Pub Date : 2010-11-01DOI: 10.1109/ISKE.2010.5680756
Jiahai Liu, Maolin Yang
For multi-core embedded systems, the traditional load balancing leads to lavish power consumption by fully utilizing all cores. This paper proposes a novel load unbalancing strategy based on periodic and aperiodic tasks in hard real-time multi-core embedded systems to reduce power consumption. The scheduling architecture uses a two-level scheduling scheme. At the top level, the periodic tasks are bounded to embedded cores by RBound-FF algorithm and the aperiodic tasks are dispatched to the rest cores as evenly as possible. At the bottom level, a rate-monotonic OS scheduler is adopted to schedule the periodic tasks and a deadline-monotonic OS scheduler is used to schedule the aperiodic tasks.
{"title":"Task scheduling of real-time systems on multi-core embedded processor","authors":"Jiahai Liu, Maolin Yang","doi":"10.1109/ISKE.2010.5680756","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680756","url":null,"abstract":"For multi-core embedded systems, the traditional load balancing leads to lavish power consumption by fully utilizing all cores. This paper proposes a novel load unbalancing strategy based on periodic and aperiodic tasks in hard real-time multi-core embedded systems to reduce power consumption. The scheduling architecture uses a two-level scheduling scheme. At the top level, the periodic tasks are bounded to embedded cores by RBound-FF algorithm and the aperiodic tasks are dispatched to the rest cores as evenly as possible. At the bottom level, a rate-monotonic OS scheduler is adopted to schedule the periodic tasks and a deadline-monotonic OS scheduler is used to schedule the aperiodic tasks.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"3 1","pages":"580-583"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88480794","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}
Pub Date : 2010-11-01DOI: 10.1109/ISKE.2010.5680803
F. Zheng
In this note, the transport processes in networks with space dependent velocities on edges and output in a node was discussed by combining functional analytical and graph theoretical methods. This problem was converted into the terminology of operator semigroups and an abstract Cauchy problem was obtained on a suitable Banach space. The well-posedness of the system was given by showing the system operator generates a c0 semigroups.
{"title":"Well-posedness of flows in networks with output","authors":"F. Zheng","doi":"10.1109/ISKE.2010.5680803","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680803","url":null,"abstract":"In this note, the transport processes in networks with space dependent velocities on edges and output in a node was discussed by combining functional analytical and graph theoretical methods. This problem was converted into the terminology of operator semigroups and an abstract Cauchy problem was obtained on a suitable Banach space. The well-posedness of the system was given by showing the system operator generates a c0 semigroups.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"122 1","pages":"98-101"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77265910","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}
Pub Date : 2010-11-01DOI: 10.1109/ISKE.2010.5680805
Yongchang Ren, Xuguang Chai, Tao Xing, Xiaoji Chen
Fuzzy rule is the core of fuzzy expert system, which use relational database methods knowledge to build knowledge base, the combination of database and knowledge base is the development trend of the knowledge base. This paper describes the fuzzy rules first, including fuzzy logic, fuzzy production rules, multi-dimensional fuzzy rules; and studies the fuzzy rule representation, including the general rule representation and fuzzy rule representation; finally researches the construction of knowledge base, including the Knowledge Base System Structure and knowledge base table structure. The results show that the type knowledge of fuzzy rule reflects the relationship between the rules of deductive reasoning logical implication of the way to the database is a natural extension from the database to the knowledge base, which has some theoretical and practical value.
{"title":"Fuzzy rule representation and knowledge base construction in expert system","authors":"Yongchang Ren, Xuguang Chai, Tao Xing, Xiaoji Chen","doi":"10.1109/ISKE.2010.5680805","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680805","url":null,"abstract":"Fuzzy rule is the core of fuzzy expert system, which use relational database methods knowledge to build knowledge base, the combination of database and knowledge base is the development trend of the knowledge base. This paper describes the fuzzy rules first, including fuzzy logic, fuzzy production rules, multi-dimensional fuzzy rules; and studies the fuzzy rule representation, including the general rule representation and fuzzy rule representation; finally researches the construction of knowledge base, including the Knowledge Base System Structure and knowledge base table structure. The results show that the type knowledge of fuzzy rule reflects the relationship between the rules of deductive reasoning logical implication of the way to the database is a natural extension from the database to the knowledge base, which has some theoretical and practical value.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"10 7-8","pages":"106-110"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91499125","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}
Pub Date : 2010-11-01DOI: 10.1109/ISKE.2010.5680826
I. Sotés, J. L. Larrabe, Miguel A. Gomez, F. J. Alvarez, M. C. Rey-Santano, V. Mielgo, E. Gastiasoro
At sea, voice and data communications have virtually global coverage via satellite. Satellite communications are increasing the bandwidth and lowering the cost, but are still far from levels that are in earth. The Principal components analysis (PCA) is a statistical technique used for lossy or non exact compression data; is a common tool for the search of pattern of multidimensional data sets. The assertion of this study was the possibility of using the PCA theory to compress, with sufficient accuracy, the large amount of data that are collected on board, and then send them all via satellite, in a cheaper or/and faster way than traditionally. This strategy is appropriate for decision making about telediagnosis and maintenance of the ship using ground equipment. Consequently, significant savings are achieved in telecommunication costs and telecommunication times.
{"title":"Telediagnosis and maintenance of the ship from land, using principal component analysis to compress acquired data offshore","authors":"I. Sotés, J. L. Larrabe, Miguel A. Gomez, F. J. Alvarez, M. C. Rey-Santano, V. Mielgo, E. Gastiasoro","doi":"10.1109/ISKE.2010.5680826","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680826","url":null,"abstract":"At sea, voice and data communications have virtually global coverage via satellite. Satellite communications are increasing the bandwidth and lowering the cost, but are still far from levels that are in earth. The Principal components analysis (PCA) is a statistical technique used for lossy or non exact compression data; is a common tool for the search of pattern of multidimensional data sets. The assertion of this study was the possibility of using the PCA theory to compress, with sufficient accuracy, the large amount of data that are collected on board, and then send them all via satellite, in a cheaper or/and faster way than traditionally. This strategy is appropriate for decision making about telediagnosis and maintenance of the ship using ground equipment. Consequently, significant savings are achieved in telecommunication costs and telecommunication times.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"1 1","pages":"470-473"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91324141","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}
Pub Date : 2010-11-01DOI: 10.1109/ISKE.2010.5680882
Futian Yao, Y. Qian, Zhenfang Hu, Jiming Li
Classification is an important task in Hyperspectral data analysis. Hyperspectral images show strong correlations across spatial and spectral neighbors. Theoretically, classifier designed with a joint spectral and spatial correlations can improve classification performance than classifier which only utilize one of the correlations. Gaussian Processes(GPs) have been used for Hyperspectral imagery classification successfully by exploiting spectral correlation. Meanwhile,conditional random fields(CRFs) classify image regions by incorporating neighborhood Spatial interactions in the labels as well as the observed data. In this paper, we make a combination of GPs and CRFs and propose a novel GPCRF classifier to exploit spectral and spatial interactions in Hyperspectral remote sensing images. Experiments on the real-world Hyperspectral image attest to the accuracy and robust of the proposed method.
分类是高光谱数据分析中的一项重要任务。高光谱图像在空间和光谱邻居之间显示出很强的相关性。从理论上讲，结合光谱和空间相关性设计的分类器比只利用其中一种相关性设计的分类器能提高分类性能。高斯过程利用光谱相关性成功地用于高光谱图像分类。同时，条件随机场(conditional random field, CRFs)通过结合标签和观测数据的邻域空间相互作用对图像区域进行分类。本文将GPs与crf相结合，提出了一种利用高光谱遥感图像中光谱与空间相互作用的GPCRF分类器。在实际高光谱图像上的实验证明了该方法的准确性和鲁棒性。
{"title":"A novel hyperspectral remote sensing images classification using Gaussian Processes with conditional random fields","authors":"Futian Yao, Y. Qian, Zhenfang Hu, Jiming Li","doi":"10.1109/ISKE.2010.5680882","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680882","url":null,"abstract":"Classification is an important task in Hyperspectral data analysis. Hyperspectral images show strong correlations across spatial and spectral neighbors. Theoretically, classifier designed with a joint spectral and spatial correlations can improve classification performance than classifier which only utilize one of the correlations. Gaussian Processes(GPs) have been used for Hyperspectral imagery classification successfully by exploiting spectral correlation. Meanwhile,conditional random fields(CRFs) classify image regions by incorporating neighborhood Spatial interactions in the labels as well as the observed data. In this paper, we make a combination of GPs and CRFs and propose a novel GPCRF classifier to exploit spectral and spatial interactions in Hyperspectral remote sensing images. Experiments on the real-world Hyperspectral image attest to the accuracy and robust of the proposed method.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"1 1","pages":"197-202"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87099778","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}
Pub Date : 2010-11-01DOI: 10.1109/ISKE.2010.5680771
Lichuan Wang, Xianyi Zeng, L. Koehl, Yan Chen
This paper presents a method permitting to determine the relationship between body measurements and human perception on morphology of body shapes, expressed by a set of emotional descriptors and fashion themes. It can be integrated into current garment CAD system for providing personalized design support. Two procedures of sensory evaluation have been used. The first one aims at evaluating abstract fashion themes by means of emotional descriptors. In this procedure, the evaluators, including fashion designers and consumers, will give relevancy degrees between fashion themes and emotional descriptors. A fuzzy cognitive map is introduced to represent the corresponding results. It can be considered as a conceptual model characterizing the cognition level of evaluators on abstract fashion themes. The other procedure aims at evaluating the previous emotional descriptors on human body shapes according to the corresponding body measurements. A set of decision trees have been established to model the relation between the emotional descriptors and the human body measurements. It can be considered as a empirical model obtained from learning data.
{"title":"Study of human perception on body shapes using intelligent techniques","authors":"Lichuan Wang, Xianyi Zeng, L. Koehl, Yan Chen","doi":"10.1109/ISKE.2010.5680771","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680771","url":null,"abstract":"This paper presents a method permitting to determine the relationship between body measurements and human perception on morphology of body shapes, expressed by a set of emotional descriptors and fashion themes. It can be integrated into current garment CAD system for providing personalized design support. Two procedures of sensory evaluation have been used. The first one aims at evaluating abstract fashion themes by means of emotional descriptors. In this procedure, the evaluators, including fashion designers and consumers, will give relevancy degrees between fashion themes and emotional descriptors. A fuzzy cognitive map is introduced to represent the corresponding results. It can be considered as a conceptual model characterizing the cognition level of evaluators on abstract fashion themes. The other procedure aims at evaluating the previous emotional descriptors on human body shapes according to the corresponding body measurements. A set of decision trees have been established to model the relation between the emotional descriptors and the human body measurements. It can be considered as a empirical model obtained from learning data.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"59 1","pages":"658-663"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85668161","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}
Pub Date : 2010-11-01DOI: 10.1109/ISKE.2010.5680864
Jianping Shen, Xuan Wang, S. Li, Lin Yao
In this paper we design a multiple features template includes basic features, prefixes and suffixed features, dictionary features and combined features for Chinese named entity recognizer CRF model-based. We do a pre-processing procedure such as pos tag, chunk dictionary-based first. Then for dictionary features, different proportion of dictionaries are used in training and testing, which is different from the work reported in the literature, especially to person name dictionary, location name dictionary and organization name dictionary. For these three named entity dictionaries, the training dictionaries are just a part of the testing dictionaries. Empirical results show that the multiple features template is comprehensive and different proportion of some dictionaries used in training and testing improve performance significantly. Our final system achieved the F-measure of 91.27% at MSRA testing corpus, which is even better than the SIGHAN 2006 at the same testing corpus.
{"title":"Exploiting rich features for Chinese named entity recognition","authors":"Jianping Shen, Xuan Wang, S. Li, Lin Yao","doi":"10.1109/ISKE.2010.5680864","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680864","url":null,"abstract":"In this paper we design a multiple features template includes basic features, prefixes and suffixed features, dictionary features and combined features for Chinese named entity recognizer CRF model-based. We do a pre-processing procedure such as pos tag, chunk dictionary-based first. Then for dictionary features, different proportion of dictionaries are used in training and testing, which is different from the work reported in the literature, especially to person name dictionary, location name dictionary and organization name dictionary. For these three named entity dictionaries, the training dictionaries are just a part of the testing dictionaries. Empirical results show that the multiple features template is comprehensive and different proportion of some dictionaries used in training and testing improve performance significantly. Our final system achieved the F-measure of 91.27% at MSRA testing corpus, which is even better than the SIGHAN 2006 at the same testing corpus.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"33 1","pages":"278-282"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73129380","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}
Pub Date : 2010-11-01DOI: 10.1109/ISKE.2010.5680743
Hui Xiao, Wei Gong
A core issue that confronts peer-to-peer streaming media application is to efficiently schedule the propagation of data segment. This paper presents a peer-to-peer scheme based on principal-agent model (PAM) that some peers play the role of agent, to gather the information of principal peers in its local physical network, which can be used to optimizing of data scheduling. We designs and implements a peer-to-peer streaming media system prototype based PAM, which called TreoStream. Experiments show that TreoStream can improve the efficiency of data scheduling, without increasing the traffic overhead of system.
{"title":"TreoStream: A peer-to-peer streaming media system prototype","authors":"Hui Xiao, Wei Gong","doi":"10.1109/ISKE.2010.5680743","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680743","url":null,"abstract":"A core issue that confronts peer-to-peer streaming media application is to efficiently schedule the propagation of data segment. This paper presents a peer-to-peer scheme based on principal-agent model (PAM) that some peers play the role of agent, to gather the information of principal peers in its local physical network, which can be used to optimizing of data scheduling. We designs and implements a peer-to-peer streaming media system prototype based PAM, which called TreoStream. Experiments show that TreoStream can improve the efficiency of data scheduling, without increasing the traffic overhead of system.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"88 1","pages":"524-527"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73205665","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}
Pub Date : 2010-11-01DOI: 10.1109/ISKE.2010.5680808
Xianglan Han, Yangguang Liu, Bin Xu, Gang Zhang
To satisfy the requirement of making scientific decision quickly and correctly in distributed network environment, a Meta Web Service based Distributed Model Management and Composition Approach is proposed. The Overall framework of Meta web service is designed, and each component is analyzed. An improved model service matching algorithm is given. Utilizing backward reasoning technique to compose model services dynamically and automatically, a process is then given which uses several model services to compose to make a single service. Compared with traditional model management approach, the approach provided here has the functions of model remote calling and running, automatic composing and executing etc., which provide a new approach to build model system for decision support system solving complex problems.
{"title":"Meta Web Service based Distributed Model Management and Composition Approach","authors":"Xianglan Han, Yangguang Liu, Bin Xu, Gang Zhang","doi":"10.1109/ISKE.2010.5680808","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680808","url":null,"abstract":"To satisfy the requirement of making scientific decision quickly and correctly in distributed network environment, a Meta Web Service based Distributed Model Management and Composition Approach is proposed. The Overall framework of Meta web service is designed, and each component is analyzed. An improved model service matching algorithm is given. Utilizing backward reasoning technique to compose model services dynamically and automatically, a process is then given which uses several model services to compose to make a single service. Compared with traditional model management approach, the approach provided here has the functions of model remote calling and running, automatic composing and executing etc., which provide a new approach to build model system for decision support system solving complex problems.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"59 1","pages":"117-122"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77806428","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}
Pub Date : 2010-11-01DOI: 10.1109/ISKE.2010.5680853
J. Alcantud, R. D. A. Calle
In some group decision making problems of real life not only is significant to rank the alternatives but it also is important to measure how much consensus this solution conveys to the group. Due to this fact, in this work we propose a new methodology to measure the degree of consensus obtained by a group decision making process. To develop that approach, we define a class of consensus measures based on particular social rules. Some of their basic properties are proved too.
{"title":"A new methodology to measure consensus","authors":"J. Alcantud, R. D. A. Calle","doi":"10.1109/ISKE.2010.5680853","DOIUrl":"https://doi.org/10.1109/ISKE.2010.5680853","url":null,"abstract":"In some group decision making problems of real life not only is significant to rank the alternatives but it also is important to measure how much consensus this solution conveys to the group. Due to this fact, in this work we propose a new methodology to measure the degree of consensus obtained by a group decision making process. To develop that approach, we define a class of consensus measures based on particular social rules. Some of their basic properties are proved too.","PeriodicalId":6417,"journal":{"name":"2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering","volume":"87 1","pages":"365-370"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74535581","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：