Quan Zhang, Xiaoying Tai, Yi-hong Dong, Shanliang Pan, Xin Luo, K. Kita
Based on the analysis of endoscope image, in this paper, a new color quantification method is proposed to extract improved CCV and the V component shape invariant moment achieving image feature base. Inspiring from general information searching, the two-level content-based endoscope image retrieval is represented using the improved CCV and V component shape invariant moment guaranteeing the first retrieval recall. Experiments prove the efficiency of these methods.
{"title":"Two-Level Content-Based Endoscope Image Retrieval","authors":"Quan Zhang, Xiaoying Tai, Yi-hong Dong, Shanliang Pan, Xin Luo, K. Kita","doi":"10.1109/ICNC.2008.502","DOIUrl":"https://doi.org/10.1109/ICNC.2008.502","url":null,"abstract":"Based on the analysis of endoscope image, in this paper, a new color quantification method is proposed to extract improved CCV and the V component shape invariant moment achieving image feature base. Inspiring from general information searching, the two-level content-based endoscope image retrieval is represented using the improved CCV and V component shape invariant moment guaranteeing the first retrieval recall. Experiments prove the efficiency of these methods.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85824524","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}
Sensory Engineering (SE) was applied in fashion industry for market exploring, consumer behavior evaluation and personalized product designing. The consumer perceptions on products were investigated and analyzed. The fashion sensory data were established for style, color, image according to the results of investigation and analysis. The expert systems based on fuzzy set theory was developed to describe the sensory on clothing in accordance with professional knowledge and consumer preference. The established expert system could be applied for product designing and fashion trends tracing in garment industry. The example was presented for fuzzy logic method application on separating and describing sensory data of fashion products.
{"title":"Formalization of Fashion Sensory Data Based on Fuzzy Set Theory","authors":"Lichuan Wang, Yan Chen, Y. Wang","doi":"10.1109/ICNC.2008.907","DOIUrl":"https://doi.org/10.1109/ICNC.2008.907","url":null,"abstract":"Sensory Engineering (SE) was applied in fashion industry for market exploring, consumer behavior evaluation and personalized product designing. The consumer perceptions on products were investigated and analyzed. The fashion sensory data were established for style, color, image according to the results of investigation and analysis. The expert systems based on fuzzy set theory was developed to describe the sensory on clothing in accordance with professional knowledge and consumer preference. The established expert system could be applied for product designing and fashion trends tracing in garment industry. The example was presented for fuzzy logic method application on separating and describing sensory data of fashion products.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73502745","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}
Lei Wang, Shen Huang, Shijin Wang, Jiaen Liang, Bo Xu
Although researchers have made great progresses on music genre classification in recent years, the need for more accurate system is still not satisfied. In this paper, we propose a method for further reducing the classification error rate based on multiple classifier fusion. First of all, MFCCs and four features from MPEG-7 audio descriptor are extracted in every short time frame, and then a group of frames are gathered into a longer segment, in which mean and variance of these short time frames features are calculated. The segment is considered as the basic unit for training and testing module. Then random forest (RF) and multilayer perceptron neural network (MLP) are executed on such segment independently. Finally, a weighted voting fusion strategy is employed to fusion the result of the two classifiers on each segment, and the whole file decision is made by selecting the most frequently labeled genre over all the segments. Experiments showed that the approach is effective. The fusion result gets 12.4% relative reduction in error rate compared to our baseline system.
{"title":"Music Genre Classification Based on Multiple Classifier Fusion","authors":"Lei Wang, Shen Huang, Shijin Wang, Jiaen Liang, Bo Xu","doi":"10.1109/ICNC.2008.815","DOIUrl":"https://doi.org/10.1109/ICNC.2008.815","url":null,"abstract":"Although researchers have made great progresses on music genre classification in recent years, the need for more accurate system is still not satisfied. In this paper, we propose a method for further reducing the classification error rate based on multiple classifier fusion. First of all, MFCCs and four features from MPEG-7 audio descriptor are extracted in every short time frame, and then a group of frames are gathered into a longer segment, in which mean and variance of these short time frames features are calculated. The segment is considered as the basic unit for training and testing module. Then random forest (RF) and multilayer perceptron neural network (MLP) are executed on such segment independently. Finally, a weighted voting fusion strategy is employed to fusion the result of the two classifiers on each segment, and the whole file decision is made by selecting the most frequently labeled genre over all the segments. Experiments showed that the approach is effective. The fusion result gets 12.4% relative reduction in error rate compared to our baseline system.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73740577","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 paper aims to present a globally exponential synchronization and parameter regulation scheme for a class of time-varying neural networks, which covers the Hopfield neural networks and cellular neural networks. By combining the adaptive control method and the Razumikhin-type theorem, a delay-independent and decentralized linear-feedback control with appropriate updated law is designed to achieve the globally exponential synchronization. The regulating law of parameters can be directly constructed. Hopfield neural networks with time-varying delays is given to show the effectiveness of the presented synchronization scheme.
{"title":"Globally Exponential Synchronization and Parameter Regulation of Chaotic Neural Networks with Time-Varying Delays via Adaptive Control","authors":"Zhongsheng Wang, Dan Xiang, Nin Yan","doi":"10.1109/ICNC.2008.32","DOIUrl":"https://doi.org/10.1109/ICNC.2008.32","url":null,"abstract":"The paper aims to present a globally exponential synchronization and parameter regulation scheme for a class of time-varying neural networks, which covers the Hopfield neural networks and cellular neural networks. By combining the adaptive control method and the Razumikhin-type theorem, a delay-independent and decentralized linear-feedback control with appropriate updated law is designed to achieve the globally exponential synchronization. The regulating law of parameters can be directly constructed. Hopfield neural networks with time-varying delays is given to show the effectiveness of the presented synchronization scheme.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74295362","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}
During the past few years, semi-supervised learning has become a hot topic in machine learning and data mining, since manually labeling training examples is a tedious, error prone and time-consuming task in many practical applications. As one of the most predominant semi-supervised learning algorithms, co-training has drawn much attention and shown its superiority in many applications. So far, there have been a variety of variants of co-training algorithms aiming to settle practical problems. In order to launch an effective co-training process, these variants as a whole create their diversities in four different ways, i.e. two-view level, underlying classifiers level, datasets level and active learning level. This paper gives a review on co-training style algorithms just from this view and presents typical examples and analysis for each level respectively.
{"title":"On Co-Training Style Algorithms","authors":"Cailing Dong, Yilong Yin, X. Guo, Gongping Yang, Guang-Tong Zhou","doi":"10.1109/ICNC.2008.874","DOIUrl":"https://doi.org/10.1109/ICNC.2008.874","url":null,"abstract":"During the past few years, semi-supervised learning has become a hot topic in machine learning and data mining, since manually labeling training examples is a tedious, error prone and time-consuming task in many practical applications. As one of the most predominant semi-supervised learning algorithms, co-training has drawn much attention and shown its superiority in many applications. So far, there have been a variety of variants of co-training algorithms aiming to settle practical problems. In order to launch an effective co-training process, these variants as a whole create their diversities in four different ways, i.e. two-view level, underlying classifiers level, datasets level and active learning level. This paper gives a review on co-training style algorithms just from this view and presents typical examples and analysis for each level respectively.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75777292","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}
Based on the understanding of the ecology, with the theoretical knowledge of the ecology take an analysis on the population of network social, the main use of the method to measure diversity on the network social stocks of the community, through analysis of the cluster species of the network society so that we can make a clear understanding on society virtual community Stocks division and define, then believe that this method for studying network society have certain merits.
{"title":"Diversity Measurement Research on Cluster Species of Network Society","authors":"Honglu Liu, Jia-wei Zuo, Zhen-ji Zhang, R. Zhang","doi":"10.1109/ICNC.2008.485","DOIUrl":"https://doi.org/10.1109/ICNC.2008.485","url":null,"abstract":"Based on the understanding of the ecology, with the theoretical knowledge of the ecology take an analysis on the population of network social, the main use of the method to measure diversity on the network social stocks of the community, through analysis of the cluster species of the network society so that we can make a clear understanding on society virtual community Stocks division and define, then believe that this method for studying network society have certain merits.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74474212","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}
Existing search algorithms for peer to peer networks are based on broadcast of query messages over the relationship connectivity among nodes in the network. In this paper, we describes our research effort to design and implement an agent based adaptive search algorithm that allows for searching in distributed systems. Autonomous adaptive agents are modeled after several ecological concepts and mechanisms. We focus on the problem of actively changing the topology of the peer to peer network by utilizing Schelling's segregation model to improve the efficiency of search. Our simulation results show that the proposed algorithm is scalable and robust to dynamic changes in a network.
{"title":"An Adaptive Search Algorithm for Distributed Systems","authors":"L. Sa, L. Shang, Jun Hou","doi":"10.1109/ICNC.2008.801","DOIUrl":"https://doi.org/10.1109/ICNC.2008.801","url":null,"abstract":"Existing search algorithms for peer to peer networks are based on broadcast of query messages over the relationship connectivity among nodes in the network. In this paper, we describes our research effort to design and implement an agent based adaptive search algorithm that allows for searching in distributed systems. Autonomous adaptive agents are modeled after several ecological concepts and mechanisms. We focus on the problem of actively changing the topology of the peer to peer network by utilizing Schelling's segregation model to improve the efficiency of search. Our simulation results show that the proposed algorithm is scalable and robust to dynamic changes in a network.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74509018","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 this paper, we prove that there exists a subsystem of a one-sided symbolic space with two symbols such that the set-valued map on it is topologically ergodic, topologically double ergodic, topologically transitive and topologically weakly mixing.
{"title":"Topological Ergodicity and Mixing for a Class of Set-Valued Discrete Dynamical System","authors":"Lidong Wang, Guifeng Huang, Shiu-wai. Tang, Zhizhi Chen","doi":"10.1109/ICNC.2008.527","DOIUrl":"https://doi.org/10.1109/ICNC.2008.527","url":null,"abstract":"In this paper, we prove that there exists a subsystem of a one-sided symbolic space with two symbols such that the set-valued map on it is topologically ergodic, topologically double ergodic, topologically transitive and topologically weakly mixing.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74615669","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}
Based on artificial immune theory, a new model of active defense for analyzing the network intrusion is presented. Dynamically evaluative equations for self, antigen, immune tolerance, mature-lymphocyte lifecycle and immune memory are presented. The concepts and formal definitions of immune cells are given, the hierarchical and distributed management framework of the proposed model are built. Furthermore, the idea of biology immunity is applied for enhancing the self-adapting and self-learning ability to adapt continuously variety environments. The experimental results show that the proposed model has the features of real-time processing, self-adaptively, and diversity, thus providing a good solution for network surveillance.
{"title":"Network Intrusion Active Defense Model Based on Artificial Immune System","authors":"Cheng Zhang, Jing Zhang, Sunjun Liu, Yintian Liu","doi":"10.1109/ICNC.2008.782","DOIUrl":"https://doi.org/10.1109/ICNC.2008.782","url":null,"abstract":"Based on artificial immune theory, a new model of active defense for analyzing the network intrusion is presented. Dynamically evaluative equations for self, antigen, immune tolerance, mature-lymphocyte lifecycle and immune memory are presented. The concepts and formal definitions of immune cells are given, the hierarchical and distributed management framework of the proposed model are built. Furthermore, the idea of biology immunity is applied for enhancing the self-adapting and self-learning ability to adapt continuously variety environments. The experimental results show that the proposed model has the features of real-time processing, self-adaptively, and diversity, thus providing a good solution for network surveillance.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73269871","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}
A stochastic optimization algorithm is proposed by combining ant colony (ACO) algorithm with artificial fish-swarm algorithm (AFSA) for solving continuous space optimization problems. The algorithm is improved with the rapid search capability of AFSA and the good search characteristics of ACO, and the convergence speed of the presented algorithm is also improved for avoiding being trapped in local optimization. The improved algorithm has been tested for varieties of functions. And the algorithm can handle these optimization problems very well.
{"title":"Application of Improved Ant Colony Algorithm","authors":"Hongyan Shi, Zhaoyu Bei","doi":"10.1109/ICNC.2008.75","DOIUrl":"https://doi.org/10.1109/ICNC.2008.75","url":null,"abstract":"A stochastic optimization algorithm is proposed by combining ant colony (ACO) algorithm with artificial fish-swarm algorithm (AFSA) for solving continuous space optimization problems. The algorithm is improved with the rapid search capability of AFSA and the good search characteristics of ACO, and the convergence speed of the presented algorithm is also improved for avoiding being trapped in local optimization. The improved algorithm has been tested for varieties of functions. And the algorithm can handle these optimization problems very well.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75331356","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：