{"title":"Recurrent neural network classifier for Three Layer Conceptual Network and performance evaluation","authors":"Md. Khalilur Rhaman, Tsutomu Endo","doi":"10.4304/jcp.5.1.40-48","DOIUrl":"https://doi.org/10.4304/jcp.5.1.40-48","url":null,"abstract":"Contextual analysis in dialog is a hard problem. In this paper three layers memory structure is adopted to address the challenge which we refer to as three layer conceptual network (TLCN). This highly efficient network simulates the human brain by episodic memory, discourse memory and ground memory. An extended case structure framework is used to represent the knowledge. The knowledge database is constructed by the collection of target system information and utterances. This knowledge is updated after every dialog conversation. A Recurrent Neural Network classifier is also introduced for classifying the knowledge for the target system. This system prototype is based on doctor-patients dialogs. 78% disease classification accuracy is observed by this system prototype. Disease identification accuracy is depending on number of disease and number of utterances. This performance evaluation is also discussed in details.","PeriodicalId":335795,"journal":{"name":"2008 11th International Conference on Computer and Information Technology","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124862110","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":"Security enhancement of MD5 hashed passwords by using the unused bits of TCP header","authors":"M.D.A. Chawdhury, A.H.M.A. Habib","doi":"10.1109/ICCITECHN.2008.4803081","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2008.4803081","url":null,"abstract":"When a password is encrypted by a hash algorithm the resultant is called hashed password. In a server client based communication system such as Yahoo Messenger, AIM, passwords of clients are hashed by MD5 and passed to the server for authentication. This type of transmission is always a subject of interception by the hackers. These hashed passwords are passed through the Internet as a data packet. TCP header is a most common part of the data packet. In a TCP header there are six reserved bits which remains always unused. In this paper we propose a new approach to enhance the security of hashed passwords by using the six reserved bits of a TCP header. Here we encrypt the hashed password by a random key using simple mathematical function. The information needed to decrypt the encrypted hashed password is carried by the six bits of TCP header.","PeriodicalId":335795,"journal":{"name":"2008 11th International Conference on Computer and Information Technology","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124872121","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}
Shaoning Pang, Tao Ban, Y. Kadobayashi, N. Kasabov
{"title":"gSVMT: Aggregating SVMs over a dynamic grid learned from data","authors":"Shaoning Pang, Tao Ban, Y. Kadobayashi, N. Kasabov","doi":"10.1109/ICCITECHN.2008.4803112","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2008.4803112","url":null,"abstract":"Addressing the problem of adaptively modelling a classifier as a modular system, a new type of SVM aggregating method termed gridding SVM tree (gSVMT) is proposed in this paper. The proposed gSVMT achieves to discover data subregions with principal discriminant knowledge through a recursive SVM-supervised data partitioning procedure. For each subregion, an individual SVM is allocated to extract the subregion knowledge. A set of such SVMs are aggregated in a specific order, resulting in a globally reliable decision rule to predict new coming samples. Experiments on a synthetic Gaussian data set and 13 benchmark machine learning data sets, have highlighted the usability of the gSVMT on its competitive classification capability. In particular, the proposed gSVMT is found to have better generalization performance than SVM classifiers for data sets with high sparseness and/or class-imbalance. Its performance has been further demonstrated with the successful real application on a face membership authentication system.","PeriodicalId":335795,"journal":{"name":"2008 11th International Conference on Computer and Information Technology","volume":"2014 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127456858","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 application program interface for vBulletin","authors":"S.S. Sami, T. Rahman, K. Hasan, J. Siddique","doi":"10.1109/ICCITECHN.2008.4802987","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2008.4802987","url":null,"abstract":"vBullletin Calendar API is built on calendar feature of vBulletin, a commercial Internet forum software produced by Jelsoft Enterprises Ltd. It acts as a remote agent for client applications intended to be developed by third party software developers. Such applications can be Facebook application, desktop application, IRC-bot and mobile applications for instant event notification and reminder. Important notices, announcements posted from departments of educational institutions often do not reach to target people, in time, due to various reasons. In this paper, we have proposed to develop an interface through which individual client applications monitor a common source of notice service center and notify users instantly.","PeriodicalId":335795,"journal":{"name":"2008 11th International Conference on Computer and Information Technology","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121248563","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}
O. Gani, I. Mehedi, M. Seraj, H. Sarwar, C.M. Rahman
{"title":"Prediction of the density of active wireless device using markov model","authors":"O. Gani, I. Mehedi, M. Seraj, H. Sarwar, C.M. Rahman","doi":"10.1109/ICCITECHN.2008.4803085","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2008.4803085","url":null,"abstract":"Location management is one of the key issues in wireless networks to provide an efficient and low-cost service. Realistic modeling of user mobility is a critical research area in wireless network. Mobility data based on real human behaviors may give us the opportunity to improve wireless and Mobile services for users in many ways. At present, several mobility models are proposed based on the analysis of real traces . In this paper, we investigate the feasibility of next state prediction using sequences of previously observed state and analyze the efficiency of MARKOV MODEL . The scenario concerns servicing wireless devices by wireless access point in the Dartmouth college campus over some period of time. The performance of the method has been verified for prediction accuracy. It is found that, on average, the choice of training data leads to prediction accuracy of 78.45%, in some cases the accuracy achieves about 95.55%.","PeriodicalId":335795,"journal":{"name":"2008 11th International Conference on Computer and Information Technology","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123051571","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 intelligent aviation obstruction warning light","authors":"M. Hasan, B. C. Sarker","doi":"10.1109/ICCITECHN.2008.4803099","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2008.4803099","url":null,"abstract":"A scheme for aviation warning light is presented here. Unlike the conventional systems used for this purpose, the system presented here is using intelligent way of sensing daylight sensor fault, intelligent way of sensing light fault, intelligent way of activating standby light in case of the main light fault, ground cable monitoring and responding system with beep for any fault occurs. Microcontroller from 8051 family with tiny operating systems is implemented here for controlling and calculating in a multitasking environment so that the system becomes dependable with advanced feature.","PeriodicalId":335795,"journal":{"name":"2008 11th International Conference on Computer and Information Technology","volume":"92 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114188801","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":"A trust-based distributed data fault detection algorithm for wireless sensor networks","authors":"Z. Taghikhaki, M. Sharifi","doi":"10.1109/ICCITECHN.2008.4803118","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2008.4803118","url":null,"abstract":"Fault detection is a difficult and complex task in WSN because of there are many factors that influence data and could cause faults. Large-scale sensor networks impose energy and communication constraints, thus it is difficult to collect data from each individual sensor node and process it at the sink to detect faulty sensors. The proposed approach saves energy and improves network lifetime by detecting data faults locally in cluster head and therefore reducing the number of transmissions required to convey relevant information to the sink. This paper presents a novel approach for detecting sensors which produce faulty data in a distributed way as well as identifying the type of data faults using trust concepts to gain a high degree of confidence. We validate our method with simulations results.","PeriodicalId":335795,"journal":{"name":"2008 11th International Conference on Computer and Information Technology","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131951294","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":"Learning intrusion detection based on adaptive bayesian algorithm","authors":"D. Farid, M.Z. Rahman","doi":"10.1109/ICCITECHN.2008.4803036","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2008.4803036","url":null,"abstract":"Recent intrusion detection have emerged an important technique for information security systems. Its very important that the security mechanisms for an information system should be designed to prevent unauthorized access of system resources and data. Last few years, many intelligent learning techniques of machine learning applied to the large volumes of complex and dynamic audit data for the construction of efficient intrusion detection systems (IDS). This paper presents, theoretical overview of intrusion detection and a new approach for intrusion detection based on adaptive Bayesian algorithm. This algorithm correctly classify different types of attack of KDD99 benchmark intrusion detection dataset with high detection accuracy in short response time. The experimental result also shows that, this algorithm maximize the detection rate (DR) and minimized the false positive rate (FPR) for intrusion detection.","PeriodicalId":335795,"journal":{"name":"2008 11th International Conference on Computer and Information Technology","volume":"256 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132078897","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 implementation scheme for multidimensional online analytical processing","authors":"N. Easmin, K. Hasan, N. Parvin","doi":"10.1109/ICCITECHN.2008.4802985","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2008.4802985","url":null,"abstract":"Multidimensional online analytical processing (MOLAP) processes data that is already stored in a multidimensional array in which all possible combinations of data are reflected. It employs multidimensional array as their basic data structure. The intent of this paper is to develop a MOLAP model based on the scheme called extended Karnaugh map representation (EKMR) and evaluate it. The basic idea of EKMR scheme is to present multidimensional array by a set of two dimensional arrays. This reduces data access time from secondary storage if the tupple of subscripts are known. Effectiveness of this scheme over traditional multidimensional array is shown with sufficient analysis and experimental results.","PeriodicalId":335795,"journal":{"name":"2008 11th International Conference on Computer and Information Technology","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131393815","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":"A practical analysis of the robustness and stability of the network stack in smartphones","authors":"Sheikh Mahbub Habib, Cyril Jacob, T. Olovsson","doi":"10.1109/ICCITECHN.2008.4803083","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2008.4803083","url":null,"abstract":"Smartphones are widely used nowadays and their popularity will certainly not slow down in the near future due to improved functionality and new technology improvements. Becoming more and more similar to PCs and laptops, they will also begin to face the same security problems especially in terms of network security. In this paper, we provide an overview of security issues for smartphones and give a brief introduction of the network stack architecture of Windows Mobile 5.0 platform in order to motivate and plan for efficient penetration tests against Windows Mobile 5.0 powered smartphones. Furthermore, a number of attacks have been done against different layers of the network stack and a list of supporting penetration tools are provided for interested practitioners. Detailed results are provided from the penetration tests performed which should be very useful for security vendors, researchers and OS vendors to give more attention to security architectures and development of security software (e.g. firewalls, antivirus) for the mobile operating systems. In a whole, robustness and stability will be assessed for the mobile OSs used by the smartphones throughout the paper.","PeriodicalId":335795,"journal":{"name":"2008 11th International Conference on Computer and Information Technology","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115883049","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}