Video surveillance systems are becoming common in commercial, industrial, and residential environments. The systems in used are constructed mainly by hard devices with no or very few soft intelligence. It is difficult for human to recognize important events as they happening and to control over unwilling situations by staring at the screens all the time. Soft intelligence to identify human behaviors in the surveillance systems is expected. A system’s architecture for this goal is presented in this paper. Bottom-up processing methods and top-down design schemes are integrated in the architecture. The integration may increase the accuracy of relevance algorithms and reduce the computing cost. The feasibility of the system is assured.
{"title":"Towards Suspicious Behavior Discovery in Video Surveillance System","authors":"Yingjie Li, Yixin Yin","doi":"10.1109/WKDD.2009.22","DOIUrl":"https://doi.org/10.1109/WKDD.2009.22","url":null,"abstract":"Video surveillance systems are becoming common in commercial, industrial, and residential environments. The systems in used are constructed mainly by hard devices with no or very few soft intelligence. It is difficult for human to recognize important events as they happening and to control over unwilling situations by staring at the screens all the time. Soft intelligence to identify human behaviors in the surveillance systems is expected. A system’s architecture for this goal is presented in this paper. Bottom-up processing methods and top-down design schemes are integrated in the architecture. The integration may increase the accuracy of relevance algorithms and reduce the computing cost. The feasibility of the system is assured.","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124219347","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}
As the dishonesty violations of the listed companies occur from time to time, the credit risk of listed companies has become an issue related to the financial system stability. By understanding the concepts of credit and credit risk, a quantitative research has been carried out on the credit taking listed company in Anhui Province as an example on the premise of considering the availability of data. According to analysis of the company's credit system, combined with of 46 financial statements of listed companies in Anhui Province, 12 indicators are selected for analysis and ranks with the company credit. Then through the cluster analysis of listed companies, these companies will be divided into three types. As results, some conclusions have been drawn from the Empirical Analysis that being work along both effective regulation and institutional innovation is an effective solution to the problem for the way of enhancing the company credit.
{"title":"Empirical Analysis and Countermeasures Research on Corporate Credit Taking Listed Companies of Anhui Province as an Example","authors":"M. Song","doi":"10.1109/WKDD.2009.150","DOIUrl":"https://doi.org/10.1109/WKDD.2009.150","url":null,"abstract":"As the dishonesty violations of the listed companies occur from time to time, the credit risk of listed companies has become an issue related to the financial system stability. By understanding the concepts of credit and credit risk, a quantitative research has been carried out on the credit taking listed company in Anhui Province as an example on the premise of considering the availability of data. According to analysis of the company's credit system, combined with of 46 financial statements of listed companies in Anhui Province, 12 indicators are selected for analysis and ranks with the company credit. Then through the cluster analysis of listed companies, these companies will be divided into three types. As results, some conclusions have been drawn from the Empirical Analysis that being work along both effective regulation and institutional innovation is an effective solution to the problem for the way of enhancing the company credit.","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130423850","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}
Some network intrusion security problems of IPv6 are researched and summarized In this paper. And this paper introduces the model of general IDS and the framework of NIDS of Ipv6. Aiming at the structure characters of IPv6 protocols, a new research method of network intrusion detection system based on protocol analysis and multi-pattern matching is put forward. Protocol analysis technology can find protocol suspicious action quickly, and pattern matching technology can detect deep attack action by character matching. Finally, a detailed designing scheme and testing result are provided.
{"title":"Research of NIDS in IPV6 Based on Protocol Analysis and Pattern Matching","authors":"Shu-qiang Huang, Huan-ming Zhang, Guo-xiang Yao","doi":"10.1109/WKDD.2009.24","DOIUrl":"https://doi.org/10.1109/WKDD.2009.24","url":null,"abstract":"Some network intrusion security problems of IPv6 are researched and summarized In this paper. And this paper introduces the model of general IDS and the framework of NIDS of Ipv6. Aiming at the structure characters of IPv6 protocols, a new research method of network intrusion detection system based on protocol analysis and multi-pattern matching is put forward. Protocol analysis technology can find protocol suspicious action quickly, and pattern matching technology can detect deep attack action by character matching. Finally, a detailed designing scheme and testing result are provided.","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129638973","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}
Various models have been constructed to explore the principles of competition diffusion of B2C e-commerce (hereafter e-commerce) in customers. The relationships between e-commerce websites also draw the attention of scholars, and many diffusion theory of e-commerce has been built to understand the competitive market environment. In fact, the potential group of customers is vitally important for e-commerce competition diffusion since the updating rate of e-commerce websites is too frequent in the information age now. In order to uncover the diffusion principles of e-commerce for competing in potential customers, this research concentrate on constructing a dynamic diffusion model of e-commerce that are striving with each other for potential customers.
{"title":"The Dynamic Competition Diffusion Model of B2C E-commerce in Potential Customers","authors":"Yuantao Jiang, Zhisheng Li","doi":"10.1109/WKDD.2009.130","DOIUrl":"https://doi.org/10.1109/WKDD.2009.130","url":null,"abstract":"Various models have been constructed to explore the principles of competition diffusion of B2C e-commerce (hereafter e-commerce) in customers. The relationships between e-commerce websites also draw the attention of scholars, and many diffusion theory of e-commerce has been built to understand the competitive market environment. In fact, the potential group of customers is vitally important for e-commerce competition diffusion since the updating rate of e-commerce websites is too frequent in the information age now. In order to uncover the diffusion principles of e-commerce for competing in potential customers, this research concentrate on constructing a dynamic diffusion model of e-commerce that are striving with each other for potential customers.","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117262560","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}
Field Programmable Gate Array (FPGA) was a new material Programmable Logic Units in end of the 20th century, FPGA was with some properties such that, large memory of capacities, short delays of time, improvement able & flexibilities etc. On the basis theory of Neural Fuzzy System of Networks (NFSN), this paper gives a FPGA method of DNMA (Dynamic Numbers Measuring Algorithm) with VCN (Variable Carrying Numbers). The algorithm takes a reusing technique of VCR (Variable Carrying Rules) path, a process of middle-data to be shaped & placed in RAM. In the deep research & analysis of testing, this algorithm is practicable.
{"title":"A Novel FPGA Mathematical Technology Based AI-Fuzzy VCN Algorithm of Automation","authors":"Tingfang Zhang, Qiusun Ye","doi":"10.1109/WKDD.2009.172","DOIUrl":"https://doi.org/10.1109/WKDD.2009.172","url":null,"abstract":"Field Programmable Gate Array (FPGA) was a new material Programmable Logic Units in end of the 20th century, FPGA was with some properties such that, large memory of capacities, short delays of time, improvement able & flexibilities etc. On the basis theory of Neural Fuzzy System of Networks (NFSN), this paper gives a FPGA method of DNMA (Dynamic Numbers Measuring Algorithm) with VCN (Variable Carrying Numbers). The algorithm takes a reusing technique of VCR (Variable Carrying Rules) path, a process of middle-data to be shaped & placed in RAM. In the deep research & analysis of testing, this algorithm is practicable.","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115267848","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}
Because there were a lot of facts that affect the intensity of coal and gas outburst, a BP neural network model for forecasting the intensity was constructed. Aimed at the shortcoming of the BP neural network, such as the slow training speed, easy to be trapped into the local optimums, and the premature convergence of Genetic Algorithm (GA) BP neural network, a method to design the BP neural network based on Immune Genetic Algorithm was proposed. The mechanisms of diversity maintaining and antibody density regulation exhibited in a biological immune system were introduced into IGA based on genetic algorithm. The proposed algorithm overcame the problems of GA on search efficiency¿individual diversity and premature¿and enhanced the convergent performance effectively. The results show that the IGA-BP neural network have better performance in convergent speed and global convergence, and the forecasting accuracy is improved.
{"title":"Research of Coal and Gas Outburst Forecasting Based on Immune Genetic Neural Network","authors":"Yu Zhu, Hong Zhang, Ling-dong Kong","doi":"10.1109/WKDD.2009.45","DOIUrl":"https://doi.org/10.1109/WKDD.2009.45","url":null,"abstract":"Because there were a lot of facts that affect the intensity of coal and gas outburst, a BP neural network model for forecasting the intensity was constructed. Aimed at the shortcoming of the BP neural network, such as the slow training speed, easy to be trapped into the local optimums, and the premature convergence of Genetic Algorithm (GA) BP neural network, a method to design the BP neural network based on Immune Genetic Algorithm was proposed. The mechanisms of diversity maintaining and antibody density regulation exhibited in a biological immune system were introduced into IGA based on genetic algorithm. The proposed algorithm overcame the problems of GA on search efficiency¿individual diversity and premature¿and enhanced the convergent performance effectively. The results show that the IGA-BP neural network have better performance in convergent speed and global convergence, and the forecasting accuracy is improved.","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115390772","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 teacher e-portfolio based on network is a product of modern information technology, it can record the teacher’s growth of instruction, strengthen their personal knowledge management, and more important, it can enhance their instruction reflection. Teacher professional development is an issue of general concern in education field, particularly with the implementation of the new curriculum reform. In this paper, we propose a new view for teacher professional development, which is teacher e-portfolio system; we design the module and function of the system based on the requirement analysis.
{"title":"Design of Teacher E-portfolio System for Teacher Professional Development","authors":"Duan Xinyu, Li Min","doi":"10.1109/WKDD.2009.49","DOIUrl":"https://doi.org/10.1109/WKDD.2009.49","url":null,"abstract":"The teacher e-portfolio based on network is a product of modern information technology, it can record the teacher’s growth of instruction, strengthen their personal knowledge management, and more important, it can enhance their instruction reflection. Teacher professional development is an issue of general concern in education field, particularly with the implementation of the new curriculum reform. In this paper, we propose a new view for teacher professional development, which is teacher e-portfolio system; we design the module and function of the system based on the requirement analysis.","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"20 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131539341","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, papers about data mining recorded by CSSCI (1998 ~ 2007) are collected and analyzed with statistical analysis and bibliometric analysis such as year distribution, journal distribution, subject distribution, the core author and the geographical distribution of the author. So we can identify the core author, core journals, research institutes and the law of research on data mining in the Chinese social science circle, and reveal the review of data mining study and the main theme in the Chinese social science circle. In collusion, this paper indicates some problems and trends about study on data mining.
{"title":"Bibliometric Analysis of Data Mining in the Chinese Social Science Circle","authors":"Chao Li, Jian Ke","doi":"10.1109/WKDD.2009.147","DOIUrl":"https://doi.org/10.1109/WKDD.2009.147","url":null,"abstract":"In this paper, papers about data mining recorded by CSSCI (1998 ~ 2007) are collected and analyzed with statistical analysis and bibliometric analysis such as year distribution, journal distribution, subject distribution, the core author and the geographical distribution of the author. So we can identify the core author, core journals, research institutes and the law of research on data mining in the Chinese social science circle, and reveal the review of data mining study and the main theme in the Chinese social science circle. In collusion, this paper indicates some problems and trends about study on data mining.","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125372723","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}
Cities are complex systems, with many dynamically changing parameters and large numbers of discrete actors. The heterogeneous nature of cities, make it difficult to generalize localized problems from that of city-wide problems. Computer modeling is becoming an increasingly important tool when examining how cities operate. Agent-based models allow for testing of different hypotheses and theories for urban change, thus leading to a greater understanding of how cities work. This paper propose a multi-agents systems/simulation model based on integration among parallel processing, coupling with vector GIS,temporal logic analysis,multi-objective evolution optimization and the integration with the rule engine. The efficiency of our approach is shown through some experimental results, which highlights how different theories can be incorporated into one model and demonstrates how the well-known principle that local action can give rise to global pattern but also how such pattern emerges as the consequence of positive feedback and learned behavior.
{"title":"Utilizing Multi Agent Simulation to Explore Cities","authors":"Jinfeng Ma, Feng Mao, Wensheng Zhou","doi":"10.1109/WKDD.2009.206","DOIUrl":"https://doi.org/10.1109/WKDD.2009.206","url":null,"abstract":"Cities are complex systems, with many dynamically changing parameters and large numbers of discrete actors. The heterogeneous nature of cities, make it difficult to generalize localized problems from that of city-wide problems. Computer modeling is becoming an increasingly important tool when examining how cities operate. Agent-based models allow for testing of different hypotheses and theories for urban change, thus leading to a greater understanding of how cities work. This paper propose a multi-agents systems/simulation model based on integration among parallel processing, coupling with vector GIS,temporal logic analysis,multi-objective evolution optimization and the integration with the rule engine. The efficiency of our approach is shown through some experimental results, which highlights how different theories can be incorporated into one model and demonstrates how the well-known principle that local action can give rise to global pattern but also how such pattern emerges as the consequence of positive feedback and learned behavior.","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123259522","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}
Bin Wang, Bin Yang, Jinfang Sheng, Meng Chen, Guoqiang He
This paper studies various training algorithms of BP neural network and proposes an improved conjugate gradient algorithm which combines conjugate gradient algorithm with inexact line search route based on generalized Curry principle. The proposed algorithm has global convergence, optimizes the learning steps using new line search rules and improves the convergence speed. The new algorithm is applied in the cost prediction of actual sintering production. Simulation results show that the algorithm has better convergence compared with traditional conjugate gradient algorithms. The MSE of prediction is 0.0098 and accuracy rate reaches 94.31%.
{"title":"An Improved Neural Network Algorithm and its Application in Sinter Cost Prediction","authors":"Bin Wang, Bin Yang, Jinfang Sheng, Meng Chen, Guoqiang He","doi":"10.1109/WKDD.2009.180","DOIUrl":"https://doi.org/10.1109/WKDD.2009.180","url":null,"abstract":"This paper studies various training algorithms of BP neural network and proposes an improved conjugate gradient algorithm which combines conjugate gradient algorithm with inexact line search route based on generalized Curry principle. The proposed algorithm has global convergence, optimizes the learning steps using new line search rules and improves the convergence speed. The new algorithm is applied in the cost prediction of actual sintering production. Simulation results show that the algorithm has better convergence compared with traditional conjugate gradient algorithms. The MSE of prediction is 0.0098 and accuracy rate reaches 94.31%.","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"387 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126739294","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：