Nasiroh Omar

Time-Varying mutation in particle swarm optimization

One of significant improvement for particle swarm optimization (PSO) is through the implementation of metaheuristics hybridization that combines different metaheuristics paradigms. By using metaheuristics hybridization, the weaknesses of one algorithm can be compensated by the strengths of other algorithms. Therefore, researchers have given a lot of interest in hybridizing PSO with mutation concept from genetic algorithm (GA). The reason for incorporating mutation into PSO is to resolve premature convergence problem due to some kind of stagnation by PSO particles. Although PSO is capable to produce fast results, particles stagnation has led the algorithm to suffer from low-optimization precision. Thus, this paper introduces time-varying mutation techniques for resolving the PSO problem. The different time-varying techniques have been tested on some benchmark functions. Results from the empirical experiments have shown that most of the time-varying mutation techniques have significantly improved PSO performances not just to the results accuracy but also to the convergence time.

Hybridization of Particle Swarm Optimization with adaptive genetic algorithm operators

Particle Swarm Optimization (PSO) is a popular algorithm used extensively in continuous optimization. One of its well-known drawbacks is its propensity for premature convergence. Many techniques have been proposed for alleviating this problem. One of the alternative approaches is hybridization. Genetic Algorithms (GA) are one of the possible techniques used for hybridization. Most often, a mutation scheme is added to the PSO, but some applications of crossover have been added more recently. Some of these schemes use adaptive parameterization when applying the GA operators. In this work, adaptively parameterized mutation and crossover operators are combined with a PSO implementation individually and in combination to test the effectiveness of these additions. The results indicate that an adaptive approach with position factor is more effective for the proposed PSO hybrids. Compared to single PSO with adaptive inertia weight, all the PSO hybrids with adaptive probability have shown satisfactory performance in generating near-optimal solutions for all tested functions.

Towards automatic column-based data object clustering for multilingual databases

The amount of data in all computer applications is growing tremendously. As a result, the organization of the huge data is crucial. Recently, many researchers consider clustering as one of the important approaches in handling data for wide range of research domains. The examples include Topic Detection and Tracking (TDT), Multilingual Document Clustering, Multilingual News Clustering, Text Clustering and Web Record. Normally, data clustering is time consuming and challenging since they involve heavy programming or scripting. In online news, data clustering analysis is very much needed as the nature of the news across the globe is dynamically changing in every second. The news can come from any web sources in the form of multilingual news. This paper proposes system architecture for an automatic data object clustering in multilingual database for online news, web record and text mining. The architecture provides an overview of a virtual scheme that handles data objects within the database tables as part of the database management system. The proposed technique architecture will provide the platform for quick extraction, data arrangement, data grouping based on pattern similarities. Thus, it will improve query processing performance in multilingual databases without the need to code or script for interface programming. This is the first attempt to apply the data clustering technique prior to data extraction in any database application in the form of semi-structured and structured data (web record).

Challenges and issues on online news management

Recently, the Internet usage spread in all areas of life. Online news is among the popular articles on the Internet, which occupies a large portion of online information. The online news will be viewed almost every second in order to follow the evolution of any desired global events. There are many organizations or political parties employ agents for tracking news by grouping the event. Therefore, news clustering is helpful and worthy for many researchers and online news readers in order to view events from multiple perspectives. Additionally, it can be used in online news summarization, topic detection and tracking for extracting and detecting new events or topics in the news articles. The news extraction can be applied on news articles in the form of monolingual or multilingual. On the other hand, news aggregation is the most important method for scrawling and collecting events based on topics or categorization. This paper investigates the challenges and issues that relate to online news research. The discussions include the overview of system architectures, online news techniques, and a few related computer applications for the above mentioned online news areas.

A Parallel Latent Semantic Indexing (LSI) Algorithm for Malay Hadith Translated Document Retrieval

Latent Semantic Indexing (LSI) is one of the well-known searching techniques which match queries to documents in information retrieval applications. LSI has been proven to improve the retrieval performance, however, as the size of documents gets larger, current implementations are not fast enough to compute the result on a standard personal computer. In this paper, we proposed a new parallel LSI algorithm on standard personal computers with multi-core processors to improve the performance of retrieving relevant documents. The proposed parallel LSI was designed to automatically run the matrix computation on LSI algorithms as parallel threads using multi-core processors. The Fork-Join technique is applied to execute the parallel programs. We used the Malay Translated Hadith of Shahih Bukhari from Jilid 1 until Jilid 4 as the test collections. The total number of documents used is 2028 of text files. The processing time during the pre-processing phase of the documents for the proposed parallel LSI is measured and compared to the sequential LSI algorithm. Our results show that processing time for pre-processing tasks using our proposed parallel LSI system is faster than sequential system. Thus, our proposed parallel LSI algorithm has improved the searching time as compared to sequential LSI algorithm.

Application-based context-awareness in collaborative workspaces: A review

In this paper, we investigate the existing research based on context-awareness elements in various collaborative applications. The investigation is based on seven context awareness entities; application, media, method, tool, platform, framework and device. This work focuses on the application which involves eight context elements; domain, activity of user, context object, locations, type of communication, type of context, digital elements and models. In order to define the attributes for each of the context element, various domains of applications are selected that include education, business, mobile, multimedia and virtual reality. Based on the attributes, a context awareness structure in collaborative workspaces is proposed. The structure visualizes a general relationship between the clustered elements in handling context awareness. Thus, the relationship enables context-awareness to be used in a broader perspective of context-aware applications as opposed to the current practice that is limited for specific circumstances.

Investigating an approach for online reading assessment

This qualitative research aims to explore alternatives to multiple-choice online reading comprehension tests, which may have high construct validity, but which also have low ecological validity and negative backwash effects at the system level. Our aim is to investigate an approach that might capture and evaluate some of the complex cognitive processes that are involved in authentic Web-based research tasks. Eight fluent readers participated and for each participant, files were generated based on all search terms used, all visited URLs, and the text of the final essay. Each participant s evidence is evaluated using latent semantic analysis to produce an indication of five factors: the degree of match between participants search goal and the given task, participants search goal and an experts Internet search goal, participants written task output with the given task, participants written task output with an experts written task output and the overall coherence of written task output.

Managing unstructured data in relational databases

A relational database is a basic repository for many businesses, with its robust data structure for retrieving, organizing, and managing data. However, despite its data structure characteristic, a massive amount of data it contains remains unstructured. These unstructured data affects query processing performance and contributes to the difficulty of the user to manage or retrieve the data. Many attempts have been made to reorganize or directly process these data. In this paper, discusses methods of managing unstructured data in the relational database management system. And show the significance of managing these data. Furthermore, the difference in managing such data between relational and NoSQL databases is highlighted. This study will help developers and researchers in managing unstructured data and in addressing important issues that affect query processing which otherwise meaningless if those were not well managed.

Towards flexible media sharing: Control and coordination issues in network collaborative virtual environment

Media is known as a medium of communication among users. Nowadays, the emergence of communication technology allows users in distributed locations to share and work interactively on digital media elements such as artifacts, documents, images, graphics and audio-video files. Users who work on the same project will form four communication relationships (one-to-one, one-to-many, one-to-selected users, many-to-many) and they share the same media. Different types of media require different handling mechanisms, especially when dealing with distributed virtual users on heterogeneous platforms. As a result, controlling and coordinating such media becoming more complex. This paper investigates the control and coordinating factors in relation to media sharing based on platform, users, media access, and API. The investigation involves comparative studies based on related research that focus on media sharing in networked collaborative workspaces. Results from this study are significant to support the control and coordination of flexible media sharing for future research.

Towards measuring self-perception in disseminating information

Online information is becoming increasingly important within strategic communication and the use of unlimited social media (the internet). Since the information can be manipulated, it is crucial to measure ones perception to avoid negative perception that may leads to threat. This paper presents two models on representing a general model of self-perception and a self perception measurement model for online media user. The online media is able to disseminate information across the globe regardless of user location and background. These models are to show how information may be changed and how a user could be evaluated through three domains of inter-related activities: receiving information, synthesizing the information and communicating the information to others. These models are not only appropriate for strategic communication, but also applicable to any application domains in relation to measurement.