Vol. 11 No. 10 OCT 2013

Vol. 11 No. 10 OCTOBER 2013 International Journal of Computer Science and Information Security

Publication OCTOBER 2013, Volume 11 No. 10 (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 30091303: The Application of Data Mining to Build Classification Model for Predicting Graduate Employment (pp. 1-7)

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 — Data mining has been applied in various areas because of its ability to rapidly analyze vast amounts of data. This study is to build the Graduates Employment Model using classification task in data mining, and to compare several of data-mining approaches such as Bayesian method and the Tree method. The Bayesian method includes 5 algorithms, including AODE, BayesNet, HNB, NaviveBayes, WAODE. The Tree method includes 5 algorithms, including BFTree, NBTree, REPTree, ID3, C4.5. The experiment uses a classification task in WEKA, and we compare the results of each algorithm, where several classification models were generated. To validate the generated model, the experiments were conducted using real data collected from graduate profile at the Maejo University in Thailand. The model is intended to be used for predicting whether a graduate was employed, unemployed, or in an undetermined situation.

Keywords-Bayesian method; Classification model; Data mining; Tree method

2. Paper 30091323: Randomness Analysis of 128 bits Blowfish Block Cipher on ECB mode (pp. 8-21)

Full Text: PDF

(1) Ashwak ALabaichi (2) Ramlan Mahmod (3) Faudziah Ahmad

(1)(3) Information Technology Department, University Utara Malaysia, 06010, Sintok, Malaysia

(1) Department of computer science, Faculty of Sciences , Kerbala University, Kerbala,00964, Iraq

(2) Faculty of Computer Science and Information Technology, University Putra Malaysia, Serdang, Selangor, 43400, Malaysia

Abstract - This paper presents the statistical test of randomness on the Blowfish Block Cipher 128-bit is continuation with our eaelier papers title" Randomness Analysis on Blowfish Block Cipher using ECB mode" and "Randomness Analysis on Blowfish Block Cipher using ECB and CBC Modes", . Blowfish128-bit is extention of blowfish 64-bit. Blowfish 128-bit resemble blowfish 64-bit but only in blowfish algorithm block size is 64 bits but in an extension version block size is 128 bits and all operations based on 64 bits instead of on 32 bits. Blowfish 128-bit is a symmetric block cipher with variable key lengths from 64 bits up to a maximum of 896 bits this leads to increase security of the algorithm. The randomness testing was performed using NIST Statistical Test Suite. The tests were performed on Blowfish 128-bit with ECB mode.Our analysis showed that Blowfish 128-bit algorithm with ECB mode such as blowfish 64-bit where is not inappropriate with text and images files that contain huge number of identical bytes and better than blowfish 64-bit with video files. c++ is used in the implementation of the blowfish 128-bit while NIST is implemented under Linux operating system.

Keywords: Block Cipher, Blowfish Algorithm 128-bit, ECB mode, randomness testing.

3. Paper 30091328: Relay Assisted Epidemic Routing Scheme for Vehicular Ad hoc Network (pp. 22-26)

Full Text: PDF

Murlidhar Prasad Singh, Deptt of CSE, UIT, RGPV Bhopal, MP, India

Dr. Piyush Kumar Shukla, Deptt of CSE, UIT, RGPV Bhopal,MP, India

Anjna Jayant Deen, Deptt of CSE, UIT, RGPV Bhopal, MP, India

Abstract — Vehicular ad hoc networks are networks in which no simultaneous end-to-end path exists. Typically, message delivery experiences long delays as a result of the disconnected nature of the network. In this form of network, our main goal is to deliver the messages to the destination with minimum delay. We propose relay assisted epidemic routing scheme in which we tend to use relay nodes (stationary nodes) at an intersection with a completely different number of mobile nodes which differs from existing routing protocols on how routing decision are made at road intersection where relay nodes are deployed. Vehicles keep moving and relay nodes are static. The purpose of deploy relay nodes is to increase the contact opportunities, reduce the delays and enhance the delivery rate. With various simulations it has been shown that relay nodes improves the message delivery probability rate and decreases the average delay.

Keywords - VANETs, Routing Protocols, Relay Nodes.

4. Paper 30091329: Blind Optimization for Data Warehouse during Design (pp. 27-31)

Full Text: PDF

Rachid El mensouri and Omar El beqali, LIILAN/ GRM2I FSDM, Sidi Mohammed Ben Abdellah University, Fes, Morocco

Ziyati Elhoussaine, RITM laboratory ENSEM - ESTC - University Hassan II Ain chock, Casablanca, Morocco

Abstract — Design a suitable data warehouse is getting increasingly complex and requires more advance technique for different step. In this paper, we present a novel data driven approach for fragmentation based on the principal components analysis (PCA). Both techniques has been treated in many works [2][7]. The possibility of its use for horizontal and vertical fragmentation of data warehouses (DW), in order to reduce the time of query execution. We focus the correlation matrices, the impact of the eigenvalues evolution on the determination of suitable situations to achieve the PCA, and a study of criteria for extracting principal components. Then, we proceed to the projection of individuals on the first principal plane, and the 3D vector space generated by the first three principal components. We try to determine graphically homogeneous groups of individuals and therefore, a horizontal fragmentation schema for the studied data table.

Keywords - data warehouse; optimization; PCA; vertical fragmentation; horizontal fragmentation; OLAP queries.

5. Paper 30091330: Traffic Intensity Estimation on Mobile Communication Using Adaptive Extended Kalman Filter (pp. 32-37)

Full Text: PDF

Rajesh Kumar, Department of Electronics and Communication, Jabalpur Engineering College, Jabalpur, India (482011)

Agya Mishra, Department of Electronics and Communication, Jabalpur Engineering College, Jabalpur, India (482011)

Abstract — Traffic estimation is an important task in network management and it makes significant sense for network planning and optimization. The biggest challenge is to control congestion in the network and the blocking probability of call to provide users a barrier less communication. Effective capacity planning is necessary in controlling congestion and call drop rates in mobile communication thus an accurate prediction of traffic results congestion control, effective utilization of resources, network management etc. In this paper a real time mobile traffic data of different mobile service providers are estimated using adaptive Extended Kalman Filter method. This paper evaluates compares and concludes that, this approach is quite efficient with min normalized root mean square error (NRMSE) and it can be used for real time mobile traffic intensity estimation.

Keywords—Traffic Intensity Estimation, recursive filter, Mobile Traffic data, Extended Kalman filter, NRMSE.

6. Paper 30091334: Test Framework Development Based Upon DO-278A Using ISTQB Framework (pp. 38-41)

Full Text: PDF

Raha Ashrafi, Computer Engineering Department, North Tehran Branch , Islamic Azad University, Tehran , Iran

Ramin Nassiri PhD, Computer Engineering Department, Central Tehran Branch, Islamic Azad University, Tehran, Iran

Abstract — DO-278A is an FAA Standard which was published for CNS/ATM software development in 2011 while ISTQB1 is the worldwide software testing standard framework. Software which are developed according to DO-289A are verified by Review, Analysis and a few other methods but they are not actually sufficient for testing so it would be quite reasonable to deploy ISTQB techniques for that purpose. This paper intends to show that ISTQB techniques may successfully work for DO-278A verification.

Keywords: component; Software Aviation system; CNS/ATM; DO-278A;, ISTQB; Verification.

7. Paper 30091344: Queuing Mechanism for WCDMA Network (pp. 42-47)

Full Text: PDF

Vandana Khare, Associate professor & HOD ECE, RITW, Hyderabad, India

Dr. Y. Madhavee Latha, Professors & Principal MRECW, Secunderabad, India

Dr. D. SrinivasRao, Professors & Head ECE Department, JNTU, Hyderabad, India

Abstract - The network traffic in the upcoming wireless network is expected to be extremely nonstationary and next generation wireless networks including 3rd generation are expected to provide a wide range of multimedia services with different QoS constraints on mobile communication because of that there is no guarantee for a given system to provide good quality of service. So that there is a need to design an efficient queuing mechanism by which the QoS is going to be improved for wideband services. This paper proposes an efficient active queue management mechanism to control the congestion at the router. This paper is mainly aimed towards the WCDMA scheme for wideband services like video. So that it integrates the WCDMA with IR-RAN using active queue management. By simulation result our proposed WCDMA architecture along with active queue management (AQM) will achieves the effective peak signal to noise ratio (PSNR).

Keywords: WCDMA, IP-RAN, QoS, PSNR.

8. Paper 30091301: Implementation of Radial Basis Function and Functional Back Propagation Neural Networks for Estimating Inframe Fill Stability (pp. 48-53)

Full Text: PDF

P. Karthikeyan, Research Scholar, Department of Civil Engineering, CMJ University.

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

Abstract - ANSYS 14 software is used for analyzing the infill frames. The numerical values of strain are used to train the artificial neural network (ANN) topology by using Back propagation algorithm (BPA) and Radial basis function network (RBF). The training patterns used for the ANN algorithms are chosen from the strain data generated using ANSYS program. During the training process, node numbers are presented in the input layer of the ANN and correspondingly, strain values are presented in the output layer of the ANN. Depending upon the type of values present in the patterns, the learning capability of the ANN algorithms varies.

Keywords: Artificial Neural Network (ANN); Back propagation algorithm (BPA); Radial basis function (RBF).

9. Paper 30091302: Impact of Part-Of-Speech Based Feature Selection in Text Summarization (pp. 54-60)

Full Text: PDF

Rajesh Wadhvani, Computer Science Department, National Institute Of Technology, Bhopal, India

R. K. Pateriya, Computer Science Department, National Institute Of Technology, Bhopal, India

Devshri Roy, Computer Science Department, National Institute Of Technology, Bhopal, India

Abstract — The standard practice in the field of summarization is to have a standard reference summary based on the queries. The summaries are manually generated by human experts. The automated summaries are then compared with the human generated summaries. In this paper a model which is useful for query-focused multi-document summarization is proposed. This model summarises documents of tagged data using cosine relevance measurement mechanism. Tagging is achieved by using the Stanford POS Tagger Package. We have used the concept of rarity in addition to traditional raw term frequency for assigning the weights to the features. In this work for a given sentence out of all possible tag sequences best is derived by using argmax computation. For evaluation DUC-2007 dataset is used. The summaries generated by our technique are compared with the stranded summaries provided by DUC 2007 using ROUGE (Recall-Oriented Understudy for Gisting Evaluation). The performance metrics used for compassion are Recall, Precision, F-score.

Keywords: Text summarization, query-based summaries, sentence extraction.

10. Paper 30091304: Detection of Microcalcification in Breast Using Radial Basis Function (pp. 61-67)

Full Text: PDF

Shaji B., Research Scholar, Vels University, Pallavaram, Chennai, India-600117.

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

Rajeswari R., Research scholar, Mother Teresa Women’s University, Kodaikanal-624102, INDIA.

Abstract - This paper presents combination of wavelet with radial basis function (RBF) in identifying the microcalcification (MC) in a mammogram image. Mammogram image is decomposed using Coiflet wavelet to 5 levels. Statistical features are extracted from the wavelet coefficients. These features are used as inputs to the RBF neural network along with a labeling of presence or absence of MC. The classification performance of RBF is minimum 95% out of the presence of total MC in a given mammogram.

Keywords: mammogram , Microcalcification, Radial basis function, Coiflet wavelet

11. Paper 30091307: Implementation of Intrusion Detection using BPARBF Neural Networks (pp. 68-72)

Full Text: PDF

Kalpana Y., Research Scholar, VELS University, Pallavaram, Chennai, India-600117

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

Rajeswari R., Research scholar, Mother Teresa Women’s University, Kodaikanal-624102, India.

Abstract - Intrusion detection is one of core technologies of computer security. It is required to protect the security of computer network systems. Due to the expansion of high-speed Internet access, the need for secure and reliable networks has become more critical. The sophistication of network attacks, as well as their severity, has also increased recently. This paper focuses on two classification types: a single class (normal, or attack), and a multi class (normal, DoS, PRB, R2L, U2R), where the category of attack is detected by the combination of Back Propagation neural network (BPA) and radial basis function (RBF) Neural Networks. Most of existing IDs use all features in the network packet to look for known intrusive patterns. A well-defined feature extraction algorithm makes the classification process more effective and efficient. The Feature extraction step aims at representing patterns in a feature space where the attack patterns are attained. In this paper, a combination of BPA neural network along with RBF networks are used s for detecting intrusions. Tests are done on KDD-99 data set.

Keywords: network intrusion detection, kdd-99 datasets, BPARABF neural networks

12. Paper 30091308: Implementation of Daubauchi Wavelet with Radial Basis Function and Fuzzy Logic in Identifying Fingerprints (pp. 73-78)

Full Text: PDF

Guhan P., Research Scholar, Department of MCA, VELS University, Chennai–600 117, India

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

Rajeswari R., Research scholar, Mother Teresa Women’s University, Kodaikanal-624102, India.

Abstract - This paper implements wavelet decomposition for extracting features of fingerprint images. These features are used to train the radial basis function neural network and Fuzzy logic for identifying fingerprints. Sample finger prints are taken from data base from the internet resource. The fingerprints are decomposed using daubauchi wavelet 1(db1) to 5 levels. The coefficients of approximation at the fifth level is used for calculating statistical features. These statistical features are used for training the RBF network and fuzzy logic. The performance comparisons of RBF and fuzzy logic are presented.

Keywords- Fingerprint; Daubauchi wavelet, radial basis function, fuzzy logic.

13. Paper 30091309: Implementation of Hidden Markov Model and Counter Propagation Neural Network for Identifying Human Walking Action (pp. 79-85)

Full Text: PDF

Sripriya P., Research Scholar, Department of MCA, VELS University, Pallavaram, Chennai, India-600117,

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

Rajeswari R., Research scholar, Mother Teresa Women’s University, Kodaikanal, India-624101.

Abstract - This paper presents the combined implementation of counter propagation network (CPN) along with hidden Markov model (HMM) for human activity recognition. Many methods are in use. However, there is increase in unwanted human activity in the public to achieve gainsay without any hard work. Surveillance cameras are installed in the crowded area in major metropolitan cities in various countries. Sophisticated algorithms are required to identify human walking style to monitor any unwanted behavior that would lead to suspicion. This paper presents the importance of CPN to identify the human GAIT.

Keywords: GAIT; human walking action; counter propagation network; hidden Markov model.

14. Paper 30091313: A Brief Study of Data Compression Algorithms (pp. 86-94)

Full Text: PDF

Yogesh Rathore, CSE,UIT, RGPV, Bhopal, M.P., India,

Manish k. Ahirwar, CSE,UIT, RGPV, Bhopal, M.P., India

Rajeev Pandey, CSE,UIT, RGPV, Bhopal, M.P., India

Abstract — This paper present survey of several lossless data compression techniques and its corresponding algorithms. A set of selected algorithms are studied and examined. This paper concluded by stating which algorithm performs well for text data.

Keywords - Compression; Encoding; REL; RLL; Huffman; LZ; LZW;

15. Paper 30091314: fMRI image Segmentation using conventional methods versus Contextual Clustering (pp. 95-98)

Full Text: PDF

Suganthi D., Research Scholar, Department of Computer Science, Mother Teresa Women’s University, Kodaikanal, Tamilnadu, India-624101,

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

Abstract - Image segmentation plays a vital role in medical imaging applications. Many image segmentation methods have been proposed for the process of successive image analysis tasks in the last decades. The paper has considered fMRI segmentation in spite of existing techniques to segment the fMRI slices. In this paper an fmri image segmentation using contextual clustering method is presented. Matlab software ‘regionprops’ function has been used as one of the criteria to show performance of CC. The CC segmentation shows more segmented objects with least discontinuity within the objects in the fMRI image. From the experimental results, it has been found that, the Contextual clustering method shows a better segmentation when compared to other conventional segmentation methods.

Keywords: Contextual clustering; segmentation; fMRI image.

16. Paper 30091318: Implementation of Human Tracking using Back Propagation Algorithm (pp. 99-102)

Full Text: PDF

Pratheepa S., Research Scholar, Mother Teresa Women's University, Kodaikanal, India-624101.

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

Abstract - Identifying moving objects from a video sequence is a fundamental and critical task in many computer-vision applications. A common approach is to perform background subtraction, which identifies moving objects from the portion of a video frame that differs significantly from a background model. In this work, a new moving object-tracking method is proposed. The moving object is recorded in video. The segmentation of the video is done. Two important properties are used to process the features of the segmented image for highlighting the presence of the human. An artificial neural network with supervised back propagation algorithm learns and provides a better estimate of the movement of the human in the video frame. A multi target human tracking is attempted.

Keywords- Back propagation algorithm (BPA), Human tracking, and Video segmentation

17. Paper 30091331: Stock Market Trend Analysis Using Hidden Markov Models (pp. 103-110)

Full Text: PDF

Kavitha G., School of Applied Sciences, Hindustan University, Chennai, India.

Udhayakumar A., School of Computing Sciences, Hindustan University, Chennai, India

Nagarajan D., Department of Information Technology, Salalah College of Technology, Salalah, Sultanate of Oman

Abstract — Price movements of stock market are not totally random. In fact, what drives the financial market and what pattern financial time series follows have long been the interest that attracts economists, mathematicians and most recently computer scientists [17]. This paper gives an idea about the trend analysis of stock market behaviour using Hidden Markov Model (HMM). The trend once followed over a particular period will sure repeat in future. The one day difference in close value of stocks for a certain period is found and its corresponding steady state probability distribution values are determined. The pattern of the stock market behaviour is then decided based on these probability values for a particular time. The goal is to figure out the hidden state sequence given the observation sequence so that the trend can be analyzed using the steady state probability distribution (p ) values. Six optimal hidden state sequences are generated and compared. The one day difference in close value when considered is found to give the best optimum state sequence.

Keywords-Hidden Markov Model; Stock market trend; Transition Probability Matrix; Emission Probability Matrix; Steady State Probability distribution

18. Paper 30091342: Computational Impact of Hydrophobicity in Protein Stability (pp. 111-116)

Full Text: PDF

Geetika S. Pandey, Research Scholar, CSE dept., RGPV, Bhopal (M.P), India

Dr. R.C Jain, Director, SATI(D), Vidisha(M.P), India

Abstract - Among the various features of amino acids, the hydrophobic property has most visible impact on stability of a sequence folding. This is mentioned in many protein folding related work, in this paper we more elaborately discuss the computational impact of the well defined ‘hydrophobic aspect in determining stability’, approach with the help of a developed ‘free energy computing algorithm’ covering various aspects - preprocessing of an amino acid sequence, generating the folding and calculating free energy. Later discussing its use in protein structure related research work.

Keywords- amino acids, hydrophobicity, free energy, protein stability.

19. Paper 31081343: Survey On MAC Protocols Used In Co-Operation Network Using Relay Nodes (pp. 117-120)

Full Text: PDF

Shalini Sharma, PG-Scholar, DoEC, SSSIST

Mukesh Tiwari, Associate Professor, DoEC, SSSIST

Jaikaran Singh, Associate Professor, DoEC, SSSTTS

Abstract — In this paper a survey on a relay based media access scheme has been proposed. It has been observed that any cooperative scheme gives better performance by availability of additional path using the concept of a relay nodes. Relay based schemes more than one relay nodes are selected to improve the performance, so that if one fails the other can be used as a back. Such a co-operative scheme will enhance the performance of the network.

Keywords: MAC, cooperation, Relay Performance, Newtwork. Scheme.