{"title":"Tree distribution classifier for automatic spoken Arabic digit recognition","authors":"N. Hammami, Mokhtar Sellam","doi":"10.1109/ICITST.2009.5402575","DOIUrl":"https://doi.org/10.1109/ICITST.2009.5402575","url":null,"abstract":"In this work we propose a novel method for automatic discrete speech recognition composed from two steps. In a first step, discrete speech features are extracted by means of Mel Frequency Cepstral Coefficients (MFCCs) followed by vector quantization (VQ). Then in a second step, the obtained features are fed to a Tree distribution classifier which provides the class-label associated with each feature by approximating the true class probability by means of an optimal spanning tree model. The experimental results obtained on a spoken Arabic digit dataset confirmed the promising capabilities of the proposed approach.","PeriodicalId":251169,"journal":{"name":"2009 International Conference for Internet Technology and Secured Transactions, (ICITST)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116426017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
N. Anandaraja, N. Sriram, C. Kathiresan, Shibi Sebastian, E. Vadivel
{"title":"Web cum mobile based dynamic market information support for Agri-Horti produces: Linking the farmers with market","authors":"N. Anandaraja, N. Sriram, C. Kathiresan, Shibi Sebastian, E. Vadivel","doi":"10.1109/ICITST.2009.5402541","DOIUrl":"https://doi.org/10.1109/ICITST.2009.5402541","url":null,"abstract":"Farmers in India are at the mercy of traders especially the middlemen who fix lower rates at the farmers end. The farmers are desperate as they are not aware of the prices elsewhere and they have meager produce at their hand. Market led agriculture is need of the hour which needs market intelligence. Tamil Nadu Agricultural University in collaboration with Centre for Development of Advanced Computing initiated the project for the benefit of farmers & traders covering SIX major markets of South India as Pilot. Main emphasis of the project is covering perishable items of 130 plus commodities, updating the daily wholesale and retail price. Ensuring the last mile connectivity and reaching large number of users, the price information is being delivered through Mobile phone. This paper explains about its additional features.","PeriodicalId":251169,"journal":{"name":"2009 International Conference for Internet Technology and Secured Transactions, (ICITST)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126134927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"IDS 3G — Third generation for intrusion detection: Applying forecasts and return on security investment to cope with unwanted traffic","authors":"E. Pontes, A. Guelfi","doi":"10.1109/ICITST.2009.5402622","DOIUrl":"https://doi.org/10.1109/ICITST.2009.5402622","url":null,"abstract":"The methods for Intrusion Detection Systems (IDS) are based on identification and prevention of attacks and threats to computer systems, but there are few studies concerning forecasting approaches. Similarly to other sciences (e.g. seismology, meteorology, and economics) in which extent efforts are done for forecasts, trend analysis could also be employed in information security field. The aim of this paper is to present the challenges in employing forecasting approaches which could be aggregated to traditional ROSI techniques in IDS. In this study, trend analysis is based on moving averages and Fibonacci sequence. Tests applied upon two datasets (DARPA, KDD) indicate that the applied techniques define incidents trends; therefore, forecasting approach may be complementary to ROSI methods.","PeriodicalId":251169,"journal":{"name":"2009 International Conference for Internet Technology and Secured Transactions, (ICITST)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125801943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An efficient Iris authentication using chaos theory-based cryptography for e-commerce transactions","authors":"Arian Rahimi, S. Mohammadi, Rozita Rahimi","doi":"10.1109/ICITST.2009.5402532","DOIUrl":"https://doi.org/10.1109/ICITST.2009.5402532","url":null,"abstract":"E-commerce is an outcome of globalization and technology outbreak of 21st century. Increasingly, more products and services are sold over Internet; hence, there is a growing need for a combination of legislation and technical solutions to globally secure customer privacy. Credit card fraud is one of the crimes especially when it is used for web-based transaction. In this paper, a technical solution using Iris authentication technique is proposed for protecting identity theft in e-commerce transactions because Iris patterns are unique to an individual. Further, this research proposes authentication of e-commerce users by using Iris biometric technique as one of the most secure biometric algorithms. Therefore, this research proposes a web-based architecture which uses a combination of Image Processing and secure transmission of customers' Iris templates along with credit card details for decreasing credit card frauds over Internet.","PeriodicalId":251169,"journal":{"name":"2009 International Conference for Internet Technology and Secured Transactions, (ICITST)","volume":"310 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125770689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The elements influencing the online price dispersion on Iranian electronic retailers","authors":"M. Arefi, A. Amini","doi":"10.1109/ICITST.2009.5402531","DOIUrl":"https://doi.org/10.1109/ICITST.2009.5402531","url":null,"abstract":"Frictionless electronic commerce is a made-up story and online price dispersion is high and steady. There is not enough proof that online prices are decreasing and becoming alike. Although the studies show that prices dispersion on the Internet is decreased, they are steady yet. Therefore, this study aims to determine the important dimensions of electronic retailers' heterogeneity and examine the markets elements that influence price dispersion. The rapid development of e-commerce in Iran has made this task feasible. Questionnaire and observation were the methods used for collecting the data in this study. 106 identical products from 56 electronic retailers and 948 price quotes in different products categories such as books, CDs, laptops, mobiles, monitors, MP3s and digital cameras in online market have been used as data. 140 questionnaires have been developed for evaluating electronic retailers' characteristics. The method used in this analysis is statistical which mostly were factor analysis, cluster and regression analyses. It has been proved that services provided by electronic retailers could be described by five basic factors. Also, the results revealed that market and electronic retailers' characteristics are the main explanatory variables of price dispersion among electronic retailers.","PeriodicalId":251169,"journal":{"name":"2009 International Conference for Internet Technology and Secured Transactions, (ICITST)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130873852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Unduplicable quantum data medium based secret decryption and verification","authors":"L. Gyongyosi, S. Imre","doi":"10.1109/ICITST.2009.5402590","DOIUrl":"https://doi.org/10.1109/ICITST.2009.5402590","url":null,"abstract":"In classical computer science any data that can be read can be copied an unlimited number of times. In the quantum world, the quantum states cannot be copied perfectly, according to the no-cloning theorem. The major difference between quantum and classical copy protection is the physical resource for data storage. The proposed quantum based data protection system lies in the fundamental difference between classical and quantum information. The classical data is stored in the secret rotation angles of non-orthogonal quantum states. In our paper we show that secret quantum decoding operations can be implemented with some associated error, which decreases exponentially with the number of quantum states of the angle state.","PeriodicalId":251169,"journal":{"name":"2009 International Conference for Internet Technology and Secured Transactions, (ICITST)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131656460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Dataset threshold for the performance estimators in supervised machine learning experiments","authors":"Zanifa Omary, F. Mtenzi","doi":"10.1109/ICITST.2009.5402500","DOIUrl":"https://doi.org/10.1109/ICITST.2009.5402500","url":null,"abstract":"The establishment of dataset threshold is one among the first steps when comparing the performance of machine learning algorithms. It involves the use of different datasets with different sample sizes in relation to the number of attributes and the number of instances available in the dataset. Currently, there is no limit which has been set for those who are unfamiliar with machine learning experiments on the categorisation of these datasets, as either small or large, based on the two factors. In this paper we perform experiments in order to establish dataset threshold. The established dataset threshold will help unfamiliar supervised machine learning experimenters to categorize datasets based on the number of instances and attributes and then choose the appropriate performance estimation method. The experiments will involve the use of four different datasets from UCI machine learning repository and two performance estimators. The performance of the methods will be measured using f1-score.","PeriodicalId":251169,"journal":{"name":"2009 International Conference for Internet Technology and Secured Transactions, (ICITST)","volume":"2010 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133197774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Low power design for silent pass authentication system","authors":"K. Alghathbar","doi":"10.1109/ICITST.2009.5402634","DOIUrl":"https://doi.org/10.1109/ICITST.2009.5402634","url":null,"abstract":"This paper presents a new full-search block-matching algorithm for a lip reading user authentication system. The proposed algorithm reduces the computational load by eliminating non-candidate blocks from the search window using an approximate DC values. This computational reduction leads to enhanced performance in terms of low power consumption and fast motion vector estimation. A low power VLSI implementation of the algorithm is presented along with experimentation results.","PeriodicalId":251169,"journal":{"name":"2009 International Conference for Internet Technology and Secured Transactions, (ICITST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129526423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Managing trade-offs between information loss and latency in real-time distributed systems","authors":"H. Maalouf","doi":"10.1109/ICITST.2009.5402614","DOIUrl":"https://doi.org/10.1109/ICITST.2009.5402614","url":null,"abstract":"Multicasting is used in many real-time distributed applications such as market data feeds, videoconferencing, interactive distance learning. The need for multicasting is either because the databases are replicated or simply because there are multiple destination nodes involved in the communication process. However consistency problems are inherent in distributed environments where the variable nature of inter-communication delays between sites may interfere with the correct order of the received data. Several consistency preserving algorithms rely on resequencing methods. In this paper, we use partial order resequencing in order to meet the temporal constraints of these real-time systems. This may cause loss of data and could affect the data integrity. By using simulation results and approximate analysis, we analyze the trade-offs between minimizing the latency and keeping the information loss acceptable.","PeriodicalId":251169,"journal":{"name":"2009 International Conference for Internet Technology and Secured Transactions, (ICITST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125679537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Trust-based framework for security enhancement of P2PSIP communication systems","authors":"Xianghan Zheng, V. Oleshchuk","doi":"10.1109/ICITST.2009.5402533","DOIUrl":"https://doi.org/10.1109/ICITST.2009.5402533","url":null,"abstract":"Today, Peer-to-Peer SIP based communication systems have attracted much attention from both academia and industry. The decentralized nature of P2P might provide the distributed peer-to-peer communication system without help of the traditional SIP server. However, it comes to the cost of reduced trustworthiness and may cause security problems, e.g. privacy leaks, unpredictable availability, etc. In this paper, we investigate on P2PSIP security issues and propose a subjective based trust model that offers trust services during P2PSIP session establishment. The main issues considered in this model include opinion calculation, opinion maintenance, data confidentiality and integrity, message routing, and NAT traversal. After that we implement a typical use scenario to show how our model is exploited to offer the trusted session initiation service and protects the security breaches through the malicious or faulty intermediate peers. We take Chord as the P2PSIP overlay for example in this paper. However, the system is independent of the Chord overlay and is extendable to the other DHT (Distributed Hash Table) technologies.","PeriodicalId":251169,"journal":{"name":"2009 International Conference for Internet Technology and Secured Transactions, (ICITST)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115675737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}