Thursday, October 19, 2017
   
Text Size
Login

Journal of Information and Communication Technology (JICT) Vol. 16, No. 2, December 2017

 
 
Nur Shazwani Aminuddin, Masrullizam Mat Ibrahim, Nursabillilah Mohd Ali, Syafeeza Ahmad Radzi, Wira Hidayat Mohd Saad & Abdul Majid Darsono
 
 
 
 
EFFICIENT MOBILE VIDEO TRANSMISSION BASED ON A JOINT CODING SCHEME
Rima Boudjadja, Mohamed Azni, Abdelnasser Dahmani & Mohamed Nadjib Zennir
 
HIGH ACCURACY EEG BIOMETRICS IDENTIFICATION USING ICA AND AR MODEL
Chesada Kaewwit, Chidchanok Lursinsap & Peraphon Sophatsathit
 
 
A LINEAR PROGRAMMING BASED MODEL TO MEASURE EFFICIENCY AND EFFECTIVENESS OF UNDERGRADUATE PROGRAMS
Maznah Mat Kasim, Rosmaini Kashim & Sahubar Ali Mohamed Nadhar Khan
 
 

 
MILITARY-BASED CYBER RISK ASSESSMENT FRAMEWORK FOR SUPPORTING CYBER WARFARE IN THAILAND
Aniwat Hemanidhi & Sanon Chimmanee
Faculty of Information Technology
Rangsit University, Thailand
ahemanidhi@rta.mi.th; sanon.s@rsu.ac.th
 
ABSTRACT | FULL TEXT
Information Technology (IT) Risk Management is designed to confirm the sufficiency of information security. There are many risk management/assessment standards, e.g. IS0 27005:2011 and NIST SP 800-30rev1, which are mainly designed for general organizations such as governments or businesses. Cyber risk assessment focused on military strategy has been rarely studied. Hence, this paper presents an innovative cyber risk assessment conceptual framework named “Cyber Risk Assessment (CRA)” which is extended from previous work with Military Risk Evaluation (MRE). This proposed CRA is the collection and integration of both quantitative and qualitative data. The Vulnerability Detection (VD) tools in Network Risk Evaluation (the previous studies) were used for the quantitative data collection and the focus group in the MRE (the proposed method) was used to collect qualitative data, which enhance the general risk assessment standard to achieve the objective of the research. The complexity of cyberspace domains with a military perspective is thoughtfully contemplated into the cyber risk assessment for national cyber security. Results of the proposed framework enable the possibility of cyber risk evaluation into score for national cyber security planning.
 
Keywords: Cyber risk assessment, risk management, cyber security, cyber warfare, Network Centric Warfare.
 
Received: 2 December 2016 Accepted: 15 March 2017
 

 
OBJECT CONTOUR COMPLETION BY COMBINING OBJECT RECOGNITION AND LOCAL EDGE CUES
Kar Seng Loke
School of Information Technology
Swinburne University of Technology Sarawak Campus, Malaysia
ksloke@swinburne.edu.my

ABSTRACT | FULL TEXT
We developed a top-down and bottom-up segmentation ofobjects using shape contours through a two-stage procedure. First, the object was identified using an edge-based contour feature and then the object contour was obtained using a constraint optimization procedure based on the results from the earlier identified contours. The initial object detection provides object category specific information for the contour completion to be effected. We argue that top-down bottom-up interaction architecture has plausible neurological correlates. This method has an advantage in that it does not require learning boundaries with large datasets.

Keywords: Computer vision, object segmentation, object detection, contour extraction, scene interpretation, image understanding.
 
Received: 6 February 2017 Accepted: 28 May 2017
 

 
A NEW APPROACH TO HIGHWAY LANE DETECTION BY USING HOUGH TRANSFORM TECHNIQUE
1Nur Shazwani Aminuddin, 2Masrullizam Mat Ibrahim, 3Nursabillilah Mohd Ali, 4Syafeeza Ahmad Radzi, 5Wira Hidayat Mohd Saad & 6Abdul Majid Darsono
Faculty of Electronic and Computer Engineering
Universiti Teknikal Malaysia Melaka, Malaysia
wanieaminuddin@gmail.com; masrullizam@utem.edu.my; nursabillilah@utem.edu.my; syafeeza@utem.edu.my; wira_yugi@utem.edu.my; 
abdmajid@utem.edu.my
 
ABSTRACT | FULL TEXT
 
This paper presents the development of a road lane detection algorithm using image processing techniques. This algorithm is developed based on dynamic videos, which are recorded using on-board cameras installed in vehicles for Malaysian highway conditions. The recorded videos are dynamic scenes of the background and the foreground, in which the detection of the objects, presence on the road area such as vehicles and road signs are more challenging caused by interference from background elements such as buildings, trees, road dividers and other related elements or objects. Thus, this algorithm aims to detect the road lanes for three significant parameter operations; vanishing point detection, road width measurements, and Region of Interest (ROI) of the road area, for detection purposes. The techniques used in the algorithm are image enhancement and edges extraction by Sobel filter, and the main technique for lane detection is a Hough Transform. The performance of the algorithm is tested and validated by using three videos of highway scenes in Malaysia with normal weather conditions, raining and a night-time scene, and an additional scene of a sunny rural road area. The video frame rate is 30fps with dimensions of 720p (1280x720) HD pixels. In the final achievement analysis, the test result shows a true positive rate, a TP lane detection  average rate of 0.925 and the capability to be used in the final application implementation.
 
Keywords: Image processing, lane detection, Region of Interest (ROI), road width, vanishing point.
 
Received: 16 February 2017 Accepted: 5 May 2017
 

 
INTELLIGENT RESPONSIVE INDOOR SYSTEM (IRIS): A POTENTIAL SHOPLIFTER SECURITY ALERT SYSTEM
Mohamad Kuzahier Mohd Zahari & Zarul Fitri Zaaba
School of Computer Sciences
Universiti Sains Malaysia, Malaysia
mkuzahier.ucom11@student.usm.my; zarulfitri@usm.my

ABSTRACT | FULL TEXT
Shoplifting can occur at any time and any place. From the big mall to a small shop, many security measures have been put in place as prevention tools. Apparently, there are numbers of shoplifting prevention tools in the market such as the Closedcircuit Television (CCTV), Electronic Article Surveillance (EAS) and Future Attribute Screening Technology (FAST). However, the cost issues and the ease of use always become the main concerns for the shopkeepers. Therefore CCTV was widely accepted because of the ease and affordable price. Although the CCTV is their main preference, it can be noted that CCTV operates in a static way where it can only records and monitor the incidents. This paper highlights the conventional CCTV issues and proposes the Intelligent Responsive Indoor System (IRiS) the as security crime prevention tool that uses face detection, recognition and behavior analysis to detect potential shoplifting intentions. Six small shop owners were interviewed to understand their insights on the problems and the need to further enhance the current CCTV. In addition, detailed discussions were provided in relation to the development of IRiS. Therefore, it can be suggested that IRiS provides a significant foundation and promises to be a security prevention tool to improve the conventional functions of the CCTV.
 
Keywords: Security, face recognition, biometrics, security alerts, intelligent system, Human Computer Interaction.
 
Received: 13 July 2016 Accepted: 2 March 2017
 

 
THERAPEUTIC SERIOUS GAME DESIGN GUIDELINES FOR STIMULATING COGNITIVE ABILITIES OF CHILDREN WITH SPEECH AND LANGUAGE DELAY
1Nadia Akma Ahmad Zaki, 2Tengku Siti Meriam Tengku Wook, 3Kartini Ahmad
1Faculty of Art, Computing and Creative Industry
Sultan Idris Education University
Perak, Malaysia
2Faculty of Information Science and Technology
Universiti Kebangsaan Malaysia
3Faculty of Health Sciences
Universiti Kebangsaan Malaysia
nadiaakma@fskik.upsi.edu.my;tsmeriam@ukm.edu.my;kart@ukm.edu.my

ABSTRACT | FULL TEXT
The creation of an effective therapeutic serious game (TSG) is highly dependent upon its design and the fundamental knowledge of the users. Furthermore, the TSG is designed for a purpose to the users by incorporating the needs of the users in all design components. Although numerous studies have been conducted on guidelines for designing serious games, to date, studies on the specific TSG’s design guidelines for stimulating the cognitive ability of children with speech and language delay (CSLD) has yet to be comprehensively studied. Therefore, this study focuses on the set of design guidelines for the development of TSG for CSLD, specifically on cognitive stimulation. The TSG design guidelines in this paper are derived through the study of relevant literature, and best practices gained from interviews with experts in the area of speech pathology. These guidelines would be useful for researchers and game designers to design TSG for CSLD focusing on cognitive stimulation.

Keywords: Design guidelines, therapeutic, serious games, cognitive stimulation, children with speech and language delay.
 
Received: 30 December 2016 Accepted: 4 May 2017
 

 
NEURAL NETWORK TRAINING USING HYBRID PARTICLEMOVE ARTIFICIAL BEE COLONY ALGORITHM FOR PATTERN CLASSIFICATION
Zakaria Noor Aldeen Mahmood Al Nuaimi & Rosni Abdullah
School of Computer Sciences
Universiti Sains Malaysia, Malaysia
zqttan2@yahoo.com; rosni@cs.usm.my

ABSTRACT | FULL TEXT
The Artificial Neural Networks Training (ANNT) process is an optimization problem of the weight set which has inspired researchers for a long time. By optimizing the training of the neural networks using optimal weight set, better results can be obtained by the neural networks. Traditional neural networks algorithms such as Back Propagation (BP) were used for ANNT, but they have some drawbacks such as computational complexity and getting trapped in the local minima. Therefore, evolutionary algorithms like the Swarm Intelligence (SI) algorithms have been employed in ANNT to overcome such issues. Artificial Bees Colony (ABC) optimization algorithm is one of the competitive algorithms in the SI algorithms group. However, hybrid algorithms are also a fundamental concern in the optimization field, which aim to cumulate the advantages of different algorithms into one algorithm. In this work, we aimed to highlight the performance of the Hybrid Particle-move Artificial Bee Colony (HPABC) algorithm by applying it on the ANNT application. The performance of the HPABC algorithm was investigated on four benchmark pattern-classification datasets and the results were compared with other algorithms. The results obtained illustrate that HPABC algorithm can efficiently be used for ANNT. HPABC outperformed the original ABC and PSO as well as other state-of-art and hybrid algorithms in terms of time, function evaluation number and recognition accuracy.

Keywords: Swarm Intelligence, Artificial Neural Networks, Artificial Bee Colony Algorithm, Particle Swarm Optimization, Pattern-Classification.
 
Received: 5 September 2016 Accepted: 13 June 2017
 

 
EFFICIENT MOBILE VIDEO TRANSMISSION BASED ON A JOINT CODING SCHEME
1Rima Boudjadja, 2Mohamed Azni, 3Abdelnasser Dahmani & 4Mohamed Nadjib Zennir
1&4Computer Science Department
2LIMED Laboratory, Faculty of Technology
University of Bejaia, Bejaia, Algeria,
3Mathematics Department
University Center of Tamanghasset, Tamanghasset, Algeria
{rima.boudjadja; mohamed.azni; zennir.med}@gmail.com; abdelnasser.dahmani@univ-bejaia.dz

ABSTRACT | FULL TEXT
In this paper, we propose a joint coding design which uses the Symbol Forward Error Correction (S-FEC) at the application layer. The purpose of this work is on one hand to minimize the Packet Loss Rate (PLR) and, on the other hand to maximize the visual quality of video transmitted over a wireless network (WN). The scheme proposed is founded on a FEC adaptable with the semantics of the H.264/AVC video encoding. This mechanism relies upon a rate distortion algorithm, controlling the channel code rates under the global rate constraints given by the WN. Based on a data partitioning (DP) tool, both packet type and packet length are taken into account by the proposed optimization mechanism which leads to unequal error protection (UEP). The performance of the proposed JSCC unequal error control is illustrated over wireless network by performing simulations under different channel conditions. The simulation results are then compared with an equal error protection (EEP) scheme.

Keywords: Data partitioning, H.264/AVC, real time video, Reed-Solomon codes, unequal error protection.
 
Received: 1 September 2016 Accepted: 5 April 2017
 

 
HIGH ACCURACY EEG BIOMETRICS IDENTIFICATION USING ICA AND AR MODEL
Chesada Kaewwit, Chidchanok Lursinsap & Peraphon Sophatsathit
Advanced Virtual and Intelligent Computing Center
Faculty of Science, Chulalongkorn University, Thailand
ckaewwit@gmail.com;lchidcha@chula.ac.th;peraphon.s@chula.ac.th

ABSTRACT | FULL TEXT
Modern biometric identification methods combine interdisciplinary approaches to enhance person identification and classification accuracy. One popular technique for this purpose is Brain-Computer Interface (BCI). The signal so obtained from BCI will be further processed by the Autoregressive (AR) Model for feature extraction. Many researches in the area find that for more accurate results, the signal must be cleaned before extracting any useful feature information. This study proposes Independent Component Analysis (ICA), k-NN classifier, and AR as the combined techniques for electroencephalogram (EEG) biometrics to achieve the highest personal identification and classification accuracy. However, there is a classification gap between using the combined ICA with the AR model and AR model alone. Therefore, this study takes one step further by modifying the feature extraction of AR and comparing the outcome with the proposed approaches in lieu of prior researches. The experiment based on four relevant locations shows that the combined ICA and AR can achieve higher accuracy than the modified AR. More combinations of channels and subjects are required in future research to explore the significance of channel effects and to enhance the identification accuracy.

Keywords: electroencephalogram (EEG), Autoregressive (AR), Independent Component Analysis (ICA), Biometrics, feature extraction, person classification.
 
Received: 16 January 2017 Accepted: 3 July 2017
 

 
CONSISTENCY OF ONLINE CONSUMERS’ PERCEPTIONS OF POSTED COMMENTS: AN ANALYSIS OF TRIPADVISOR REVIEWS
Foo Sheng Khoo, Phoey Lee Teh & Pei Boon Ooi
Department of Computing and Information Systems
Sunway University, Malaysia
kfoosheng@hotmail.com; phoeyleet@sunway.edu.my; peiboono@sunway.edu.my

ABSTRACT | FULL TEXT
Ratings and comments play a dominant role in online reviews. The question, thus, arises as to whether or not there is any consistency in consumer perception of the reviews, and how future choices might be influenced. We analysed 2000 comments of 20 different hotels posted on TripAdvisor to determine if the comments posted by previous guests of a hotel influence the decisions of potential guests. Two hundred human raters were asked to consider 20 reviews and to rate a hotel based on the reviews. The Cohen Kappa coefficient was used to evaluate the degree of agreement on the hotel quality as determined by the human raters and the star rating given by the original reviewer. The results showed a high consistency between the human raters’ evaluation and the reviewers’ star rating. This research reveals the importance of website feedback such as TripAdvisor in influencing consumer choice.

Keywords: Cohen Kappa, comments, degree of agreement, rating, online reviews.
 
Received: 24 November 2016 Accepted: 3 July 2017
 

 
A LINEAR PROGRAMMING BASED MODEL TO MEASURE EFFICIENCY AND EFFECTIVENESS OF UNDERGRADUATE PROGRAMS
Maznah Mat Kasim, Rosmaini Kashim & Sahubar Ali Mohamed Nadhar Khan
School of Quantitative Sciences
Universiti Utara Malaysia, Malaysia
maznah@uum.edu.my;rosmaini@uum.edu.my;sahubar@uum.edu.my

ABSTRACT | FULL TEXT
Measuring performance of an educational program based on its academic achievement is not sufficient without considering the cost and the impact of the program. This paper aims to demonstrate the construction of a measurement model consisting of the input, output and outcome variables. The model can estimate both the efficiency and the effectiveness of undergraduate programs. After the aforementioned variables were identified for each individual efficiency and effectiveness model, a linear programming based tool, Data Envelopment Analysis (DEA) was used as the analysis method to integrate the models since it has the ability to consider all the variables simultaneously. The two models were integrated as a product, and was defined as the final model which was verified by applying it to measure the performance of 26 undergraduate programs in a university. The results show that seven programs are efficient, six programs are effective, and six programs are both efficient and effective. The model is flexible since it can be extended to include more variables or it can be modified by defining new variables in measuring efficiency and effectiveness of other programs or organizations.

Keywords: Efficiency, effectiveness, undergraduate programs, Data Envelopment Analysis.
 
Received: 13 September 2016 Accepted: 28 May 2017
 

 
A SYSTEMATIC READING IN STATISTICAL TRANSLATION: FROM THE STATISTICAL MACHINE TRANSLATION TO THE NEURAL TRANSLATION MODELS.
Zakaria El Maazouzi, Badr Eddine El Mohajir & Mohammed Al Achhab
N2T Laboratory, National School of Applied Sciences
University Abdelmalek Essaadi, Morocco
z.elmaazouzi.ma@ieee.org; b.elmohajir@ieee.ma; alachhab@ieee.ma

ABSTRACT | FULL TEXT
Achieving high accuracy in automatic translation tasks has been one of the challenging goals for researchers in the area of machine translation since decades. Thus, the eagerness of exploring new possible ways to improve machine translation was always the matter for researchers in the field. Automatic translation as a key application in the natural language processing domain has developed many approaches, namely statistical machine translation and recently neural machine translation that improved largely the translation quality especially for Latin languages. They have even made it possible for the translation of some language pairs to approach human translation quality. In this paper, we present a survey of the state of the art of statistical translation, where we describe the different existing methodologies, and we overview the recent research studies while pointing out the main strengths and limitations of the different approaches.
 
Keywords: Neural networks, recurrent neural networks, natural language processing, neural language model.
 
Received: 3 July 2017 Accepted: 28 August 2017

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