Vol. 12 No. 12 DEC 2014

Vol. 12 No. 12 DECEMBER 2014 International Journal of Computer Science and Information Security

Publication DECEMBER 2014, Volume 12 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 30111409: A Framework for Offline Biometric Identity Authentication (pp. 1-7)

Full Text: PDF

Hanan Elazhary, Computers and Systems Department, Electronics Research Institute, Cairo, Egypt

Abstract—Identity authentication based on held paper-based documents such as paper identification cards (IDS) and Hajj permits is not always reliable due to many reasons such as the unclear or relatively outdated photographs in IDs. A better more secure and more reliable approach involves matching biometric features such as fingerprints and iris images. Unfortunately, such an approach typically relies on matching an input live feature (obtained from the stakeholder whose identity is to be authenticated) against a similar feature belonging to the assumed stakeholder but stored in a database. This requires maintaining an expensive local or remote database accessed through a reliable Internet connection and having the access rights to such a database and this is not always feasible. In this paper, we propose a framework for offline biometric identity authentication that does not require the presence of a database (during authentication). It relies on embedding a biometric feature (watermark) in the paper-based document and extracting it at the time of authentication for matching and identity validation. The same framework is suitable for the copyright protection of digital images where the identity of the owner is authenticated offline without having to maintain a database of user-defined watermarks. The framework has different possible implementations and security levels can be added as required with a tradeoff between performance and security. Thus, the paper identifies application requirements that have to be assessed before developing any application-specific implementation of the framework and explains how each of these requirements affects the design and implementation decisions.

Keywords-Biometrics, copyright protection, identity authentication, image watermarking, security, TA permutation

2. Paper 31101425: Evaluate the quality of service in the WiMax environment using the RED-FEC mechanism (pp. 8-12)

Full Text: PDF

Sami Brini, Faculty of Sciences, University of Dammam, Dammam, KSA

Chokri Idoudi, University of Sousse, ISITCom, Sousse, Tunisia

Abdelbasset, College of Technical (Riadh), TVTC, KSA, Riadh, KSA

Trad Habib Youssef, University of Sousse, ISITCom, Sousse, Tunisia

Abstract - The new information technologies and communication technologies (NTIC) are the basis of the knowledge economy. They allow you to store, process and disseminate an increasing amount of data quickly and cost and are a source of more and more important for productivity gains. Our daily, lives have been improved and work became a lot easier. In this article, we are going to discuss the things where modern technology became useful. This paper study aims to explore the effect of transferring the VoIP network via WiMax. A study of IEEE 802.16 is given by comparing with standards of WiFi (IEEE 802.11, 802.11e ...). A second part of the paper will be devoted to the evaluation by simulation of the transmission performance of VoIP in a WiMax network. In the third part, we propose an architecture based on the use of two mechanisms for QoS RED (Random Early Detection) and FEC (Forward Error Correction). Based on the results, we propose a new architecture that allows us to keep the level of service quality in good condition.

Keywords: VOIP, WiMax, Audio codecs, FEC, RED

3. Paper 30111401: Human Intentions Mining Through Natural Language Text Survey (pp. 13-16)

Full Text: PDF

E. A. Raslan, Bch of Computer Science, Faculty of Computers and Information Sciences, Ain Shams University, Cairo, Egypt

Dr. Y. E. Mohammed, Dept. of Computer Science, Faculty of Computers and Information Sciences, Mansoura University, Mansoura, Egypt

Dr. M. Z. Rashad, Dept. of Computer Science, Faculty of Computers and Information Sciences, Mansoura University, Mansoura, Egypt

Abstract - Human intention driven textual analysis is the identification of intentions from natural language text. Human intentions have been widely studied in psychology and behavior sciences, as they are an important feature of human nature, it has also attracted the attention of researchers in computer science especially in the field of human computer interpretation. The ways people use words convey a great deal of information about themselves, their audience, and the situations they are in. Individuals’ choice of words can hint at their social status, age, sex, and motives [1]. For more than 50 years, linguists and computer scientists had tried to get computers to understand human language using semantics software. We're still in a long way from having a computer that can understand language as well as a human being does, but we've made definite progress toward that goal [2]. Intention Mining is a new subject and stays at the crossroads of Information Retrieval, Information Extraction and Web Mining. In this survey we presented a basic background that covered the progress of intentions mining field. Furthermore we mentioned the related work in the intention mining and its applications.

Keywords- Human Intentions Knowledge Base, Human Intentions Detection System, and Web Mining.

4. Paper 30111403: Analyzing Different Machine Learning Techniques for Stock Market Prediction (pp. 17-23)

Full Text: PDF

Waqas Ahmad, NUST, College of Electrical and Mechanical engineering Rawalpindi Pakistan

Abstract— Stock market prediction is one of most challenging issue and attracted attention from many researches and stock market investors. With passing time these stock market prediction techniques are getting better with different machine learning algorithms and investors have started relying on these prediction model proposed by many researchers. Many machine learning techniques for stock market prediction are developed. There are no specifications available that which techniques are optimal or not. Also I will analyze and compare different techniques and will discuss their strength and weakness. I have analyzed how these technique works and compare these techniques with other stock market prediction techniques and explained how some techniques have advantage over others and perform better.

Keywords— Stock Market, Machine Learning, Neural Networks, Rough Set, Time Series, Support Vector Machine, Hidden Markov Models, Prediction

5. Paper 30111411: Steganography Using Genetic Encryption Along With Visual Cryptography (pp. 24-31)

Full Text: PDF

Shruti Sekra, Samta Balpande, Karishma Mulani

G. H. Raisoni Institute of Engineering and technology, Wagholi, Pune, Maharashtra, India

Abstract - Authentication login plays a major rule in today’s world. Due to unavoidable hacking of the databases, it is always quite difficult to trust the information. The project work aims to solve the problem of authenticity. In this paper, we are proposing a technique utilizing image processing, Steganography and visual cryptography, and then dividing it into shares. In this project the message or the text file is taken as an input from the user which needs to get embedded in the image file. The image file can be of the extensions .jpg or .png. It focuses on hiding secret messages inside a cover medium(image). The most important property of a cover medium is the amount of data that can be stored inside it without changing its noticeable properties. There are many sophisticated techniques with which to hide, analyze, and recover that hidden information. This paper discusses an exploration in the use of Genetic Algorithm operators on the cover medium. Elitism is used for the fitness function. The model presented here is applied on image files, though the idea can also be used on other file types. Our results show this approach satisfied both security and hiding capacity requirements.

Keywords—Genetic Algorithm, Steganography, visual cryptography, Encryption, Decryption

6. Paper 30111413: Performance Evaluation of Statistical Approaches for Automatic Text-Independent Gender Identification System (pp. 32-38)

Full Text: PDF

R. Rajeswara Rao, Department of CSE, JNTUK Kakinada-Vizianagaram, AP, India

Abstract - In this paper, robust feature for Automatic text-independent Gender Identification System has been explored. Through different experimental studies, it is demonstrated that the timing varying speech related information can be effectively captured using Hidden Markov Models (HMMs) than Gaussian Mixture Models (GMMs) . The study on the effect of feature vector size for good Gender Identification demonstrates that, feature vector size in the range of 18-22 can capture Gender related information effectively for a speech signal sampled at 16 kHz, it is established that the proposed Gender Identification system requires significantly less amount of data during both during training as well as in testing. The Gender Identification study using robust features for different states and different mixtures components, training and test duration has been exploited on TIMIT database.

Keywords ‐ Gaussian Mixture Model (GMM),Ergodic Hidden Markov Models (EHMM) Gender, LPC, MFCC.

7. Paper 30111421: Book Related Information Retrieval Using Ontology Based Semantic Search and WordPress (pp. 39-43)

Full Text: PDF

P B Lahoti, Computer Science & Engineering, Government College of Engineering, Aurangabad, India.

V A Chakkarwar, Computer Science & Engineering, Government College of Engineering, Aurangabad, India

Abstract - Nowadays most of the contents are stored and shared on the web, so it is difficult to an intelligent user to find the exact content when it comes to finding and properly managing information in massive volumes. This difficulties are occurred due to Traditional keyword search engine model. Aiming to solve the limitations of keyword-based search engine Semantic Web (SW) has been introduced. Main idea of this research paper is to explore the current state of the semantic information retrieval with major focus on ontology based search. The research paper includes introductory knowledge on the Semantic Web and its layer cake, proposed method which make use of WordPress which is a free and open source blogging tool and a content management system (CMS) based on PHP and MySQL.

Keywords-Semantic retrieval, Ontology based Information search, Book search, WORDPRESS, Ontology based Data Integration (ONDINE), MIEL++.