Search

Most IoT devices are designed and built for cheap and basic functions, therefore, the security aspects of these devices are not taken seriously. Yet, IoT devices tend to play an important role in this era, where the amount of IoT devices is predicted to exceed the number of traditional computing devices such as desktops and laptops. This causes more and more cybersecurity attacks to target IoT devices and malware attack is known to be the most common attack in IoT networks. However, most research only focuses on malware detection in traditional computing devices. The purpose of this research is to compare the performance of Random Forest and Naïve Bayes algorithm in terms of accuracy, precision, recall and F1-score in classifying the malware attack and benign traffic in IoT network traffic. Research is conducted with the Aposemat IoT-23 dataset, a labelled dataset that contains IoT malware infection traffic and IoT benign traffic. To determine the data in IoT network traffic packets that are useful for threat detection, a study is conducted and the threat data is cleaned up and prepared using RStudio and RapidMiner Studio. Random Forest and Naïve Bayes algorithm is used to train and classify the cleaned dataset. Random Forest can prevent the model from overfitting while Naïve Bayes requires less training time. Lastly, the accuracy, precision, recall and F1-score of the machine learning algorithms are compared and discussed. The research result displays the Random Forest as the best machine learning algorithm in classifying the malware attack traffic.

Adopting e-government services presents numerous challenges for governmental sectors in developing countries. These problems can fail some projects involving e-government. Therefore, a solution is required to address these problems. This paper presents a conceptual model and measurement to identify crucial factors that impact cloud computing technology in e-government to address the issues with e-government. According to the recent studies on technology adoption models, a theoretical model is proposed in this study. Extracting items from the literature and adapting them, creates the measurement scales for the proposed model’s structures. Through the use of face validity, pre-testing, and a pilot study, the authors confirm the scales’ content validity and reliability. The data used for this study were collected by the authors from 40 information technology IT professionals for the pilot study in the top 10 government departments in Libya who are responsible for many IT decisions in e-government. In this study, the authors first examine the reliability of the scale using Cronbach’s alpha and perform exploratory factor analysis to assess the scales’ validity. The data were analyzed using partial least squares structural equation modelling (PLS-SEM). The findings demonstrate that the scale measurements satisfy the standard requirements for the validity and reliability According to previous studies on cloud computing adoption from the IS perspectives, this paper theoretically provides a combination model for investigating the cloud-based implementation services to provide a more comprehensive model and the objective is to develop an empirical instrument for analyzing countries’ e-government adoption of cloud computing.

Disasters are becoming one of the most challenging situations to be faced by humanity, at which it tests our capability in handling such situation. It is impossible to stop a disaster from happening. Instead, there are ways on how to reduce the disasters? effect before, during or after a disaster has happened. Flood is a common term well known as one of the types of natural disasters that frequently hits the Malaysian region. Many researches from multiple agencies has already started working on the ways of reducing and overcoming the negative effects of disasters. The main motivation for this research was inspired out of the inefficient flood disaster prediction and warning system in Malaysia. The Drainage and Irrigation Department (DID) that generates and distributes the prediction and warning signal for the Malaysian flood disaster has been faced with numerous challenges, which arose due to the absence of reliable flood prediction model. A reliable flood prediction model will assist DID in setting the victims preparation in facing it before, during and after the disaster has happened in Malaysia. This paper focuses on flood disaster overview and some reviews based on previous literatures for developing the rainfall prediction models by enhancing the existing model in further research steps.

Vehicular Ad hoc Network (VANET), a subclass of mobile ad hoc networks (MANETs), is a promising approach for the intelligent transportation system (ITS). The key difference of VANET and MANET is the special mobility pattern and rapidly changeable topology. Temporary network fragmentation problem and the broadcast storm problem are further considered for designing Message propagation in VANETs. The temporary network fragmentation problem which happens in free flow caused by rapidly changeable topology influence on the performance of data transmissions. The broadcast storm problem in congested flow network seriously affects the successful rate of message delivery in VANETs. This paper presents a connectivity analysis under free flow and congested flow scenario in Vehicular Ad hoc Networks.

The web application security scanner is a computer program that assessed web application security with penetration testing technique. The benefit of automated web application penetration testing is huge, which web application security scanner not only reduced the time, cost, and resource required for web application penetration testing but also eliminate test engineer reliance on human knowledge. Nevertheless, web application security scanners are possessing weaknesses of low test coverage, and the scanners are generating inaccurate test results. Consequently, experimentations are frequently held to quantitatively quantify web application security scanner's quality to investigate the web application security scanner's strengths and limitations. However, there is a discovery that neither a standard methodology nor criterion is available for quantifying the web application security scanner's quality. Hence, in this paper systematic review is conducted and analysed the methodology and criterion used for quantifying web application security scanners' quality. In this survey, the experiment methodologies and criterions that had been used to quantify web application security scanner's quality is classified and review using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) protocol. The objectives are to provide practitioners with the understanding of methodologies and criterions that available for measuring web application security scanners' test coverage, attack coverage, and vulnerability detection rate, while provides the critical hint for development of the next testing framework, model, methodology, or criterions, to measure web application security scanner quality.

Malicious programs are malignant software’s designed by hackers or cyber offenders with a harmful intent to disrupt computer operation. In various researches, we found that the balance between designing an accurate architecture that can detect the malware and track several advanced techniques that malware creators apply to get variants of malware are always a difficult line. Hence the study of malware detection techniques has become more important and challenging within the security field. This review paper provides a detailed discussion and full reviews for various types of malware, malware detection techniques, various researches on them, malware analysis methods and different dynamic programming-based tools that could be used to represent the malware sampled. We have provided a comprehensive bibliography in malware detection, its techniques and analysis methods for malware researchers.

OppNets is a subset of MANET in which there is no point to point connection between devices. Despite challenges of intermittent connectivity and unpredictable mobility characteristics, mobile nodes need to communicate and share valuable information without infrastructure. The routing strategy in OppNet follows a store-carry-forward paradigm, in which a node store messages in its buffer, carry the messages as it moves about its daily activities and opportunistically relay the messages one after another upon meeting their target destinations. This paper presents a movement pattern extraction, a new approach for extracting regular movement pattern of nodes from existing traces to predict a node future location. Human movement is predictable with a high degree of certainty that people visit certain locations and have the opportunity to meet other people on a regular basis. The proposed method incorporate message lifetime and previous history of encounter to extract locations from the GPS trace with respect to message lifetime using Neural Network to predict future location visit of nodes. Prediction method can be used in geocast routing schemes to determine the node’s contribution in forwarding a message to a destination location. Experiment result indicates that the proposed method achieves significant performance over existing methods in terms of accuracy and stability in prediction.

Geocasting supports communication in a challenged environment by addressing various routing issues to a wide range of applications it exploits intermittent connectivity among mobile devices to support opportunistic message transfer over a short-range radio transmission, Variety of surveys have been carried out in the literature concerning general OppNets. The main purpose of this paper is to provide a survey of OppNet geocast routing protocols. It further highlights Geocast OppNet characteristics and envisioned application areas different from general OppNets. Additionally, this paper studies existing geocasting routing solutions based on message endpoint, forwarding utility computation approach, determining the relay node, routing decision approach and message dissemination. Finally, we have identified current challenges and future research direction for routing in OppNet geocast.

The advent of information and communication technology (ICT) has shaped the world today. Due to the potential increase in technology, the introduction into the healthcare industry has been progressively investigated. In 1997, Malaysia introduced a health initiative called telehealth. However, progress in IT implementation is progressively slow. Although the global healthcare sector is increasing, the implementation of the Health Information System (HIS) in Malaysia has been slow-informed due to various barriers. These barriers are due to a series of problems related to end users and challenges for IT departments and vendors. This article therefore focuses on the current situation of HIS in selected Malaysian public hospital. In addition, an interview conducted with the end users, IT department and the system providers. The data from the interview was then converted into a summary of the table. In this context, the obstacles that delay the implementation of HIS in Malaysia have been identified primarily in terms of suppliers, financial, organizational and human aspects.

Automated web application penetration testing has emerged as a trend. The computer was assigned the task of penetrating web application security with penetration testing technique. Relevant computer program reduces time, cost, and resources required for assessing a web application security. At the same time, scaling down tester reliance on human knowledge. Web application security scanner is such kind of program that is designed to assess web application security automatically with penetration testing technique. The downside is that computer is not well-formed as human. Consequently, web application security scanner often found generating the false alarms, especially in a testing environment, which web application source codes are unreachable. Thus, in this paper, the state-of-the-art of black box web application security scanner is systematically reviewed, to investigate the approaches for detecting web application vulnerability in an ambiguous testing environment. This survey is critical in providing insights on how to design efficient algorithms for assessing web application security with penetration testing technique in the ambiguous environment.

In current era of sharing unlimited digital information via the network, protecting the privacy of information is crucial even during the data mining process due to a high possibility of the information security risks such as being abused or leakage. Such problems motivate the research in Privacy Preserving Data Mining (PPDM) and it became one of the newest trends. Therefore, this papers reviews the related works in terms of issues, approaches, techniques, performance quantification as well as thorough discussions on pros and cons of previous researches. We also propose an improved PPDM that applying Geometrical Data Transformation Method (GDTM) and K-Means Clustering Algorithm for optimum accuracy of mining and zero data loss while preserving the privacy of information.

Display Omitted A multi-criteria CF recommender system in tourism domain is proposed.Predictive accuracy of multi-criteria CF recommender systems is improved.EM algorithm, ANFIS and PCA are applied in the proposed method.PCA is applied for solving multi-collinearity problem.ANFIS is applied for developing the prediction models. In order to improve the tourist experience, recommender systems are used to offer personalized information for online users. The hotel industry is a leading stakeholder in the tourism sector, which needs to provide online facilities to their customers. Collaborative Filtering (CF) techniques, which attempt to predict what information will meet a user's needs based on data coming from similar users, are becoming increasingly popular as ways to combat information overload. They use a single rating as input. However, the multi-criteria based CF presents a possibility to provide accurate recommendations by considering the user preferences in multiple aspects and they can be an appropriate choice for the tourist. In this paper, we propose a new hybrid method for hotel recommendation using dimensionality reduction and prediction techniques. Accordingly, we have developed the multi-criteria CF recommender systems for hotel recommendation to enhance the predictive accuracy by using Gaussian mixture model with Expectation Maximization (EM) algorithm and Adaptive Neuro-Fuzzy Inference System (ANFIS). We have also used the Principal Component Analysis (PCA) for dimensionality reduction and to address multi-collinearity induced from the interdependencies among criteria in multi-criteria CF dataset. Our experiments confirmed that the proposed hybrid method achieved high accuracy for hotel recommendation for the tourism sector.

Malware a piece of code that deliberately fulfills the harmful intent of an attacker causes harm to the host computer, it is considered as the root cause of many Internet security problems. To evade detection by malware detectors, malware writers use various obfuscation techniques to transform their malware. Metamorphic Malware is hardly detectable with regular string signatures. Several detection techniques have been used to detect metamorphic malware. In this paper, we propose a framework that leads to a novel approach of a signature and behavior based technique for improving detection of metamorphic malware, using a standard dataset of known malware text samples represented in string format we identify the various functions and parameters that they are calling, hence pinpointing parameters repeatedly called by same functions. This indicates the risky zone of the malware file(s) that holds the actual piece of code which has been injected with some ineffective benign instructions. Hence, this procedure facilitates detection of unknown malware file(s), making detection process faster and more accurate.

Data center is a place where a lot of data and information stored together. Pooling all data in one large place called data center will make management work become complex and hard to be manage. Threats become one major problem which can cause disaster to data center. Disaster management is one important step that need to be done in reducing disaster impact and disaster loss when threats attacked or strike to data center. This paper presents on features selection for efficient Data Center Disaster Management (DCDM) approach as one propose solution. The features of disaster management is listed and compared in evaluating the suitable DCDM mechanism to improve the previous disaster management processes. Based on all selected features, a comparison of features from existing DCDM approach are analyzed and the selected features was identified toward a better development of the new DCDM approach.

Multi-criteria collaborative filtering (MC-CF) presents a possibility to provide accurate recommendations by considering the user preferences in multiple aspects of items. However, scalability and sparsity are two main problems in MC-CF which this paper attempts to solve them using dimensionality reduction and Neuro-Fuzzy techniques. Considering the user behavior about items' features which is frequently vague, imprecise and subjective, we solve the sparsity problem using Neuro-Fuzzy technique. For the scalability problem, higher order singular value decomposition along with supervised learning (classification) methods is used. Thus, the objective of this paper is to propose a new recommendation model to improve the recommendation quality and predictive accuracy of MC-CF and solve the scalability and alleviate the sparsity problems in the MC-CF. The experimental results of applying these approaches on Yahoo!Movies and TripAdvisor datasets with several comparisons are presented to show the enhancement of MC-CF recommendation quality and predictive accuracy. The experimental results demonstrate that SVM dominates the K-NN and FBNN in improving the MC-CF predictive accuracy evaluated by most broadly popular measurement metrics, F1 and mean absolute error. In addition, the experimental results also demonstrate that the combination of Neuro-Fuzzy and dimensionality reduction techniques remarkably improves the recommendation quality and predictive accuracy of MC-CF in relation to the previous recommendation techniques based on multi-criteria ratings.

Password authentication has become a widely recognized element of computer security practices where human users are proven or confirmed as legitimate u sers for access to secure systems. Using this syste m, every user needs to recall its password correctly b efore access can be granted to an intended services or applications. Remembering the secure passwords is a n everyday problem for users because of individual memory limitation. In an effort to solve this probl em, graphical password was presented as one promising athentication alternative taking advantage of pictu re superiority over texts. The main objective of th is study is to provide a comprehensive survey of array of gr aphical password schemes in different categories ba sed on their common features with the primary aim of id entifying the memorability features and propose a n ew graphical authentication system with enhanced memorability features.

Recommender systems are software tools and techniques for suggesting items in an automated fashion to users tailored their preferences. Collaborative Filtering (CF) techniques, which attempt to predict what information will meet a user's needs from the neighborhoods of like-minded people, are becoming increasingly popular as ways to overcome the information overload. The multi-criteria based CF presents a possibility to provide accurate recommendations by considering the user preferences in multiple aspects and several methods have been proposed for improving the accuracy of these systems. However, the problem of multi-criteria recommendations with a single and overall rating is still considered an optimization problem. In addition, increasing the accuracy in predicting the appropriate items tailored to the users' preferences is on of the main challenges in these systems. Hence, in this research new recommendation methods using Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and Self-Organizing Map (SOM) clustering are proposed to improve predictive accuracy of criteria CF. In this research, SOM enables us to generate high quality clusters of dataset and ANFIS is used for discovering knowledge (fuzzy rules) from users' ratings in multi-criteria dataset, generating appropriate membership functions (MFs), overall rating prediction and input selection. Using exhaustive search method for input selection, the effective inputs are determined to build the ANFIS models in all generated clusters. Furthermore, new fuzzy-based algorithms, Weighted Fuzzy MC-CF (WFuMC-CF), Fuzzy Euclidean MC-CF (FuEucMC-CF) and Fuzzy Average MC-CF (FuAvgMC-CF), are presented for prediction task in multi-criteria CF. FuEucMC-CF and FuAvgMC-CF algorithms uses the fuzzy-based Euclidian distance and fuzzy-based average similarity, respectively, the WFuMC-CF algorithm uses fuzzy-based user- and item-based prediction in a weighted approach. Experimental results on real-world dataset demonstrate that the proposed hybrid methods remarkably improve the accuracy of multi-criteria CF in relation to the previous methods based on multi-criteria ratings.

Collaborative Filtering (CF) is the most widely used prediction technique in recommender systems. It makes recommendations based on ratings that users have assigned to items. Most of the current CF recommender systems maintain only single user ratings inside the user-item ratings matrix. Multi-criteria based CF presents a possibility of providing accurate recommendations by considering the user preferences in multi aspects of items. However, in the multi-criteria CF, the user behavior about items' features is frequently subjective, imprecise and vague. These in turn induce uncertainty in reasoning and representation of items' features that exactly cannot be solved using crisp machine learning techniques. In contrast, approaches such as fuzzy methods instead of crisp methods can better solve the issue of uncertainty. In addition, fuzzy methods can predict the users' preference more accurately and even better alleviate the sparsity problem in overall rating by considering user perception about items' features. Apart from this, in the multi-criteria CF, users provide the ratings on different aspects (criteria) of an item in new dimensions; thereby, increasing the scalability problem. Appropriate dimensionality reduction techniques are thus needed to capture the high dimensions all together without reducing them into lower dimensions to reveal the latent associations among the components. This study presents a new model for multi-criteria CF using Adaptive Neuro-Fuzzy Inference System (ANFIS) combined with subtractive clustering and Higher Order Singular Value Decomposition (HOSVD). HOSVD is used for dimensionality reduction for improving the scalability problem and ANFIS is used for extracting fuzzy rules from the experimental dataset, alleviating the sparsity problems in overall ratings and representing and reasoning the users' behavior on items' features. Experimental results on real-world dataset show that combination of two techniques remarkably improves the predictive accuracy and recommendation quality of multi-criteria CF.

This paper starts with an overview of vehicular ad hoc networks (VANETs) and their characteristics. Then this paper reviews diverse applications of VANETs and the requirements of these applications. In addition it reviews VANETs standards, different broadcasting presented in a variety of studies, and also associated issues with data dissemination in connected and fragmented vehicular networks to solve broadcast storm problem and temporary disconnected VANETs. The discussion will be about the encountered challenges and presented solutions with respect to the related issues, based on the literature and strength and weakness of each protocol.

Vehicular Ad hoc Network (VANET) is a special type of Mobile Ad hoc Network (MANET). VANETs provide a collection of interesting safety applications. Many of these applications rely on broadcasting of messages to other vehicles. The simplest broadcasting algorithm is flooding. Because of large number of vehicles during peak hour, blindly flooding may lead to packet collision and high contention named broadcast storm problem. This paper presents a new broadcasting approach for safety messages (BSM) that dynamically adjusts waiting time of a vehicle according to the number of neighbor vehicles and distance to source. We evaluate the performance of our proposed approach in terms of reachability, overhead and forwarding node ratio. The simulation results show BSM introduces better performance than AMB.

Parallelism is a technique to accelerate various applications. Nowadays, parallel operations are used to solve computer problems such as sort, search, and cryptography, which result in a reasonable speed. Sequential algorithms can be parallelized by being implemented on parallel architectures. Cryptography is the science of hiding information, which by the increase in the applications on insecure communication environments, has become one of the most important aspects of the digital world. In this article, we propose a parallel RSA utilizing parallel processing on RSA using tree architecture. RSA is a well-known public key cryptography which is not as fast as symmetric cryptographies. Parallelizing it, we can achieve speedup and more security. We also investigate the state of the art methods of RSA and figure out that their low speed can be faster with reasonable security using parallel architecture.

Modern machining processes such as abrasive waterjet (AWJ) are widely used in manufacturing industries nowadays. Optimizing the machining control parameters are essential in order to provide a better quality and economics machining. It was reported by previous researches that artificial bee colony (ABC) algorithm has less computation time requirement and offered optimal solution due to its excellent global and local search capability compared to the other optimization soft computing techniques. This research employed ABC algorithm to optimize the machining control parameters that lead to a minimum surface roughness (R $$_{a})$$ value for AWJ machining. Five machining control parameters that are optimized using ABC algorithm include traverse speed (V), waterjet pressure (P), standoff distance (h), abrasive grit size (d) and abrasive flow rate (m). From the experimental results, the performance of ABC was much superior where the estimated minimum R $$_{a }$$ value was 28, 42, 45, 2 and 0.9 % lower compared to actual machining, regression, artificial neural network (ANN), genetic algorithm (GA) and simulated annealing (SA) respectively.

Vehicular Ad hoc Network (VANET) is a subclass of mobile ad hoc networks (MANETs). VANETs provide a variety of interesting applications. Many of these applications rely on broadcasting of messages to other vehicles. The simplest broadcasting algorithm is flooding. Because of a large number of vehicles during peak hour, blindly flooding may lead to packet collision and high contention named broadcast storm problem. This paper presents a broadcasting approach for safety messages that dynamically adjust waiting time of a vehicle according to the number of neighbor vehicles and distance to source. We evaluate the performance of our proposed approach in terms of reachability, reliability. The simulation results show our protocol introduces better performance than flooding and random waiting time protocol.

*1 Mehrbakhsh Nilashi, 2 Mohammad Fathian, 3 Mohammad Reza Gholamian, 4 Othman bin Ibrahim, 5 Amir Talebi , 6 Norafida Ithnin *1 Department of Computer Engineering, Islamic Azad University of Roudsar and Amlash, Nilashidotnet@Yahoo.com 2 Department of Industrial Engineering, Iran University of Science & Technology, Fathian@iust.ac.ir 3 Department of Industrial Engineering, Iran University of Science & Technology, Gholamian@iust.ac.ir 4 Department of Computer Science and Information System, Universiti Teknologi Malaysia, Othmanibrahim@utm.my 5 Department of Computer Science and Information System, Universiti Teknologi Malaysia, Amirtalebi@gmail.com 6 Department of Computer Science and Information System, Universiti Teknologi Malaysia, Afida@utm.my

Protecting images against illegal duplications is an important fact and recently many watermarking algorithms have been published to protect these images. In this paper two SVD-based watermarking algorithms are proposed and the results are compared with Chang’s method. In the proposed methods U component is explored for embedding the watermark. Experimental results show that imperceptibility and robustness of the algorithm is good.