Friday, August 17, 2018
   
Text Size
Login

Forthcoming Articles

These articles have been peer-reviewed and accepted for publication in JICT, but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the JICT standard. Additionally, titles, authors, abstracts and keywords may change before publication.


EXTENSIONS TO THE K-AMH ALGORITHM FOR NUMERICAL CLUSTERING
Ali Seman and Azizian Mohd Sapawi
Center for Computer Science Studies, Faculty of Computer and Mathematical Sciences,
Universiti Teknologi MARA (UiTM), 40450 Shah Alam, Selangor, Malaysia
aliseman@tmsk.uitm.edu.my; azizian@tmsk.uitm.edu.my

Abstract
The k-AMH algorithm has been proven efficient in clustering categorical datasets. It can also be used for numerical clustering with minimum modification to its original algorithm. In this paper, we present two algorithms that extend the k-AMH algorithm for numerical clustering. The original k-AMH algorithm for categorical clustering 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 clustering. 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 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 result significantly proved that the k-AMH Numeric I and k-AMH Numeric II can be used for numerical clustering.

Keywords: Cluster analysis, partitional clustering algorithms, categorical and numerical data



IDENTIFYING SKYLINES IN CLOUD DATABASES WITH INCOMPLETE DATA

1Yonis Gulzar, 2Ali A. Alwan, 3Norsaremah Salleh & 4Imad Fakhri Al Shaikhli
1,2,3&4International Islamic University Malaysia, Malaysia
younisgulzar@gmail.com; aliamer@iium.edu.my; norsaremah@iium.edu.my; imadf@iium.edu.my

Abstract
Skyline queries is a rich area of research in database community. Due to its great benefits, it has been integrated in many database applications including but not limited to personalized recommendation, multi-objective, decision support and decision-making systems. Many variations of skyline technique have been proposed in the literature addressing the issue of handling skyline queries in incomplete database. Nevertheless, these solutions are designed to fit with centralized incomplete database (single access). However, in many real-world database systems, this might not be the case, particularly for a database with large amount of incomplete data distributed over various remote locations such as cloud databases. It is inadequate to directly apply skyline solutions designed for centralized incomplete database to work on cloud due to the prohibitive cost. Thus, this paper introduces a new solution processing skyline queries in incomplete database aiming at minimizing the amount of data transfer and the number of pairwise comparisons that need to be conducted to derive the skyline. The proposed approach adopts a filtration process that attempts to prune the dominated data items before applying skyline process. Filtering the initial database before applying skyline assists in decreasing the number of pairwise comparisons. Most importantly, pruning the dominated data before join helps in reducing the amount of data transfer due to transferring a small portion of the data instead of the transferring the entire database from one datacenter to another. Several experiments have been performed emphasize on evaluating the effectiveness of the proposed approach. The results show that our approach outperforms the previous state-of-the-art approaches in terms of number of pairwise comparisons and the amount of data transferred. We argue that our solution is practical and can be adopted in many contemporary database systems to process skyline queries in an incomplete database.

Keywords: preference queries, skyline queries, algorithms, incomplete data, cloud databases.


 
VIBRANT SEARCH MECHANISM FOR NUMERICAL OPTIMIZATION FUNCTIONS
Moh’d Khaled Yousef Shambour
The Custodian of the Two Holy Mosques Institute for Hajj and Umrah Research, Umm Al-Qura University, Makkah, Saudi Arabia
Myshambour@uqu.edu.sa

Abstract
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.



THE IMPACT OF PERSUASIVE TECHNOLOGY ON USER EMOTIONAL EXPERIENCE AND USER EXPERIENCE OVER TIME
1,2Wan Nooraishya Wan Ahmad and 1Nazlena Mohamad Ali
1Institute of Visual Informatics, Universiti Kebangsaan Malaysia (UKM), Malaysia
2Faculty of Computing and Informatics, Universiti Malaysia Sabah (UMS), Malaysia
wanaishya@gmail.com; nazlena.ali@ukm.edu.my

Abstract
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, emotion, hedonic, persuasive technology, pragmatic, user experience

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