{"title":"Real-time Image Processing by Cellular Neural Network Using Reaction-Diffusion Model","authors":"Pham Hong Long, P. T. Cat","doi":"10.1109/KSE.2009.35","DOIUrl":"https://doi.org/10.1109/KSE.2009.35","url":null,"abstract":"In this paper we propose two architectures of Cellular Neural Network (CNN) for edge detection and segmentation of noisy image based on FitzHugh-Nagumo reaction-diffusion equation. These networks give better results compare to other methods and are capable to real-time applications due to parallel processing nature of the CNN. The mathematical description and nonlinear phenomena analysis of the FitzHugh-Nagumo reaction-diffusion equation are given to show its operating principle in edge detection and segmentation. The method to define the templates of these CNNs is presented and we also give some Matlab simulations to demonstrate the effectiveness of the proposed method","PeriodicalId":347175,"journal":{"name":"2009 International Conference on Knowledge and Systems Engineering","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130865405","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":"Performance Comparison of Register Allocation Algorithms in Dynamic Binary Translation","authors":"Zhanju Cai, Alei Liang, Zhengwei Qi, Lingyan Jiang, Xiaolong Li, Haibing Guan, Ying Chen","doi":"10.1109/KSE.2009.16","DOIUrl":"https://doi.org/10.1109/KSE.2009.16","url":null,"abstract":"This paper presents performance comparison of register allocation algorithms in DBT (Dynamic Binary Translation). A group of register allocation algorithms including SRA(Simple Register Allocation), GRA(Global Register Allocation), NRA(Next-use Register Allocation) and SGRA(Simplified Graph-coloring Register Allocation) are implemented in a DBT system and evaluated. SGRA is a simplified version of graph-coloring register allocation method proposed by us. NRA and GRA are also an optimization versions based on the target platform. From the experimental result, SGRA has the best performance on all the six programs chosen from SPEC CINT2000. The improvement of SGRA is 7.3% on average over SRA. And based on comparison of the performance of DBT system with super block technique switching on or off, we find SGRA has better performance in big allocation scope, such as super blocks and traces.","PeriodicalId":347175,"journal":{"name":"2009 International Conference on Knowledge and Systems Engineering","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114070082","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 Vietnamese Question Answering System","authors":"D. Q. Nguyen, Dat Quoc Nguyen, S. Pham","doi":"10.1109/KSE.2009.42","DOIUrl":"https://doi.org/10.1109/KSE.2009.42","url":null,"abstract":"Question answering systems aim to produce exact answers to users' questions instead of a list of related documents as used by current search engines. In this paper, we propose an ontology-based Vietnamese question answering system that allows users to express their questions in natural language. To the best of our knowledge, this is the first attempt to enable users to query an ontological knowledge base using Vietnamese natural language. Experiments of our system on an organizational ontology show promising results.","PeriodicalId":347175,"journal":{"name":"2009 International Conference on Knowledge and Systems Engineering","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124563624","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":"Spatial Dilemma Strategies of Intelligent Agents: Coalition Formation in Environmental Game","authors":"D. Nguyen, Y. Ishida","doi":"10.1109/KSE.2009.30","DOIUrl":"https://doi.org/10.1109/KSE.2009.30","url":null,"abstract":"When agents are uncertain about actions or strategies of their potential neighbors, coalition formation for the environmental problem is a critical one. We use spatial strategies of spatial prisoner's dilemma to model for this problem when coalitions are formed. Our model allows agents not only to follow their major but also to choose suitable decisions by themselves. However, there are specific strategies interacting between a numbers of decision-makers.","PeriodicalId":347175,"journal":{"name":"2009 International Conference on Knowledge and Systems Engineering","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131831793","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":"Detecting Probable Regions of Humans in Still Images Using Raw Edges","authors":"Trung Tran Ngoc, Phong Vo Dinh, Bac Le Hoai","doi":"10.1109/KSE.2009.14","DOIUrl":"https://doi.org/10.1109/KSE.2009.14","url":null,"abstract":"Human detection remains a challenge in computer vision due to highly articulated body postures, viewpoints changes, varying illumination conditions and cluttered background. Because of these difficulties, most of the previous publications often focus only on low-articulated postures, e.g. pedestrians, in still images. In this paper, we propose a new method to detect a human region from still images using raw edges. Not exhaustively detecting all of people occurrences in images; nevertheless; our approach can perform significantly on many types of images, typically, sports images with various poses. Instead of sliding window-style approaches for detecting, we rely on characteristics of boundaries and interest points by combining several image-processing techniques such as image filter, image segmentation, edge detection…Afterward, we use K-mean algorithm and probability for choosing a human region. Especially, we do not need a training phase. Despite not being the same purpose on detecting domain to previous works, in certain degrees, we also try to compete to typical works. Two challenging datasets are involved in discovering interesting facts needed to be concerned when designing proposed method for detecting people.","PeriodicalId":347175,"journal":{"name":"2009 International Conference on Knowledge and Systems Engineering","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121945809","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 Three-tier Structured Model of Overlay Networks","authors":"Mei Wu, Chanle Wu, M. Collier","doi":"10.1109/KSE.2009.26","DOIUrl":"https://doi.org/10.1109/KSE.2009.26","url":null,"abstract":"One of the open research problems in the area of overlay networks is the creation of an adequate network topology and a proper network model. Current models mainly focus on traffic demands and loads between the nodes. However it is more challenging to find a model which supports scalability, adaptability and robustness in a heterogeneous environment. We introduce a new three-tier model based on regular-graph theory called STree and its two-stage joining mechanism. We compare STree with other models such as NICE, DTree and HMRB. Our results suggest that STree is a robust and scalable model for overlay networks in large, dynamic and heterogeneous environments.","PeriodicalId":347175,"journal":{"name":"2009 International Conference on Knowledge and Systems Engineering","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127486986","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":"Heuristic Revision by Heuristic Space Exploration","authors":"P. Taillandier","doi":"10.1109/KSE.2009.31","DOIUrl":"https://doi.org/10.1109/KSE.2009.31","url":null,"abstract":"Heuristics are often used to solve complex problems. Indeed, such problem-specific knowledge, when pertinent, helps to efficiency find good solutions to complex problems. Unfortunately, acquiring and maintaining a heuristic set can be fastidious. In order to face this problem, a approach consists in revising the heuristic sets by means of experiments. In this paper, we are interested in a specific revision method of this type based on the exploration of the heuristic space. The principle of this method is to revise the heuristic set by searching among all possible heuristics the ones that maximize an evaluation function. In this context, we propose a revision approach, dedicated to heuristics represented by production rules, based on the reduction of the search space and on a filtered local search. We present an experiment we carried out in an application domain where heuristics are widely used: cartographic generalization.","PeriodicalId":347175,"journal":{"name":"2009 International Conference on Knowledge and Systems Engineering","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126740371","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}
Nguyen Thi Huong Thao, N. Thai, Nguyen Le Minh, Hà Quang Thụy
{"title":"Vietnamese Noun Phrase Chunking Based on Conditional Random Fields","authors":"Nguyen Thi Huong Thao, N. Thai, Nguyen Le Minh, Hà Quang Thụy","doi":"10.1109/KSE.2009.43","DOIUrl":"https://doi.org/10.1109/KSE.2009.43","url":null,"abstract":"Noun phrase chunking is an important and useful task in many natural language processing applications. It is studied well for English, however with Vietnamese it is still an open problem. This paper presents a Vietnamese Noun Phrase chunking approach based on Conditional random fields (CRFs) models. We also describe a method to build Vietnamese corpus from a set of hand annotated sentences. For evaluation, we perform several experiments using different feature settings. Outcome results on our corpus show a high performance with the average of recall and precision 82.72% and 82.62% respectively.","PeriodicalId":347175,"journal":{"name":"2009 International Conference on Knowledge and Systems Engineering","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115618427","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 Extreme Algorithm for Network-Topology Construction Based on Constrained Delaunay Triangulation","authors":"N. M. Nam, Le Bac, Nguyen Vinh Nam","doi":"10.1109/KSE.2009.37","DOIUrl":"https://doi.org/10.1109/KSE.2009.37","url":null,"abstract":"This paper presents a fast algorithm for network topology construction. The algorithm works in two phases: input analyzing, and topology construction. In the first phase,inconsistencies in input are solved based on constrained Delaunay triangulation. The second phase consists of two parts:the sorting edges construction, and establish the topology relationship. The time of the first part highly depends on the input data distribution, and the second part, which presents our solution, runs in O(NlogN), what is confirmed by experiments using real data from geographic database.","PeriodicalId":347175,"journal":{"name":"2009 International Conference on Knowledge and Systems Engineering","volume":"357 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122807077","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}
Philip H. P. Nguyen, K. Kaneiwa, D. Corbett, Minh-Quang Nguyen
{"title":"Representing Event Assertions in an Upper Event Ontology","authors":"Philip H. P. Nguyen, K. Kaneiwa, D. Corbett, Minh-Quang Nguyen","doi":"10.1109/KSE.2009.18","DOIUrl":"https://doi.org/10.1109/KSE.2009.18","url":null,"abstract":"This paper presents an upper event ontology under Conceptual Structure Theory with an emphasis on formalizing the event relation type hierarchy of the ontology to enable representation and classification of event assertions. The proposed ontology essentially consists of an event type hierarchy created from basic event assertions, an event relation type hierarchy built from predicates on event types and other formal relationships between these structures. Representation of event assertions enables inference on events, which can be used in the Semantic Web for automated inference and query answering.","PeriodicalId":347175,"journal":{"name":"2009 International Conference on Knowledge and Systems Engineering","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121525032","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}