Sri Devi Ravana

Cybercrime detection in online communications

The popularity of online social networks has created massive social communication among their users and this leads to a huge amount of user-generated communication data. In recent years, Cyberbullying has grown into a major problem with the growth of online communication and social media. Cyberbullying has been recognized recently as a serious national health issue among online social network users and developing an efficient detection model holds tremendous practical significance. In this paper, we have proposed set of unique features derived from Twitter; network, activity, user, and tweet content, based on these feature, we developed a supervised machine learning solution for detecting cyberbullying in the Twitter. An evaluation demonstrates that our developed detection model based on our proposed features, achieved results with an area under the receiver-operating characteristic curve of 0.943 and an f-measure of 0.936. These results indicate that the proposed model based on these features provides a feasible solution to detecting Cyberbullying in online communication environments. Finally, we compare result obtained using our proposed features with the result obtained from two baseline features. The comparison outcomes show the significance of the proposed features. We propose a set of unique features based on tweets information to detect cyberbullying.Machine learning model based on the proposed features is developed.The developed model is effective in detecting cyberbullying in the Twitter network.

Low-cost evaluation techniques for information retrieval systems: A review

For a system-based information retrieval evaluation, test collection model still remains as a costly task. Producing relevance judgments is an expensive, time consuming task which has to be performed by human assessors. It is not viable to assess the relevancy of every single document in a corpus against each topic for a large collection. In an experimental-based environment, partial judgment on the basis of a pooling method is created to substitute a complete assessment of documents for relevancy. Due to the increasing number of documents, topics, and retrieval systems, the need to perform low-cost evaluations while obtaining reliable results is essential. Researchers are seeking techniques to reduce the costs of experimental IR evaluation process by the means of reducing the number of relevance judgments to be performed or even eliminating them while still obtaining reliable results. In this paper, various state-of-the-art approaches in performing low-cost retrieval evaluation are discussed under each of the following categories; selecting the best sets of documents to be judged; calculating evaluation measures, both, robust to incomplete judgments; statistical inference of evaluation metrics; inference of judgments on relevance, query selection; techniques to test the reliability of the evaluation and reusability of the constructed collections; and other alternative methods to pooling. This paper is intended to link the reader to the corpus of ‘must read’ papers in the area of low-cost evaluation of IR systems.

Web‐Based Diet Information System with Case‐Based Reasoning Capabilities

Encouraging socio‐economic development in developing countries has resulted in many changes in the lifestyle of communities. Changes in dietary patterns are one of the main outcomes from the rapid socio‐economics advancement, for example excessive intake of fat, high‐protein diet (animal protein), salt and preservatives. Chronic diseases such as diabetes, coronary artery disease, hypertension and cancer are mostly related to diet. With the community becoming more nutrition and health conscious, one of the challenges faced is to make sure that the information and knowledge on diet and healthy lifestyle gets across to the community. This paper presents a model of web‐based diet system (WebDIET) that attempts to make diet information and menu plans that are customised to local preference more accessible via the use of Internet. The system is to be used by dieticians who serve as administrators and the public who are the end users. The dietary standard adapted in developing the system is Recommended Dietary Allowances (RDA) for Malaysia. The Malaysian Dietary Guidelines was also referred as it emphasises on Malaysian diet. The system consists of six modules namely Authentication Module, Menu Plan Module, Diabetic Menu Plan Module, Food Selection Module, Disease Info Module and Feedback Module. Diabetic menu plan module models the reasoning process employed by dieticians in suggesting menu plans. The planning task is solved using an artificial intelligence technique through the case‐based reasoning (CBR) approach. CBR, generally describes, the process of solving the current problem based on the proposed solution of similar problems in the past. Nearest Neighbour Algorithm was used to compute the similarities in weighted average. Tools used for the development of the system are Microsoft Visual Interdev, Microsoft FrontPage 2000, while HTML, VBScript and JavaScript are the scripting languages used to develop the system.

Unsupervised Rare Pattern Mining: A Survey

Association rule mining was first introduced to examine patterns among frequent items. The original motivation for seeking these rules arose from need to examine customer purchasing behaviour in supermarket transaction data. It seeks to identify combinations of items or itemsets, whose presence in a transaction affects the likelihood of the presence of another specific item or itemsets. In recent years, there has been an increasing demand for rare association rule mining. Detecting rare patterns in data is a vital task, with numerous high-impact applications including medical, finance, and security. This survey aims to provide a general, comprehensive, and structured overview of the state-of-the-art methods for rare pattern mining. We investigate the problems in finding rare rules using traditional association rule mining. As rare association rule mining has not been well explored, there is still specific groundwork that needs to be established. We will discuss some of the major issues in rare association rule mining and also look at current algorithms. As a contribution, we give a general framework for categorizing algorithms: Apriori and Tree based. We highlight the differences between these methods. Finally, we present several real-world application using rare pattern mining in diverse domains. We conclude our survey with a discussion on open and practical challenges in the field.

E-construction waste exchange in Malaysia: A preliminary study

As a developing country, Malaysia is no exception in facing construction waste management issues. Since demand of new construction project increases every year, construction waste dump at landfill has also increased at an alarming rate. In this preliminary study, current construction waste situation and construction waste exchange system are studied. Representative from Institute for Environmental and Development, LESTARI and Construction Industry Development Board of Malaysia (CIDB) were interviewed, and a survey has was carried out to understand contractors and developers view of construction waste management. As a result, e-conWasteExchange model has been developed and targeted users are contractors, developers, local council and Construction Industry Development Board of Malaysia (CIDB).

Identifying the influential spreaders in multilayer interactions of online social networks

Online social networks (OSNs) portray a multi-layer of interactions through which users become a friend, information is propagated, ideas are shared, and interaction is constructed within an OSN. Identifying the most influential spreaders in a network is a significant step towards improving the use of existing resources to speed up the spread of information for application such as viral marketing or hindering the spread of information for application like virus blocking and rumor restraint. Users communications facilitated by OSNs could confront the temporal and spatial limitations of traditional communications in an exceptional way, thereby presenting new layers of social interactions, which coincides and collaborates with current interaction layers to redefine the multiplex OSN. In this paper, the effects of different topological network structure on influential spreaders identification are investigated. The results analysis concluded that improving the accuracy of influential spreaders identification in OSNs is not only by improving identification algorithms but also by developing a network topology that represents the information diffusion well. Moreover, in this paper a topological representation for an OSN is proposed which takes into accounts both multilayers interactions as well as overlaying links as weight. The measurement results are found to be more reliable when the identification algorithms are applied to proposed topological representation compared when these algorithms are applied to single layer representations.

Quasi-Static Behavior of Palm-Based Elastomeric Polyurethane: For Strengthening Application of Structures under Impulsive Loadings

In recent years, attention has been focused on elastomeric polymers as a potential retrofitting material considering their capability in contributing towards the impact resistance of various structural elements. A comprehensive understanding of the behavior and the morphology of this material are essential to propose an effective and feasible alternative to existing structural strengthening and retrofitting materials. This article presents the findings obtained from a series of experimental investigations to characterize the physical, mechanical, chemical and thermal behavior of eight types of palm-based polyurethane (PU) elastomers, which were synthesized from the reaction between palm kernel oil-based monoester polyol (PKO-p) and 4,4-diphenylmethane diisocyanate (MDI) with polyethylene glycol (PEG) as the plasticizer via pre-polymerization. Fourier transform infrared (FT-IR) spectroscopy analysis was conducted to examine the functional groups in PU systems. Mechanical and physical behavior was studied with focus on elongation, stresses, modulus, energy absorption and dissipation, and load dispersion capacities by conducting hardness, tensile, flexural, Izod impact, and differential scanning calorimetry tests. Experimental results suggest that the palm-based PU has positive effects as a strengthening and retrofitting material against dynamic impulsive loadings both in terms of energy absorption and dissipation, and load dispersion. In addition, among all PUs with different plasticizer contents, PU2 to PU8 (which contain 2% to 8% (w/w) PEG with respect to PKO-p content) show the best correlation with mechanical response under quasi-static conditions focusing on energy absorption and dissipation and load dispersion characteristics.

Score Estimation, Incomplete Judgments, and Significance Testing in IR Evaluation

Comparative evaluations of information retrieval systems are often carried out using standard test corpora, and the sample topics and pre-computed relevance judgments that are associated with them. To keep experimental costs under control, partial relevance judgments are used rather than exhaustive ones, admitting a degree of uncertainty into the per-topic effectiveness scores being compared. Here we explore the design options that must be considered when planning such an experimental evaluation, with emphasis on how effectiveness scores are inferred from partial information.

Analysis of Online Social Network Connections for Identification of Influential Users: Survey and Open Research Issues

Online social networks (OSNs) are structures that help users to interact, exchange, and propagate new ideas. The identification of the influential users in OSNs is a significant process for accelerating the propagation of information that includes marketing applications or hindering the dissemination of unwanted contents, such as viruses, negative online behaviors, and rumors. This article presents a detailed survey of influential users’ identification algorithms and their performance evaluation approaches in OSNs. The survey covers recent techniques, applications, and open research issues on analysis of OSN connections for identification of influential users.

Role of social media in information-seeking behaviour of international students: A systematic literature review

The purpose of this paper is to investigate the information-seeking behaviour of international students in terms of their information needs and to highlight the role of social media.,In this paper, a systematic literature survey was conducted in order to investigate information-seeking trends among international students while using social media. As a result, an exhaustive systematic literature review (SLR) was carried out in order to investigate social media as a source for the observation of the behaviours of international students. For this purpose, 71 articles were selected from various well-known sources after an intensive SLR process of searching, filtering and enforcing the inclusion and exclusion criteria.,As an outcome of this study, the information-seeking behaviour of international students was highlighted with respect to social media as a source of information. In addition, this research identifies the information needs of the international students and categorizes them by the roles played by the social media in fulfilling the information needs.,A comparative study that highlighted the dearth of studies which merge the social media and information-seeking behaviour of international students as well as identify the future direction for the researchers and for benefits of international students.,A detail SLR which highlights the need of shifting the information seeking behaviour from libraries to social media in regard to the new environment for international students.