Amirrudin Kamsin

Malicious accounts

Over the last few years, online social networks (OSNs), such as Facebook, Twitter and Tuenti, have experienced exponential growth in both profile registrations and social interactions. These networks allow people to share different information ranging from news, photos, videos, feelings, personal information or research activities. The rapid growth of OSNs has triggered a dramatic rise in malicious activities including spamming, fake accounts creation, phishing, and malware distribution. However, developing an efficient detection system that can identify malicious accounts, as well as their suspicious behaviors on the social networks, has been quite challenging. Researchers have proposed a number of features and methods to detect malicious accounts. This paper presents a comprehensive review of related studies that deal with detection of malicious accounts on social networking sites. The review focuses on four main categories, which include detection of spam accounts, fake accounts, compromised accounts, and phishing. To group the studies, the taxonomy of the different features and methods used in the literature to identify malicious accounts and their behaviors are proposed. The review considered only social networking sites and excluded studies such as email spam detection. The significance of proposed features and methods, as well as their limitations, are analyzed. Key issues and challenges that require substantial research efforts are discussed. In conclusion, the paper identifies the important future research areas with the aim of advancing the development of scalable malicious accounts detection system in OSNs. Propose taxonomy of features for identifying malicious accounts in social networks.Propose taxonomy of methods for detecting malicious accounts in social networks.Discuss the significance of each feature category as well as the methods.Identify issues and challenges with existing features and methods.Propose a framework for malicious account detection in social networks.

Comparative analysis of reference evapotranspiration equations modelling by extreme learning machine

Forecasting ET0 is important for agricultural production and irrigation scheduling.Differences of performance between compared ELM models are not very significant.Results showed that ELM ET0,AHARG can be applied to forecast ET0 effectively. This study presents an extreme learning machine (ELM) approach, for estimating monthly reference evapotranspiration (ET0) in two weather stations in Serbia (Nis and Belgrade stations), for a 31-year period (1980-2010). The data set including minimum and maximum air temperatures, actual vapour pressure, wind speed and sunshine hours was employed for modelling ET0 using the adjusted Hargreaves (ET0,AHARG), Priestley-Taylor (ET0,PT) and Turc (ET0,T) equations. The reliability of the computational model was accessed based on simulation results and using five statistical tests including mean absolute percentage error (MAPE), mean absolute deviation (MAD), root-mean-square error (RMSE), Pearson correlation coefficient (r) and coefficient of determination (R2). The validity of ELM modelled ET0 are compared with the FAO-56 Penman-Monteith equation (ET0,PM) which is used as the reference model. For the Belgrade and Nis stations, the ET0,AHARG ELM model with MAPE=9.353 and 10.299%, MAD=0.142 and 0.151mm/day, RMSE=0.180 and 0.192mm/day, r=0.994 and 0.992, R2=0.988 and 0.984 in testing period, was found to be superior in modelling monthly ET0 than the other models, respectively.

Computational intelligence approaches for classification of medical data: State-of-the-art, future challenges and research directions

Abstract The explosive growth of data in volume, velocity and diversity that are produced by medical applications has contributed to abundance of big data. Current solutions for efficient data storage and management cannot fulfill the needs of heterogeneous data. Therefore, by applying computational intelligence (CI) approaches in medical data helps get better management, faster performance and higher level of accuracy in detection. This paper aims to investigate the state-of-the-art of computational intelligence approaches in medical data and to categorize the existing CI techniques, used in medical fields, as single and hybrid. In addition, the techniques and methodologies, their limitations and performances are presented in this study. The limitations are addressed as challenges to obtain a set of requirements for Computational Intelligence Medical Data (CIMD) in establishing an efficient CIMD architectural design. The results show that on the one hand Support Vector Machine (SVM) and Artificial Immune Recognition System (AIRS) as a single based computational intelligence approach were the best methods in medical applications. On the other hand, the hybridization of SVM with other methods such as SVM-Genetic Algorithm (SVM-GA), SVM-Artificial Immune System (SVM-AIS), SVM-AIRS and fuzzy support vector machine (FSVM) had great performances achieving better results in terms of accuracy, sensitivity and specificity.

SMSAD: a framework for spam message and spam account detection

Short message communication media, such as mobile and microblogging social networks, have become attractive platforms for spammers to disseminate unsolicited contents. However, the traditional content-based methods for spam detection degraded in performance due to many factors. For instance, unlike the contents posted on social networks like Facebook and Renren, SMS and microblogging messages have limited size with the presence of many domain specific words, such as idioms and abbreviations. In addition, microblogging messages are very unstructured and noisy. These distinguished characteristics posed challenges to existing email spam detection models for effective spam identification in short message communication media. The state-of-the-art solutions for social spam accounts detection have faced different evasion tactics in the hands of intelligent spammers. In this paper, a unified framework is proposed for both spam message and spam account detection tasks. We utilized four datasets in this study, two of which are from SMS spam message domain and the remaining two from Twitter microblog. To identify a minimal number of features for spam account detection on Twitter, this paper studied bio-inspired evolutionary search method. Using evolutionary search algorithm, a compact model for spam account detection is proposed, which is incorporated in the machine learning phase of the unified framework. The results of the various experiments conducted indicate that the proposed framework is promising for detecting both spam message and spam account with a minimal number of features.

Resource Scheduling in Mobile Cloud Computing: Taxonomy and Open Challenges

Resource scheduling approaches (RSA) are the core component of mobile cloud computing (MCC) systems that aim to optimally allocate cloud-based remote resources to resource-intensive components of mobile applications. The ultimate goal of RSA is to reduce execution time and energy consumption of resource-intensive mobile applications which contributes to successful MCC adoption. Role of RSA is critical in efficiently executing resource-intensive mobile applications in the cloud. Although several aspects of MCC have been extensively reviewed, analysis of RSAs in MCC is overlooked. Therefore, it is important to provide a comprehensive review of RSA to complement existing literature in MCC. In this paper, we conduct a survey to review the state-of-the-art RSA approaches in MCC and present the taxonomy of existing RSA approaches. We present a brief tutorial on resource scheduling in MCC followed by a critical review of some of the most credible approaches to highlight their advantages and disadvantages. We then discuss the open challenges in this area and point out future research directions.

Personal task management: my tools fall apart when I'm very busy!

Existing applications tend to highlight tasks that people should be doing at any given time based on the parameters of urgency (e.g. deadline), assigned priority and reminders. Our field studies demonstrate that people consider existing applications as inadequate to flexibly adapt to current changes in other essential factors, including, task size, complexity and interdependency and the unexpected situations that people face over time. Another key challenge facing busy people is that there is no mechanism that can monitor their work habits and match their tasks with their time constraints. Grounded in our data, we propose important requirements for tools that support users in managing tasks and assessing their schedules.

A Real Time Simulation of Flood Hazard

Kuala Lumpur city is located at the confluence of two rivers and are flood prone area. With rapid development and uncontrolled town planning, the city had experience several major flash flood incidents and have caused tremendous damage to country. This research describes a study made to model and simulate the flash flood incident that struck Kuala Lumpur on 10 June 2007 using 3D computer graphic and fluid simulation techniques. The aim is to examine the stability and effectiveness of this approach as a solution tool for environmental hazard studies. Particle-based method used to model the fluid objects using MAYA software. Light detection and ranging (LIDAR) data and remote sensing imagery were used to model the study area. The main contribution of this study is the introduction of this approach to enhance realistic visualization for environmental studies thus enable better planning and countermeasures created to prevent the disaster.

A Bibliometric Approach to Tracking Big Data Research Trends

The explosive growing number of data from mobile devices, social media, Internet of Things and other applications has highlighted the emergence of big data. This paper aims to determine the worldwide research trends on the field of big data and its most relevant research areas. A bibliometric approach was performed to analyse a total of 6572 papers including 28 highly cited papers and only papers that were published in the Web of ScienceTM Core Collection database from 1980 to 19 March 2015 were selected. The results were refined by all relevant Web of Science categories to computer science, and then the bibliometric information for all the papers was obtained. Microsoft Excel version 2013 was used for analyzing the general concentration, dispersion and movement of the pool of data from the papers. The t test and ANOVA were used to prove the hypothesis statistically and characterize the relationship among the variables. A comprehensive analysis of the publication trends is provided by document type and language, year of publication, contribution of countries, analysis of journals, analysis of research areas, analysis of web of science categories, analysis of authors, analysis of author keyword and keyword plus. In addition, the novelty of this study is that it provides a formula from multi-regression analysis for citation analysis based on the number of authors, number of pages and number of references.

Preserving Content Integrity of Digital Holy Quran: Survey and Open Challenges

In recent years, a new trend has come up, which is that of reading the digital Quran online. This text was revealed more than 1400 years ago in the Arabic language and has been protected from all possible ways of distortion until today. Unfortunately, driven by the desire to make profit or gain publicity, fraudsters have started modifying certain Quranic verses. These alterations are misleading many people who are thus deprived of the original and accurate message of the Holy Quran. This paper focuses on systematically analyzing and categorizing existing research related to preserving and verifying the content integrity of the Quran. This paper further assesses these existing studies in terms of their evaluation parameters and findings. We find that the existing studies can be classified according to their format and methods, i.e., the online formats in which the Quranic content is available, methods employed to protect the Quranic content from modification, and last methods of verification. This paper concludes with the issue of future challenges and their possible solutions.

Game Rhetoric: Interaction Design Model of Persuasive Learning for Serious Games

Serious Games is an emerging technology that can be used in a learning environment. This technology is an effective interaction design paradigm which can be embedded as a persuasive learning tool to attract learners’ attention. This article will explore the concept of game rhetoric as an element in game systems for persuading students to engage with the learning context. We identified three types of rhetorical concept that can be integrated with the current game rhetoric model to support attention elements: visual, procedural and digital rhetoric. Three interaction design elements have been used in the model to support learners’ attention: cognition, emotion and social interaction. In this paper, we propose a new interaction design model based on game rhetoric perspectives to support user interaction in Serious Games for persuasive learning.