Showing papers presented at "International Conference on Computer and Information Science in 2012"

A low-cost game framework for a home-based stroke rehabilitation system

Abstract: Stroke is a major cause of severe physical disability, leading into a variety of impairments. In general, stroke rehabilitation is a process which requires intensive direct physical therapy and is usually guided by physiotherapists. The long and intensive therapy sessions often results in patients losing the motivation to continue with the therapy, and as a result patients do not recover to their prospective. With increasing occurrence of stroke incidence, therapists are under pressure for time. At present most of the rehabilitation programmes are highly human intensive. Thus an innovative game technology that supports stroke rehabilitation may provide new opportunities. The main objective of this paper is to present a new low cost game framework for stroke rehabilitation programme that would increase patients' motivation for therapy, and also to study the feasibility and effect of a new game based technology to support hand and leg rehabilitation. In this paper, some important new game design principles for hand and leg rehabilitation with a standard angle based representation of the full body motion during exercise, for improving the accuracy of stroke exercise are presented. The design of serious games, with important game design principle frequently linked with worthy user engagement, may offer perceptions into how more effective systems can be developed for stroke rehabilitation. The additional bio-signal and online database will enable evaluation of patient s movement performance.

Significance level of image enhancement techniques for underwater images

Abstract: Underwater imaging is quite a challenging in the area of photography especially for low resolution and ordinary digital camera. There are a few problems occur in underwater images such as limited range visibility, low contrast, non uniform lighting, blurring, bright artefacts, color diminished and noise. This paper concentrates on color diminished. Significant application of standard computer vision techniques to underwater imaging is required in dealing with the said problems. Both manual and auto level techniques are used to record the mean values of the stretched histogram. The objective of the paper is to identify which technique is more significant in terms of color correction. It is hoped that the finding will benefit to non divers to visualize the underwater as the real underwater world.

A propose framework for requirement Change Management in Global Software Development

Abstract: Presently, software systems are becoming an important module of businesses in the world. Most of the organizations are adopting Global Software Development (GSD), and it is continuously getting faster. Organizations are trying to distribute their work worldwide. However, distributed software development is not an easy task and the organizations face different challenges. Software Requirement Change Management (RCM) is one of them and it becomes more difficult in the context of the GSD. Currently, there is no framework available, which can be used for the RCM in GSD organizations. The aim of this study is to propose a framework for RCM in geographically distributed software development systems and describe the identification of the communication risks, their causes and effects during RCM in GSD systems.

Performance evaluation of energy consumption for AODV and DSR routing protocols in MANET

Abstract: Proposing energy efficient routing protocols for Mobile Ad hoc Network (MANET) and Wireless Sensor Network is an uphill and challenging task. Many different routing protocols based on different features have been proposed to the IETF. Performances of many of these routing protocols have been evaluated focusing on metrics such as delay, routing overhead, and packet delivery. However, no studies have been done to investigate energy aspect of these routing protocols. Thus, this paper will discuss about the power consumption aspect of the MANET routing protocols. A performance comparison of Dynamic Source Routing (DSR) and Ad hoc On-Demand Distance Vector (AODV) routing protocols with respect to average energy consumption and routing energy consumption are explained thoroughly. Then, an evaluation of how the varying metrics in diverse scenarios affect the power consumption in these two protocols is discussed. A detailed simulation model using Network Simulator 2 (NS2) with different mobility and traffic models are used to study their energy consumption. Finally, an evaluation of these routing protocols based on energy consumption is presented.

User acceptance of eGovernment: Integrating risk and trust dimensions with UTAUT model

Abstract: Studies suggest that there are factors that affects citizens' behavioural intention and adoption behaviour towards the use of government e-services. Low patronage of eGovernment has become an issue in developing nations. Therefore, this paper proposes an integration of trust dimensions and risk taken propensity to the UTAUT model. We tested the model on 101 university students in Malaysia. The survey instrument items were carefully selected from previously validated constructs. Structural equation modeling (SEM) was used to examine the relationship between the constructs. The study showed that Performance Expectation, Peer Influence, Trust belief and Risk taken propensity are significant in predicting behavioural intention to adopt e-government. Furthermore, implications for practice and further research were also discussed.

Mapping job requirements of software engineers to Big Five Personality Traits

Abstract: Software engineering is a booming industry and is contributing to world economy in terms of providing employment and monetary benefits. Unfortunately, despite its importance, research in this field is still not mature. Studies so far done in this field have heavily focused on technical aspects rather than non-technical. In fact, software development is a human activity (performed by humans) which emphasizes the importance of research on non-technical (human or soft aspects) of software engineering. Recently there has been an increase on studies which are focusing more on the soft aspects of software engineering. This study also focuses on the human aspect of software engineering namely personality. Software engineers belong to various categories and their roles differ from each other based on their job requirements and skills needed to perform those jobs. This study mapped the hard and soft skills required by various software engineers and then linked them to personality traits using Big Five Personality Traits.

Employing artificial intelligence techniques in Mental Health Diagnostic Expert System

Abstract: The Mental Health Diagnostic Expert System (MeHDES) is proposed to assist the Malaysian psychology industry in diagnosing and treating their mental patients, and also to allow each mental patient to have several options on selecting a treatment plan that fits their budget without jeopardizing their overall health conditions. MeHDES will be using three artificial intelligence (AI) reasoning techniques: rule-based reasoning, fuzzy logic, and fuzzy-genetic algorithm (fuzzy-GA). The human experts' knowledge in the area of mental health and disorders will be transformed and encoded into a knowledge base using the rule-based reasoning technique; fuzzy logic then allows the severity level of a particular disorder to be measured; and fuzzy-GA will be used to determine and propose the suitable treatment for each of the mental patients based on their budget and their overall health conditions.

Analysis of Bluetooth signal parameters for indoor positioning systems

Abstract: Bluetooth is a low-cost and low-power short range wireless communication standard. Now a days nearly all the portable devices are equipped with Bluetooth functionality. Due to its wide spread usage and applications for short range wireless communication, this technology can be used for indoor position estimation. Currently, Bluetooth specifications provide two kinds of signal parameters which can be classified as connection-based and inquiry-based signal parameters. Connection-based signal parameters require an active Bluetooth connection between sender and receiver, while an inquiry-based signal parameters do not require an active connection. This paper investigates both kinds of signal parameters experimentally using different sets of Bluetooth USB dongles in order to select the suitable parameter for distance estimation.

Using Genetic Algorithm in implementing Capacitated Vehicle Routing Problem

Abstract: Vehicle Routing Problem (VRP) has been considered as a significant segment in logistic handling Thus, a proper selection of vehicle routes plays a very important part to ameliorate the economic benefits of logistic operations In this paper, we consider the application of a Genetic Algorithm (GA) to a Capacitated Vehicle Routing Problem (CVRP) in which a set of vehicles with limits on capacity and travel time are available to service a set of customers and constrained by earliest and latest time for serving The results of our test show that GA is able to determine the optimum route for the vehicles while maintaining their constraints of capacity and travel time

An approach towards intrusion detection using PCA feature subsets and SVM

Abstract: Presently many intrusion detection approaches are available but have drawbacks like training overhead as well as their performance factor. Increased detection rate with less false alarms can enhanced the efficiency of an intrusion detection system. One of the main limitations is the processing of raw features for classification which increases the architecture complexity and decreases the accuracy of detecting intrusions. Because of the limitations in earlier approaches, this PCA based subsets has been proposed. An SVM based IDS mechanism with Principal Component Analysis (PCA) feature subsets has been presented. Support Vector Machines (SVM) used as classifier to test and train the subsets of extracted features with Radial Basis Function (RBF) kernel.

Implement of cloud computing for e-learning system

Abstract: E-learning systems provide processes of delivering the learning contents to learners who have different backgrounds, interests, and locations away from a classroom in order to maximize the effectiveness of learning. Usually, the classical e-learning system is based on client/server architecture thus they lack of the scalability, flexibility and interoperability. It makes the learning resources cannot share, and the system improvement is not easily. This paper proposes the cloud computing architecture in the e-learning system that the architecture separate into three layers includes infrastructure, platform and application. This architecture needs to design components in order to transfer the learning resources to the cloud platform. Infrastructure layer, the learning resources from the traditional system are transferred to the cloud database instead of the usual DBMS. Platform layer, a new e-learning system that consists of the CMS, AMS, and other service components were developed. These components were developed to be the intermediary between cloud database and the applications. Finally, application layer, CAT web application and WBI application were developed for interacting with the student's client. The results shown that all applications co-operated with the other components suitably. Applying the cloud computing makes the classical e-learning more scalability, flexibility, and interoperability. Moreover, cloud computing induces the way that e-learning can be share and distribute the learning resources to any kind of devices and platforms. Since the e-learning services are used for a relative short time, pay per use of the cloud could reduce the cost thus the organization pay only for capacity that actually used.

A norms mining approach to norms detection in multi-agent systems

Abstract: In this paper, we propose a norms mining technique for a visitor agent to detect the norms of a community of local agents to comply with the community's normative protocol. In this technique, the visitor agent is equipped with an algorithm, which detects the potential norms through the system's log file, interactions with the local agents, and observing the local agents in action. The visitor agent detects the norms from these sources depending on their availability. Due to security issues, access is prevented to one or more of these sources. The norms mining technique entails the process of data formatting and filtering and identifying the norms' components that contribute to the strength of the norms. The results of an example mining operation show that the technique is successful in discovering the potential norms.

Interference-aware virtual machine placement in cloud computing systems

Abstract: Cloud computing provides scalable computing and storage resources. These scalable resources can be dynamically organized as many virtual machines (VMs) to run user applications based on a pay-per-use basis. This paper investigates the interference-aware VM placement (IAVMP) problem. In addition to fully exploiting the resources of PMs, the IAVMP problem considers the quality of service (QoS) requirements of user applications and the VM interference reduction. We first formulate the IAVMP problem by an Integer Linear Programming (ILP) model to solve it optimally. Due to the computation complexity of the ILP model, we also propose a polynomial-time heuristic algorithm to efficiently solve the IAVMP problem. Finally, simulation experiments are performed to demonstrate the effectiveness of the proposed heuristic algorithm by comparing with other VM placement algorithms.

A study of User Interface Design principles and requirements for developing a Mobile learning prototype

Abstract: This paper describes a study of User Interface Design (UID) principles and requirements by utilizing mobile device as an instrument for Mobile learning purpose. Thus, methods for designing and developing a learning prototype that are compatible with small screen interfaces and limited capabilities of mobile devices are planned to ensure the learners are able to grasp the concepts of a mobile learning prototype. We also highlight ARCS learning design strategy, which is appropriate for a mobile-based learning application. The mobile learning prototype was developed using Adobe Flash CSS for learning Dijkstra's shortest path algorithm as a technical subject on a touch-screen iPhone 4, operated on iPhone Operating System (iOS). We present discussions on the UID principles and guidelines used for designing and developing the mobile-based learning prototype. Finally, a survey was conducted to evaluate the usability of this prototype among 20 Computer Science undergraduate students who had previously studied or are still taking the subject. The findings show that the learners perceived the mobile application as usable and the application has contained UI principles and requirements.

SGameFlow framework: How to experience enjoyment in Serious Game (SG) for Motor Impaired Users (MIU)

Abstract: Benefiting from the popularity of computer game, Serious Game (SG) has been reaching a wide range of users. However, research on user interface design factors in SG for the Motor Impaired User (MIU) is still narrow, especially for the enjoyment experience context. This paper is aimed to proposed user interface design factors framework (SGameFlow) that makes MIU experience enjoyment when playing SG. This study is based on GameFlow Model to develop a rigorous user interface design factors that makes MIU experience enjoyment when playing SG. We make use of certain original model's factors together with three new factors (learning opportunities, accessibility and adaptivity) to predict user interface design factors of MIU enjoyment experience in SG.

Usability of user interface styles for learning a graphical software application

Abstract: This paper examines usability of user interface styles for learning a graphical software application, namely Adobe Flash CS4. An empirical study was performed to investigate the usability attributes of effectiveness, efficiency and satisfaction scores for learning Adobe Flash CS4. There were 32 participants recruited whom consist of interface designers and software developers. A set of 10 tasks were designed to compare the different effects of user interface styles between graphical user interface (GUI) and command line interface (CLI). Performance variables (effectiveness, efficiency, duration, number of errors and number of helps) were measured for tasks performed by all the participants in the test. Satisfaction score was measured using QUIS (Questionnaire for User Interface Satisfaction) tool. The result revealed that the average effectiveness score higher than 75% (96.88%), and average efficiency (7.43) for all the 10 tasks given. The satisfaction score also showed above average (>3.5) for majority of the user interface satisfaction attributes of software regardless of users' background.

A hybrid approach using Naïve Bayes and Genetic Algorithm for childhood obesity prediction

Abstract: Naive Bayes is a data mining technique that has been used by many researchers for predictions in various domains. This paper presents a framework of a hybrid approach using Naive Bayes for prediction and Genetic Algorithm for parameter optimization. This framework is a solution applied to the childhood obesity prediction problem that has a small ratio of negative samples compared to the positive samples. The Naive Bayes has shown a weakness in prediction involving a zero value parameter. Therefore, in this paper we propose a solution for this weakness which is using Genetic Algorithm optimization. The study begins with a literature review of the childhood obesity problem and suitable data mining techniques for childhood obesity prediction. As a result of the review, 19 parameters were selected and the Naive Bayes technique was implemented for childhood obesity prediction. The initial experiment to identify the usability of the proposed approach has indicated a 75% improvement in accuracy.

A preliminary study on heuristics for mobile games

Abstract: Playtesting and expert evaluation methods are common these days to evaluate games. In order to find out playability problems in mobile games, an evaluation method is needed to evaluate mobile games with a set of playability heuristics. Heuristics evaluation method is good for identifying playability problems deeply but a set of playability heuristics is needed to apply this method. This research is conducted to identify and explore more playability problems in mobile games. It has been reviewed that some of the problems were still unidentified by evaluators when they evaluated the games with present playability heuristics set. In this research some problems were identified from literature analysis and survey results. This research has been conducted by using survey methodology tools (interviews & questionnaire), the questionnaire is divided into 3 sections and it contains 20 questions. 100 questionnaires were distributed among university students and all were returned with positive feedback. The outcome of this research proposed some new playability heuristics for mobile games, in order to identify playability problems. Consequently, these heuristics may help game designers and developers while considering these heuristics during development of mobile games.

Cloud services - Enhancing the Malaysian healthcare sector

Abstract: The Malaysian hospital environment is predominantly device focused: whereby application services are typically installed manually on devices where the services are required. For an example, the software to review MRI images are only being made available to certain devices, typically located at the scanner itself. In order to facilitate resource integration and data sharing to provide better services to patients, the medical world eco-system is undergoing a transition from a device oriented based architecture to a software as service based architecture (SaaS), this translates to the availability of application service on every device. Devices here can be categorized from smart phones to PDA's and workstations located both local and remotely. To fully support medical related applications in a dynamic environment, medical devices will need to be treated as being part of the cloud, where software modules are automatically deployed on demand when required with the appropriate resources. In this paper, we will propose an architecture that will tightly link the various medical institutions' and as at present, the level of access to medical information is not the same among medical institutions. Cloud computing will bridge the current gap and provide a much connected environment hence improving overall efficiency of operations.

Computer aided diagnosis system based on machine learning techniques for lung cancer

Abstract: Cancer is a leading cause of death worldwide. Lung cancer is a type of cancer that is considered as one of the most leading causes of death globally. In Malaysia, it is the 3rd common cancer type and the 2nd type of cancer among men. In this paper, machine learning techniques have been utilized to develop a computer-aided diagnosis system for lung cancer. The system consists of feature extraction phase, feature selection phase and classification phase. For feature extraction/selection, different wavelets functions have been applied in order to find the one that produced the highest accuracy. Clustering-K-nearest-neighbor algorithm has been developed/utilized for classification. Japanese Society of Radiological Technology's standard dataset of lung cancer has been used to test the system. The data set has 154 nodule regions (abnormal) and 92 non-nodule regions (normal). Accuracy levels of over 96% for classification have been achieved which demonstrate the merits of the proposed approach.

Review on online and mobile weight loss management system for overcoming obesity

Abstract: This paper reviews previous research that used ICT intervention for weight loss management to overcome obesity. The aim of this review is to identify ways that ICT contribute towards effective weight loss management and the opportunities that ICT can provide towards successful weight loss. This paper not only includes review of journal papers but also review of various available online weight loss management systems. Main finding from this review is, ICT's usage for weight loss management can be classified into: Diet Plan and Guideline, Online Community and Mobile Applications. In addition to this, ICT namely the Internet and mobile applications offer vast opportunities towards effective weight loss through self-monitoring which is a key success factor for weight loss.

A novel approach of automation testing on mobile devices

Abstract: Mobile phones and mobile applications have now become an integral part of our everyday life. Mobile application testing plays a pivotal role in making the mobile applications more reliable and defect free. Existing test automation tools have been tailored to perform mobile test automation through mobile emulators. Other tools require the mobile device where the application is installed, to be connected to a computer so that the tests can be run. Obviously, the results obtained from emulators often differ from those obtained on actual mobile devices. To our best knowledge only a few solutions for creating automated tests of mobile applications exist and their functionality is very limited. In this paper, we introduce the idea of implementing a mobile test automation framework MobTAF which performs mobile test automation on the mobile device where connection to a computer is not required. The framework moves the testing infrastructure to the phone, to support test situations that cannot easily be replicated with an emulator. A prototype application was then implemented to test the mobile automation framework, MobTAF. The results prove that MobTAF framework is an efficient way of performing mobile application tests directly on the mobile devices.

Effective content-based image retrieval: Combination of quantized histogram texture features in the DCT domain

Abstract: Effective Content-Based Image Retrieval (CBIR) is based on efficient low level features extraction for indexing and on effective query image matching with indexed images for retrieval of similar images. Feature extraction in compressed domain is an attractive area because at present almost all the images are represented in the compressed form using the DCT (Discrete Cosine Transformation) blocks transformation. Some critical information is removed in compression and only perceptual information is left which has significant attraction for information retrieval in the compressed domain. In this paper the statistical texture features are extracted from the quantized histograms in the DCT domain using only the DC and first three AC coefficients of the DCT blocks of image having more significant information. We study the effect of combination of texture features in effective image retrieval. We perform experimental comparison of combination of various statistical texture features to get the optimum combination of features for the effective image retrieval in terms of precision. Experiments on the Corel database using the proposed approach, give results which show that the combination of various features of quantized histograms give good performance in retrieval as compared to use single or less number of texture features combination.

Mobile language translation game

Abstract: English has always been the International language both in reality and cyber world. It is one of the compulsory subjects in the Malaysian education syllabus. Many Malaysian children face difficulties in learning English. In addition, current methods of teaching English are not engaging enough especially for primary school children. Thus, the use of a bilingual game in teaching English can help make the learning process for these children more exciting and effective. To design and develop a suitable mobile-based bilingual educational game for preschool and primary school, studies on learning theories and suitable learning theories that can support these children's learning process had been carried out. This study undertakes the study and development of a mobile language translation game developed for five to seven year old children. It was developed to run on the Android platform. A total of 40 respondents were involved in the usability testing. This study shows that mobile applications could engage children at a longer period of time in learning environment. Besides the attractiveness of using current technology, the impacts also seen through the improvement of marks obtained from the game. The findings show that most of the teachers and parents believe that the usage of the Bilingual Mobile Game is attractive and helpful in teaching English. Most of the respondents also agree to the implementation of SPELL IT! game as a learning tool to complement existing learning methods for the intended audience.

A prototype of Halal product recognition system

Abstract: Halal industry has been the fastest growing global business in Malaysia, therefore Malaysia has focused to set up the world's first development corporation in making Halal development business communities. Today, Muslim consumer still faces problem in identifying, verify or recognized Halal products in the market. Time to time technology development in communications has given advantage in deploying the system to solve this issue. Today new technology would be one the advantage in verifying Halal product. This research has presented a system to identify the Halal product by using Smartphone which called MyHalal system. Smartphone scanner, camera and barcode readers are tested. This system is able to verify and recognized the information of products and confirmed their Halal status in real time which has accessibility to its database while they do shopping. It operated on Android 2.1 open source operating system and can be used at higher application programming interface (API) level. This prototype system is novel from others by having detailed information features, large database and enable users to contact directly to product business market. Direct contact features also can be made to the Malaysian Islamic authority department (JAKIM) on recognition the products. The features of this application would ease, help and benefit Muslim consumers to overcome the issue on Halal recognition products in the market.

Wi-City: A federated architecture of metropolitan databases to support mobile users in real time

Abstract: Metadata based approaches have been widely proposed to integrate distributed databases that allow the users to take advantage from all the information stored on disparate/distributed databases relevant for their activities. Aim of the paper is to illustrate the implementation architecture of a metropolitan information system, called Wi-City, able to provide real time location based services (LBSs) to support effectively the mobile users by exploiting all the information publicly available on heterogeneous systems. The paradigm Model-View-Controller (MVC) is adopted to develop user centered LBSs. Advantages and future works of using MVC for supporting mobile users are discussed by illustrating the main functions and user interface of Wi-City.

The studies of Knowledge Management System in organization: A systematic review

Abstract: The main objective of this paper is to scrutinize current studies of Knowledge Management System (KMS) in organization throughout contemporary literatures. The focus is to discover theories, models as well as their approaches of existing studies. The review analyses 30 published articles between 2003–2010 from high quality journals. The results reveal that the majority of existing studies fundamentally based on traditional theories and conventional models of adoption, acceptance and diffusion to study the impact of KMS in the organization while the focus of factor based study is mainly from implementation study. On the other hand, the theoretical approaches to conduct the research in this field generally from variance whereas the process approach is scant. Therefore, the future research could give more attention on process approach which allows exploiting more on interpretive paradigm and qualitative as methodological approach which could possibly generate new knowledge in this field of study.

A framework of software process tailoring for small and medium size IT companies

Abstract: Global software development has brought a number of revolutionary changes in the existing software development practices. Project outsourcing and agile based methodologies have emerged as the new generation of processes and practices. As a result of project outsourcing, small and medium sized software development companies have increased in large number. Due to the limitations of resources these companies are unable to follow traditional heavyweight software engineering approaches and thus follow lightweight agile methodologies. Creating a new process from the scratch in also not possible for them and they prefer to adapt a software process according to their own requirements. The existing works on software process tailoring are very general and superficial and do not provide guidelines to small and medium sized software development companies. This research addresses this issue and presents a process tailoring framework which is based on the critical elements of agile methodologies. Both case study of real projects and survey questionnaires have been used to validate the framework. The initial results show that the framework completely identifies the important elements of projects in small and medium sized companies and derives the schema of process tailoring. The outcome of the research is the lightweight process tailoring framework which generates a process tailoring schema for small and medium sized (SMEs) software development companies.

A gap between Business Process Intelligence and redesign process

Abstract: Business process management systems are introduced to change information system's traditional data driven approaches to process centric approaches. Benefits of process oriented approaches are reduction in operational complexity, change management and easy understanding of processes. Process oriented systems are very effective in identification of flow obstruction and bottlenecks through which improvement in business processes is identified. As the process activities increases identification and measurement of process weakness turns into a challenge. A lot of work has been done in the domain of process improvement and redesign. Researchers have proposed Business Process Intelligence (BPI) framework, which is based on Business Intelligence techniques and provides a multi dimensional way of information representation. Previous researches posses a gap in provision of act of improvement in redesign process. Therefore, this research aims to focus on a guided way of process improvement that can provide optimize redesign process. Process improvement also depends on the effective way of agent assignment and resources assignment to an activity. This research will also provide a discussion on need of methods for optimized agent and resources assignment.

Half-Against-Half Multi-Class Support Vector Machines in classification of benthic macroinvertebrate images

Abstract: In this paper we investigated how Half-Against-Half Support Vector Machine (HAH-SVM) succeed in the classification of the benthic macroinvertebrate images. Automated taxa identification of benthic macroinvertebrates is a slightly researched area and in this paper HAH-SVM was for the first time applied to this application area. The main problem in HAH-SVM is to find the right way to divide the classes in a node. We solved the problem by using two different approaches. Firstly, we applied the Scatter method which is a novel approach for the class division problem. Secondly, we formed the class divisions in an HAH-SVM by a random choice. We performed extensive experimental tests with four different feature sets and tested every feature set with seven different kernel functions. The tests showed that by the Scatter method and random choice formed HAH-SVMs performed from classification problem very well obtaining over 95% accuracy. Moreover, the 7D and 15D feature sets together with the RBF kernel function are good choices for this classification task. Generally speaking, HAH-SVM is a promising strategy for automated benthic macroinvertebrate identification.