Pub Date : 2009-09-22DOI: 10.1109/GRC.2009.5255149
W. Deng, Qinghua Zheng, Lin Chen
There are two key issues for collaborative filtering: curse of dimension and long-consuming training. In our proposed algorithm, the curse of dimension problem is resolved by the proposed Reduced-SVD technique effectively and long-consuming training is addressed by Extreme Learning Machine (ELM) which is hundreds of times faster than iterative algorithms (e.g. BP). This will enable the algorithm more accurate and faster.
{"title":"A fast and accurate collaborative filter","authors":"W. Deng, Qinghua Zheng, Lin Chen","doi":"10.1109/GRC.2009.5255149","DOIUrl":"https://doi.org/10.1109/GRC.2009.5255149","url":null,"abstract":"There are two key issues for collaborative filtering: curse of dimension and long-consuming training. In our proposed algorithm, the curse of dimension problem is resolved by the proposed Reduced-SVD technique effectively and long-consuming training is addressed by Extreme Learning Machine (ELM) which is hundreds of times faster than iterative algorithms (e.g. BP). This will enable the algorithm more accurate and faster.","PeriodicalId":388774,"journal":{"name":"2009 IEEE International Conference on Granular Computing","volume":"19 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114091305","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 : 2009-09-22DOI: 10.1109/GRC.2009.5255059
Shuliang Wang, He-hua Chi, Xiao Feng, Jinfei Yin
In order to make the human facial expression recognition and analysis effectively, cloud model is used to mine the knowledge of human facial expression in this paper. Backward cloud generator without certainty degree treats the original input image as a cloud droplet image. The outputs are used to describe the three numerical characteristics-(Ex, En, He). How the three numerical characteristics of the cloud model (Ex, En, He) to embody the knowledge of facial expression? With two different sets of original images, two experiments are made to explain the specific meaning of the three numerical characteristics (Ex, En, He). Under the experiments, the profound knowledge may be extracted on the facial expression, i.e. Ex is the common of standard face, En is the difference, and He is the range of the difference.
{"title":"Human facial expression mining based on cloud model","authors":"Shuliang Wang, He-hua Chi, Xiao Feng, Jinfei Yin","doi":"10.1109/GRC.2009.5255059","DOIUrl":"https://doi.org/10.1109/GRC.2009.5255059","url":null,"abstract":"In order to make the human facial expression recognition and analysis effectively, cloud model is used to mine the knowledge of human facial expression in this paper. Backward cloud generator without certainty degree treats the original input image as a cloud droplet image. The outputs are used to describe the three numerical characteristics-(Ex, En, He). How the three numerical characteristics of the cloud model (Ex, En, He) to embody the knowledge of facial expression? With two different sets of original images, two experiments are made to explain the specific meaning of the three numerical characteristics (Ex, En, He). Under the experiments, the profound knowledge may be extracted on the facial expression, i.e. Ex is the common of standard face, En is the difference, and He is the range of the difference.","PeriodicalId":388774,"journal":{"name":"2009 IEEE International Conference on Granular Computing","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114698172","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 : 2009-09-22DOI: 10.1109/GRC.2009.5255091
T. Lin
The term granular computing (GrC), roughly speaking, is jointly coined by Lin and Zadeh in the fall of 1996 (Zadeh, 1998). Since then, special interest group conferences, workshops, special sessions and special issues have gradually flourished. Many opinions have been expressed. We shall mentioned our initial idea: Zadeh gave an intuitive definition in (Zadeh, 1996) and outline his seminal paper (Zadeh, 1997), where he said “TFIG (which is GrC) • • • • are mathematics in nature.” While we share his view, but took an incremental approach. The First GrC Model (neighborhood systems or pre-topology) was investigated (Lin, 1989, 1998) from the view of topological spaces, rough sets, databases and computer security.
{"title":"Formal theory of granular computing, and two major applications","authors":"T. Lin","doi":"10.1109/GRC.2009.5255091","DOIUrl":"https://doi.org/10.1109/GRC.2009.5255091","url":null,"abstract":"The term granular computing (GrC), roughly speaking, is jointly coined by Lin and Zadeh in the fall of 1996 (Zadeh, 1998). Since then, special interest group conferences, workshops, special sessions and special issues have gradually flourished. Many opinions have been expressed. We shall mentioned our initial idea: Zadeh gave an intuitive definition in (Zadeh, 1996) and outline his seminal paper (Zadeh, 1997), where he said “TFIG (which is GrC) • • • • are mathematics in nature.” While we share his view, but took an incremental approach. The First GrC Model (neighborhood systems or pre-topology) was investigated (Lin, 1989, 1998) from the view of topological spaces, rough sets, databases and computer security.","PeriodicalId":388774,"journal":{"name":"2009 IEEE International Conference on Granular Computing","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129010085","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 : 2009-09-22DOI: 10.1109/GRC.2009.5255151
Jianhua Dai
The collection of all the rough sets of an approximation space can be made into a 3-valued Lukasiewicz algebra called rough 3-valued Lukasiewcz algebras. BCI-algebras and BCK-algebras are two important classes of logical algebras. In this paper, it is shown that a rough 3-valued Lukasiewicz algebra is a BCI-algebra and a BCK-algebra. The direct relation between rough set theory and BCI-algebras/BCK-algebras is constructed. The definition of rough BCI-algebras and rough BCK-algebras are also given.
{"title":"Rough 3-valued Lukasiewicz algebras and BCI-algebras","authors":"Jianhua Dai","doi":"10.1109/GRC.2009.5255151","DOIUrl":"https://doi.org/10.1109/GRC.2009.5255151","url":null,"abstract":"The collection of all the rough sets of an approximation space can be made into a 3-valued Lukasiewicz algebra called rough 3-valued Lukasiewcz algebras. BCI-algebras and BCK-algebras are two important classes of logical algebras. In this paper, it is shown that a rough 3-valued Lukasiewicz algebra is a BCI-algebra and a BCK-algebra. The direct relation between rough set theory and BCI-algebras/BCK-algebras is constructed. The definition of rough BCI-algebras and rough BCK-algebras are also given.","PeriodicalId":388774,"journal":{"name":"2009 IEEE International Conference on Granular Computing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128773054","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 : 2009-09-22DOI: 10.1109/GRC.2009.5255128
Y. Hamasuna, Y. Endo, S. Miyamoto
In this paper, we will propose two types of tolerant fuzzy c-means clustering with regularization terms. One is L2-regularization term and the other is L1-regularization one for tolerance vector. Introducing a concept of clusterwise tolerance, we have proposed tolerant fuzzy c-means clustering from the viewpoint of handling data more flexibly. In tolerant fuzzy c-means clustering, a constraint for tolerance vector which restricts the upper bound of tolerance vector is used. In this paper, regularization terms for tolerance vector are used instead of the constraint. First, the concept of clusterwise tolerance is introduced. Second, optimization problems for tolerant fuzzy c-means clustering with regularization term are formulated. Third, optimal solutions of these optimization problems are derived. Fourth, new clustering algorithms are constructed based on the explicit optimal solutions. Finally, effectiveness of proposed algorithms is verified through numerical examples.
{"title":"Comparison of tolerant fuzzy c-means clustering with L2- and L1-regularization","authors":"Y. Hamasuna, Y. Endo, S. Miyamoto","doi":"10.1109/GRC.2009.5255128","DOIUrl":"https://doi.org/10.1109/GRC.2009.5255128","url":null,"abstract":"In this paper, we will propose two types of tolerant fuzzy c-means clustering with regularization terms. One is L2-regularization term and the other is L1-regularization one for tolerance vector. Introducing a concept of clusterwise tolerance, we have proposed tolerant fuzzy c-means clustering from the viewpoint of handling data more flexibly. In tolerant fuzzy c-means clustering, a constraint for tolerance vector which restricts the upper bound of tolerance vector is used. In this paper, regularization terms for tolerance vector are used instead of the constraint. First, the concept of clusterwise tolerance is introduced. Second, optimization problems for tolerant fuzzy c-means clustering with regularization term are formulated. Third, optimal solutions of these optimization problems are derived. Fourth, new clustering algorithms are constructed based on the explicit optimal solutions. Finally, effectiveness of proposed algorithms is verified through numerical examples.","PeriodicalId":388774,"journal":{"name":"2009 IEEE International Conference on Granular Computing","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122964314","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 : 2009-09-22DOI: 10.1109/GRC.2009.5255041
Jian Xu, Jianhua Chen, Bin Li
We study the problem of detecting and profiling terrorists using a combination of an ensemble classifier, namely random forest and relational information. Given a database for a set of individuals characterized by both “local” attributes such as age and criminal background, and “relational” information such as communications among a subset of the individuals, with a subset of the individuals labeled as terrorist or normal people, our task is to design a classifier that captures the patterns of terrorists and achieves good accuracy in predicting the labels of the remaining part of the database. In previous work, a hybrid approach was presented that iteratively applies a flat classifier (such as decision trees, fuzzy clustering) augmented with flattened relational attributes for learning and classification. In the current work, our approach is to use random forest as the “flat” classifier in the terrorist detection setting. Random forest is known to have advantage in handling tasks with high dimensionality in input data. This merit of random forest method is very useful for relational learning if the number of “flattened” relational attributes is quite large, which is indeed the case for the terrorist detection task. We report our experiments on a synthetic terrorist database that compare the prediction accuracy of random forest with two other “flat” classifiers, namely, ordinary decision tree and fuzzy clustering. The experimental results show that random forest outperforms both ordinary decision tree and fuzzy clustering. random forest
{"title":"Random forest for relational classification with application to terrorist profiling","authors":"Jian Xu, Jianhua Chen, Bin Li","doi":"10.1109/GRC.2009.5255041","DOIUrl":"https://doi.org/10.1109/GRC.2009.5255041","url":null,"abstract":"We study the problem of detecting and profiling terrorists using a combination of an ensemble classifier, namely random forest and relational information. Given a database for a set of individuals characterized by both “local” attributes such as age and criminal background, and “relational” information such as communications among a subset of the individuals, with a subset of the individuals labeled as terrorist or normal people, our task is to design a classifier that captures the patterns of terrorists and achieves good accuracy in predicting the labels of the remaining part of the database. In previous work, a hybrid approach was presented that iteratively applies a flat classifier (such as decision trees, fuzzy clustering) augmented with flattened relational attributes for learning and classification. In the current work, our approach is to use random forest as the “flat” classifier in the terrorist detection setting. Random forest is known to have advantage in handling tasks with high dimensionality in input data. This merit of random forest method is very useful for relational learning if the number of “flattened” relational attributes is quite large, which is indeed the case for the terrorist detection task. We report our experiments on a synthetic terrorist database that compare the prediction accuracy of random forest with two other “flat” classifiers, namely, ordinary decision tree and fuzzy clustering. The experimental results show that random forest outperforms both ordinary decision tree and fuzzy clustering. random forest","PeriodicalId":388774,"journal":{"name":"2009 IEEE International Conference on Granular Computing","volume":"36 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125725978","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 : 2009-09-22DOI: 10.1109/GRC.2009.5255094
Jian-li Li, Hong Zhen, Kai Xu
Strategic alliance among liner-shipping companies is one of the key factors for enterprises to realize win-win strategy, but there also exists huge crises. We mainly utilize method of attribute coordinate to analyze the dynamic alliance behavior among shipping companies, in which relationships between cooperation and such aspects as trade-off cost and repeated gaming is discussed. We further expatriate the psychological changing process of strategic alliance in bilateral manner among enterprises.
{"title":"Multi-attribute based analysis of stability of strategic alliance among liner shipping companies","authors":"Jian-li Li, Hong Zhen, Kai Xu","doi":"10.1109/GRC.2009.5255094","DOIUrl":"https://doi.org/10.1109/GRC.2009.5255094","url":null,"abstract":"Strategic alliance among liner-shipping companies is one of the key factors for enterprises to realize win-win strategy, but there also exists huge crises. We mainly utilize method of attribute coordinate to analyze the dynamic alliance behavior among shipping companies, in which relationships between cooperation and such aspects as trade-off cost and repeated gaming is discussed. We further expatriate the psychological changing process of strategic alliance in bilateral manner among enterprises.","PeriodicalId":388774,"journal":{"name":"2009 IEEE International Conference on Granular Computing","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125738233","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 : 2009-09-22DOI: 10.1109/GRC.2009.5255038
HaiFeng Xue
The paper proposes a binding theory and security prerequisites proposition to authentication protocols. The binding theory constructs a formal theory model by which can quickly infer some security properties. Binding theory comes from the basic ideas that the key used in cryptographic protocols is the kernel component for the security protocols. Based on binding theory, security prerequisites proposition to authentication protocols is modeled and proved. Binding theory and security prerequisites proposition to authentication protocols can simply and efficiently decide security properties when authentication protocols have security weakness for authentication properties. Some classical security protocols are taken as examples to infer and discover some of their security properties broken by binding theory and security prerequisites proposition.
{"title":"Prerequisites to authentication protocols proved by binding theory","authors":"HaiFeng Xue","doi":"10.1109/GRC.2009.5255038","DOIUrl":"https://doi.org/10.1109/GRC.2009.5255038","url":null,"abstract":"The paper proposes a binding theory and security prerequisites proposition to authentication protocols. The binding theory constructs a formal theory model by which can quickly infer some security properties. Binding theory comes from the basic ideas that the key used in cryptographic protocols is the kernel component for the security protocols. Based on binding theory, security prerequisites proposition to authentication protocols is modeled and proved. Binding theory and security prerequisites proposition to authentication protocols can simply and efficiently decide security properties when authentication protocols have security weakness for authentication properties. Some classical security protocols are taken as examples to infer and discover some of their security properties broken by binding theory and security prerequisites proposition.","PeriodicalId":388774,"journal":{"name":"2009 IEEE International Conference on Granular Computing","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127090683","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 : 2009-09-22DOI: 10.1109/GRC.2009.5255106
Gang Lei, Xiaohua Li, Jiliu Zhou, Xiao-gang Gong
In this paper, a novel Geometric features extraction method for facial expression recognition is proposed. ASM automatic fiducial point location algorithm is firstly applied to a facial expression image, and then calculating the Euclidean distances between the center of gravity coordinate and the annotated fiducial points' coordinates of the face image. In order to extract the discriminate deformable geometric information, the system extracts the geometric deformation difference features between a person's neural expression and the other seven basic expressions. A multiclass Support Vector Machine (SVM) classifier is used to recognize the facial expressions. Experiments indicate that our proposed method can obtain good classification accuracy.
{"title":"Geometric feature based facial expression recognition using multiclass support vector machines","authors":"Gang Lei, Xiaohua Li, Jiliu Zhou, Xiao-gang Gong","doi":"10.1109/GRC.2009.5255106","DOIUrl":"https://doi.org/10.1109/GRC.2009.5255106","url":null,"abstract":"In this paper, a novel Geometric features extraction method for facial expression recognition is proposed. ASM automatic fiducial point location algorithm is firstly applied to a facial expression image, and then calculating the Euclidean distances between the center of gravity coordinate and the annotated fiducial points' coordinates of the face image. In order to extract the discriminate deformable geometric information, the system extracts the geometric deformation difference features between a person's neural expression and the other seven basic expressions. A multiclass Support Vector Machine (SVM) classifier is used to recognize the facial expressions. Experiments indicate that our proposed method can obtain good classification accuracy.","PeriodicalId":388774,"journal":{"name":"2009 IEEE International Conference on Granular Computing","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127384195","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 : 2009-09-22DOI: 10.1109/GRC.2009.5255157
Hongmei Chen, Tianrui Li, Chengxiang Hu, Xiaolan Ji
Approximations of a concept in the variable precision rough set model will change when an information system varies with time. Usually, it is an effective method to carry out incremental updating approximations by using existing information in the dynamic environment. This paper focuses on the incremental updating principle of computing approximations while objects in information systems dynamically change. The properties of approximations and approaches for updating approximations are provided while objects in the universe evolve over time.
{"title":"An incremental updating principle for computing approximations in information systems while the object set varies with time","authors":"Hongmei Chen, Tianrui Li, Chengxiang Hu, Xiaolan Ji","doi":"10.1109/GRC.2009.5255157","DOIUrl":"https://doi.org/10.1109/GRC.2009.5255157","url":null,"abstract":"Approximations of a concept in the variable precision rough set model will change when an information system varies with time. Usually, it is an effective method to carry out incremental updating approximations by using existing information in the dynamic environment. This paper focuses on the incremental updating principle of computing approximations while objects in information systems dynamically change. The properties of approximations and approaches for updating approximations are provided while objects in the universe evolve over time.","PeriodicalId":388774,"journal":{"name":"2009 IEEE International Conference on Granular Computing","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128123514","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：