Md. Hafiz Selamat

Hybridized term-weighting method for Dark Web classification

The role of intelligence and security informatics based on statistical computations is becoming more significant in detecting terrorism activities proactively as the extremist groups are misusing many of the obtainable facilities on the Internet to incite violence and hatred. However, the performance of statistical methods is limited due to the inadequate accuracy produced by the inability of these methods to comprehend the texts created by humans. In this paper, we propose a hybridized feature selection method based on the basic term-weighting techniques for accurate terrorism activities detection in textual contexts. The proposed method combines the feature sets selected based on different individual feature selection methods into one feature space for effective web pages classification. UNION and Symmetric Difference combination functions are proposed for dimensionality reduction of the combined feature space. The method is tested on a selected dataset from the Dark Web Forum Portal and benchmarked using various famous text classifiers. Experimental results show that the hybridized method efficiently identifies the terrorist activities content and outperforms the individual methods. Furthermore, the results revealed that the classification performance achieved by hybridizing few feature sets is relatively competitive in the number of features used for classification with higher hybridization levels. Moreover, the experiments of hybridizing functions show that the dimensionality of the feature sets is significantly reduced by applying the Symmetric Difference function for feature sets combination. A hybrid text classifications method with term-weighting techniques is proposed.The proposed method combines various feature sets for effective classification.We proposed a method to reduce the dimension of feature sets for classification.The method is tested on a selected dataset from the Dark Web Portal Forum.Experimental results show that the proposed method outperforms other methods.

Scalable e-business social network using MultiCrawler agent

Social networking is a big buzz phrase nowadays. It refers to the practice of interacting with others online via blogs, forums, social media sites and other outlets. The importance of social networking is to let others know that we are exists. Social network can show how people in our extended network are related to each other. In this paper, we are focusing on e-business network since e-business is sprouting on the Internet these days like wild mushrooms. Moreover, with the rapid growth of the e-business in the Web, searching the popular web page of e-business and its relationship with others web page becomes an interesting and important issue for the user especially for the firms. Currently, we realized which of the e-business having the highest popularity via the newspaper, magazines and Internet. However, the e-business having a lack of information - the quality of the connection. In order to collect the e-business web sites from the Internet, crawler agent is used. The crawler will obtain information in the links and keeps the information in the repository for later processing. Here, we proposed the MultiCrawler agent to develop a scalable e-business social network. The genetic algorithm is used to optimize the e-business web pages fetched by the crawler based on the user profiles. The result is the visualization of e-business social network mapping that related to the Multimedia Super Corridor (MSC) companies in Malaysia.

Web Mining for Malaysia's Political Social Networks Using Artificial Immune System

Currently, politic is one of the critical and hot issues in Malaysia. There are many aspects that are related with politics. These politic aspects are mainly about spreading rumors and information through cyberspace that created positive and negative effects to the political situations in Malaysia. There are many branches of cyberspace that can be used by the Internet users to channel their opinions such as websites, forums and blogs which contain the political issues in Malaysia. In this paper, we have analyzed an adaptive model of web mining using Artificial Immune System (AIS) to retrieve the list of URLs that have relevant information on political issues in Malaysia. In addition, we have also used a concept of social network analysis in order to understand the relationships among the websites and web pages related to the political issues in Malaysia. The results from this model have been used to analyze the social networks and the impact of online community which contribute to the outcome of Malaysias 12th general election.

Agent Verification Design of Short Text Messaging System Using Formal Method

Today, in the evolution of hardware and software system in mobile-driven applications, failure is unacceptable to many entrepreneurs. The use of Short Message Service (SMS) for internet-based business is acknowledged to be one of the applications that have a potential to give unreliable results to the information systems. Once the workload is optimized, the network traffic becomes congested, which minimizes the performance of the system. Therefore, to develop a dependable SMS system, we need a reliable verification method. Besides the agent-based verification method, formal method verification on the design is also needed. This is to ensure that the system design is secured from the unseen errors and bugs in the early stage of development. In order to make this successful, this paper will discuss more on the verification design of short-text messaging system with the implementation of an agent-based system known as model checking. The aim of this paper is to provide a reliable and verifiable system designs, using Spin as the model checker.

Agent Architecture for Criminal Mobile Devices Identification Systems

Current techniques of language identification are based on a method that assigns one or more textual documents into a set of predefined languages that are relevant to page contents. In this paper, we proposed an agent architecture that is used in criminal mobile devices identification systems. It is based on the usage of a software agent to process at least one document by using a dictionary that belong to a set of languages in order to determine the type of language features to be used in the text preprocessing module. Then, the agent will map at least one of the documents with the content of the dictionary in order to identify the languages used in the text by the language identification agent. Finally, the digital forensic agent will check the potential criminal short messages through the predefined keyword repository of corresponding language. Form our experiments, the agent architecture has been able to identify correctly the types of languages written in the short text messaging (SMS) system.

Optimization of e-business social network mapping using genetic algorithm

In this paper, we present the optimization of e-business social network visualization using genetic algorithm (GA). Basically, it is important to visualize the map of the Internet searching because it helps user to better understand how and why they interact with each other. It is also helps them to search information in a very fast way and more related to their searched. Furthermore, the result returns by the conventional search engine sometimes are not relevant to the user search. Here, we proposed the query optimization search system based on genetic algorithm (GA) to solve this problem and visualize the connection between them. Experiment results demonstrate that it is very effective to improve the search of the relevant Web pages using the genetic algorithm.