Opposition-based Differential Evolution (ODE) has been proved to be an effective method to Differential Evolution (DE) in solving many optimization functions, and it's faster and more robust convergence than classical DE. In this paper, a fast ODE algorithm (FODE), using a local search method with Cauchy mutation is proposed. The simulation experiments are conducted on a comprehensive set of 10 complex benchmark functions. Compared with ODE, FODE is faster and more robust.
{"title":"A Fast Opposition-Based Differential Evolution with Cauchy Mutation","authors":"Yong Wu, Bin Zhao, Jinglei Guo","doi":"10.1109/GCIS.2012.91","DOIUrl":"https://doi.org/10.1109/GCIS.2012.91","url":null,"abstract":"Opposition-based Differential Evolution (ODE) has been proved to be an effective method to Differential Evolution (DE) in solving many optimization functions, and it's faster and more robust convergence than classical DE. In this paper, a fast ODE algorithm (FODE), using a local search method with Cauchy mutation is proposed. The simulation experiments are conducted on a comprehensive set of 10 complex benchmark functions. Compared with ODE, FODE is faster and more robust.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115162947","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}
Novelty detection builds a model only with a large number of normal samples to detect unknown abnormalities. Based on the kernel theory and the optimization method, One-Class Support Vector Machine (OCSVM) can build a high-performance detection model with only a small part of training samples. As a result, OCSVM has become a very popular novelty detection method. However, with the increasing of the sensor precision and the data acquisition frequency in large-scale complex production processes, the collected data present high-dimension and more complex trend. Each data shows obviously functional nature (called functional data). Therefore, How to deal with these functional data and to dig out the production performance messages in them brings a new challenge to novelty detection. For this purpose, this paper proposes an OCSVM algorithm based on Functional Data Analysis (FDA), which is called Functional OCSVM. The experimental results show that Functional OCSVM can achieve better detecting results than original OCSVM by using the functional nature of data.
新颖性检测是用大量的正常样本建立一个模型来检测未知的异常。单类支持向量机(OCSVM)基于核理论和优化方法，只用一小部分训练样本就能建立高性能的检测模型。因此，OCSVM已成为一种非常流行的新颖性检测方法。然而，随着大规模复杂生产过程中传感器精度的提高和数据采集频率的提高，采集到的数据呈现出高维化、复杂化的趋势。每个数据都具有明显的功能性(称为功能性数据)。因此，如何对这些功能数据进行处理，并从中挖掘出产品性能信息，对新颖性检测提出了新的挑战。为此，本文提出了一种基于功能性数据分析(Functional Data Analysis, FDA)的OCSVM算法，称为功能性OCSVM。实验结果表明，利用数据的功能特性，功能OCSVM可以获得比原始OCSVM更好的检测效果。
{"title":"One-Class Support Vector Machine for Functional Data Novelty Detection","authors":"Ma Yao, Huangang Wang","doi":"10.1109/GCIS.2012.19","DOIUrl":"https://doi.org/10.1109/GCIS.2012.19","url":null,"abstract":"Novelty detection builds a model only with a large number of normal samples to detect unknown abnormalities. Based on the kernel theory and the optimization method, One-Class Support Vector Machine (OCSVM) can build a high-performance detection model with only a small part of training samples. As a result, OCSVM has become a very popular novelty detection method. However, with the increasing of the sensor precision and the data acquisition frequency in large-scale complex production processes, the collected data present high-dimension and more complex trend. Each data shows obviously functional nature (called functional data). Therefore, How to deal with these functional data and to dig out the production performance messages in them brings a new challenge to novelty detection. For this purpose, this paper proposes an OCSVM algorithm based on Functional Data Analysis (FDA), which is called Functional OCSVM. The experimental results show that Functional OCSVM can achieve better detecting results than original OCSVM by using the functional nature of data.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123085630","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 open system, the user nodes and resource nodes are variable, it is tiresome for the system administrator to assign roles for the users, and it is almost impossible to check their priorities to access different kind of resources in the system in which the traditional Role Based Access Control (RBAC) model is adapted. To simplify the access control and standardize security strategy in open system, a flexible RBAC model based on trust is proposed. Use the evaluation between the user node and resource node to calculate the direct trust of them, and employ the evaluation among the resource nodes to get the recommended trust of the resource nodes. Using two trust values, together with the session history of user nodes and resource nodes, the system assigns the roles as well as its corresponding priorities for the user node flexibly, and recommends proper resource nodes to process their assignments. AIMD (Additive-increase, multiplicative-decrease) algorithm is adopted in the trust evaluation of the system to punish the node with malicious behaviors. Also, the notion of accuracy is introduced into the system to make the evaluation between the user and resource reasonable and objective.
{"title":"A Flexible RBAC Model Based on Trust in Open System","authors":"Wenyang Deng, Zhouyi Zhou","doi":"10.1109/GCIS.2012.79","DOIUrl":"https://doi.org/10.1109/GCIS.2012.79","url":null,"abstract":"In open system, the user nodes and resource nodes are variable, it is tiresome for the system administrator to assign roles for the users, and it is almost impossible to check their priorities to access different kind of resources in the system in which the traditional Role Based Access Control (RBAC) model is adapted. To simplify the access control and standardize security strategy in open system, a flexible RBAC model based on trust is proposed. Use the evaluation between the user node and resource node to calculate the direct trust of them, and employ the evaluation among the resource nodes to get the recommended trust of the resource nodes. Using two trust values, together with the session history of user nodes and resource nodes, the system assigns the roles as well as its corresponding priorities for the user node flexibly, and recommends proper resource nodes to process their assignments. AIMD (Additive-increase, multiplicative-decrease) algorithm is adopted in the trust evaluation of the system to punish the node with malicious behaviors. Also, the notion of accuracy is introduced into the system to make the evaluation between the user and resource reasonable and objective.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127495108","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 P-sets, attribute transfer causes element transfer, thus the information granulation of P-sets changes. From the aspect of granulation, this paper gives the information granulation of P-sets, analyzes the dynamic characteristic of information granulation, and makes its application in the image recognition, provides a new theory for image recognition.
{"title":"Dynamic Characteristic Analysis in Granularity of P-sets and Its Application on Face Recognition","authors":"Yan Shan, Chunying Zhang","doi":"10.1109/GCIS.2012.32","DOIUrl":"https://doi.org/10.1109/GCIS.2012.32","url":null,"abstract":"In P-sets, attribute transfer causes element transfer, thus the information granulation of P-sets changes. From the aspect of granulation, this paper gives the information granulation of P-sets, analyzes the dynamic characteristic of information granulation, and makes its application in the image recognition, provides a new theory for image recognition.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125788569","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}
With the aim of solving the problems of complex Petri nets system parallelization and simulation execution, several methods are proposed to transform senior Petri nets systems, such as color and predicate/transition etc. into the Place/Transition nets, so as to simulate them to run concurrently. In accordance with the characteristics and the internal relations between senior Petri nets of color and predicate/transition, and P/T nets systems, the structural model and algebraic model are studied, and the validity of the methods of transformation is verified through case-studying and programming. Experimental results show that the methods proposed is feasible and effective.
{"title":"Research on Methods of Transformation of Petri Nets Systems into the Place/Transition Nets","authors":"Wenjing Li, Wen Yang, Weizhi Liao, Shuang Li","doi":"10.1109/GCIS.2012.33","DOIUrl":"https://doi.org/10.1109/GCIS.2012.33","url":null,"abstract":"With the aim of solving the problems of complex Petri nets system parallelization and simulation execution, several methods are proposed to transform senior Petri nets systems, such as color and predicate/transition etc. into the Place/Transition nets, so as to simulate them to run concurrently. In accordance with the characteristics and the internal relations between senior Petri nets of color and predicate/transition, and P/T nets systems, the structural model and algebraic model are studied, and the validity of the methods of transformation is verified through case-studying and programming. Experimental results show that the methods proposed is feasible and effective.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126135295","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}
Particle Swarm Optimization has been applied in many optimization problems. In this paper, we proposed a new algorithm based on PSO and applied to optimal the weighted fuzzy neural network. It takes some measures to avoid the algorithm into a local convergence and determine the structure of the fuzzy neural network based on the effective rules. Satisfactory results through experiments are obtained.
{"title":"Particle Swarm Optimization of Weighted Fuzzy Neural Network Model","authors":"Ming Ma, Li-Biao Zhang","doi":"10.1109/GCIS.2012.12","DOIUrl":"https://doi.org/10.1109/GCIS.2012.12","url":null,"abstract":"Particle Swarm Optimization has been applied in many optimization problems. In this paper, we proposed a new algorithm based on PSO and applied to optimal the weighted fuzzy neural network. It takes some measures to avoid the algorithm into a local convergence and determine the structure of the fuzzy neural network based on the effective rules. Satisfactory results through experiments are obtained.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115356946","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}
Using balance sheet data for a panel of Chinese Listed firms, we try to find evidence of the balance sheet channel of monetary policy transmission. The results indicate that the quality of firms' balance sheet during the tighten period is worse than the quality during the loose period, and the effect of changes in monetary policy on the quality of firms' balance sheet is asymmetric over time. In periods of tight monetary conditions, M1 has significant positive correlation with the interest bear ratio, while the correlation is not significant during loose periods. The results also suggest that the balance sheet channel of monetary policy transmission is not subject to the nature of corporate, while have significant positive correlation with ownership concentration. Small firms bear most of the reductions, they suffer more from monetary tightening than big firms.
{"title":"The Balance Sheet Channel of Monetary Policy Transmission: Evidence from Chinese Listed Companies","authors":"Zhi-xin Liu, Xin Pang, Lingling Huang","doi":"10.1109/GCIS.2012.54","DOIUrl":"https://doi.org/10.1109/GCIS.2012.54","url":null,"abstract":"Using balance sheet data for a panel of Chinese Listed firms, we try to find evidence of the balance sheet channel of monetary policy transmission. The results indicate that the quality of firms' balance sheet during the tighten period is worse than the quality during the loose period, and the effect of changes in monetary policy on the quality of firms' balance sheet is asymmetric over time. In periods of tight monetary conditions, M1 has significant positive correlation with the interest bear ratio, while the correlation is not significant during loose periods. The results also suggest that the balance sheet channel of monetary policy transmission is not subject to the nature of corporate, while have significant positive correlation with ownership concentration. Small firms bear most of the reductions, they suffer more from monetary tightening than big firms.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"34 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116056654","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}
Designs a conceptual model of service template based on SMCAVS (Soft Man Component dynamic Evolution System), which is called SMS (Soft Man Service). First, establish a hierarchical and scalable model, by defining the service body, service bindings, service ports, sub-services, and other elements. Second, the DTD specification document is given, which is used to describe the information of the SMS service template. And the storage and management methods are designed on this basis. At last, verify the design of the SMS conceptual model is correct and reliable, through the test of service componentization.
{"title":"Research on SMC Based Service","authors":"Qi Wang, G. Zeng","doi":"10.1109/GCIS.2012.51","DOIUrl":"https://doi.org/10.1109/GCIS.2012.51","url":null,"abstract":"Designs a conceptual model of service template based on SMCAVS (Soft Man Component dynamic Evolution System), which is called SMS (Soft Man Service). First, establish a hierarchical and scalable model, by defining the service body, service bindings, service ports, sub-services, and other elements. Second, the DTD specification document is given, which is used to describe the information of the SMS service template. And the storage and management methods are designed on this basis. At last, verify the design of the SMS conceptual model is correct and reliable, through the test of service componentization.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122994381","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}
Through using the ArcGIS software as the platform, and taking DEM analysis, raster calculation and spatial interpolation of spatial analysis technology as the core method, this paper selects Menghai County as the study area, combines with the Delphi method, analytic hierarchy process, fuzzy membership function, farmland Integrated Fertility Index ( IFI ) and other methods, to establish major factors of influence and their weights for the farmland land productivity, as well as built a comprehensive evaluation system and it's spatial computing model. Meanwhile, the analysis such as spatial distribution, area statistics and farmland nutrient analysis for the evaluating results is also discussed in detail. The experimental results and analysis show that, 51575.73 hectares of cultivated land in Menghai County is divided into six grades, which percentages on the total farmland from grade one to grade six respectively are 14.12%, 27.4%, 20.17%, 17.23%, 12.70% and 8.38%, and the level over three grade of cultivated land occupies only less than 60%. As a result, it could be declared that the overall situation of cultivated land fertility is not good, which needs the government to adjust measures to local conditions to maintain the existing quality of cultivated land resources, as well as to enhance the farming ability of cultivated land from level of grade 3, especially grade 4 and 5 to higher level.
{"title":"GIS-Based Evaluating and Analysis for Farmland Fertility of Men-hai County","authors":"Quanli Xu, Kun Yang, Jun-hua Yi, Li-yang Li","doi":"10.1109/GCIS.2012.30","DOIUrl":"https://doi.org/10.1109/GCIS.2012.30","url":null,"abstract":"Through using the ArcGIS software as the platform, and taking DEM analysis, raster calculation and spatial interpolation of spatial analysis technology as the core method, this paper selects Menghai County as the study area, combines with the Delphi method, analytic hierarchy process, fuzzy membership function, farmland Integrated Fertility Index ( IFI ) and other methods, to establish major factors of influence and their weights for the farmland land productivity, as well as built a comprehensive evaluation system and it's spatial computing model. Meanwhile, the analysis such as spatial distribution, area statistics and farmland nutrient analysis for the evaluating results is also discussed in detail. The experimental results and analysis show that, 51575.73 hectares of cultivated land in Menghai County is divided into six grades, which percentages on the total farmland from grade one to grade six respectively are 14.12%, 27.4%, 20.17%, 17.23%, 12.70% and 8.38%, and the level over three grade of cultivated land occupies only less than 60%. As a result, it could be declared that the overall situation of cultivated land fertility is not good, which needs the government to adjust measures to local conditions to maintain the existing quality of cultivated land resources, as well as to enhance the farming ability of cultivated land from level of grade 3, especially grade 4 and 5 to higher level.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114460673","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}
N-SA K-anonymity Model: A Model Exclusive of Tuple Suppression Technique is used to protect released data which contains multiple sensitive attributes. On the basis of K-anonymity model sensitive information cannot be distinguished from at least K-1 individuals whose information also appears in the release. N-SA K-anonymity model proposed to maintain the confidentiality of respondents. Tuple suppression causes data loss as well as disturbs the accuracy of sensitive information. Tuple suppression is applied on record when particular record not satisfying K factor. If multiple dissimilar records present in dataset increases the percentage of data distortion. N-SA K-anonymity model suggest adding extra records from population to satisfy not only K-anonymity also increase data availability as well as help to maintain the accuracy of multiple sensitive information. Records are added in such a way, they will not disturb accuracy of multiple sensitive information.
N-SA k -匿名模型:一种排除元组抑制技术的模型，用于保护包含多个敏感属性的发布数据。根据k -匿名模型，敏感信息不能与至少K-1个个体区分，这些个体的信息也出现在发布中。提出N-SA - k匿名模型，以保持被调查者的机密性。元组抑制不仅会导致数据丢失，还会影响敏感信息的准确性。当特定记录不满足K因子时，对记录应用元组抑制。如果数据集中存在多个不同的记录，则会增加数据失真的百分比。N-SA k -匿名模型建议从人口中增加额外的记录，不仅满足k -匿名性，还可以提高数据的可用性，并有助于保持多个敏感信息的准确性。以这种方式添加记录，不会干扰多个敏感信息的准确性。
{"title":"N-SA K-anonymity Model: A Model Exclusive of Tuple Suppression Technique","authors":"N. Maheshwarkar, K. Pathak, V. Chourey","doi":"10.1109/GCIS.2012.77","DOIUrl":"https://doi.org/10.1109/GCIS.2012.77","url":null,"abstract":"N-SA K-anonymity Model: A Model Exclusive of Tuple Suppression Technique is used to protect released data which contains multiple sensitive attributes. On the basis of K-anonymity model sensitive information cannot be distinguished from at least K-1 individuals whose information also appears in the release. N-SA K-anonymity model proposed to maintain the confidentiality of respondents. Tuple suppression causes data loss as well as disturbs the accuracy of sensitive information. Tuple suppression is applied on record when particular record not satisfying K factor. If multiple dissimilar records present in dataset increases the percentage of data distortion. N-SA K-anonymity model suggest adding extra records from population to satisfy not only K-anonymity also increase data availability as well as help to maintain the accuracy of multiple sensitive information. Records are added in such a way, they will not disturb accuracy of multiple sensitive information.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126234409","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：