In construction cost forecasting system, a great many uncertain factors effect the cost decision-making, so it is difficult to do effective forecasting by using traditional methods such as time series approach, regression analysis. In this paper, a nonlinear model based on RBF Neural Network is presented. There are some ameliorated measures in leaning algorithm of Radial Basis Function (RBF) neural network. The number and the centric value of hidden layer are determined by using immune algorithm. The supervisory algorithm is taken as method of adjustable weight of output layer. Using above measures, the network is optimized, and the forecast model obtains the precise and objective solution. The construction cost forecasting model based on RBF neural network, realized the classification, analysed and forecasted the construction cost and realized the intellectualized management of congstruction project., which also provide the construction manager with better decision-making basis. After considering a number of uncertain factors, the result is more accrurate. Moreover, the result of the experiment had indicated that the validity and superiority of the method of RBF neural network, comparing to artificial neural network (Back Propagation, BP). So it has broad application prospect in other fields.
在工程造价预测系统中,影响造价决策的不确定因素较多,传统的时间序列法、回归分析等方法难以进行有效的预测。本文提出了一种基于RBF神经网络的非线性模型。径向基函数(RBF)神经网络的学习算法有一些改进措施。利用免疫算法确定隐层的个数和中心值。采用监督算法作为输出层权值可调的方法。利用上述措施对网络进行了优化,预测模型得到了精确、客观的解。基于RBF神经网络的工程造价预测模型,实现了工程造价的分类、分析和预测,实现了工程造价的智能化管理。,也为施工管理者提供了更好的决策依据。在考虑了许多不确定因素后,所得结果更为准确。与人工神经网络(BP, Back Propagation)相比,实验结果表明了RBF神经网络方法的有效性和优越性。因此在其他领域具有广阔的应用前景。
{"title":"The Application of RBF Neural Network on Construction Cost Forecasting","authors":"Zhigang Ji, Yajing Li","doi":"10.1109/WKDD.2009.53","DOIUrl":"https://doi.org/10.1109/WKDD.2009.53","url":null,"abstract":"In construction cost forecasting system, a great many uncertain factors effect the cost decision-making, so it is difficult to do effective forecasting by using traditional methods such as time series approach, regression analysis. In this paper, a nonlinear model based on RBF Neural Network is presented. There are some ameliorated measures in leaning algorithm of Radial Basis Function (RBF) neural network. The number and the centric value of hidden layer are determined by using immune algorithm. The supervisory algorithm is taken as method of adjustable weight of output layer. Using above measures, the network is optimized, and the forecast model obtains the precise and objective solution. The construction cost forecasting model based on RBF neural network, realized the classification, analysed and forecasted the construction cost and realized the intellectualized management of congstruction project., which also provide the construction manager with better decision-making basis. After considering a number of uncertain factors, the result is more accrurate. Moreover, the result of the experiment had indicated that the validity and superiority of the method of RBF neural network, comparing to artificial neural network (Back Propagation, BP). So it has broad application prospect in other fields.","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"20 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":"114844586","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}
This paper presents a new theoretical data mining framework that adapts the existing data mining systems with the architecture of the Knowledge Grid, the mechanism of the ontologies, and the factor of the human-driven knowledge. Aiming at much of the research to date focusing on the technique and algorithms, the new framework describes the essential factors from systemic and technical viewpoints respectively in order to balance the effect between the two aspects.
{"title":"Promoting Data Mining Methodologies by Architecture-Level Optimizations","authors":"Xin-Jing Ge, E. Ding, Hongxia Xie","doi":"10.1109/WKDD.2009.52","DOIUrl":"https://doi.org/10.1109/WKDD.2009.52","url":null,"abstract":"This paper presents a new theoretical data mining framework that adapts the existing data mining systems with the architecture of the Knowledge Grid, the mechanism of the ontologies, and the factor of the human-driven knowledge. Aiming at much of the research to date focusing on the technique and algorithms, the new framework describes the essential factors from systemic and technical viewpoints respectively in order to balance the effect between the two aspects.","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"42 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":"129389354","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}
automated vehicle recognition is of great importance today in Intelligent Transportation Systems. In the process of the feature extraction of vehicle recognition system, the edge vector must be extracted first. However, there are many regions in an image, and it is difficult to extract the edge vectors of the regions of the image. Therefore a novel edge tracing method based on scan-line of image for vehicle recognition tasks is proposed. In particular, all of the edge vectors are extracted from the regions of the image at the same time. Experimental results are presented that show a short time in computation can be achieved.
{"title":"Research on Edge Tracing Based on Scan-Line Algorithm","authors":"Weihua Wang","doi":"10.1109/WKDD.2009.86","DOIUrl":"https://doi.org/10.1109/WKDD.2009.86","url":null,"abstract":"automated vehicle recognition is of great importance today in Intelligent Transportation Systems. In the process of the feature extraction of vehicle recognition system, the edge vector must be extracted first. However, there are many regions in an image, and it is difficult to extract the edge vectors of the regions of the image. Therefore a novel edge tracing method based on scan-line of image for vehicle recognition tasks is proposed. In particular, all of the edge vectors are extracted from the regions of the image at the same time. Experimental results are presented that show a short time in computation can be achieved.","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"124 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":"128471436","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 current research of Agent, Agent architecture is an important topic. Architecture of multi-agent system had been proposed to explain the relationship among the policy control layer, the self-control and behavior constraint layer, the organizational management layer and the middle connection layer. In policy control layer, we design two kinds of organizations, and a set of behavior rules, which can be seemed as the higher command of the self-control and behavior constraint layer. In self-control and behavior constraint layer, we implement policy driven autonomic agent model, to map regulation into agent’s behavior. Finally, the middle connection layer is used for connecting the above two layers.
{"title":"A Multi Agent Architecture Based on PGN-AO Model","authors":"Jun Hu, Shengye Huang, J. Umugwaneza","doi":"10.1109/WKDD.2009.55","DOIUrl":"https://doi.org/10.1109/WKDD.2009.55","url":null,"abstract":"In current research of Agent, Agent architecture is an important topic. Architecture of multi-agent system had been proposed to explain the relationship among the policy control layer, the self-control and behavior constraint layer, the organizational management layer and the middle connection layer. In policy control layer, we design two kinds of organizations, and a set of behavior rules, which can be seemed as the higher command of the self-control and behavior constraint layer. In self-control and behavior constraint layer, we implement policy driven autonomic agent model, to map regulation into agent’s behavior. Finally, the middle connection layer is used for connecting the above two layers.","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"7 6 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":"129338358","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}
Proposing a new algorithm which is simple but effective. Using characteristic of biological evolution and common sense to design the selection operator, improve the variation method of the crossover probability and the mutation probability. Numerical experiments show that the new algorithm is more effective than the comparative algorithm in realizing the high convergence speed, convergence precision, reducing the convergence generation and good at keeping the stability of the adaptive genetic algorithm.
{"title":"A Self-adaptive Genetic Algorithm Based on Region Balance Variation","authors":"Siyan Wang, Guoli Zhang","doi":"10.1109/WKDD.2009.167","DOIUrl":"https://doi.org/10.1109/WKDD.2009.167","url":null,"abstract":"Proposing a new algorithm which is simple but effective. Using characteristic of biological evolution and common sense to design the selection operator, improve the variation method of the crossover probability and the mutation probability. Numerical experiments show that the new algorithm is more effective than the comparative algorithm in realizing the high convergence speed, convergence precision, reducing the convergence generation and good at keeping the stability of the adaptive genetic algorithm.","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"65 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":"127110351","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 modeling and simulation of container terminal logistics system is rapidly developed and widely applied. This paper describes three parts of the modeling and simulation of container terminal logistics system, which includes Logistics system modeling technology, Verification Validation and Accreditation and screening test, and then the research approach and target, the primary coverage and the key problem is given after summarized and selected. This study is devoted to determine the key problems and the best solutions in the process of modeling and simulation, which contributes to reduce the difference between the simulation and reality system and increase the capacity and efficiency of container terminal logistics system.
{"title":"Modeling and Simulation of Container Terminal Logistics System","authors":"Li Li, Xiaodong Wang","doi":"10.1109/WKDD.2009.57","DOIUrl":"https://doi.org/10.1109/WKDD.2009.57","url":null,"abstract":"The modeling and simulation of container terminal logistics system is rapidly developed and widely applied. This paper describes three parts of the modeling and simulation of container terminal logistics system, which includes Logistics system modeling technology, Verification Validation and Accreditation and screening test, and then the research approach and target, the primary coverage and the key problem is given after summarized and selected. This study is devoted to determine the key problems and the best solutions in the process of modeling and simulation, which contributes to reduce the difference between the simulation and reality system and increase the capacity and efficiency of container terminal logistics system.","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":"130050981","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}
After entering the 1990s, a new metal oxide semiconductor device-- insulated gate bipolar transistor (IGBT) was first widely used in the industrial driving device. The voltage source converter using IGBT has the ability to turn off current and it can also carry out passive inversion by using pulse width modulation (PWM) technology, which solves the problem of DC transmission to load points without AC supply. Because of strong function and small volume of this converter, it can reduce filtering devices in converter stations, omit converter transformers and simplify the structure of converter station, it is called HVDC light. This paper emphasizes the control technology of HVDC Light system based on VSC core research and designs the experimental system of HVDC Light, including overall design, parameter configuration of main circuit and software and hardware implementation schemes, etc; among these, converter is simulated by IGBT intelligent power module (IPM) and the control algorithm of the system is realized by DSP TMS320F2812A.
{"title":"Development and Research of HVDC Light System Based on DSP","authors":"Yanping Gao, Xianqiang Lv, Xianjiu Guo","doi":"10.1109/WKDD.2009.164","DOIUrl":"https://doi.org/10.1109/WKDD.2009.164","url":null,"abstract":"After entering the 1990s, a new metal oxide semiconductor device-- insulated gate bipolar transistor (IGBT) was first widely used in the industrial driving device. The voltage source converter using IGBT has the ability to turn off current and it can also carry out passive inversion by using pulse width modulation (PWM) technology, which solves the problem of DC transmission to load points without AC supply. Because of strong function and small volume of this converter, it can reduce filtering devices in converter stations, omit converter transformers and simplify the structure of converter station, it is called HVDC light. This paper emphasizes the control technology of HVDC Light system based on VSC core research and designs the experimental system of HVDC Light, including overall design, parameter configuration of main circuit and software and hardware implementation schemes, etc; among these, converter is simulated by IGBT intelligent power module (IPM) and the control algorithm of the system is realized by DSP TMS320F2812A.","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"8 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":"129025124","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 analysis of limitations of existing Real Time Specification for Java (RTSJ) and Java developing model, we have designed a predictable real time Java developing profile which can be used to develop embedded high-reliability real-time systems. The profile adopts a three-layer developing architecture, including Creation Layer, Execution Layer and Recycle Layer. The Creation Layer creates and starts various groups of threads and objects. The Execution Layer executes threads that have been started. The Recycle Layer recovers the memory that is no longer in use. The application practice shows that the mechanisms, such as creating various groups of threads, periodic garbage collection, etc, not only guarantee the predictability of system developed with this profile, but also reduce memory usage of system requirement.
在分析现有Java实时规范(Real Time Specification for Java, RTSJ)的局限性和Java开发模型的基础上,设计了一种可预测的Java实时开发框架,可用于开发嵌入式高可靠性实时系统。该配置文件采用三层开发架构,包括创建层、执行层和回收层。创建层创建并启动各种线程和对象组。执行层执行已经启动的线程。回收层恢复不再使用的内存。应用实践表明,该配置文件所采用的创建不同线程组、定时垃圾回收等机制不仅保证了系统的可预测性,而且降低了系统对内存的使用需求。
{"title":"Predictable Real-Time Java Profile Based on RTSJ","authors":"Yong-xian Jin","doi":"10.1109/WKDD.2009.63","DOIUrl":"https://doi.org/10.1109/WKDD.2009.63","url":null,"abstract":"Based on the analysis of limitations of existing Real Time Specification for Java (RTSJ) and Java developing model, we have designed a predictable real time Java developing profile which can be used to develop embedded high-reliability real-time systems. The profile adopts a three-layer developing architecture, including Creation Layer, Execution Layer and Recycle Layer. The Creation Layer creates and starts various groups of threads and objects. The Execution Layer executes threads that have been started. The Recycle Layer recovers the memory that is no longer in use. The application practice shows that the mechanisms, such as creating various groups of threads, periodic garbage collection, etc, not only guarantee the predictability of system developed with this profile, but also reduce memory usage of system requirement.","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"25 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":"125662102","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 class of parallel manipulators known as Rotary Humanoid Wrist (RHW), which is actuated by six circular motors on the circular base and dose not involve any prismatic joint, is analyzed based on screw theory. Model of RHW is build by using simulink tools with constant length limbs. The mobility of RHW is analyzed and the optimal combination of the main parameters for maximizing the workspace volume of RHW is also given
{"title":"A Novel Parallel Manipulator for Rotary Humanoid Wrist Based on Screw Theory","authors":"Guoxin Zhang, Song Zhu, Dachang Zhu, Cui Wu","doi":"10.1109/WKDD.2009.104","DOIUrl":"https://doi.org/10.1109/WKDD.2009.104","url":null,"abstract":"A class of parallel manipulators known as Rotary Humanoid Wrist (RHW), which is actuated by six circular motors on the circular base and dose not involve any prismatic joint, is analyzed based on screw theory. Model of RHW is build by using simulink tools with constant length limbs. The mobility of RHW is analyzed and the optimal combination of the main parameters for maximizing the workspace volume of RHW is also given","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"50 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":"132255992","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}
Currently, with the popularization of the computer and Internet technologies, electronic documents have become the most important resource in enterprises or organizations. The security of documents and protecting the information resident in these documents is of paramount importance to the organization’s progress and in some cases, their survival too. Hence, electronic documents are the target of the insider abuse and attacker. Traditionally, methods of document access control protect the information of documents by setting accessing privileges. However, the weaknesses of this are the coarse granularity of control and lack of capability to adjust dramatically to adapt well to different operating context. In this paper, an information flaw security model based on colored Petri nets (CPN) is introduced, which analyze information flow dynamically and then find out the potential approaches that lead to the leak of information by examining the reachability graph of the CPN model. Consequently, we can take some measures to prevent information leaks and achieve the goal of protecting confidential information.
{"title":"Colored Petri Nets Based Modeling of Information Flow Security","authors":"Weiguo Li, Ruoyu Wu, He Huang","doi":"10.1109/WKDD.2009.171","DOIUrl":"https://doi.org/10.1109/WKDD.2009.171","url":null,"abstract":"Currently, with the popularization of the computer and Internet technologies, electronic documents have become the most important resource in enterprises or organizations. The security of documents and protecting the information resident in these documents is of paramount importance to the organization’s progress and in some cases, their survival too. Hence, electronic documents are the target of the insider abuse and attacker. Traditionally, methods of document access control protect the information of documents by setting accessing privileges. However, the weaknesses of this are the coarse granularity of control and lack of capability to adjust dramatically to adapt well to different operating context. In this paper, an information flaw security model based on colored Petri nets (CPN) is introduced, which analyze information flow dynamically and then find out the potential approaches that lead to the leak of information by examining the reachability graph of the CPN model. Consequently, we can take some measures to prevent information leaks and achieve the goal of protecting confidential information.","PeriodicalId":143250,"journal":{"name":"2009 Second International Workshop on Knowledge Discovery and Data Mining","volume":"44 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":"130252849","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}