Recently, 3D laser scanning is getting great interest for its relevant simplicity and speed. However, the output of 3D laser scanner is characterized as sub-randomly distributed 3D point clouds, the information associated with the object structure cannot be extracted directly. In this paper, a surface segmentation algorithm based on region dilation strategy for 3D laser scanning data is proposed. A Roland LPX-250 3D laser scanner is used in our experiment and the results show that this algorithm works well on various types of 3D laser scanning data.
{"title":"3D Laser Scanning Data Segmentation Based on Region Dilation Strategy","authors":"Meng Li, P. Fu, Shenghe Sun","doi":"10.1109/HIS.2009.68","DOIUrl":"https://doi.org/10.1109/HIS.2009.68","url":null,"abstract":"Recently, 3D laser scanning is getting great interest for its relevant simplicity and speed. However, the output of 3D laser scanner is characterized as sub-randomly distributed 3D point clouds, the information associated with the object structure cannot be extracted directly. In this paper, a surface segmentation algorithm based on region dilation strategy for 3D laser scanning data is proposed. A Roland LPX-250 3D laser scanner is used in our experiment and the results show that this algorithm works well on various types of 3D laser scanning data.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128434045","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}
To overcome the intrinsic weaknesses of conventional back-propagation (BP) neural networks, a novel type of feed-forward neural network is constructed in this paper, which adopts a three-layer structure but with the hidden-layer neurons activated by a group of Euler polynomials. A weights-direct-determination (WDD) method is thus able to be derived for it, which obtains the optimal weights of the neural network directly (i.e., just in one step). Furthermore, a structure-automatic-determination (SAD) algorithm is presented to determine the optimal number of hidden-layer neurons of the Euler neural network (ENN). Computer-simulations substantiate the efficacy of such a Euler neural network with its WDD and SAD algorithms.
{"title":"Euler Neural Network with Its Weight-Direct-Determination and Structure-Automatic-Determination Algorithms","authors":"Yunong Zhang, Lingfeng Li, Yiwen Yang, Gongqin Ruan","doi":"10.1109/HIS.2009.278","DOIUrl":"https://doi.org/10.1109/HIS.2009.278","url":null,"abstract":"To overcome the intrinsic weaknesses of conventional back-propagation (BP) neural networks, a novel type of feed-forward neural network is constructed in this paper, which adopts a three-layer structure but with the hidden-layer neurons activated by a group of Euler polynomials. A weights-direct-determination (WDD) method is thus able to be derived for it, which obtains the optimal weights of the neural network directly (i.e., just in one step). Furthermore, a structure-automatic-determination (SAD) algorithm is presented to determine the optimal number of hidden-layer neurons of the Euler neural network (ENN). Computer-simulations substantiate the efficacy of such a Euler neural network with its WDD and SAD algorithms.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129304324","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}
Sayan Ghosh, Debarati Kundu, K. Suresh, Swagatam Das, A. Abraham, B. K. Panigrahi, V. Snás̃el
Particle Swarm Optimization (PSO) is arguably one of the most popular nature- inspired algorithms for real parameter optimization at present. The existing theoretical research on PSO is mostly based on the gbest (global best) particle topology, which usually is susceptible to false or premature convergence over multi-modal fitness landscapes. The present standard PSO (SPSO 2007) uses an lbest (local best) topology where a particle is stochastically attracted not towards the best position found in the entire swarm, but towards the best position found by any particle in its topological neighborhood. This paper presents a first step towards a probabilistic analysis of the lbest PSO with variable random neighborhood topology by addressing issues like inter-particle interaction and probabilities of selection based on particle ranks.
{"title":"On Some Properties of the lbest Topology in Particle Swarm Optimization","authors":"Sayan Ghosh, Debarati Kundu, K. Suresh, Swagatam Das, A. Abraham, B. K. Panigrahi, V. Snás̃el","doi":"10.1109/HIS.2009.288","DOIUrl":"https://doi.org/10.1109/HIS.2009.288","url":null,"abstract":"Particle Swarm Optimization (PSO) is arguably one of the most popular nature- inspired algorithms for real parameter optimization at present. The existing theoretical research on PSO is mostly based on the gbest (global best) particle topology, which usually is susceptible to false or premature convergence over multi-modal fitness landscapes. The present standard PSO (SPSO 2007) uses an lbest (local best) topology where a particle is stochastically attracted not towards the best position found in the entire swarm, but towards the best position found by any particle in its topological neighborhood. This paper presents a first step towards a probabilistic analysis of the lbest PSO with variable random neighborhood topology by addressing issues like inter-particle interaction and probabilities of selection based on particle ranks.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130343816","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}
Prostate hyperplasia is usually found affecting male adults in developed countries. Transrectal ultrasoundgraphy (TRUS) imaging is widely used to diagnose prostate disease. Ultrasonic images are often argued with their primitive echo perturbations and speckle noise, which may confuse the physicians in inspection. Therefore, in this paper, we propose an automatic prostate segmentation system in TRUS images. The automatic segmentation system utilizes a prostate classifier which consists of Validation Incremental Neural Network and Radial-Basis Function Neural Networks for prostate segmentation. Experimental results show that the proposed method has higher accuracy than Active Contour Model (ACM).
{"title":"Integrating the Validation Incremental Neural Network and Radial-Basis Function Neural Network for Segmenting Prostate in Ultrasound Images","authors":"Chuan-Yu Chang, Yi-Lian Wu, Y. Tsai","doi":"10.1109/HIS.2009.47","DOIUrl":"https://doi.org/10.1109/HIS.2009.47","url":null,"abstract":"Prostate hyperplasia is usually found affecting male adults in developed countries. Transrectal ultrasoundgraphy (TRUS) imaging is widely used to diagnose prostate disease. Ultrasonic images are often argued with their primitive echo perturbations and speckle noise, which may confuse the physicians in inspection. Therefore, in this paper, we propose an automatic prostate segmentation system in TRUS images. The automatic segmentation system utilizes a prostate classifier which consists of Validation Incremental Neural Network and Radial-Basis Function Neural Networks for prostate segmentation. Experimental results show that the proposed method has higher accuracy than Active Contour Model (ACM).","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129239551","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}
Automatic network topology discovery is important for network management and network analysis in ITSM system. Issues like network environment configuration, performance testing and fault detecting all require accurate information of the network topology. According to the requirement of the ITSM system, in this paper we propose an efficient algorithm that is based on SNMP for discovering Layer 3 and Layer 2 topology of the network. The proposed algorithm only requires SNMP to be enabled on routers and managed switches. For Layer 3 topology discovery, this paper proposes a shared subnet based approach to analyze connections between routers. In addition, the algorithm uses a STP based method to discover Layer 2 topology, which does not require the completeness of switch’s AFT information. The algorithm has been implemented and tested in several enterprise-level networks, and the results demonstrate that it discovers the network topology accurately and efficiently.
{"title":"Research and Application on Automatic Network Topology Discovery in ITSM System","authors":"Yide Wang, Dancheng Li, Chunyan Han, Zhiliang Zhu","doi":"10.1109/HIS.2009.180","DOIUrl":"https://doi.org/10.1109/HIS.2009.180","url":null,"abstract":"Automatic network topology discovery is important for network management and network analysis in ITSM system. Issues like network environment configuration, performance testing and fault detecting all require accurate information of the network topology. According to the requirement of the ITSM system, in this paper we propose an efficient algorithm that is based on SNMP for discovering Layer 3 and Layer 2 topology of the network. The proposed algorithm only requires SNMP to be enabled on routers and managed switches. For Layer 3 topology discovery, this paper proposes a shared subnet based approach to analyze connections between routers. In addition, the algorithm uses a STP based method to discover Layer 2 topology, which does not require the completeness of switch’s AFT information. The algorithm has been implemented and tested in several enterprise-level networks, and the results demonstrate that it discovers the network topology accurately and efficiently.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121409258","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}
The inadaptability of the existing network management protocol for the space network environment is analyzed in the paper. A new Spaces Network Management Protocol SP-SNMP is proposed and in which SER, the polling based on MIB and table operation protocol message used are detailed introduced, and conversion gateway is designed for different protocols. At last the performance of the protocol is tested in the simulation platform. Test results show that SP-SNMP with the short PDU length and high management operation efficiency is suitable for the high-delay and the limited bandwidth space networks.
{"title":"Design and Emulation of Space Simple Network Management Protocol","authors":"Yueqiu Jiang, Daozhu Zhang, Wenbo Zhang, Sun Kun","doi":"10.1109/HIS.2009.174","DOIUrl":"https://doi.org/10.1109/HIS.2009.174","url":null,"abstract":"The inadaptability of the existing network management protocol for the space network environment is analyzed in the paper. A new Spaces Network Management Protocol SP-SNMP is proposed and in which SER, the polling based on MIB and table operation protocol message used are detailed introduced, and conversion gateway is designed for different protocols. At last the performance of the protocol is tested in the simulation platform. Test results show that SP-SNMP with the short PDU length and high management operation efficiency is suitable for the high-delay and the limited bandwidth space networks.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114100915","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}
Ontology is applied to a real-world web intelligent question answering system in PC troubleshooting domain as an improvement, so semantic relations need to be extracted to construct ontology semi-automatically. The paper mainly pays attention to "product-trouble" relation and "product-attribute" relation. A two stage semantic relation extraction method is proposed. In stage one, relation identification is executed to produce high-precision relations instance as the seed for next stage; stage two is the actual relation extraction process, the related terms which describe troubleshooting information and attribute information are extracted based on association rules, then the terms is clustered to find target semantic relation. The relation extraction integrated the advantage of pattern-based and clustering-based methods. The experimental results show it is superior to individual pattern-based and clustering-based methods in precision and recall.
{"title":"Two Stage Semantic Relation Extraction","authors":"Jibin Fu, Xiaozhong Fan, Jintao Mao, Xiaoming Liu","doi":"10.1109/HIS.2009.71","DOIUrl":"https://doi.org/10.1109/HIS.2009.71","url":null,"abstract":"Ontology is applied to a real-world web intelligent question answering system in PC troubleshooting domain as an improvement, so semantic relations need to be extracted to construct ontology semi-automatically. The paper mainly pays attention to \"product-trouble\" relation and \"product-attribute\" relation. A two stage semantic relation extraction method is proposed. In stage one, relation identification is executed to produce high-precision relations instance as the seed for next stage; stage two is the actual relation extraction process, the related terms which describe troubleshooting information and attribute information are extracted based on association rules, then the terms is clustered to find target semantic relation. The relation extraction integrated the advantage of pattern-based and clustering-based methods. The experimental results show it is superior to individual pattern-based and clustering-based methods in precision and recall.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121655559","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}
In the competitive electricity market environment, the bidding strategy of the generation companies(GenCos) is made based on the incomplete information. Thus, risk will be introduced inevitably. In this paper, a new risk evaluation method is presented considering fuzzy uncertainty of GenCos’ competitive bidding behaviors, the creditability of the real profit less than the fuzzy expected profit is taken as risk index.On this basis, the chance-constrained programming model of the GenCos’ optimal bidding strategy is presented. A hybrid intelligent algorithm of fuzzy simulation and neural network combined with GA is used to solve this problem. In the chance constrained programming model the object function and the chance-constrained formulas are uncertain functions, therefore the fuzzy simulation technique is used to obtain the function value and neural network is used to approach the uncertain function. In the end the feasibility of the model and solving method is tested by an IEEE-5 system case.
{"title":"Study on Generation Companies' Bidding Strategy Based on Hybrid Intelligent Method","authors":"H. Da-wei, Han Xue-shan","doi":"10.1109/HIS.2009.295","DOIUrl":"https://doi.org/10.1109/HIS.2009.295","url":null,"abstract":"In the competitive electricity market environment, the bidding strategy of the generation companies(GenCos) is made based on the incomplete information. Thus, risk will be introduced inevitably. In this paper, a new risk evaluation method is presented considering fuzzy uncertainty of GenCos’ competitive bidding behaviors, the creditability of the real profit less than the fuzzy expected profit is taken as risk index.On this basis, the chance-constrained programming model of the GenCos’ optimal bidding strategy is presented. A hybrid intelligent algorithm of fuzzy simulation and neural network combined with GA is used to solve this problem. In the chance constrained programming model the object function and the chance-constrained formulas are uncertain functions, therefore the fuzzy simulation technique is used to obtain the function value and neural network is used to approach the uncertain function. In the end the feasibility of the model and solving method is tested by an IEEE-5 system case.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"3 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113965649","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}
With the extensive applications of IT and network, the information, especially those considered useless in the past is likely to exert its enormous potential value by Information Lifecycle Management. This paper analyzes the meaning of Information Lifecycle Management and the basic theory of Enterprise Architecture and then put forward the enterprise’ model of Information Lifecycle Management based on Enterprise Architecture. In the model, three different dimensionalities are described in detail: information lifecycle, information application and enterprise architecture. The idea of the article will have a certain referential significance for Information Lifecycle Management.
{"title":"Research on the Enterprise' Model of Information Lifecycle Management Based on Enterprise Architecture","authors":"Huiyan Liu, Xueying Wang, Qizhe Quan","doi":"10.1109/HIS.2009.246","DOIUrl":"https://doi.org/10.1109/HIS.2009.246","url":null,"abstract":"With the extensive applications of IT and network, the information, especially those considered useless in the past is likely to exert its enormous potential value by Information Lifecycle Management. This paper analyzes the meaning of Information Lifecycle Management and the basic theory of Enterprise Architecture and then put forward the enterprise’ model of Information Lifecycle Management based on Enterprise Architecture. In the model, three different dimensionalities are described in detail: information lifecycle, information application and enterprise architecture. The idea of the article will have a certain referential significance for Information Lifecycle Management.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124535031","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}
Since their appearance in 1993, first approaching the Shannon limit, turbo codes gave a new direction in the channel encoding field, especially since they have been adopted for multiple telecommunication norms. To obtain good performance, it is necessary to design a robust turbo code interleaver. This paper proposes a a differential evolution approach to find above average turbo code interleavers. Performance is compared with the conventional genetic algorithm approach and the empirical results illustrate that DE performs well.
{"title":"Optimization of Turbo Codes by Differential Evolution and Genetic Algorithms","authors":"P. Krömer, V. Snás̃el, J. Platoš, A. Abraham","doi":"10.1109/HIS.2009.289","DOIUrl":"https://doi.org/10.1109/HIS.2009.289","url":null,"abstract":"Since their appearance in 1993, first approaching the Shannon limit, turbo codes gave a new direction in the channel encoding field, especially since they have been adopted for multiple telecommunication norms. To obtain good performance, it is necessary to design a robust turbo code interleaver. This paper proposes a a differential evolution approach to find above average turbo code interleavers. Performance is compared with the conventional genetic algorithm approach and the empirical results illustrate that DE performs well.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127633801","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：