Sunday, October 21, 2018
Text Size

Journal of Information and Communication Technology (JICT) Vol.17, No. 4,October 2018

Bagus Priambodo & Azlina Ahmad
Mounir Achouri, Adel Alti, Makhlouf Derdour, Sébastien Laborie,Philippe Roose
Rosmaini Kashim, Maznah Mat Kasim & Rosshairy Abd Rahman
Ali Seman & Azizian Mohd Sapawi
Wan Nooraishya Wan Ahmad & Nazlena Mohamad Ali
Mohamud Sheikh Ibrahim Abdullahi, Norsaremah Salleh, Azlin Nordin & Ali Amer Alwan
Mayank Srivastava, Jamshed Siddiqui & Mohammad Athar Ali
Moh’d Khaled Yousef Shambour

1Bagus Priambodo & 2Azlina Ahmad
1Faculty of Computer Science, Universitas Mercu Buana, Indonesia
2Institute of Visual Informatic, Universiti Kebangsaan Malaysia, Malaysia

Monitoring and understanding traffic congestion seems difficult due to its complex nature. This is because the occurrence of traffic congestion is dynamic and interrelated and it depends on many factors. Traffic congestion can also propagate from one road to neighbouring roads. Recent research shows that there is a spatial correlation between neighbouring roads with different traffic flow pattern on weekdays and on weekends. Previously, prediction of traffic flow propagation was based on day and time during weekdays and on weekends. Results obtained from past studies show that further investigation is needed to reduce errors using a more efficient method. We observed from previous research that similarity of traffic condition on weekdays and weekends was not taken into account in predicting traffic flow propagation. Hence, our study is to create and evaluate a new prediction model for traffic flow propagation at neighbouring roads using similarity of traffic flow pattern on weekdays and weekends to achieve more accurate results. We exploit similarity of traffic flow pattern on weekdays and weekends by adding time cluster in our proposed model. Thus, our neural network model proposed high correlation road, time and day clusters as input factors in neural network model prediction. Our initial phase of the methodology involves investigation on correlation between neighbouring roads. This paper discusses the results of experiments we have conducted to determine relationship between roads in a neighbouring area and to determine input factors for our neural network traffic flow prediction model. To choose a particular road as a predicting factor, we calculated the distance between roads in neighbouring area to identify the nearest road. Then, we calculated correlation based on traffic condition (congestion) between roads in neighbouring area. The results were then used as input factors for prediction of traffic flow. We compared the results of the experiment using neural network without cluster parameters and multiple regression methods. We observed that neural network with time cluster parameter produced better results compared to neural network without parameter and multiple regression method in predicting average speed of vehicles on neighbouring roads.

Keywords: Traffic congestion, traffic prediction, neural network, multiple regression method.

btn fulltext

1Mounir Achouri, 2Adel Alti, 1Makhlouf Derdour, 3Sébastien Laborie,3Philippe Roose
1Department of Computer Science, University of Tebessa, Algeria
2Department of Computer Science, University Ferhat Abbas Setif-1, Algeria
3LUIPPA Laboratory, University of Pau and Pays of Adour , France;;
Ontologies are considered a backbone for supporting advanced situation management in various smart domains, particularly smart health. It plays a vital role in understanding user context in order to determine patients’ safety, situation identification accuracy, and provide personalized comfort. The smart health domain contains a huge number of different types of context profiles related to interactive devices, linked health objects, and smart-home. The key role of context profiles is to deduce urgent situations that are needed to run adaptation components on a specific smarthealth Fog. Existing platforms and middlewares lack support to efficiently analyze a large number of heterogeneous specific profiles and continuous context changing in near real time. In this paper, we focus on data and dissemination of information from services related to the field of e-health. This paper aims to provide a new generic user situation-aware profile ontology (GUSP-Onto) for a semantic description of heterogeneous users’ profiles with efficient patients’ situation management and health multimedia information dissemination related to smart health services. Based on the users’ situation management ontology, a two-layered architecture was proposed. The first layer is used to achieve a quality diagnosis of urgent situations including a smart fog computing enhanced with semantic profile modeling that offers efficient situation management. The second layer allows a more in-depth situation analysis for patients and enhanced rich services using cloud computing that provides good scalability. The most innovative of this architecture is the potential benefits from the semantic representation to conduct emergency situation knowledge reasoning and ultimately realize early service selection and adaptation process. The experimental results show a decreased time response and an enhanced accuracy of the proposed approach.
Keywords: Semantic fog-based platform, situation awareness ontology, health services, smart health, connected health objects.
btn fulltext

Rosmaini Kashim, Maznah Mat Kasim & Rosshairy Abd Rahman
School of Quantitative Sciences
Universiti Utara Malaysia, Malaysia;;
An efficiency measurement model of a university faculty is proposed with additional new sub-functions that produce new output variables, based on the network Data Envelopment Analysis (DEA) model for systems with a hierarchical structure.For production systems composed of hierarchical processes, the system efficiency is well represented as the aggregated performance of the components involved in the system. It is identified that the conventional DEA model ignores internal process activities in a university. Therefore, an improved DEA model based on a network structure that accounts for more activities in a university is proposed to measure its overall efficiency. The impact of major functions of a university are taken into account to represent the output variables in assessing the efficiency. Currently, collaboration activities have been given more attention, so, this variable is suggested as a new output for the hierarchical production system. In order to show the practicality of the model, a hypothetical set of data of 14 faculties has been used as a numerical example. The results show that none of the faculties is relatively efficient since its functions were found to be inefficient. The proposed model enables to help the management of university faculties to identify weaknesses of each function and thus to plan for suitable actions on improving the overall performance of the university.
Keywords: Data envelopment analysis, efficiency measurement model, hierarchy structure, network model.

btn fulltext

Ali Seman & Azizian Mohd Sapawi
Faculty of Computer and Mathematical Sciences
Universiti Teknologi MARA, Malaysia 
The k-AMH algorithm has been proven efficient in clustering categorical datasets. It can also be used to cluster numerical values with minimum modification to the original algorithm. In this paper, we present two algorithms that extend the k-AMH algorithm to the clustering of numerical values. The original k-AMH algorithm for categorical values uses a simple matching dissimilarity measure, but for numerical values it uses Euclidean distance. The first extension to the k-AMH algorithm, denoted k-AMH Numeric I, enables it to cluster numerical values in a fashion similar to k-AMH for categorical data. The second extension, k-AMH Numeric II, adopts the cost function of the fuzzy k-Means algorithm together with Euclidean distance, and has demonstrated performance similar to that of k-AMH Numeric I. The clustering performance of the two algorithms was evaluated on six real-world datasets against a benchmark algorithm, the fuzzy k-Means algorithm. The results obtained indicate that the two algorithms are as efficient as the fuzzy k-Means algorithm when clustering numerical values. Further, on an ANOVA test, k-AMH Numeric I obtained the highest accuracy score of 0.69 for the six datasets combined with p-value less than 0.01, indicating a 95% confidence level. The experimental results prove that the k-AMH Numeric I and k-AMH Numeric II algorithms can be effectively used for numerical clustering. The significance of this study lies in that the k-AMH numeric algorithms have been demonstrated as potential solutions for clustering numerical objects.
Keywords: Cluster analysis, partitional clustering algorithms, categorical and numerical data mining.

btn fulltext

1,2Wan Nooraishya Wan Ahmad & 1Nazlena Mohamad Ali
1Institute of Visual Informatics Universiti Kebangsaan Malaysia, Malaysia
2Faculty of Computing and Informatics Universiti Malaysia Sabah, Malaysia 


Experience is key in deciding whether or not to adopt a system such as persuasive technology, which aims to persuade people to take up a targeted attitude or behavior. Thousands of persuasive technologies have been developed for commercial and academic uses; however, many studies on experience have mainly been conducted on products and none have focused on studying experience in the context of persuasive technologies. Therefore, this study aims to investigate emotional experience and user experience when using persuasive technology. Twenty-five participants comprising university staffs and students were given 6 weeks to use two different persuasive web applications—one on health and the other on environmental issues. A pre-post interaction approach was carried out to analyze the participants’ emotional experiences; Positive and Negative Affect Schedule (PANAS) instruments and questionnaires were used to assess user experience based on the pragmatic, hedonic, and appeal quality of the web applications. From 20 PANAS emotions, only six emotions were found to have significant impact. Although a significant change happened in user experience perceptions from the pre-interaction to post-interaction stages, no significant change happened in user emotional experience. The findings imply that the changes in user experience perceptions over time may contribute towards altering persuasion, whether by increasing or reducing persuasion via persuasive technology. As a result, this study contributes new information to the theory of designing persuasive technology such that more concern is put on the hedonic quality and appealingness of a system for greater user experience and an emotionally impactful and successful persuasion.

Keywords: Emotional experience, hedonic dimention, persuasive technology, user experience.

btn fulltext

Mohamud Sheikh Ibrahim Abdullahi, Norsaremah Salleh, Azlin Nordin & Ali Amer Alwan
Department of Computer Science
International Islamic University Malaysia, Malaysia
Cloud-based Learning Systems (CBLS) refers to the systems that provide electronic or online content to enable the learning process by offering tools and functionalities through platform available in Cloud. This research seeks to examine the effectiveness of CBLS in improving programming skills among undergraduate students by measuring students’ performance in solving programming problems. This is because there is no empirical evidence on the effectiveness of CBLS when compared with the traditional method of learning programming among student beginners. Traditionally, teaching programming courses has been performed in a classroom setting and it can be very challenging for an instructor to go beyond covering the language’s syntax such as program design skills and problem-solving skills due to the wide variety of students’ background in such bounded class duration. In this study, three single-subject experiments were conducted using 40 undergraduate students enrolled in Web Programming course. The experiments compared the time students spent to solve programming tasks by using traditional learning method and CBLS. A survey to measure students’ self-efficacy was administered before and after the experiments. The findings of this study showed that there is a statistically significant difference in learning programming using CBLS when compared with traditional method. Our results showed that students solve programming problems in less time when using CBLS. The study also found out that CBLS is effective for improving students’ self-efficacy. 
KeywordsCloud computing, cloud-based learning system, programming skills.

btn fulltext

1Mayank Srivastava, 2Jamshed Siddiqui & 3Mohammad Athar Ali
1Institute of Engineering and Technology, Ganeshi Lal Agrawal University, India
2Department of Computer Science, Aligarh Muslim University, India
3Department of Applied Computing, University of Buckingham, United Kingdom

The rapid development of image editing software has resulted in widespread unauthorized duplication of original images. This has given rise to the need to develop robust image hashing technique which can easily identify duplicate copies of the original images apart from differentiating it from different images. In this paper, we have proposed an image hashing technique based on discrete wavelet transform and Hough transform, which is robust to large number of image processing attacks including shifting and shearing. The input image is initially pre-processed to remove any kind of minor effects. Discrete wavelet transform is then applied to the pre-processed image to produce different wavelet coefficients from which different edges are detected by using a canny edge detector. Hough transform is finally applied to the edge-detected image to generate an image hash which is used for image identification. Different experiments were conducted to show that the proposed hashing technique has better robustness and discrimination performance as compared to the state-of-the-art techniques. Normalized average mean value difference is also calculated to show the performance of the proposed technique towards various image processing attacks. The proposed copy detection scheme can perform copy detection over large databases and can be considered to be a prototype for developing online real-time copy detection system. 

KeywordsContent-based copy detection, digital watermarking, discrete wavelet transform, hough transform, image forensics, image hashing.

btn fulltext

Moh’d Khaled Yousef Shambour
Institute for Hajj and Umrah Research
Umm Al-Qura University, Saudi Arabia

Recently, various variants of evolutionary algorithms have been offered to optimize the exploration and exploitation abilities of the search mechanism. Some of these variants still suffer from slow convergence rates around the optimal solution. In this paper, a novel heuristic technique is introduced to enhance the search capabilities of an algorithm, focusing on certain search spaces during evolution process. Then, employing a heuristic search mechanism that scans an entire space before determining the desired segment of that search space. The proposed method randomly updates the desired segment by monitoring the algorithm search performance levels on different search space divisions. The effectiveness of the proposed technique is assessed through harmony search algorithm (HSA). The performance of this mechanism is examined with several types of benchmark optimization functions, and the results are compared with those of the classic version and two variants of HSA. The experimental results demonstrate that the proposed technique achieves the lowest values (best results) in 80% of the non-shifted functions, whereas only 33.3% of total experimental cases are achieved within the shifted functions in a total of 30 problem dimensions. In 100 problem dimensions, 100% and 25% of the best results are reported for non-shifted and shifted functions, respectively. The results reveal that the proposed technique is able to orient the search mechanism toward desired segments of search space, which therefore significantly improves the overall search performance of HSA, especially for non-shifted optimization functions. 

Keywords: Evolutionary algorithms, exploration and exploitation, harmony search algorithm, heuristic search, optimization functions.

btn fulltext

Universiti Utara Malaysia Press
 Universiti Utara Malaysia, 06010 UUM Sintok
Kedah Darul Aman, MALAYSIA
Phone: +604-928 4816, Fax : +604-928 4792

All Right Reserved. Copyright © 2010, Universiti Utara Malaysia Press