Volume 1, Issue 3, 2011

By | September 4, 2018

Robust Sign Language Recognition System Using ToF Depth Cameras

Morteza Zahedi, Ali Reza Manashty
Department of Computer Engineering and IT, Shahrood University of Technology, Iran.

Abstract: Sign language recognition has been a difficult task, yet required for many applications in real-time speed. Using RGB cameras for recognition of sign languages is not very successful in practical situations and accurate 3D imaging requires expensive and complex instruments. With introduction of Time-of-Flight (ToF) depth cameras in recent years, it has become easier to scan the environment for accurate, yet fast depth images of the objects without the need of any extra calibrating object. In this paper, a robust system for sign language recognition using ToF depth cameras is presented for converting the recorded signs to a standard and portable XML sign language named SiGML for easy transfer and converting to real-time 3D animated virtual characters. Feature extraction using moments and classification using nearest neighbor classifier are used to track hand gestures and significant result of 100% is achieved for the proposed approach.

Keywords : sign language; Time-of-Flight camera; sign recognition; SigML; Moments; hand tracking; range cameras.

A Comparison of Trojan Virus Behavior in Linux and Windows Operating Systems

Ghossoon. M. W. Al-Saadoon, College of Administrative Science, Applied Science University, Kingdom of Bahrain.
Hilal M.Y. Al-Bayatti, College of Arts and Science, Applied Science University, Kingdom of Bahrain.

Abstract: Trojan virus attacks pose one of the most serious threats to computer security. A Trojan horse is typically separated into two parts – a server and a client. It is the client that is cleverly disguised as significant software and positioned in peer-to-peer file sharing networks, or unauthorized download websites. The most common means of infection is through email attachments. The developer of the virus usually uses various spamming techniques in order to distribute the virus to unsuspecting users. Malware developers use chat software as another method to spread their Trojan horse viruses such as Yahoo Messenger and Skype. The objective of this paper is to explore the network packet information and detect the behavior of Trojan attacks to monitoring operating systems such as Windows and Linux. This is accomplished by detecting and analyzing the Trojan infected packet from a network segment -which passes through email attachment- before attacking a host computer.The results that have been obtained to detect information and to store infected packets through monitoring when using the web browser also compare the behaviors of Linux and Windows using the payload size after implementing the Wireshark sniffer packet results. Conclusions of the figures analysis from the packet captured data to analyze the control bits and , check the behavior of the control bits, and the usability of the operating systems Linux and Windows.

Keywords : Trojan horse behavior; Internet Security; Segment of Network; Pcap- Packet CAPture; Payload.

A Cloud-based Approach for Context Information Provisioning

Elarbi Badidi, Faculty of Information Technology, United Arab Emirates University,  United Arab Emirates.
Larbi Esmahi, School for Computing & Information Systems, Athabasca University, Canada.

Abstract: As a result of the phenomenal proliferation of modern mobile Internet-enabled devices and the widespread utilization of wireless and cellular data networks, mobile users are increasingly requiring services tailored to their current context. High-level context information is typically obtained from context services that aggregate raw context information sensed by various sensors and mobile devices. Given the massive amount of sensed data, traditional context services are lacking the necessary resources to store and process these data, as well as to disseminate high- level context information to a variety of potential context consumers. In this paper, we propose a novel framework for context information provisioning, which relies on deploying context services on the cloud and using context brokers to mediate between context consumers and context services using a publish/subscribe model. Moreover, we describe a multi- attributes decision algorithm for the selection of potential context services that can fulfill context consumers’ requests for context information. The algorithm calculates the score of each context service, per context information type, based on the quality-of-service (QoS) and quality-of- context information (QoC) requirements expressed by the context consumer. One of the benefits of the approach is that context providers can scale up and down, in terms of cloud resources they use, depending on current demand for context information. Besides, the selection algorithm allows ranking context services by matching their QoS and QoC offers against the QoS and QoC requirements of the context consumer.

Keywords : mobile users; context-aware web services; context services; cloud services; quality-of-context; quality-of-service; service selection.

Citadel E-Learning: A New Dimension to Learning System

Awodele O., Kuyoro S. O., Adejumobi A. K., Awe O., Makanju O
Department of Computer Science and Mathematics, Babcock University, Nigeria.

Abstract: E-learning has been an important policy for education planners for many years in developed countries. This policy has been adopted by education in some developing countries; it is therefore expedient to study its emergence in the Nigerian education system. The birth of contemporary technology shows that there is higher requirement for education even in the work
force. This has been an eye opener to importance of Education which conveniently can be achieved through E-learning. This work presents CITADEL E-learning approach to Nigeria institutions; its ubiquity, its implementations, its flexibility, portability, ease of  use and feature that are synonymous to the standard of education in Nigeria and how it can be enhanced to improve learning for
both educators and learners to help them in their learning endeavour.

Keywords-E-learning environment; ICT; Distance learning.

A Hybrid Classifier using Boosting, Clustering, and Naïve Bayesian Classifier

A. J. M. Abu Afza, Dewan Md. Farid, and Chowdhury Mofizur Rahman
Department of Computer Science and Engineering, United International University, Dhaka-1209, Bangladesh.

Abstract—a new classifier based on boosting, clustering, and naïve Bayesian classifier is introduced in this paper, which considers the misclassification error produced by each training example and update the weights of training examples in training dataset associated to the probability of each attribute of that example. The proposed classifier clusters the training examples based on the
similarity of attribute values and then generates the probability set for each cluster using naïve Bayesian classifier. Boosting trains a series of classifiers for a number of rounds that emphasis to the misclassification rate in each round. The proposed classifier addresses the problem of classifying the large data set and it has been successfully tested on a number of benchmark problems
from the UCI repository, which achieved high classification rate.

Keywords- clustering; naïve Bayesian classifier; boosting; hybrid classifier.

A proposed Modified Data Encryption Standard algorithm by Using Fusing Data Technique

Alaa H. AL-Hamami, Computer Sciences Dept., Amman Arab University, Amman, Jordan.
Mohammad A. AL-Hamami, Computer Sciences Dept., Delmon University, Manama, Bahrain.
Soukaena H. Hashem, Computer Sciences Dept., University of Technology, Baghdad, Iraq.

Abstract— Data Encryption Standard (DES) is a block cipher that encrypts data in 64-bit blocks. A 64-bit block of plaintext goes in one end of the algorithm and a 64-bit block of cipher text comes out of the other end. Blowfish is a block cipher that encrypts data in 8-byte blocks .Blowfish consists of two parts: a key-expansion part and a data-encryption part. Key expansion converts a variable-length key of at most 56 bytes (448 bits) into several subkey arrays totaling 4168 bytes. Blowfish has 16 rounds, such as DES. In this research the fusion philosophy will be used to fuse DES’s with blowfish and Genetic Algorithms by taking the strong points in all of these techniques to create a proposed Fused DES-Blowfish algorithm. The proposed algorithm is presented as a modified DES depending on the advantage in key generation complexity in blowfish and advantage of optimization in Genetic Algorithm to give the optimal solution. The solution will be the depended tool for creation of the strong keys.

Keywords- Fusing; Blowfish; Genetic Algorithm; Strong keys; and Data Encryption Standard.

Artificial Neural Network Model for Forecasting Foreign Exchange Rate

Adewole Adetunji Philip, Akinwale Adio Taofiki, Akintomide Ayo Bidemi
Department of Computer Science, University of Agriculture, Abeokuta, Nigeria.

Abstract— The present statistical models used for forecasting cannot effectively handle uncertainty and instability nature of foreign exchange data. In this work, an artificial neural network foreign exchange rate forecasting model (AFERFM) was designed for foreign exchange rate forecasting to correct some of these problems. The design was divided into two phases, namely: training and forecasting. In the training phase, back propagation algorithm was used to train the foreign exchange rates and learn how to approximate input. Sigmoid Activation Function (SAF) was used to transform the input into a standard range [0, 1]. The learning weights were randomly assigned in the range [-0.1, 0.1] to obtain the output consistent with the training. SAF was  depicted using a hyperbolic tangent in order to increase the learning rate and make learning efficient. Feed forward Network was used to improve the efficiency of the back propagation. Multilayer Perceptron Network was designed for forecasting. The datasets from oanda website were used as input in the back propagation for the evaluation and forecasting of foreign exchange rates. The design was implemented using matlab7.6 and visual studio because of their supports for implementing forecasting system. The system was tested using mean square error and standard deviation with learning rate of 0.10, an input layer, 3 hidden layers and an output layer. The best known related work, Hidden Markov foreign exchange rate forecasting model (HFERFM) showed an accuracy of 69.9% as against 81.2% accuracy of AFERFM. This shows that the new approach provided an improved technique for carrying out foreign exchange rate forecasting.

Keywords- Artificial Neural Network; Back propagation Algorithm; Hidden Markov Model; Baum- Weld Algorithm; Sigmoid Activation Function and Foreign Exchange Rate.

Internet Banking Security Management through Trust Management

Ioannis Koskosas, Department of Informatics and Telecommunications Engineering, University of Western Macedonia, KOZANI, Greece.
Maria-Mirela Koskosa, Department of Architecture and Visual Arts, University of East London, London, UK.

Abstract— The aim of this research is to investigate information systems security in the context of security risk management. In doing so, it adopts a social and organizational approach by investigating the role and determinants of trust in the process of security goal setting with regard to internet banking risks. The research seeks to demonstrate the important role of trust in the risk
management context from a goal setting point of view through a case study approach within three financial institutions in Greece. The determinants of trust are also explored and discussed as well as the different goal setting procedures within different information system groups. Ultimately, this research provides a discussion of an interpretive research approach with the study of trust and goal setting in the risk management context and its grounding within an interpretive epistemology.

Keywords- trust; goal setting; security management; internet banking; interpretive  epistemology.

Precluding Emerging Threats from Cyberspace: An Autonomic Administrative Approach

Vivian Ogochukwu Nwaocha, Inyiama H.C.
Department of Computer Science, University of Nigeria, Nsukka, Nigeria.

Abstract— Information Technology and Network Security Managers face several challenges in securing their organization’s network due to the increased sophistication of attacks. Besides, the number of attacks and vulnerabilities are rising due to the inability of the existing intrusion detection and prevention system to detect and prevent novel attacks. Hence, intrusion detection
systems which were previously adequate to wedge the evolving attacks in cyberspace have become ineffective in impeding these attacks. Consequently, intrusion detection and prevention systems are required to actually prevent attacks before they cause harm. A major consideration of this work is to present an architecture that provides protection through the self-healing and self-protecting properties of the autonomic computing. The proposed system which operates by means of autonomous agents is based on risk assessment. The application of risk analysis and assessment reduces the number of false-positive alarms. Furthermore, the system autonomous features enables it to automatically diagnose, detect and respond to disruptions, actively adapt to changing environments, monitor and tune resources, as well as anticipate and provide protection against imminent threats.

Keywords- Agent; Autonomic Computing; Computer system; Intrusion; Intrusion detection and prevention; Network; Threats.

Robust Sign Language Recognition System Using ToF Depth Cameras

Morteza Zahedi, Ali Reza Manashty
Department of Computer Engineering and IT, Shahrood University of Technology, Shahrood, Iran.

Abstract—Sign language recognition is a difficult task, yet required for many applications in real-time speed. Using RGB cameras for recognition of sign languages is not very successful in practical situations and accurate 3D imaging requires expensive and complex instruments. With introduction of Time-of-Flight (ToF) depth cameras in recent years, it has become easier to scan the environment for accurate, yet fast depth images of the objects without the need of any extra calibrating object. In this paper, a robust system for sign language recognition using ToF depth cameras is presented for converting the recorded signs to a standard and portable XML sign language named SiGML for easy transferring and converting to real-time 3D virtual characters animations.
Feature extraction using moments and classification using nearest neighbor classifier are used to track hand gestures and significant result of 100% is achieved for the proposed approach.

Keywords-sign language; Time-of-Flight camera; sign recognition; SigML; Moments; hand tracking; range cameras.

Using MI Method for Feature Weighting to Improve Text Classification Performance

Morteza Zahedi, Aboulfazl Sarkardei
Department of Computer Engineering and IT, Shahrood University of Technology, Shahrood, Iran.

Abstract— In text classification, feature weighting is a main step of preprocessing. Commonly used feature weighting methods only consider the distribution of a feature in the documents and do not consider the class information for feature weighting. Mutual Information (MI) method which represents the dependency of a feature in the regarding class, has been previously used for feature selection. The aim of this paper is to show that the use of MI method for feature weighting increases the performance of text classification, in terms of average recall and average precision. While K-nearest neighbor classifier is employed for classification, the average recall is increased about 18% and average precision is increased about 10%. It is shown that the results for average precision and average recall become 91.7% and 89.29% respectively.

Keywords- text classification; mutual information; MI; feature weighting; Hamshahri; K-nearest neighbor.

A Multi-Phase Feature Selection Approach for the Detection of SPAM

Ahmed Khalid, Izzeldin M. Osman
Department of computer science, Sudan University of Science and Technology, Khartoum, Sudan.

Abstract- In the past few years the Naïve Bayesian (NB) classifier has been trained automatically to detect spam (unsolicited bulk e-mail). The paper introduces a simple feature selection algorithm to construct a feature vector on which the classifier will be built. We conduct an experiment on SpamAssassin public email corpus to measure the performance of the NB classifier built on
the feature vector constructed by the introduced algorithm against the feature vector constructed by the Mutual Information algorithm which is widely used in the literature. The effect of the stop-list and the phrases-list on the classifier performance was also investigated. The results of the experiment show that the introduced algorithm outperforms the Mutual Information algorithm.

Keywords- component; detection; feature selection; Naïve Bayesian classifiers.

Leave a Reply

Your email address will not be published. Required fields are marked *