gateway connected to the infrastructure for managing

seamless information processes from the Internet to wireless communication

networks. On the other hand, the software component of the DSS is used for

managing the entire data collection, processing, and the communication process on

the basis of the existing infrastructure. It implies that integration between hardware

and software is one of the key challenges in developing the DSS solution where

various wireless technologies are involved and playing significant roles.

Quintero et al. [37] describe the intelligent DSS for coordinating urban

infrastructures management by identifying data and associative treatments common

to municipal activities for improving service delivery. This approach used a case-

based reasoning involving a four-step process, namely, retrieving, in which target

problems are/were retrieved from memory; reusing, in which the solution is mapped

from the previous cases; revising, in which a new solution is mapped from the

previous solutions and is tested within the real world; and finally retaining, in which

the new case as adapted to the target problem is stored. Advantages offered from the

case-based reasoning method in DSS development are the analytical provisions, in

which the decision makers can obtain accurate information support.

Cheung et al. [7] describe an intelligent DSS for service network planning, in

which a two-stage methodology using optimization and simulation modeling has

been used to reach the planning solution. However, Delen and Pratt [8] demonstrate


639

the limitation of simulation or model-based DSS as it is found lacking when

addressing real needs for manufacturing managers‘ decision making. As such, it is

proposed an intelligent DSS that solves the current problems of the manufacturing

systems by introducing a new DSS approach that is capable of helping decision

makers throughout the identified decision making life-cycle [8]. The cycle includes

structuring the problem, analysis tools for addressing problems, conducting

analysis, and providing decision results in an understandable way. This method

addresses broader requirements for the decision making rather than focusing on a

specific purpose, such as information support for monitoring. Another intelligent

DSS solution proposed by [28] shows that the domain experts can tailor a/the

knowledge base for DSS application development. The approach addresses the

continuously changing requirements in operational decision making. The vital

understanding in this approach is that the entire solution approach can be tailored to

the situation and regulations changes within the decision making context.

Considering the benefits of cloud computing and information demand from

various service delivery locations, research is required for empirical solution design,

particularly for user-specific services. To address the limitations of existing DSS

models with end-user service delivery provision, it is argued that a new approach is

required for advancement in DSS design using case-based reasoning, for integrating

video and audio information into enhanced on-demand decision making. The new

approach should also promote rapid decision making through the utilization of

cloud computing.

3. RESEARCH METHODS

Design science research has the potential to address any new solution requirements

and its further development. Muntermann [29], cited by Nunamaker et al. [31],

states that the design science research is ―utility-centric where identified practical

problems are addressed with novel system designs in order to provide suitable

solutions‖ (p. 83). Hevner et al. [19] contend that the design science ―seeks to create

innovations that define the ideas, practices, technical capabilities, and products

through which the analysis, design, implementation, and use of information systems

can be effectively and efficiently accomplished‖ (p. 75). This implies that the design

science research addresses IT artifact design for any problem space. As such, design

science approaches can be used as a methodological lens to conduct our study as we

have identified an unsolved problem space for outlining a new solution concept.

In IS design research, Gregor and Jones [16] describe the objective of design

activity as ―the description of an artefact in terms of its organisation and

functioning‖ (p. 317). As mentioned earlier, McKay et al. [27] depict various design

dimensions in artifact design such as product, process, intention, planning,

communication, user-experience, value, professional practice, and service. This

broader concept helped define the characteristics of our intended design artifact

within the problem context. The design artifact is, however, defined in many diverse

ways. For instance, Simon [40] defines the artifact as something that is artificial

(that is, developed by human actors) as opposed to something that is developed

naturally. A study [41] describes that the artifact can be a ―combined hardware and


640

software system that is designed and implemented within an organisational context

and whose purpose is to collect, [and?] organise… information needed.‖ The IT

artifact is defined by March and Smith [25] as system architecture, system design,

or prototype system that is designed for demonstrating applicability of the

developed solution models [29]. In respect to these definitions, our research follows

the conceptual understanding of [41] and [25] for outlining a conceptual DSS

solution design.

Figure 1: Six activities for the DSS design adapted from Peffers et al. [35]

In addition to the requirement of conducting the entire design process, a study

[24] propose a conceptual model by highlighting the theory of ‗diffusion of

innovations‘ and ‗theory of IS development‘ for developing intelligent DSS in

agriculture. Rogers' [38] diffusion of innovation theory provides support for linking

the three essential parts: the method that is employed for solution design; the design

context in which the properties of the solution design are outlined; and the ultimate

adoption which is required to be conducted through the evaluation process [24].

This model reinforces the significance of intelligent DSS development through

addressing the users‘ needs within the problem context. Lynch‘s [24] concept shows

relevance with the current literature of design science. We argue that such

development methods can be applicable for our intended solution design through a

design mental model proposed by [35]. The framework incorporates six activities,

which include: problem identification, defining solution objectives, design and

development, demonstration, evaluation, and communication. Figure 1 shows the

activities applicable to our design context.

Activity One involves outlining the decision problem to facilitate the

development of the solution artifact. It is important to structure the problem so that

the intended solution artifact can capture the problem‘s complexity. Activity Two


641

defines the objectives of the DSS design artifacts through examining where a new

artifact is expected to support solutions to problems not hitherto addressed, whereas

Activity Three incorporates new artifact design that creates a new set of properties

for the technical solution. Activity Four involves identifying the design context to

demonstrate application of the design to a context to determine relevant instances of

the problem area. Activity Five evaluates the effectiveness and efficiency of the

design artifact by comparing the objectives of the design to actual outcomes from

the use of the solution. The key qualities are contained in performance elements,

such as response time, completeness, or data availability. Finally in Activity Six, the

solution design and its implications are presented to the target users.

4. PROPOSED DSS CONCEPT ON CLOUD

This section describes cloud architectural considerations for the proposed DSS

solution model. We also present the technical details of a conceptual DSS solution.

4.1 Architectural considerations

The cloud architectural model has been classified into three types: a) private cloud,

in which resources are shared across the local network, b) public cloud, in which

resources are shared from the public network, and c) hybrid cloud, in which a

combination of both provisions is present. The combined cloud has the potential to

accommodate DSS applications because most of the target decision makers require

access through private and public networks (e.g., road safety authorities work from

their LAN). On the other hand, it is suggested that application design for the cloud

is different from the application design for a stand-alone machine. Studies identify

some considerations that must comply for cloud application design [47]. Design

considerations are: the simplest application design, splitting functions of the

applications into clusters, realizing network communication, and testability.

Following the guidelines, we compose the DSS functions into three clusters: the

DSS user interface, business rules for decision making, and the preservation of

databases. This helps improve application performance in clusters, enhances

testability through multiple clusters, and monitors its integration points from the

network environment. Figure 2 below illustrates the possible architectural

consideration of the proposed DSS design on cloud.


642

Figure 2: Proposed DSS design clusters on cloud computing

4.2 Conceptual DSS model

The objective of the study is to outline a conceptual framework that can

automatically detect when a driver is using a hand-held device, generating an alert

message through an onboard device. To minimize risk, if the use of the device

continues, relevant information will be automatically wirelessly sent to the legal

authority.

Figure 3: Proposed conceptual DSS framework with operational scenario.

Figure 3 above illustrates a model operational scenario of the proposed DSS

framework with possible input and output data. A study [23] propose a cluster-

based approach for the efficient computation of density queries for objects moving

in road networks through the utilization of wireless communication. This solution is

Public network

Client environment

Moving vehicle

Cluster A Cluster B Cluster C

User

interface

Business

logics Database

Public Cloud

Private Cloud

DSS application on public cloud


643

aimed for use in traffic management systems to identify dense locations with a high

concentration of moving objects (such as vehicles) in a road network, mainly for

predicting congested roads or traffic jams. However, as our plan is to install an

intelligent sensor device in every vehicle to interact with the external wireless

network, it would automatically determine the query from every single vehicle since

each of the in-vehicle sensor devices can hold a unique identifier. At the same time,

in terms of keeping continuous records in a dynamic database and providing

facilities for user-behavior analysis for recommendation systems, we examine the

potential of a/the cluster-based approach.

We have identified three major goals involved in the proposed model. Firstly,

there is the design/deployment of an automatic system that would detect the driver

of a moving car talking on a hand-held mobile device using an onboard processing

device containing a video sensor, GPS navigator, and/or in-built speedometer

reading and wireless communication device. Secondly, the system facilitates the

automatic generation of an alert message for a certain period of time. To minimize

the risk, wireless transmission of relevant information is processed to notify the

legal authority, if necessary.

The following five processes have been identified to meet the goals defined

above:

Determining vehicle motion

The main purpose here is to prevent drivers from using in-vehicle hand-held devices

while driving. The first processing step is to determine whether the vehicle is

moving. The processing unit can determine this either from the odometer reading or

using an onboard GPS navigation system.

Capturing video and audio data inside the vehicle

A fixed in-vehicle camera with static background can precisely identify a driver

interacting with a hand-held device by capturing and analyzing the audiovisual

information. To achieve this, the smart processing unit shown in Figure 3 needs to

be installed at the front side of a vehicle to clearly capture at least the upper part of

the driver, driver‘s seat and steering wheel.

Detecting the use of hand-held device while driving

The captured video frames need to be analyzed to basically detect the following

subsequent phases:

a) detection of drivers carrying hand-held devices and

b) detection of drivers interacting with hand-held devices.

Shape- and texture-based video object segmentation techniques can be explored for

this purpose [1].

Transmitting and generating warning message

As alluded to above, it is evident from the literature [43] that a warning message can

bring substantial benefits in increasing safer behavior on the road. The smart

processing unit will be able to transmit records of the car and drivers to a database


644

located at cloud server. The processing unit will have the ability to generate a

warning relevant to the driver‘s activity determined from phase 3.

Communicating automatically with a designated server and/or legal

authority

If the use of a hand-held device continues after the warning, the processing unit will

automatically start communicating with a designated server or a legal authority

through a/the cloud server by sending urgent messages. The communication

includes vehicle details with its current location (automatically obtainable from the

on-board GPS navigation system) and the type of driver activity.

5. DISCUSSIONS AND CONCLUSION

This article claims to be a potential research avenue for developing a real DSS

solution for the Australian road safety authority. It is argued that current DSS

suffers from end-users provisioning issues within complex network environments.

The conceptual study outlined a research requirement for developing a novel cloud-

based DSS solution in the bedrock of an intelligent DSS. We have discussed the

innovative design requirements within a design science methodology to exemplify

the methodological underpinning. Knowledge from both problem space and

previous literature supports further extensive investigation on establishing further

empirical contribution. This initiative would enhance DSS scholarship within new

provisioning cloud technology.

The successful implementation of the design model would potentially provide

invaluable services to the road transport authority and drivers by enhancing road

safety features, and thus help prevent risky driving practices. For instance,

traditional intelligent DSSs are designed particularly for monitoring purposes, often

based on a model or analytical algorithms, rather than the flexible approach

presented in this study.

We believe that legal and privacy implications are the paramount concerns in

implementing this proposed solution. Previous studies have addressed these issues

in appropriate ways. In North American regions, an appropriate Public Safety

Answering Point, Enhanced 911 service is used to track callers‘ physical address for

emergency responders. The Enhanced 911 wireless-based enhanced emergency

service is established through the special privacy legislation. From a law

enforcement point of view, Phillips [36] suggested consequences of ―reasonably

available‖ information as a legal precedent for law enforcement authorities and

police agencies through telecommunication providers. This principle could also be

applied for life-saving purposes for drivers on Australian roads. With respect to the

second concern (privacy), Santos et al. [39] suggested a trusted cloud framework

over traditional security technologies, in that the cloud administrator‘s privileges

were reduced in the virtual execution environment of clients. The features of the

trusted cloud framework [39] ensure the integrity and confidentiality of their

outsourced computations through clouding. Further study is required for evaluating

the initial framework with potential users and authorities within a practical context.


645

REFERENCES

1. Ahmed, R., Karmakar, GC, and Dooley, LS. "Efficient Probabilistic Spatio-Temporal

Video Object Segmentation," 6th IEEE International conference on Computer and

Information Science (ICIS), 2007, Melbourne, Australia.

2. Armbrust, M., Fox, A., Griffith, R., Joseph, AD., and Katz, R. "Above the Clouds: A

Berkeley View of Cloud Computing", 2009, retrieved on 23rd October, 2010, from

http://www.eecs.berkeley.edu/Pubs/TechRpts/2009/EECS-2009-28.pdf

3. Car Accident Cell Phone Statistics-CACPS, 2010. Retrieved 18 July 2010, from

http://www.edgarsnyder.com/car-accident/cell/statistics.html.

4. Carlsson, C., Turban, E. "DSS: Directions for the Next Decade," Decision Support

Systems, 33 (2002), 105–110.

5. Carlsson, S.A. "Design Science Research in Information Systems: A Critical Realist

Perspective", 17th Australasian Conference on Information Systems, (ACIS), 2006,

Adelaide, Australia.

6. Chen, YL. "Driver Personality Characteristics Related to Self-Reported Accident

Involvement and Mobile Phone Use While Driving", Safety Science, 45 (2007), 823–831

7. Cheung, W., Leung, LC, and Tam, P.C.F. "An Intelligent Decision Support System for

Service Network Planning", Decision Support Systems 39 (2005), 415–428.

8. Delen, D., Pratt, DB. "An Integrated and Intelligent Dss for Manufacturing Systems,"

Expert Systems with Applications, 30 (2006), 325–336.

9. Donovan, RJ, Jalleh, G., and Henley, N. "Executing Effective Road Safety Advertising:

Are Big Production Budgets Necessary?" Accident Analysis and Prevention, 31 (1999),

243–252.

10. Eby, DW, Vivoda, JM., and Louis, RMS. "Driver Hand-Held Cellular Phone Use: A

Four-Year Analysis," Journal of Safety Research, 37 (2006), 261–265.

11. Ferlazzo, F., Fagioli, S., Nocera, F.D., and Sdoia, S. "Shifting Attention across Near and

Far Spaces: Implications for the Use of Hands-Free Cell Phones While Driving,"

Accident Analysis and Prevention 40 (2008.), 1859–1864.

12. Fernandez-Caballero, A., Gomez, F.J., and Lopez-Lopez, J. "Road Traffic Monitoring by

Knowledge-Driven Static and Dynamic Image Analysis," Expert Systems with

Applications, 35 (2008), 701–719

13. FitzGerald, J., Dennis, A. Fundamentals of Business Data Communications, 10th

Edition, John Wiley & Sons, Inc, 2010

14. Gao, S., Wang, H., Xu, D., and Wang, Y. "An Intelligent Agent-Assisted Decision

Support System for Family Financial Planning," Decision Support Systems, 44 (2007),

60–78.

15. Gras, ME., Cunill, M., Sullman, MJM, Planes, M., Aymerich, M., and Font-Mayolas, S.

"Mobile Phone Use While Driving in a Sample of Spanish University Workers,"

Accident Analysis and Prevention 39 (2007), 347–355.

16. Gregor, S., Jones, D. "The Anatomy of a Design Theory," Journal of the Association for

Information Systems 8:5 (2007),321–335.


646

17. Hamada, T. "Experimental Analysis of Interactions between 'Where' and 'What' Aspects

of Information in Listening and Driving: A Possible Cognitive Risk of Using Mobile

Phones During Driving," Transportation Research Part F, 11 (2008), 75–82.

18. Hayes, B. Cloud Computing" Communications of the ACM, 51, (2008), 9–11.

19. Hevner, A., March, S., Park, J., and Ram, S. "Design Science in Information Systems

Research," MIS Quarterly, 28 (2004), 75–105.

20. Iivari, J. "A Paradigmatic Analysis of Information Systems as a Design Science,"

Scandinavian Journal of Information Systems, 19 (2007), 39–64.

21. Jessop, G. "Who's on the Line? Policing and Enforcing Laws Relating to Mobile Phone

Use While Driving," International Journal of Law, Crime and Justice 36 ( 2008), 135–

152.

22. Katherine, M.W., Melissa, K.H., Shari, P.W., and Watson, B. "Mobile Phone Use While

Driving: An Investigation of the Beliefs Influencing Drivers‘ Hands-Free and Hand-Held

Mobile Phone Use," Transportation Research Part F, 13 (2010) 9–20.

23. Lai, C., Wang, L., Chen, J., Meng, X., and Zeitouni, K. "Effective Density Queries for

Moving Objects in Road Networks," Springer-Verlag Berlin Heidelberg (LNCS 4505),

2007, 200–211.

24. Lynch, T., Gregor, S., and Midmore, D. "Intelligent Support Systems in Agriculture:

How Can We Do Better?" Australian Journal of Experimental Agriculture, 40, (2000),

609–620.

25. March, S.T., Smith, G. "Design and Natural Science Research on Information

Technology", Decision Support Systems,15 (1995), 251–266.

26. McEvoy, SP., Stevenson, MR., and Woodward, M. "The Contribution of Passengers

Versus Mobile Phone Use to Motor Vehicle Crashes Resulting in Hospital Attendance by

the Driver," Accident Analysis and Prevention, 39 (2007), pp 1170–1176.

27. McKay, J., Marshall, P., and Heath, G. "An Exploration of the Concept of Design in

Information Systems," The 4th Biennial ANU Workshop on Information Systems

Foundations, ISF2008, S. Gregor and D. Hart (eds.), 2008, Australian National

University, Canberra, Australia.

28. Miah, S.J., Kerr, D., and Gammack, J. "A Methodology to Allow Rural Extension

Professionals to Build Target-Specific Expert Systems for Australian Rural Business

Operators," Expert Systems with Applications, 36 (2009), 735–744.

29. Muntermann, J. "Towards Ubiquitous Information Supply for Individual Investors: A

Decision Support System Design," Decision Support Systems, 47 (2009), 82–92

30. Nikolaev, AG., Robbins, MJ, and Jacobson, SH. "Evaluating the Impact of Legislation

Prohibiting Hand-Held Cell Phone Use While Driving," Transportation Research Part A,

44 (2010), 182–193

31. Nunamaker, J.F., Chen, M., and Purdin, TD. "Systems Development in Information

Systems Research," Journal of Management Information Systems 7 (1991) 89–106.

32. Nurmi, D., Wolski, R., Grzegorczyk, C., Obertelli, G., Soman, S., Youseff, L., and

Zagorodnow, D. "Eucalyptus: A Technical Report on an Elastic Utility Computing

Architecture Linking Your Programs to Useful Systems," 2009, UCSB Computer

Science Technical Report Number 2008-10, retrieved on 22 October, 2010, from

http://open.eucalyptus.com/documents/nurmi_et_al-eucalyptus_tech_report-

august_2008.pdf


647

33. Nurmi, D., Wolski, R., Grzegorczyk, C., Obertelli, G., Soman, S., Youseff, L. and

Zagorodnow, D. "The Eucalyptus Open-Source Cloud-Computing System, 2009," the

9th IEEE/ACM International Symposium on Cluster Computing and the Grid, retrieved

on 22 October, 2010, from http://www.cca08.org/papers/Paper32-Daniel-Nurmi.pdf

34. Papamichail, K.N., and French, S.. "Design and Evaluation of an Intelligent Decision

Support System for Nuclear Emergencies," Decision Support Systems 41 (2005), 84–

111.

35. Peffers, K., Tuunanen, T., Rothenberger, M.A., and Chatterjeea, S. "Design Science

Research Methodology for Is Research," Journal of Management Information Systems

24:3 (2008), 45–77

36. Phillips, D. J. "Beyond Privacy: Confronting Locational Surveillance in Wireless

Communication," Communication Law and Policy, 8 (2003),1–23.

37. Quintero, A., Konare, D., and Pierre, S. "Prototyping an Intelligent Decision Support

System for Improving Urban Infrastructure Management", European Journal of

Operational Research, 162 (2005), 654–672.

38. Rogers, EM. Diffusion of Innovations, (Fourth Edition). Free Press,1995.

39. Santos, N., Gummadi, K. P. and Rodrigues, R. "Towards Trusted Cloud Computing",

2009 retrieved on 22 October, 2010, from http://www.mpi-

sws.org/~gummadi/papers/trusted_cloud.pdf

40. Simon, H.A. The Sciences of the Artificial. Cambridge, MA, USA: The MIT Press,

1996.

41. Srinivasan, A., March, S., and Saunders, "Information Technology and Organizational

Contexts: Orienting Our Work Along Key Dimensions," Proceedings of the 26th

International Conference on Information Systems (AIS), D.G. D. Avison, J. I. DeGross

(ed.), 2005, Las Vegas, NV, USA, 991–1001

42. Tornros, J., Bolling, A. "Mobile Phone Use – Effects of Conversation on Mental

Workload and Driving Speed in Rural and Urban Environments," Transportation

Research Part F, 9 (2006), 298–306.

43. Vashitz, G., Shinar, D., and Blum, Y. "In-Vehicle Information Systems to Improve

Traffic Safety in Road Tunnels," Transportation Research Part F, 11 (2008), 61–74.

44. Vouk, M.A. 2008. "Cloud Computing – Issues, Research and Implementations," Journal

of Computing and Information Technology–CIT (16:4), pp 235–246.

45. Virtual Revolution, SBS Documentary-Oct 26, 8:30pm, 2010, retrieved on 20 July 2011,

from http://www.sbs.com.au/documentary/program/virtualrevolution

46. Watson, B.C. 2004. "How Effective Is Deterrence Theory in Explaining Driver

Behaviour: A Case Study of Unlicensed Driving", Road Safety Research, Policing and

Education Conference, Perth, Western Australia.

47. Whitepaper 2010, "Application Architecture for Cloud Computing," retrieved on 20th

October, 2010, from http://www.rpath.com/corp/images/stories/white_papers/WP_

ArchitectureForCloudComputing.pdf


648

A Cloud-Based DSS Model for Driver Safety and Monitoring on Australian Roads

Documents