In this paper, new classes of generalized type I functions are introduced by combining the concepts of B- (p, r, a)-invex function and generalized type I function. several optimality sufficient conditions are obtained for multi-objective programming under weaker convexity.
{"title":"Optimality Conditions under Generalized Type I Invexity","authors":"Xiangyou Li, Qingxiang Zhang","doi":"10.1109/CIS.2013.170","DOIUrl":"https://doi.org/10.1109/CIS.2013.170","url":null,"abstract":"In this paper, new classes of generalized type I functions are introduced by combining the concepts of B- (p, r, a)-invex function and generalized type I function. several optimality sufficient conditions are obtained for multi-objective programming under weaker convexity.","PeriodicalId":294223,"journal":{"name":"2013 Ninth International Conference on Computational Intelligence and Security","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128776142","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 applications of CUSUM quality control chart to financial markets is not new in literature. It has been shown that the filter trading rule is mathematically equivalent to the CUSUM quality control test as both are based on change point detection theory. Filter trading rule has been extensively studied in the field of testing the financial market efficiency. In this paper, we studied the filter trading rule under a model assumption of Markov switching model (MSM) which has become very popular in financial applications. From our studies, it is found that the filter trading rule may beat the buy-and-hold strategy when the two-regime MSM fit the asset returns well.
{"title":"An Application of CUSUM Chart on Financial Trading","authors":"Ling Xin, P. Yu, K. Lam","doi":"10.1109/CIS.2013.44","DOIUrl":"https://doi.org/10.1109/CIS.2013.44","url":null,"abstract":"The applications of CUSUM quality control chart to financial markets is not new in literature. It has been shown that the filter trading rule is mathematically equivalent to the CUSUM quality control test as both are based on change point detection theory. Filter trading rule has been extensively studied in the field of testing the financial market efficiency. In this paper, we studied the filter trading rule under a model assumption of Markov switching model (MSM) which has become very popular in financial applications. From our studies, it is found that the filter trading rule may beat the buy-and-hold strategy when the two-regime MSM fit the asset returns well.","PeriodicalId":294223,"journal":{"name":"2013 Ninth International Conference on Computational Intelligence and Security","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128812093","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, a new model for reputation collusion detection is established based on hyper graph theory. Users of a e-commerce system may have some kind of relationship according to the corresponding application. Such kind of connected users can be viewed as vertices jointed by hyper-edges, and thus formed a hyper graph. Colluders are those clusters in the hyper graph that all of their vertices are closely connected via hyper edges. Thus the task of detecting colluders from common users is converted to be a problem of finding those tightly connected clusters, which can be found by splitting the hyper graph according to modularity defined in this paper. Experiment shows that such modularity attribute of colluder groups are generally of large values while are of little value for common user groups, which demonstrates the effectiveness of our proposed model and algorithm.
{"title":"Colluder Detection Based on Hypergraph Decomposition","authors":"Jicheng Hu, Dongjian Fang, Xiaofeng Wei, Jian Xie","doi":"10.1109/CIS.2013.138","DOIUrl":"https://doi.org/10.1109/CIS.2013.138","url":null,"abstract":"In this paper, a new model for reputation collusion detection is established based on hyper graph theory. Users of a e-commerce system may have some kind of relationship according to the corresponding application. Such kind of connected users can be viewed as vertices jointed by hyper-edges, and thus formed a hyper graph. Colluders are those clusters in the hyper graph that all of their vertices are closely connected via hyper edges. Thus the task of detecting colluders from common users is converted to be a problem of finding those tightly connected clusters, which can be found by splitting the hyper graph according to modularity defined in this paper. Experiment shows that such modularity attribute of colluder groups are generally of large values while are of little value for common user groups, which demonstrates the effectiveness of our proposed model and algorithm.","PeriodicalId":294223,"journal":{"name":"2013 Ninth International Conference on Computational Intelligence and Security","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116686215","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}
Bus trip is a healthy way to travel, and optimal bus dispatching decides social and economic benefits. Based on the analysis for both the existing traffic environment and bus dispatching, a mathematical model of the regional multi-line bus dispatching within is proposed in this paper such that the goal function of this model are the average maximal satisfaction for passengers, the average loading rate of the maximum and the minimal average bus departure frequency of the bus company, respectively. Furthermore, the genetic algorithm is improved further to prevent premature for the algorithm and ensure fast convergence of the algorithm. Finally, case analysis gives a satisfying departure interval for each time period in a day and verifies the effectiveness of the algorithm.
{"title":"Improved Genetic Algorithm for the Regional Multi-line Bus Dispatching","authors":"Jinling Du, L. Cao","doi":"10.1109/CIS.2013.183","DOIUrl":"https://doi.org/10.1109/CIS.2013.183","url":null,"abstract":"Bus trip is a healthy way to travel, and optimal bus dispatching decides social and economic benefits. Based on the analysis for both the existing traffic environment and bus dispatching, a mathematical model of the regional multi-line bus dispatching within is proposed in this paper such that the goal function of this model are the average maximal satisfaction for passengers, the average loading rate of the maximum and the minimal average bus departure frequency of the bus company, respectively. Furthermore, the genetic algorithm is improved further to prevent premature for the algorithm and ensure fast convergence of the algorithm. Finally, case analysis gives a satisfying departure interval for each time period in a day and verifies the effectiveness of the algorithm.","PeriodicalId":294223,"journal":{"name":"2013 Ninth International Conference on Computational Intelligence and Security","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121200858","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}
Shot-Boundary detection is a critical step in video retrieval system. The accuracy of Shot-Boundary detection directly affects the retrieval system performance. There are many shot boundary detection algorithms, such as pixel-based algorithms and histogram-based algorithms, etc. However, these shot boundary detection algorithms are not good at detecting motion shot. This paper proposes an adaptive shot boundary detection algorithm based on HSV space. Comparing with existing pixel-based algorithms, our algorithm consider the characteristics of two shot transitions and uses different data processing in cut and gradual transition detection. Compared with histogram method, the algorithm using partitioning technology, combined with the relationship between spatial and color information. Experimental results show that the proposed method has stronger anti-interference performance compared with existing algorithms.
{"title":"A Method of Shot-Boundary Detection Based on HSV Space","authors":"Q. Fu, Yichun Zhang, Liyong Xu, Huixin Li","doi":"10.1109/CIS.2013.53","DOIUrl":"https://doi.org/10.1109/CIS.2013.53","url":null,"abstract":"Shot-Boundary detection is a critical step in video retrieval system. The accuracy of Shot-Boundary detection directly affects the retrieval system performance. There are many shot boundary detection algorithms, such as pixel-based algorithms and histogram-based algorithms, etc. However, these shot boundary detection algorithms are not good at detecting motion shot. This paper proposes an adaptive shot boundary detection algorithm based on HSV space. Comparing with existing pixel-based algorithms, our algorithm consider the characteristics of two shot transitions and uses different data processing in cut and gradual transition detection. Compared with histogram method, the algorithm using partitioning technology, combined with the relationship between spatial and color information. Experimental results show that the proposed method has stronger anti-interference performance compared with existing algorithms.","PeriodicalId":294223,"journal":{"name":"2013 Ninth International Conference on Computational Intelligence and Security","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116209925","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 optical touch platform, this research firstly analyzes the principle of contact detecting and puts forward a method for single contact identifying and positioning. Secondly, facing the problems such as the disconnection often occurring in the process of user's fast lineation by the traditional contact positioning method, we have introduced the Kalman filtering algorithm for tracking the contact movement and have improved the model of the contact moving system to increase the dimensionality of the moving system state. The simulation test result on the OpenCV Platform has shown that the improved Kalman filtering algorithm can effectively enhance the tracking effect of the moving contact.
{"title":"An Improved Kalman Filtering Algorithm for Moving Contact Detecting and Tracking","authors":"Xiuqin Deng, Weijia Cai, Chengyan Fang, Weiqing Kong, Jia Liao","doi":"10.1109/CIS.2013.56","DOIUrl":"https://doi.org/10.1109/CIS.2013.56","url":null,"abstract":"Based on the optical touch platform, this research firstly analyzes the principle of contact detecting and puts forward a method for single contact identifying and positioning. Secondly, facing the problems such as the disconnection often occurring in the process of user's fast lineation by the traditional contact positioning method, we have introduced the Kalman filtering algorithm for tracking the contact movement and have improved the model of the contact moving system to increase the dimensionality of the moving system state. The simulation test result on the OpenCV Platform has shown that the improved Kalman filtering algorithm can effectively enhance the tracking effect of the moving contact.","PeriodicalId":294223,"journal":{"name":"2013 Ninth International Conference on Computational Intelligence and Security","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116454289","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 Korean, the pronunciations of phonemes are severely affected by their contexts. Thus, using phonemes directly translated from their written forms as basic units for acoustic modeling is problematic, as these units lack the ability to capture the complex pronunciation variations occurred in continuous speech. Allophone, a sub-phone unit in phonetics but served as independent phoneme in speech recognition, is considered to have the ability to describe complex pronunciation variations. This paper presents a novel approach called Automatic Allophone Deriving (AAD). In this approach, statistics from Gaussian Mixture Models are used to create measurements for allophone candidates, and decision trees are used to derive allophones. Question set used by the decision tree is also generated automatically, since we assumed no linguistic knowledge would be used in this approach. This paper also adopts long-time features over conventional cepstral features to capture acoustic information over several hundred milliseconds for AAD, as co-articulation effects are unlikely to be limited to a single phoneme. Experiment shows that AAD outperforms previous approaches which derive allophones from linguistic knowledge. Additional experiments use long-time features directly in acoustic modeling. The results show that performance improvement achieved by using the same allophones can be significantly improved by using long-time features, compared with corresponding baselines.
{"title":"Automatic Allophone Deriving for Korean Speech Recognition","authors":"Ji Xu, Yujing Si, Jielin Pan, Yonghong Yan","doi":"10.1109/CIS.2013.169","DOIUrl":"https://doi.org/10.1109/CIS.2013.169","url":null,"abstract":"In Korean, the pronunciations of phonemes are severely affected by their contexts. Thus, using phonemes directly translated from their written forms as basic units for acoustic modeling is problematic, as these units lack the ability to capture the complex pronunciation variations occurred in continuous speech. Allophone, a sub-phone unit in phonetics but served as independent phoneme in speech recognition, is considered to have the ability to describe complex pronunciation variations. This paper presents a novel approach called Automatic Allophone Deriving (AAD). In this approach, statistics from Gaussian Mixture Models are used to create measurements for allophone candidates, and decision trees are used to derive allophones. Question set used by the decision tree is also generated automatically, since we assumed no linguistic knowledge would be used in this approach. This paper also adopts long-time features over conventional cepstral features to capture acoustic information over several hundred milliseconds for AAD, as co-articulation effects are unlikely to be limited to a single phoneme. Experiment shows that AAD outperforms previous approaches which derive allophones from linguistic knowledge. Additional experiments use long-time features directly in acoustic modeling. The results show that performance improvement achieved by using the same allophones can be significantly improved by using long-time features, compared with corresponding baselines.","PeriodicalId":294223,"journal":{"name":"2013 Ninth International Conference on Computational Intelligence and Security","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115791759","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}
B. Shuai, Haifeng Li, Mengjun Li, Quan Zhang, Chaojing Tang
In order to solve the problems of traditional SVM classifier for software defect prediction, this paper proposes a novel dynamic SVM method based on improved cost-sensitive SVM (CSSVM) which is optimized by the Genetic Algorithm (GA). Through selecting the geometric classification accuracy as the fitness function, the GA method could improve the performance of CSSVM by enhancing the accuracy of defective modules and reducing the total cost in the whole decision. Experimental results show that the GA-CSSVM method could achieve higher AUC value which denotes better prediction accuracy both for minority and majority samples in the imbalanced software defect data set.
{"title":"Software Defect Prediction Using Dynamic Support Vector Machine","authors":"B. Shuai, Haifeng Li, Mengjun Li, Quan Zhang, Chaojing Tang","doi":"10.1109/CIS.2013.61","DOIUrl":"https://doi.org/10.1109/CIS.2013.61","url":null,"abstract":"In order to solve the problems of traditional SVM classifier for software defect prediction, this paper proposes a novel dynamic SVM method based on improved cost-sensitive SVM (CSSVM) which is optimized by the Genetic Algorithm (GA). Through selecting the geometric classification accuracy as the fitness function, the GA method could improve the performance of CSSVM by enhancing the accuracy of defective modules and reducing the total cost in the whole decision. Experimental results show that the GA-CSSVM method could achieve higher AUC value which denotes better prediction accuracy both for minority and majority samples in the imbalanced software defect data set.","PeriodicalId":294223,"journal":{"name":"2013 Ninth International Conference on Computational Intelligence and Security","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122347135","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}
Xin-Lei Feng, Xiaoli Yang, Zhihe Zhang, Zhongwei Si
In this paper, we consider group consensus problem with switching topology by giving a kind of new protocol in which communication graph weights are all nonnegative. This is also consistent with classic protocols. The sufficient conditions which group consensus under this kind of protocols can reach for both single and second order multi-agent system are obtained. Finally, numerical examples are given to illustrate our theoretical results.
{"title":"Group Consensus with Switching Topology of Multi-agent Systems","authors":"Xin-Lei Feng, Xiaoli Yang, Zhihe Zhang, Zhongwei Si","doi":"10.1109/CIS.2013.68","DOIUrl":"https://doi.org/10.1109/CIS.2013.68","url":null,"abstract":"In this paper, we consider group consensus problem with switching topology by giving a kind of new protocol in which communication graph weights are all nonnegative. This is also consistent with classic protocols. The sufficient conditions which group consensus under this kind of protocols can reach for both single and second order multi-agent system are obtained. Finally, numerical examples are given to illustrate our theoretical results.","PeriodicalId":294223,"journal":{"name":"2013 Ninth International Conference on Computational Intelligence and Security","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122372849","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}
When determining the weights of the factor influencing the cluster system load balancing, judgments are inevitably somehow subjective, which will affect the results of decision making. Reducing the influence on weights from subjective factors as much as possible is very important for load balancing. This paper introduces the group decision theory based on analytic hierarchy process (AHP) and constructs load balancing model based on the group AHP. The dynamic weights of each expert can be obtained by analyzing the similarity of judgment matrixes experts offer, and then we can get the objective and representative polymerization decisive opinions which enhance the reliability of the decision-making results. The experiments in the paper prove the validity of the method which is simple and easy to implement.
{"title":"Load Balancing Based on Group Analytic Hierarchy Process","authors":"Jiandong Zhang, Xuan Ma, Jin Yang, Zhonghua Li","doi":"10.1109/CIS.2013.165","DOIUrl":"https://doi.org/10.1109/CIS.2013.165","url":null,"abstract":"When determining the weights of the factor influencing the cluster system load balancing, judgments are inevitably somehow subjective, which will affect the results of decision making. Reducing the influence on weights from subjective factors as much as possible is very important for load balancing. This paper introduces the group decision theory based on analytic hierarchy process (AHP) and constructs load balancing model based on the group AHP. The dynamic weights of each expert can be obtained by analyzing the similarity of judgment matrixes experts offer, and then we can get the objective and representative polymerization decisive opinions which enhance the reliability of the decision-making results. The experiments in the paper prove the validity of the method which is simple and easy to implement.","PeriodicalId":294223,"journal":{"name":"2013 Ninth International Conference on Computational Intelligence and Security","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128087101","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：