International Journal of Computer Science and Information Security

Vol. 11 No. 12 DEC 2013

Vol. 11 No. 12 DECEMBER 2013 International Journal of Computer Science and Information Security

Publication DECEMBER 2013, Volume 11 No. 12 (Download Full Journal) (Archive) (Download 2)

Copyright © IJCSIS. This is an open access journal distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

1. Paper 30111332: A Robust Kernel Descriptor for Finger Spelling Recognition based on RGB-D Information (pp. 1-7)

Full Text: PDF

Karla Otiniano-Rodrıguez, Guillermo Camara-Chavez

Department of Computer Science (DECOM), Federal University of Ouro Preto, Ouro Preto-MG-Brazil

Abstract — Systems of communication based on sign language and finger spelling are used by deaf people. Finger spelling is a system where each letter of the alphabet is represented by a unique and discrete movement of the hand. Intensity and depth images can be used to characterize hand shapes corresponding to letters of the alphabet. The advantage of depth sensors over color cameras for sign language recognition is that depth maps provide 3D information of the hand. In this paper, we propose a robust model for finger spelling recognition based on RGB-D information using a kernel descriptor. In the first stage, motivated by the performance of kernel based features, we decided to use the gradient kernel descriptor for feature extraction from depth and intensity images. Then, in the second stage, the Bag-of-Visual-Words approach is used to search semantic information. Finally, the features obtained are used as input of our Support Vector Machine (SVM) classifier. The performance of this approach is quantitatively and qualitatively evaluated on a dataset of real images of the American Sign Language (ASL) finger spelling. This dataset is composed of 120,000 images. Different experiments were performed using a combination of intensity and depth information. Our approach achieved a high recognition rate with a small number of training samples. With 10% of samples, we achieved an accuracy rate of 88.54% and with 50% of samples, we achieved a 96.77%; outperforming other state-of-the-art methods, proving its robustness.

2. Paper 30111304: A Novel Non-Shannon Edge Detection Algorithm for Noisy Images (pp. 8-13)

Full Text: PDF

El-Owny, Hassan Badry Mohamed A.

Department of Mathematics, Faculty of Science ,Aswan University , 81528 Aswan, Egypt.

Current: CIT College, Taif University, 21974 Taif, KSA.

Abstract— Edge detection is an important preprocessing step in image analysis. Successful results of image analysis extremely depend on edge detection. Up to now several edge detection methods have been developed such as Prewitt, Sobel, Zerocrossing, Canny, etc. But, they are sensitive to noise. This paper proposes a novel edge detection algorithm for images corrupted with noise. The algorithm finds the edges by eliminating the noise from the image so that the correct edges are determined. The edges of the noise image are determined using non-Shannon measures of entropy. The proposed method is tested under noisy conditions on several images and also compared with conventional edge detectors such as Sobel and Canny edge detector. Experimental results reveal that the proposed method exhibits better performance and may efficiently be used for the detection of edges in images corrupted by Salt-and-Pepper noise.

Keywords -Non-Shannon Entropy; Edge Detection; Threshold Value; Noisy images.

3. Paper 30111308: Influence of Stimuli Color and Comparison of SVM and ANN classifier Models for BCI based Applications using SSVEPs (pp. 14-22)

Full Text: PDF

Rajesh Singla, Department of Instrumentation and Control Engineering, Dr. B. R. Ambedkar National Institute of Technology Jalandhar, Punjab-144011, India

Arun Khosla, Department of Electronics and Communication Engineering, Dr. B. R. Ambedkar National Institute of Technology Jalandhar, Punjab-144011, India

Rameshwar Jha, Director General, IET Bhaddal, Distt.- Ropar, Punjab-140108 ,India

Abstract - In recent years, Brain Computer Interface (BCI) systems based on Steady-State Visual Evoked Potential (SSVEP) have received much attentions. In this study four different flickering frequencies in low frequency region were used to elicit the SSVEPs and were displayed on a Liquid Crystal Display (LCD) monitor using LabVIEW. Four stimuli colors, green, blue, red and violet were used in this study to investigate the color influence in SSVEPs. The Electroencephalogram (EEG) signals recorded from the occipital region were segmented into 1 second window and features were extracted by using Fast Fourier Transform (FFT). This study tries to develop a classifier, which can provide higher classification accuracy for multiclass SSVEP data. Support Vector Machines (SVM) is a powerful approach for classification and hence widely used in BCI applications. One-Against-All (OAA), a popular strategy for multiclass SVM is compared with Artificial Neural Network (ANN) models on the basis of SSVEP classifier accuracies. Based on this study, it is found that OAA based SVM classifier can provide a better results than ANN. In color comparison SSVEP with violet color showed higher accuracy than that with other stimuli.

Keywords- Steady-State Visual Evoked Potential; Brain Computer Interface; Support Vector Machines; ANN.

4. Paper 30111311: Comparative Study of Person Identification System with Facial Images Using PCA and KPCA Computing Techniques (pp. 23-27)

Full Text: PDF

Md. Kamal Uddin, Abul Kalam Azad, Md. Amran Hossen Bhuiyan

Department of Computer Science & Telecommunication Engineering, Noakhali Science & Technology University, Noakhali-3814, Bangladesh

Abstract — Face recognition is one of the most successful areas of research in computer vision for the application of image analysis and understanding. It has received a considerable attention in recent years both from the industry and the research community. But face recognition is susceptible to variations in pose, light intensity, expression, etc. In this paper, a comparative study of linear (PCA) and nonlinear (KPCA) based approaches for person identification has been explored. The Principal Component Analysis (PCA) is one of the most well-recognized feature extraction tools used in face recognition. The Kernel Principal Component analysis (KPCA) was proposed as a nonlinear extension of a PCA. The basic idea of KPCA is to maps the input space into a feature space via nonlinear mapping and then computes the principal components in that feature space. In this paper, facial images have been classified using Euclidean distance and performance has been analysed for both feature extraction tools.

Keywords—Face recognition; Eigenface; Principal component analysis; Kernel principal component analysis.

5. Paper 30111312: Color Image Enhancement of Face Images with Directional Filtering Approach Using Bayer’s Pattern Array (pp. 28-34)

Full Text: PDF

Dr. S. Pannirselvam, Research Supervisor & Head, Department of Computer Science, Erode Arts & Science College (Autonomous), Erode, Tamil Nadu, India

S. Prasath, Ph.D (Research Scholar), Department of Computer Science, Erode Arts & Science College (Autonomous), Erode, Tamil Nadu, India

Abstract - Today, image processing penetrates into various fields, but till it is struggling in quality issues. Hence, image enhancement came into existence as an essential task for all kinds of image processings. Various methods are been presented for color image enhancement, especially for face image. In this paper various filters are used for face image enhancement. In order to improve of the image quality directional filtering approach using Bayer’s pattern are has been applied. In this method the color image are get decomposed into three color component array, then the Bayer’s pattern array is applied to enhance those color component and interpolate the three colors into a single RGB color image. The experimental result shows that this method provides better enhancement in term of quality when compared with the existing methods such as Bilinear Method, Gaussian Filter and Vector Median Filter. The peak Signal Noise Ratio (PSNR) and Mean Square Error (MSE) are been used for similarity measures.

Keywords- VMF, GF, BM, PBPM, RGB, YbCr , PSNR, MSE

6. Paper 30111314: An Agent-Based Framework for Virtual Machine Migration in Cloud Computing (pp. 35-39)

Full Text: PDF

Somayeh Soltan Baghshahi, Computer Engineering Department, Islamic of Azad University, North Tehran Branch, Tehran, Iran

Sam Jabbehdari, Computer Engineering Department, Islamic of Azad University, North Tehran Branch, Tehran, Iran

Sahar Adabi, Computer Engineering Department, Islamic of Azad University, North Tehran Branch

Abstract — Cloud computing is a model for large-scale distributed computing, which services to customers be done through a dynamic virtual resources with high computational power of using the Internet. The cloud service providers use different methods to manage virtual resources, that to use of autonomous nature of the intelligent agents, it can improve quality of service in a cloud distributed environment. In this paper, we design a framework by using of the multiple intelligent agents, which these agent interactions with together and they manage to provide the service. Also, In this framework, an agent is designed to improve the migration technique of virtual machines.

Keywords- Cloud Computing; Virtualizaion; Virtual Machine Migration; Agent-Based Framework

7. Paper 30111315: Migration of Virtual Clusters with Using Weighted Fair Queuing Method in Cloud Computing (pp. 40-44)

Full Text: PDF

Leila Soltan Baghshahi, Computer Engineering Department, Islamic of Azad University, South Tehran Branch, Tehran, Iran

Ahmad Khademzadeh, Education and National International Scientific Cooperation Department, Research Institute for ICT(ITRC), Tehran, Iran

Sam Jabbehdari, Computer Engineering Department, Islamic of Azad University, North Tehran Branch, Tehran, Iran

Abstract — Load Balancing, Failure Recovery and Quality of Services, portability are some of the advantages in virtualization technology and cloud computing environment. In this environment, with uses the feature of Encapsulation, virtual machines together is considered as a cluster, that these clusters are able to provide the service in cloud environments. In this paper, multiple virtual machines are considered as a cluster. These clusters are migrated from a data center to another data center with using weighted fair queuing. This method is simulated in CloudSim tools in Eclipse and Java programming language. Simulation results show that the bandwidth parameter plays an important role for the virtual machine migration.

Keywords-Cloud Computing; Virtualizaion; Virtual Cluster; Live Migration

8. Paper 30111317: Fisher’s Linear Discriminant and Echo State Neural Networks for Identification of Emotions (pp. 45-49)

Full Text: PDF

Devi Arumugam, Research Scholar, Department of Computer Science, Mother Teresa Women’s University, Kodaikanal, India.

Dr. S. Purushothaman, Professor, PET Engineering College, Vallioor, India-627117.

Abstract — Identifying the emotions from facial expression is a fundamental and critical task in human-computer vision. Here expressions like anger, happy, fear, sad, surprise and disgust are identified by Echo State Neural Network. Based on a threshold, the presence of an expression is concluded followed by separation of expression. In each frame, complete face is extracted. The complete face is from top of head to bottom of chin and left ear to right ear. Features are extracted from a face using Fisher’s Linear Discriminant function. The features are extracted from a face is considered as a pattern. If 20 frames belonging to a video are considered, then 20 patterns are created. All 20 patterns are labeled as (1/2/3/4/5/6) according to the labelling decided. The labelling is done as anger=1, fear=2, happy=3, sad=4, surprise=5 and disgust=6. If 20 frames from each video is obtained then number of patterns available for training the proposed Echo State neural Networks are 6 videos x 20 frames= 120 frames. Hence, 120 patterns are formed which are used for training ESNN to obtain final weights. This process is called during the testing of ESNN. In testing of ESNN, FLD features are presented to the input layer of ESNN. The output obtained in the output layer of ANN is compared with threshold to decide the type of expression. For ESNN, the expression identification is highest.

Keywords- Video frames; Facial tracking; Eigen Value and eigen vector; Fisher’s Linear Discriminant (FLD); Echo State Neural Network (ESNN);

9. Paper 30111321: A New Current-Mode Multifunction Inverse Filter Using CDBAs (pp. 50-52)

Full Text: PDF

Anisur Rehman Nasir, Syed Naseem Ahmad

Dept. of Electronics and Communication Engg. Jamia Millia Islamia, New Delhi-110025, India

Abstract - A novel current-mode multifunction inverse filter configuration using current differencing buffered amplifiers (CDBAs) is presented. The proposed filter employs two CDBAs and passive components. The proposed circuit realizes inverse lowpass, inverse bandpass and inverse highpass filter functions with proper selection of admittances. The feasibility of the proposed multifunction inverse filter has been tested by simulation program. Simulation results agree well with the theoretical results.

Keywords: CDBA, multifunction, inverse filter

10. Paper 30111324: Assessment of Customer Credit through Combined Clustering of Artificial Neural Networks, Genetics Algorithm and Bayesian Probabilities (pp. 53-57)

Full Text: PDF

Reza Mortezapour, Department of Electronic And Computer, Islamic Azad University, Zanjan, Iran

Mehdi Afzali, Department of Electronic And Computer, Islamic Azad University, Zanjan, Iran

Abstract — Today, with respect to the increasing growth of demand to get credit from the customers of banks and finance and credit institutions, using an effective and efficient method to decrease the risk of non-repayment of credit given is very necessary. Assessment of customers' credit is one of the most important and the most essential duties of banks and institutions, and if an error occurs in this field, it would leads to the great losses for banks and institutions. Thus, using the predicting computer systems has been significantly progressed in recent decades. The data that are provided to the credit institutions' managers help them to make a straight decision for giving the credit or not-giving it. In this paper, we will assess the customer credit through a combined classification using artificial neural networks, genetics algorithm and Bayesian probabilities simultaneously, and the results obtained from three methods mentioned above would be used to achieve an appropriate and final result. We use the K_folds cross validation test in order to assess the method and finally, we compare the proposed method with the methods such as Clustering-Launched Classification (CLC), Support Vector Machine (SVM) as well as GA+SVM where the genetics algorithm has been used to improve them.

Keywords - Data classification; Combined Clustring; Artificial Neural Networks; Genetics Algorithm; Bayesian Probabilities.

11. Paper 30111327: A Cross Layer UDP-IP protocol for Efficient Congestion Control in Wireless Networks (pp. 58-68)

Full Text: PDF

Uma S V, K S Gurumurthy

Department of ECE, University Visveswaraya College of Engineering, Bangalore University, Bangalore, India

Abstract — Unlike static wired networks, mobile wireless networks present a big challenge to congestion and flow control algorithms as wireless links are in a constant competition to access the shared radio medium. The transport layer along with IP layer plays a major role in Congestion control applications in all such networks. In this research, a twofold approach is used for more efficient Congestion Control. First, a Dual bit Congestion Control Protocol (DBCC) that uses two ECN bits in the IP header of a pair of packets as feedback is used. This approach differentiates between the error and congestion-caused losses, and is therefore capable of operating in all wireless environments including encrypted wireless networks. Secondly, for better QoS and fairshare of bandwidth in mobile multimedia wireless networks, a combined mechanism, called the Proportional and Derivative algorithm [PDA] is proposed at the transport layer for UDP traffic congestion control. This approach relies on the buffer occupancy to compute the supported rate by a router on the connection path, carries back this information to the traffic source to adapt its actual transmission rate to the network conditions. The PDA algorithm can be implemented at the transport layer of the base station in order to ensure a fair share of the 802.11 bandwidth between the different UDP-based flows. We demonstrate the performance improvements of the cross layer approach as compared to DPCP and VCP through simulation and also the effectiveness of the combined strategy in reducing Network Congestion.

Keywords — congestion; explicit congestion bits [ECN]; transport layer; Internet Protocol [IP]; transmission rate;

12. Paper 30111331: The Development of Educational Quality Administration: a Case of Technical College in Southern Thailand (pp. 69-72)

Full Text: PDF

Bangsuk Jantawan, Department of Tropical Agriculture and International Cooperation, National Pingtung University of Science and Technology, Pingtung, Taiwan

Cheng-Fa Tsai, Department of Management Information Systems, National Pingtung University of Science and Technology, Pingtung, Taiwan

Abstract — The purpose of this research were: to survey the needs of using the information system for educational quality administration; to develop Information System for Educational quality Administration (ISEs) in accordance with quality assessment standard; to study the qualification of ISEs; and to study satisfaction level of ISEs user. Subsequently, the tools of study have been employed that there were the collection of 47 questionnaires and 5 interviews to specialist by responsible officers for Information center of Technical colleges and Vocational colleges in Southern Thailand. The analysis of quantitative data has employed descriptive statistics using mean and standard deviation as the tool of measurement. Hence, the result was found that most users required software to search information rapidly (82.89%), software for collecting data (80.85%) and required Information system which could print document rapidly and ready for use (78.72%). The ISEs was created and developed by using Microsoft Access 2007 and Visual Basic. The ISEs was at good level with the average of 4.49 and SD at 0.5. Users’ satisfaction of this software was at good level with the average of 4.36 and SD at 0.58.

Keywords- Educational Quality Assurance; Educational Quality Administration; Information System;

13. Paper 31101306: Performance Evaluation Of Data Compression Techniques Versus Different Types Of Data (pp. 73-78)

Full Text: PDF

Doa'a Saad El-Shora, Faculty of Computers and Informatics, Zagazig University, Zagazig, Egypt

Ehab Rushdy Mohamed, Faculty of Computers and Informatics, Zagazig University, Zagazig, Egypt

Nabil Aly Lashin, Faculty of Computers and Informatics, Zagazig University, Zagazig, Egypt

Ibrahim Mahmoud El- Henawy, Faculty of Computers and Informatics, Zagazig University, Zagazig, Egypt

Abstract — Data Compression plays an important role in the age of information technology. It is now very important a part of everyday life. Data compression has an important application in the areas of file storage and distributed systems. Because real world files usually are quit redundant, compression can often reduce the file sizes considerably, this in turn reduces the needed storage size and transfer channel capacity. This paper surveys a variety of data compression techniques spanning almost fifty years of research. This work illustrates how the performance of data compression techniques is varied when applying on different types of data. In this work the data compression techniques: Huffman, Adaptive Huffman and arithmetic, LZ77, LZW, LZSS, LZHUF, LZARI and PPM are tested against different types of data with different sizes. A framework for evaluation the performance is constructed and applied to these data compression techniques.

Page updated

Google Sites

Report abuse