Myeong-Soo Cheong, Byun-Gon Kim, C. Pan, Kyung-Taek Chung, K. Pyun, Sang-Tae Lee, Byoung-Sil Chon
{"title":"A New Packet Marking Scheme for Fairness Improvement of AF Services in DiffServ Network","authors":"Myeong-Soo Cheong, Byun-Gon Kim, C. Pan, Kyung-Taek Chung, K. Pyun, Sang-Tae Lee, Byoung-Sil Chon","doi":"10.1109/ISITC.2007.13","DOIUrl":"https://doi.org/10.1109/ISITC.2007.13","url":null,"abstract":"This paper presents a new scheme based on average transmission rate, using the achieved rate and fairness of each flow to provide fairly marking for Assured Forwarding services in DiffServ network. A record unit and a promotion/demotion probability generator are added to the conventional traffic conditioner. Hence the impacts of Round Trip Time, UDP/TCP interactions, and different target rates can be mitigated effectively by proposed scheme. A simulation and a performance evaluation of the proposed scheme are also presented.","PeriodicalId":394071,"journal":{"name":"2007 International Symposium on Information Technology Convergence (ISITC 2007)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116808288","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}
Gi-Su Heo, Minwoo Kim, Insook Jung, Duk-Ryong Lee, Il-Seok Oh
{"title":"Extraction of Car License Plate Regions Using Line Grouping and Edge Density Methods","authors":"Gi-Su Heo, Minwoo Kim, Insook Jung, Duk-Ryong Lee, Il-Seok Oh","doi":"10.1109/ISITC.2007.49","DOIUrl":"https://doi.org/10.1109/ISITC.2007.49","url":null,"abstract":"In this paper we propose the double chance algorithm as an approach to car license plate extraction. The first algorithm extracts the line segments and groups them based on a set of geometrical conditions. It detects a rectangle at the plate boundary accurately. The second algorithm finds plate regions at which the vertical edges appear densest. We evaluated the double chance framework with and without the verification process. The verification process is performed using the character segmentation module. Using a real-life database collected by the speed enforcement camera, we obtained a high success rate of 99.45%, through use of the double chance approach with verification.","PeriodicalId":394071,"journal":{"name":"2007 International Symposium on Information Technology Convergence (ISITC 2007)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117046858","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":"Design the Time-Interval Based Fairness Partitioning Method in DVE","authors":"Dongkee Won, B. Kim, Seungjong Chung, D. An","doi":"10.1109/ISITC.2007.39","DOIUrl":"https://doi.org/10.1109/ISITC.2007.39","url":null,"abstract":"MMORPGs may involve a great number of concurrent players, and those servers usually have to manage hundred, or even thousands of avatars coexisting in the same virtual world. So if failing to send a command or an event message, or sending it too late may cause damages to the avatar evolution(death, injury, loss of resources), and may result in unjustified penalties for the player. Many policies could be defined to realize a ranking evaluation of available servers. Unfortunately, due to the highly dynamic characteristics of server loads and network performances, any optimal allocation would soon become sub-optimal. In order to solve those problems we propose the \"time-interval based fairness partitioning method\" (TIP). TIP will distribute the avatar to the game server equally in order to avoid the problems form the unfairness of game servers load.","PeriodicalId":394071,"journal":{"name":"2007 International Symposium on Information Technology Convergence (ISITC 2007)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127820228","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":"Artificial Neural Network for Document Classification Using Latent Semantic Indexing","authors":"C. Li, Soon-cheol Park","doi":"10.1109/ISITC.2007.27","DOIUrl":"https://doi.org/10.1109/ISITC.2007.27","url":null,"abstract":"In this study, we construct document classification systems using artificial neural network training by the multi-output perceptron learning algorithm (MOPL) and back-propagation neural network (BPNN). Most classic classification systems represent the contents of documents with a set of index terms, which is termed the vector space model (VSM). However, this method requires a high dimensional space to represent the documents, and it does not take into account the semantic relationship between the terms, which could lead to a poor classification performance. In this paper, we introduce latent semantic indexing (LSI) in our systems. It could not only reduce the dimensionality to a great extent but also determine important associative relationships between the terms. The LSI also aids in accelerating the training speed and improves the classification accuracy. We test our classification systems on the standard Reuter-21578 collection. The experimental evaluations show that the system training with the LSI is considerably faster than the original system training with the VSM and that the former yields better classification results.","PeriodicalId":394071,"journal":{"name":"2007 International Symposium on Information Technology Convergence (ISITC 2007)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128453869","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":"On Fast Hybrid Source Coding Design","authors":"Zhu Chen, M. Lee","doi":"10.1109/ISITC.2007.71","DOIUrl":"https://doi.org/10.1109/ISITC.2007.71","url":null,"abstract":"We address a new representation of DCT/DFT/wavelet matrices via one hybrid architecture. Based on an element inverse matrix factorization algorithm, we show that the DCT, DFT and wavelet which based on Haar matrix have the similar recursive computational pattern, all of them can be decomposed to one orthogonal character matrix and a special sparse matrix. The special sparse matrix belongs to Jacket matrix, whose inverse can be from element-wise inverse or block-wise inverse. Based on this trait, we can develop a fast hybrid DCT/DFT/HWT source coding.","PeriodicalId":394071,"journal":{"name":"2007 International Symposium on Information Technology Convergence (ISITC 2007)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132978205","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":"Mazda - a software for texture analysis","authors":"P. Szczypiński, M. Strzelecki, A. Materka","doi":"10.1109/ISITC.2007.66","DOIUrl":"https://doi.org/10.1109/ISITC.2007.66","url":null,"abstract":"This paper presents MaZda software for quantitative image texture analysis. This software, primarily developed for classification of magnetic resonance images, can be applied for wide class of textured images including color ones and 3D data. It enables estimation of almost 300 texture features; includes procedures for their reduction and classification. Feature clustering is also provided. The software has been developed since 1998. Currently it is a reliable and efficient tool used by many research institutes for different image analysis tasks.","PeriodicalId":394071,"journal":{"name":"2007 International Symposium on Information Technology Convergence (ISITC 2007)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131343189","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 Use of Microscopic Traffic Simulation Model for Traffic Control Systems","authors":"Hwan Chang, Yun Wang, Petros A. Ioannou","doi":"10.1109/ISITC.2007.89","DOIUrl":"https://doi.org/10.1109/ISITC.2007.89","url":null,"abstract":"A highway network model is constructed using a microscopic traffic flow simulation model, VISSIM, and is intended to provide an evaluation environment for advanced traffic control systems. Since the microscopic traffic flow simulation model can capture a greater level of details of the network, it can closely evaluate the effectiveness and robustness of a controller in a real transportation network before an actual implementation. The highway stretch is based on the Berkeley Highway Laboratory (BHL) and is validated with field data. The validation results show that the model properly captures the congestion characteristics of the BHL section. Also, based on the validated model, critical densities and other traffic flow characteristics in mixed manual and ACC (Adaptive Cruise Control) traffics are estimated.","PeriodicalId":394071,"journal":{"name":"2007 International Symposium on Information Technology Convergence (ISITC 2007)","volume":"32 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131590858","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 Application of Levenberg-Marquardt Algorithm in On-Line Monitoring for XLPE Cables","authors":"Jiantao Sun, X. Wen","doi":"10.1109/ISITC.2007.87","DOIUrl":"https://doi.org/10.1109/ISITC.2007.87","url":null,"abstract":"The insulation condition of XLPE cables could be evaluated comprehensively by its working insulation resistance, equivalent capacitance and dielectric loss factor. To calculate the three parameters precisely, an improved data processing method was presented, in which the nonlinear least-squares fitting algorithm was utilized based on Levenberg-Marquardt algorithm that took the results of fast Fourier transform as the initial value for iteration. The parameters of fundamental component were extracted from the sampled signals quickly, and the influences caused by the frequency fluctuation, harmonic content and direct current content were restrained well using this method. The simulation results were given to show the effectiveness of this method. The reliability of on-line monitoring could be promoted.","PeriodicalId":394071,"journal":{"name":"2007 International Symposium on Information Technology Convergence (ISITC 2007)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116006901","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":"Jacket Matrix Construction Using M-Sequences","authors":"Yuri L. Borissov, M. Lee, S. P. Balakannan","doi":"10.1109/ISITC.2007.62","DOIUrl":"https://doi.org/10.1109/ISITC.2007.62","url":null,"abstract":"We propose a construction of Jacket matrices based on additive characters of the finite field Fq and q-ary m-sequences. This approach is a generalization of method of obtaining Hadamard matrices from binary PN-sequences.","PeriodicalId":394071,"journal":{"name":"2007 International Symposium on Information Technology Convergence (ISITC 2007)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123338202","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 Type 2 Diabetic Patient Management System Using Evolutionary Computation and FCM Algorithm","authors":"Eungyeong Kim, M. Lee, Hyogun Yoon, T. Gatton","doi":"10.1109/ISITC.2007.25","DOIUrl":"https://doi.org/10.1109/ISITC.2007.25","url":null,"abstract":"The present study proposes a management system combining fuzzy c-means (FCM) and evolutionary computation in order to provide an optimal treatment method based on the patient's context information in ubiquitous environment. Because FCM has the shortcoming of falling easily into a local solution, we adjusted the initial values sensitively through evolutionary computation. In fitness evaluation, we used Bayesian validation so that superior solutions are selected, and in performance evaluation, experiment and evaluation were made with type 2 diabetic patients.","PeriodicalId":394071,"journal":{"name":"2007 International Symposium on Information Technology Convergence (ISITC 2007)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123443052","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}