Pub Date : 2012-07-15DOI: 10.1109/ICMLC.2012.6359483
Fachao Li, Zan Zhang
This paper presents a method to determine the fuzzy measure based on knowledge factors, in order to solve the problem of interaction among indices in the comprehensive evaluation, and make full use of the knowledge existing in the information system. The method can be used as a strategy for measuring the significance of the attributes. Furthermore, the Choquet integral is an important aggregation operator used in various fields. In combination with the Choquet integral, the method is applied to the assessment of graduate scholarship. The result shows that the method offers good interpretation and operation.
{"title":"A method of determining the fuzzy measure based on knowledge factors","authors":"Fachao Li, Zan Zhang","doi":"10.1109/ICMLC.2012.6359483","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359483","url":null,"abstract":"This paper presents a method to determine the fuzzy measure based on knowledge factors, in order to solve the problem of interaction among indices in the comprehensive evaluation, and make full use of the knowledge existing in the information system. The method can be used as a strategy for measuring the significance of the attributes. Furthermore, the Choquet integral is an important aggregation operator used in various fields. In combination with the Choquet integral, the method is applied to the assessment of graduate scholarship. The result shows that the method offers good interpretation and operation.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117038703","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 : 2012-07-15DOI: 10.1109/ICMLC.2012.6359464
Bai-Cheng Zhu, Tianping Zhang
An adaptive neural network control scheme is proposed for a class of nonlinear switched systems in pure-feedback form. The design is based on the dynamic surface technique, the approximation capability of neural networks and the dwell-time approach. The design makes the approach of dynamic surface control being extended to the switched nonlinear system, and relaxes the extent of application of the approach of dynamic surface control. Compared with existing literatures, the proposed approach relaxes the requirements of the system. And the explosion of complexity in traditional backstepping design caused by repeated differentiations of virtual control is avoided. By theoretical analysis, the closed-loop control system is shown to be semi-globally uniformly ultimately bounded. Finally, simulation results are presented to illustrate the effectiveness of the proposed approach.
{"title":"Robust adaptive control for a class of switched nonlinear systems in pure-feedback form","authors":"Bai-Cheng Zhu, Tianping Zhang","doi":"10.1109/ICMLC.2012.6359464","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359464","url":null,"abstract":"An adaptive neural network control scheme is proposed for a class of nonlinear switched systems in pure-feedback form. The design is based on the dynamic surface technique, the approximation capability of neural networks and the dwell-time approach. The design makes the approach of dynamic surface control being extended to the switched nonlinear system, and relaxes the extent of application of the approach of dynamic surface control. Compared with existing literatures, the proposed approach relaxes the requirements of the system. And the explosion of complexity in traditional backstepping design caused by repeated differentiations of virtual control is avoided. By theoretical analysis, the closed-loop control system is shown to be semi-globally uniformly ultimately bounded. Finally, simulation results are presented to illustrate the effectiveness of the proposed approach.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129012848","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 : 2012-07-15DOI: 10.1109/ICMLC.2012.6358897
Bin Liu, Shu-Gui Cao, D. Cao, Qing-Chun Li, Hai-Tao Liu, Shao-Nan Shi
In distributed data mining (DDM) systems, the semantic heterogeneity between data sources has not got universal attentions, which may produce the potential risks of damaging the quality of the final result. This paper presents a semantic distance measurement framework to extract the essential semantic heterogeneity between data sources. In this framework, an ontology-matching based multi-strategy voting method is utilized to comprehensively synthesize the semantic distances between two data source ontologies in element level and structure level. The output of the framework can be leveraged as the foundation to group the data sources for optimizing the DDM result. Finally, the framework is integrated into a DDM architecture we have proposed.
{"title":"An ontology based semantic heterogeneity measurement framework for optimization in distributed data mining","authors":"Bin Liu, Shu-Gui Cao, D. Cao, Qing-Chun Li, Hai-Tao Liu, Shao-Nan Shi","doi":"10.1109/ICMLC.2012.6358897","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6358897","url":null,"abstract":"In distributed data mining (DDM) systems, the semantic heterogeneity between data sources has not got universal attentions, which may produce the potential risks of damaging the quality of the final result. This paper presents a semantic distance measurement framework to extract the essential semantic heterogeneity between data sources. In this framework, an ontology-matching based multi-strategy voting method is utilized to comprehensively synthesize the semantic distances between two data source ontologies in element level and structure level. The output of the framework can be leveraged as the foundation to group the data sources for optimizing the DDM result. Finally, the framework is integrated into a DDM architecture we have proposed.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129462266","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 : 2012-07-15DOI: 10.1109/ICMLC.2012.6359560
Zhiying Lu, Jian-Pei Wang
In this paper radar reflectivity image, a range of weather conditions, and image processing technology were applied to extract features of strong convective echoes (hail, torrential rain) from the radar images. Area, vertically integrated liquid water (VIL), vertically integrated liquid water density (VTLD) and other features were obtained to construct the characteristic database. Rough set theory was used to dig out useful rules that can form the knowledge base, thereby the objective model of identifying strong convection weather was established. Finally the objective model was used to identify and forecast hail and torrential rain. Test results indicated that the three features properties of hail and torrential rain had effective recognition results, and prediction accuracy was 76.25% which meets the requirements of preliminary classification.
{"title":"Strong convective echoes identification based on rough set theory","authors":"Zhiying Lu, Jian-Pei Wang","doi":"10.1109/ICMLC.2012.6359560","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359560","url":null,"abstract":"In this paper radar reflectivity image, a range of weather conditions, and image processing technology were applied to extract features of strong convective echoes (hail, torrential rain) from the radar images. Area, vertically integrated liquid water (VIL), vertically integrated liquid water density (VTLD) and other features were obtained to construct the characteristic database. Rough set theory was used to dig out useful rules that can form the knowledge base, thereby the objective model of identifying strong convection weather was established. Finally the objective model was used to identify and forecast hail and torrential rain. Test results indicated that the three features properties of hail and torrential rain had effective recognition results, and prediction accuracy was 76.25% which meets the requirements of preliminary classification.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123526787","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 : 2012-07-15DOI: 10.1109/ICMLC.2012.6359678
Bo You, Ming Liu, Bingquan Liu, Xiaolong Wang
Detecting hot topics with a fine granularity in technology news streams is an interesting and important problem given the large amount of reports and a relatively narrow range of topics. In this paper, a three-phase method is proposed. In the first phase, the document topic distribution vector is generated and keywords are extracted for each document using topic model pachinko allocation. In the second phase, the documents are clustered based on the document topic distribution vector obtained from the previous phase using affinity propagation. And in the last phase, actual events denoted by combinations of keywords within each cluster are found out using frequent pattern mining algorithms. We evaluate our approach on a collection of technology news reports from various sites in a fixed time period. T he results show that this method is effective.
{"title":"Detecting hot topics in technology news streams","authors":"Bo You, Ming Liu, Bingquan Liu, Xiaolong Wang","doi":"10.1109/ICMLC.2012.6359678","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359678","url":null,"abstract":"Detecting hot topics with a fine granularity in technology news streams is an interesting and important problem given the large amount of reports and a relatively narrow range of topics. In this paper, a three-phase method is proposed. In the first phase, the document topic distribution vector is generated and keywords are extracted for each document using topic model pachinko allocation. In the second phase, the documents are clustered based on the document topic distribution vector obtained from the previous phase using affinity propagation. And in the last phase, actual events denoted by combinations of keywords within each cluster are found out using frequent pattern mining algorithms. We evaluate our approach on a collection of technology news reports from various sites in a fixed time period. T he results show that this method is effective.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"52 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120915898","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 : 2012-07-15DOI: 10.1109/ICMLC.2012.6359577
Shin-An Wang, R. Chiu, Sheng-Jen Jian
In this paper, an intelligent decision support system based on the technique of fuzzy expert systems is developed for the risk assessment of chronic kidney disease (CKD). In the meanwhile, the system is deployed on the Google cloud platform by leveraging Google Application Engine as a cloud service system. Through the aid of this service system, the publics may take advantage of this system over the Internet to conduct the self-assessment for his/her risk of contracting CKD. Consequently, suffering from early CKD can be prevented and the health may be maintained under a better situation in all his/her life.
{"title":"The implementation of an intelligent cloud service system for disease risk assessment - chronic kidney disease as an example","authors":"Shin-An Wang, R. Chiu, Sheng-Jen Jian","doi":"10.1109/ICMLC.2012.6359577","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359577","url":null,"abstract":"In this paper, an intelligent decision support system based on the technique of fuzzy expert systems is developed for the risk assessment of chronic kidney disease (CKD). In the meanwhile, the system is deployed on the Google cloud platform by leveraging Google Application Engine as a cloud service system. Through the aid of this service system, the publics may take advantage of this system over the Internet to conduct the self-assessment for his/her risk of contracting CKD. Consequently, suffering from early CKD can be prevented and the health may be maintained under a better situation in all his/her life.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"152 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116338552","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 : 2012-07-15DOI: 10.1109/ICMLC.2012.6358947
Hui Yu, Fei Zhang
Collaborative filtering recommender system is wildly used in e-commerce system. According to the profiles of user or items, a collaborative filtering recommender system recommends items to targeted customers according to the preferences of their similar customers. It provides customer useful relevant information. Unfortunately, the recommender system is vulnerable to profile injection attacks. In the profile inject attack, the similar user profiles are manipulated by injecting a large number of fake profiles into the system. In this paper, four new attributes for the injection attack detection are proposed. We also discuss the profile injection attacks in adversarial learning environment. By applying the Localized Generalization Error Model (L-GEM), a more robustness attack profile detection system is proposed. Experimental results show that L-GEM based detection classifier has better robustness.
{"title":"Collaborative filtering recommender system in adversarial environment","authors":"Hui Yu, Fei Zhang","doi":"10.1109/ICMLC.2012.6358947","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6358947","url":null,"abstract":"Collaborative filtering recommender system is wildly used in e-commerce system. According to the profiles of user or items, a collaborative filtering recommender system recommends items to targeted customers according to the preferences of their similar customers. It provides customer useful relevant information. Unfortunately, the recommender system is vulnerable to profile injection attacks. In the profile inject attack, the similar user profiles are manipulated by injecting a large number of fake profiles into the system. In this paper, four new attributes for the injection attack detection are proposed. We also discuss the profile injection attacks in adversarial learning environment. By applying the Localized Generalization Error Model (L-GEM), a more robustness attack profile detection system is proposed. Experimental results show that L-GEM based detection classifier has better robustness.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121639957","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 : 2012-07-15DOI: 10.1109/ICMLC.2012.6359493
Dong-Mei Li, B. Liu, Y. Qu
The implication and feature of input and output efficiency of science and technology are analyzed. The evaluation index system of input and output efficiency of science and technology is established by using a new feature selection method based on principal component analysis. The input and output efficiency of science and technology of each province is calculated and evaluated by using data envelopment analysis model. The input and output status of science and technology in our country is analyzed. The countermeasures and suggestions to raise input and output efficiency of science and technology are put forward.
{"title":"Evaluation of input and output efficiency of science and technology based on DEA model","authors":"Dong-Mei Li, B. Liu, Y. Qu","doi":"10.1109/ICMLC.2012.6359493","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359493","url":null,"abstract":"The implication and feature of input and output efficiency of science and technology are analyzed. The evaluation index system of input and output efficiency of science and technology is established by using a new feature selection method based on principal component analysis. The input and output efficiency of science and technology of each province is calculated and evaluated by using data envelopment analysis model. The input and output status of science and technology in our country is analyzed. The countermeasures and suggestions to raise input and output efficiency of science and technology are put forward.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126352761","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 : 2012-07-15DOI: 10.1109/ICMLC.2012.6359007
L. Liang, Fanchen Meng, Li-Jie Cao
Structural equation model (SEM) was employed to analyze the interaction factors that affecting operational risk management (ORM) from questionnaires for commercial banks in the research. Based on lots of international and Chinese documentation and questionnaire, the model was constructed with 20 affecting factors and 4 layers (bank employee, section & sub-branch, head office & branch office and bank conditions). “Bank employee level” is taken as the endogenous latent variable, and other levels are taken as the exogenous latent variables from the research results. According to the modification indices (MI) of the model and the modification corresponding criterion, the model was modified so as to get optimized model. The main innovation includes two parts, one is to design the questionnaire for ORM to get important information, and the other one is to employ SEM to analyze ORM factors.
{"title":"Research on affecting factors of operational risk management for commercial bank based on structural equation model","authors":"L. Liang, Fanchen Meng, Li-Jie Cao","doi":"10.1109/ICMLC.2012.6359007","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359007","url":null,"abstract":"Structural equation model (SEM) was employed to analyze the interaction factors that affecting operational risk management (ORM) from questionnaires for commercial banks in the research. Based on lots of international and Chinese documentation and questionnaire, the model was constructed with 20 affecting factors and 4 layers (bank employee, section & sub-branch, head office & branch office and bank conditions). “Bank employee level” is taken as the endogenous latent variable, and other levels are taken as the exogenous latent variables from the research results. According to the modification indices (MI) of the model and the modification corresponding criterion, the model was modified so as to get optimized model. The main innovation includes two parts, one is to design the questionnaire for ORM to get important information, and the other one is to employ SEM to analyze ORM factors.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126212716","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 : 2012-07-15DOI: 10.1109/ICMLC.2012.6358876
Xiao Yu, You-Dong Zuo
This paper puts forward one kind of profit and loss computation model based on the Markov chain for the data synchronization application between data subset and application system on university information platform. The data synchronization Markov model of a single link and dual link is given, computation model based on the profit or loss of the stationary distribution of a single link and dual link is deduced, and whether to upgrade a single link to a dual link is changed from qualitative interpretation into quantitative calculation.
{"title":"Profit and loss calculation model of data synchronization based on Markov chain","authors":"Xiao Yu, You-Dong Zuo","doi":"10.1109/ICMLC.2012.6358876","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6358876","url":null,"abstract":"This paper puts forward one kind of profit and loss computation model based on the Markov chain for the data synchronization application between data subset and application system on university information platform. The data synchronization Markov model of a single link and dual link is given, computation model based on the profit or loss of the stationary distribution of a single link and dual link is deduced, and whether to upgrade a single link to a dual link is changed from qualitative interpretation into quantitative calculation.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125605360","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：