Wednesday, November 30, 2022

Izzad Ramli, Nursuriati Jamil & Noraini Seman
Antipas T. Teologo Jr. & Lawrence Materum
Wan Mohd Yusoff Wan Yaacob, Nur Haryani Zakaria & Zahurin Mat Aji

Arvinder Kaur & Yugal Kumar
Department of Computer Science and Information Technology, Jaypee University of Information Technology, India;
This paper presents a new diagnostic model for various diseases. In the proposed diagnostic model, a water wave optimization (WWO) algorithm was implemented for improving the diagnosis accuracy. It was observed that the WWO algorithm suffered from the absence of global best information and premature convergence problems. Therefore in this work, some improvements were proposed to formulate the WWO algorithm as more promising and efficient. The global best information issue was addressed by using an improved solution search equation and the aim of this was to explore the global best optimal solution. Furthermore, a premature convergence problem was rectified by using a decay operator. These improvements were incorporated in the propagation and refraction phases of the WWO algorithm. The proposed algorithm was integrated into a diagnostic model for the analysis of healthcare data. The proposed algorithm aimed to improve the diagnosis accuracy of various diseases. The diverse disease datasets were considered for implementing the performance of the proposed diagnostic model based on accuracy and F-score performance indicators, while the existing techniques were regarded to compare the simulation results. The results confirmed that the WWO-based diagnostic model achieved a higher accuracy rate as compared to existing models/techniques with most disease/healthcare datasets. Therefore, it stated that the proposed diagnostic model is more promising and efficient for the diagnosis of different diseases.

Keywords: Computational intelligence, water wave optimization, disease diagnosis, diagnostic model, metaheuristic technique.

 btn fulltext

Izzad Ramli, Nursuriati Jamil & Noraini Seman
Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, Malaysia;;
Intonation generation in expressive speech such as storytelling is essential to produce high quality Malay language expressive speech synthesizer. Intonation generation, for instance explicit control, has shown good performance in terms of intelligibility with reasonably natural speech; thus, it was selected in this research. This approach modifies the prosodic features, such as pitch contour, intensity, and duration, to generate the intonation. However, modification of pitch contour remains a problem because the desired pitch contour is not achieved. This paper formulated an improved pitch contour algorithm to develop a modified pitch contour resembling the natural pitch contour. In this work, the syllable pitch contours of nine storytellers were extracted from their storytelling speeches to create an expressive speech syllable dataset called STORY_DATA. All the shapes of pitch contours from STORY_DATA were analyzed and clustered into the standard six main pitch contour clusters for storytelling. The clustering was performed using one minus the Pearson product moment correlation. Then, an improved iterative two-step sinusoidal pitch contour formulation was introduced to modify the pitch contours of a neutral speech into an expressive pitch contour of natural speeches. Overall, the improved pitch contour formulation was able to achieve 93 percent high correlated matches, indicating the high resemblance as compared to the previous pitch contour formulation at 15 percent. Therefore, the improved formula can be used in a text-to-speech (TTS) synthesizer to produce a more natural expressive speech. The paper also discovered unique expressive pitch contours in the Malay language that need further investigations in the future.
Keywords: Pitch contour formulation, prosody modification, speech synthesis, storytelling.
btn fulltext 

1,2 Abdullah Almogahed & 2Mazni Omar
1Department of Software Engineering, Taiz University, Yemen
2School of Computing, Universiti Utara Malaysia, Malaysia; 

Refactoring is a critical task in software maintenance and is commonly applied to improve system design or to cope with design defects. There are 68 different types of refactoring techniques and each technique has a particular purpose and effect. However, most prior studies have selected refactoring techniques based on their common use in academic research without obtaining evidence from the software industry. This is a shortcoming that points to the existence of a clear gap between academic research and the corresponding industry practices. Therefore, to bridge this gap, this study identified the most frequently used refactoring techniques, the commonly used programming language, and methods of applying refactoring techniques in the current practices of software refactoring among software practitioners in the industry, by using an online survey. The findings from the survey revealed the most used refactoring techniques, programming language, and the methods of applying the refactoring techniques. This study contributes toward the improvement of software development practices by adding empirical evidence on software refactoring used by software developers. The findings would be beneficial for researchers to develop reference models and software tools to guide the practitioners in using these refactoring techniques based on their effect on software quality attributes to improve the quality of the software systems as a whole.

Keywords: Exploratory study, software refactoring, survey, refactoring techniques.
btn fulltext

1Antipas T. Teologo Jr. & 2Lawrence Materum
1&2Department of Electronics and Communications Engineering, De La Salle University, Philippines
1Electrical and Electronics Engineering Department, FEU Institute of Technology, Philippines
2International Centre, Tokyo City University, Japan;;
Wireless multipath clustering is an important area in channel modeling, and an accurate channel model can lead to a reliable wireless environment. Finding the best technique in clustering wireless multipath is still challenging due to the radio channels’ time-variant characteristics. Several clustering techniques have been developed that offer an improved performance but only consider one or two parameters of the multipath components. This study improved the K-PowerMeans technique by incorporating weights or loads based on the principal component analysis and utilizing the Minkowski distance metric to replace the Euclidean distance. K-PowerMeans is one of the several methods in clustering wireless propagation multipaths and has been widely studied. This improved clustering technique was applied to the indoor datasets generated from the COST 2100 channel Model and considered the multipath components’ angular domains and their delay. The Jaccard index was used to determine the new method’s accuracy performance. The results showed a significant improvement in the clustering of the developed algorithm than the standard K-PowerMeans.
Keywords: Channel model, Minkowski distance, multipath clustering, principal component analysis, radio wave propagation.
btn fulltext

1Wan Mohd Yusoff Wan Yaacob, 2Nur Haryani Zakaria & 2Zahurin Mat Aji
1Department of Information Technology & Communication, Politeknik Sultan Abdul Halim Mu’adzam Shah, Malaysia
2School of Computing, Universiti Utara Malaysia, Malaysia;;
Nowadays, there are growing views of potentially addictive behaviors such as digital addiction, especially Online Game Addiction (OGA). This study argues that all types of addictions are related to common components, such as salience, mood modification, tolerance, withdrawal, conflict, relapse, and problems. Despite the plethora of online game consequences, there is no standard or benchmark used to classify between addicted and non-addicted users. Therefore, this study is organized to identify the factors that contribute to OGA and examine the level of OGA especially among adolescents by utilizing the Online Game Addiction Scale (OGAS). Using the same scale, the adolescents were classified into addicted and non-addicted categories. Driven by previous studies of conventional game addiction, this study adopted all the distinct common components to measure seven underlying criteria related to OGA. The dimensional structure of the scale was analyzed based on the samples of adolescents among students of higher learning institutions (HLI) in Northern Malaysia. Data were collected from 389 participants who responded to an online survey. Based on OGAS, 35 percent of the participants were found to be addicted to online games. In addition, the findings demonstrated good concurrent validity as shown by the coherent associations between the time spent on playing games and the category of the games. This study contributes to the identification of factors that influence OGA among adolescents, which are significant in preventing the occurrence of other behavioral issues such as insecure cyber and emotional behaviors.
Keywords: Addictive behavior, digital addiction, online game addiction, online game disorder, scale, adolescent.

btn fulltext 

1Bahaa Ahmad Masmas & 2Azlinah Mohamed
1Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA (UiTM), Malaysia
2Institute for Big Data Analytics and Artificial Intelligence, Universiti Teknologi MARA (UiTM), Malaysia; 



Emergency management systems (EMS) assist emergency managers to resolve emergencies on hand, through analyzing the emergency characteristics and consolidating data from different departments that are involved in resolving the emergency. Many countries have adopted various forms of EMS that are specialized in resolving one type of emergency, and studies demonstrate their effectiveness in producing better decisions. However, the COVID-19 pandemic uncovered the lack of a comprehensive framework that could deal with different emergencies. It also revealed the inability of the current systems to communicate with each other to retrieve the needed data. The aim of this study is to show the current state of EMS in emergency departments by constructing a framework for a knowledge-based decision support system for emergency management focusing on resolving pandemics. Qualitative approach was adopted in this research, where the authors reviewed emergency management in general and pandemics in specific. Existing EMS systems were investigated, and knowledge-based decision support systems were explored. Approaches for integration, communication, and collaboration were also studied. As a result of this study, a comprehensive framework, i.e., a knowledge-based decision support system for emergency departments, focusing on resolving pandemics was introduced. The framework was validated by a domain expert who provided insights and suggestions for future research. While the primary research focus is to assist emergency managers in resolving the COVID-19 pandemic, the proposed framework is unique by adopting different approaches and techniques that enable the system to deal with various emergencies not limited to the current pandemic.
Keywords: Decision support system, emergency management, knowledge-based system, pandemic.
btn fulltext

1Maha Thabet, 2Mehdi Ellouze & 3Mourad Zaied
1ISITCom, University of Sousse, Tunisia
2Faculty of Economics and Management of Sfax, Sfax University,Tunisia
3Research Team in Intelligent Machines, Gabes University Gabes, Tunisia;;
Video concept detection means describing a video with semantic concepts that correspond to the content of the video. The concepts help to retrieve video quickly. These semantic concepts describe high-level elements that depict the key information present in the content. In recent years, many efforts have been done to automate this task because the manual solution is time-consuming. Nowadays, videos come with comments. Therefore, in addition to the content of the videos, the comments should be analyzed because they contain valuable data that help to retrieve videos. This paper focused especially on videos shared on social media. The specificity of these videos was the presence of massive comments. This paper attempted to exploit comments by extracting concepts from them. This would support the research effort that works only on the visual content. Natural language processing techniques were used to analyze comments and to filter words to retain only the ones that could be considered as concepts. The proposed approach was tested on YouTube videos. The results demonstrated that the proposed approach was able to extract accurate data and concepts from the comments that could be used to ease the retrieval of videos. The findings supported the research effort of working on the visual and audio contents of the videos. 
Keywords: Keywords-based video retrieval, social media tagging, natural language processing, video concept detection.
btn fulltext

1Azlin Ahmad, 2Rubiyah Yusof, 3Nor Saradatul Akmar Zulkifli & 4Mohd Najib Ismail
1Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, Malaysia
2Malaysia-Japan International Institute of Technology, Universiti Teknologi Malaysia, Malaysia
3Faculty of Computer System & Software Engineering, Universiti Malaysia Pahang
4School of Computing Asia Pacific University Technology Park Malaysia,Malaysia;;; 
The data distribution issue remains an unsolved clustering problem in data mining, especially in dealing with imbalanced datasets. The Kohonen Self-Organising Map (KSOM) is one of the well-known clustering algorithms that can solve various problems without a pre-defined number of clusters. However, similar to other clustering algorithms, this algorithm requires sufficient data for its unsupervised learning process. The inadequate amount of class label data in a dataset significantly affects the clustering learning process, leading to inefficient and unreliable results. Numerous research have been conducted by hybridising and optimising the KSOM algorithm with various optimisation techniques. Unfortunately, the problems are still unsolved, especially separation boundary and overlapping clusters. Therefore, this research proposed an improved pheromone-based PKSOM algorithm known as iPKSOM to solve the mentioned problem. Six different datasets, i.e. Iris, Seed, Glass, Titanic, WDBC, and Tropical Wood datasets were chosen to investigate the effectiveness of the iPKSOM algorithm. All datasets were observed and compared with the original KSOM results. This modification significantly impacted the clustering process by improving and refining the scatteredness of clustering data and reducing overlapping clusters. Therefore, this proposed algorithm can be implemented in clustering other complex datasets, such as high dimensional and streaming data.
Keywords: Clustering, imbalanced data, Kohonen self-organising map, optimisation, pheromone.
btn fulltext

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

Creative Commons License

All articles published in Journal of Information and Communication Technology (JICT) are licensed under a Creative Commons Attribution 4.0 International License.