Pub Date : 2010-12-01DOI: 10.1109/PIC.2010.5688016
B. Oshidari, Babak Nadjar Araabi
Feature extraction is an important and challenging phase of facial expression recognition problem. In this paper, an effective feature extraction method is proposed. Our facial feature representation method is based on an adaptive Gabor wavelet transform. In this method, we used a fuzzy controller for tuning the orientation parameter of filter. This filter can detect the most significant edges of facial images. Furthermore, the proposed adaptive filter improves the drawbacks of conventional Gabor filters. Nearest neighbor and multi-class Support Vector Machine (SVM) classifiers are applied for classification task. Experimental results on Japanese Female Facial Expression (JAFFE) database show that the proposed method can provide high recognition rate. The main advantage of proposed method over other methods is its flexibility.
{"title":"An effective feature extraction method for facial expression recognition using adaptive Gabor wavelet","authors":"B. Oshidari, Babak Nadjar Araabi","doi":"10.1109/PIC.2010.5688016","DOIUrl":"https://doi.org/10.1109/PIC.2010.5688016","url":null,"abstract":"Feature extraction is an important and challenging phase of facial expression recognition problem. In this paper, an effective feature extraction method is proposed. Our facial feature representation method is based on an adaptive Gabor wavelet transform. In this method, we used a fuzzy controller for tuning the orientation parameter of filter. This filter can detect the most significant edges of facial images. Furthermore, the proposed adaptive filter improves the drawbacks of conventional Gabor filters. Nearest neighbor and multi-class Support Vector Machine (SVM) classifiers are applied for classification task. Experimental results on Japanese Female Facial Expression (JAFFE) database show that the proposed method can provide high recognition rate. The main advantage of proposed method over other methods is its flexibility.","PeriodicalId":142910,"journal":{"name":"2010 IEEE International Conference on Progress in Informatics and Computing","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122125505","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 : 2010-12-01DOI: 10.1109/PIC.2010.5688002
Xin Li, Xinhuai Tang, Zhaoteng Song, X. Yuan, D. Chen
Automated Web Service composition is an important way for integrating information flexibly and quickly. However, existing composition approaches are insufficient for satisfying users' requirements. In this paper, we firstly discuss the limitations of the existing web service composition approaches and then introduce the separation model to separate the representation of web service type definitions from instance definitions in order to organize the expected thousands of web services well. At last we construct an automated web service composition system, which allows for fast and flexible composition of web services. This system AFlow consists of two subsystems: AI Planning subsystem and Service Matchmaking subsystem. The AI Planning subsystem receives the user's request to form an abstract workflow and transfer it to the Service Matchmaking subsystem. The Service Matchmaking subsystem selects the most suitable service instances according to the abstract workflow via the matchmaking engine and then generates an executable workflow to execute.
{"title":"AFlow: An Automated Web Services composition system based on the AI planning and workflow","authors":"Xin Li, Xinhuai Tang, Zhaoteng Song, X. Yuan, D. Chen","doi":"10.1109/PIC.2010.5688002","DOIUrl":"https://doi.org/10.1109/PIC.2010.5688002","url":null,"abstract":"Automated Web Service composition is an important way for integrating information flexibly and quickly. However, existing composition approaches are insufficient for satisfying users' requirements. In this paper, we firstly discuss the limitations of the existing web service composition approaches and then introduce the separation model to separate the representation of web service type definitions from instance definitions in order to organize the expected thousands of web services well. At last we construct an automated web service composition system, which allows for fast and flexible composition of web services. This system AFlow consists of two subsystems: AI Planning subsystem and Service Matchmaking subsystem. The AI Planning subsystem receives the user's request to form an abstract workflow and transfer it to the Service Matchmaking subsystem. The Service Matchmaking subsystem selects the most suitable service instances according to the abstract workflow via the matchmaking engine and then generates an executable workflow to execute.","PeriodicalId":142910,"journal":{"name":"2010 IEEE International Conference on Progress in Informatics and Computing","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129495534","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 : 2010-12-01DOI: 10.1109/PIC.2010.5687452
Emmanuel Sardis, V. Anagnostopoulos, A. Voulodimos, T. Varvarigou
Workflow control performance is a cornerstone of operational excellence in refining and calculating either the human resources or the materials that belong to a sequence of events constituting a workflow. Controlling events in real life industrial environments and monitoring them through surveillance applications has become mainstream in the refining industry and is changing the maintenance methodology surrounding control assets from predictive to condition based. This has made monitoring and diagnosing control and alarming problems challenging. Identifying specific events in a process and raising an alarm for security and safety reasons is the main point of this article. In brief we present the general system architecture of our proposed solution and an application that uses surveillance video inputs and raises appropriate alarms in case of normal or abnormal workflows. The paper also presents main issues that have been considered during our research on alarming systems and explains the main problems of applying those in industrial environments.
{"title":"On surveillance and workflow control system design","authors":"Emmanuel Sardis, V. Anagnostopoulos, A. Voulodimos, T. Varvarigou","doi":"10.1109/PIC.2010.5687452","DOIUrl":"https://doi.org/10.1109/PIC.2010.5687452","url":null,"abstract":"Workflow control performance is a cornerstone of operational excellence in refining and calculating either the human resources or the materials that belong to a sequence of events constituting a workflow. Controlling events in real life industrial environments and monitoring them through surveillance applications has become mainstream in the refining industry and is changing the maintenance methodology surrounding control assets from predictive to condition based. This has made monitoring and diagnosing control and alarming problems challenging. Identifying specific events in a process and raising an alarm for security and safety reasons is the main point of this article. In brief we present the general system architecture of our proposed solution and an application that uses surveillance video inputs and raises appropriate alarms in case of normal or abnormal workflows. The paper also presents main issues that have been considered during our research on alarming systems and explains the main problems of applying those in industrial environments.","PeriodicalId":142910,"journal":{"name":"2010 IEEE International Conference on Progress in Informatics and Computing","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128389185","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 : 2010-12-01DOI: 10.1109/PIC.2010.5687453
Ying Gao, Xiao Hu, Huiliang Liu
Copula is a powerful tool for multivariate probability analysis. Estimation of distribution algorithms are a class of optimization algorithms based on probability distribution model. This paper introduces a new estimation of distribution algorithm with multivariate Gaussian copulas. In the algorithm, Gaussian copula parameters are firstly estimated by estimating Kendall's tau and using the relationship of Kendall's tau and correlation matrix, thus, joint distribution is estimated. Then, the Monte Carte simulation is used to generate new individuals. The relative experimental results show that the new algorithm is effective.
{"title":"Estimation of distribution algorithm based on multivariate Gaussian copulas","authors":"Ying Gao, Xiao Hu, Huiliang Liu","doi":"10.1109/PIC.2010.5687453","DOIUrl":"https://doi.org/10.1109/PIC.2010.5687453","url":null,"abstract":"Copula is a powerful tool for multivariate probability analysis. Estimation of distribution algorithms are a class of optimization algorithms based on probability distribution model. This paper introduces a new estimation of distribution algorithm with multivariate Gaussian copulas. In the algorithm, Gaussian copula parameters are firstly estimated by estimating Kendall's tau and using the relationship of Kendall's tau and correlation matrix, thus, joint distribution is estimated. Then, the Monte Carte simulation is used to generate new individuals. The relative experimental results show that the new algorithm is effective.","PeriodicalId":142910,"journal":{"name":"2010 IEEE International Conference on Progress in Informatics and Computing","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129164192","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 : 2010-12-01DOI: 10.1109/PIC.2010.5687973
Yuan Liao, Juhua Huang, Qun Zeng
Intelligent vehicle obtains path information by computer vision, and tracks detected path automatically by intelligent control. Through imitating preview driving behavior of human, and integrating driving experience of excellent drivers, an simple and effective preview fuzzy control method for path tracking of intelligent vehicle is presented in this study. The preview fuzzy control method adjusts vehicle speed by preview control according to future path information and adjusts vehicle direction by fuzzy control according to present path information. Simulations and experiments show that intelligent vehicle controlled by the preview fuzzy control method can track various paths accurately, stably and robustly.
{"title":"Preview fuzzy control method for intelligent vehicle path tracking","authors":"Yuan Liao, Juhua Huang, Qun Zeng","doi":"10.1109/PIC.2010.5687973","DOIUrl":"https://doi.org/10.1109/PIC.2010.5687973","url":null,"abstract":"Intelligent vehicle obtains path information by computer vision, and tracks detected path automatically by intelligent control. Through imitating preview driving behavior of human, and integrating driving experience of excellent drivers, an simple and effective preview fuzzy control method for path tracking of intelligent vehicle is presented in this study. The preview fuzzy control method adjusts vehicle speed by preview control according to future path information and adjusts vehicle direction by fuzzy control according to present path information. Simulations and experiments show that intelligent vehicle controlled by the preview fuzzy control method can track various paths accurately, stably and robustly.","PeriodicalId":142910,"journal":{"name":"2010 IEEE International Conference on Progress in Informatics and Computing","volume":"4 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123661284","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 : 2010-12-01DOI: 10.1109/PIC.2010.5687404
Nianyun Shi, Lingling Liu
Feature Selection (FS) is one of the most important issues in Text Classification (TC). A good feature selection can improve the efficiency and accuracy of a text classifier. Based on the analysis of the feature's distributional information, this paper presents a feature selection method named DIFS. In DIFS a new estimation mechanism is proposed to measure the relevance between feature's distribution characteristics and contribution to categorization. In addition, two kinds of algorithms are designed to implement DIFS. Experiments are carried out on a Chinese corpus and by comparison the proposed approach shows a better performance.
{"title":"A new feature selection method based on distributional information for Text Classification","authors":"Nianyun Shi, Lingling Liu","doi":"10.1109/PIC.2010.5687404","DOIUrl":"https://doi.org/10.1109/PIC.2010.5687404","url":null,"abstract":"Feature Selection (FS) is one of the most important issues in Text Classification (TC). A good feature selection can improve the efficiency and accuracy of a text classifier. Based on the analysis of the feature's distributional information, this paper presents a feature selection method named DIFS. In DIFS a new estimation mechanism is proposed to measure the relevance between feature's distribution characteristics and contribution to categorization. In addition, two kinds of algorithms are designed to implement DIFS. Experiments are carried out on a Chinese corpus and by comparison the proposed approach shows a better performance.","PeriodicalId":142910,"journal":{"name":"2010 IEEE International Conference on Progress in Informatics and Computing","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121396008","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 : 2010-12-01DOI: 10.1109/PIC.2010.5687869
M. Takhtravanchi, M. Azadnia
This paper investigates the effect of Information Technology on E-health; specifically, the development of IT/ICT and E-health/Telemedicine in Iran. According to different research, some professionals believe that the development of IT/ICT could have the positive and direct impact on development of using E-health/Telemedicine in all health sectors that could lead to saving times and poor and disabled people can use best and complete medical facilities from far distances. On the other hand, some professionals believe that the best diagnosis is occurred when they have a face-to-face contact with patients. This paper reviews the development of IT and the effects that it could have on developing E-health and whether the development of E-health has any impact on preventing prevalence of HIV in Iran or not. For this purpose, the IT/ICT and Health indicators are investigated and e-readiness score of Iran is investigated during the past decade. This conclusion is reached that the development process of both IT/ICT and E-health are in progress, but the former is faster and more sensible, also the IT/ICT development trend has an impact on preventing prevalence of HIV but it is not so sensible.
{"title":"An investigation into the effect of Information Technology on E-health in Iran","authors":"M. Takhtravanchi, M. Azadnia","doi":"10.1109/PIC.2010.5687869","DOIUrl":"https://doi.org/10.1109/PIC.2010.5687869","url":null,"abstract":"This paper investigates the effect of Information Technology on E-health; specifically, the development of IT/ICT and E-health/Telemedicine in Iran. According to different research, some professionals believe that the development of IT/ICT could have the positive and direct impact on development of using E-health/Telemedicine in all health sectors that could lead to saving times and poor and disabled people can use best and complete medical facilities from far distances. On the other hand, some professionals believe that the best diagnosis is occurred when they have a face-to-face contact with patients. This paper reviews the development of IT and the effects that it could have on developing E-health and whether the development of E-health has any impact on preventing prevalence of HIV in Iran or not. For this purpose, the IT/ICT and Health indicators are investigated and e-readiness score of Iran is investigated during the past decade. This conclusion is reached that the development process of both IT/ICT and E-health are in progress, but the former is faster and more sensible, also the IT/ICT development trend has an impact on preventing prevalence of HIV but it is not so sensible.","PeriodicalId":142910,"journal":{"name":"2010 IEEE International Conference on Progress in Informatics and Computing","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128092447","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 particle swarm optimization approach for the energy-based acoustic source localization of a wireless sensor network is presented. For this work, it is assumed that there is one acoustic source with unknown localizations which transmit acoustic signals that can be received by the nodes. The only available information to the system is the received signal energy which is not very accurate in general because of the attenuation in the process of propagation. To obtain better estimated localization of the acoustic source, maximum likelihood method is applied to transform it into extremal function, the particle swarm optimization scheme searches the optimal solution. Experimental results show that the proposed approach has the advantages of higher precision and lower computational complexity.
{"title":"Source localization based on particle swarm optimization for wireless sensor network","authors":"Yue Huang, Chengdong Wu, Yunzhou Zhang, Jian Zhang","doi":"10.1109/PIC.2010.5687575","DOIUrl":"https://doi.org/10.1109/PIC.2010.5687575","url":null,"abstract":"In this paper, a particle swarm optimization approach for the energy-based acoustic source localization of a wireless sensor network is presented. For this work, it is assumed that there is one acoustic source with unknown localizations which transmit acoustic signals that can be received by the nodes. The only available information to the system is the received signal energy which is not very accurate in general because of the attenuation in the process of propagation. To obtain better estimated localization of the acoustic source, maximum likelihood method is applied to transform it into extremal function, the particle swarm optimization scheme searches the optimal solution. Experimental results show that the proposed approach has the advantages of higher precision and lower computational complexity.","PeriodicalId":142910,"journal":{"name":"2010 IEEE International Conference on Progress in Informatics and Computing","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131355294","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 : 2010-12-01DOI: 10.1109/PIC.2010.5687929
César Stradiotto, S. Bedin, H. C. Hoeschl, T. C. Bueno
This work describes a multilingual ontology editor where the concepts and semantic relations are constructed inside a three-dimensional space. Initially the prototype is being programmed to compare three types of ontology editors. This editor will serve to construct ontologies viewed as relationship networks, and its concepts can be written in multiple languages, and can be related to normalized concepts (universal words) of the UNL project. These concepts also can be associated to 3D objects, or associated among themselves, through relations from UML Class Diagram. These kind of relations are used for better representation, communication and understanding of concepts among worldwide users, and also are used to model semantic relations to improve results of searching tools.
{"title":"3D editor for multilingual ontologies using universal words","authors":"César Stradiotto, S. Bedin, H. C. Hoeschl, T. C. Bueno","doi":"10.1109/PIC.2010.5687929","DOIUrl":"https://doi.org/10.1109/PIC.2010.5687929","url":null,"abstract":"This work describes a multilingual ontology editor where the concepts and semantic relations are constructed inside a three-dimensional space. Initially the prototype is being programmed to compare three types of ontology editors. This editor will serve to construct ontologies viewed as relationship networks, and its concepts can be written in multiple languages, and can be related to normalized concepts (universal words) of the UNL project. These concepts also can be associated to 3D objects, or associated among themselves, through relations from UML Class Diagram. These kind of relations are used for better representation, communication and understanding of concepts among worldwide users, and also are used to model semantic relations to improve results of searching tools.","PeriodicalId":142910,"journal":{"name":"2010 IEEE International Conference on Progress in Informatics and Computing","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131937324","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 : 2010-12-01DOI: 10.1109/PIC.2010.5687905
Chunjiang Pang, Xiao Xie
In order to increase transmission and processing speed, it is essential to compress the non-stationary leakage current in the insulator monitored system. Compressed Sensing (CS) combines sampling and compression with a small amount of sample to reconstruct signal well, which not only reduces hardware requirements, but also improves compression efficiency. However, computational complexity is high in CS recovery process of non-stationary signals. In this paper, CS combines with empirical mode decomposition method (EMD). Decompose Non-stationary leakage current into a finite number of stationary intrinsic mode functions (IMF), and then CS processes stationary IMFs. The experiment results indicate that it enhances not only the speed of process and operational efficiency but also compression ratio and reconstruction accuracy in the case that CS processes leakage current signal by EMD decomposition.
{"title":"Insulator leakage current data compression based on EMD and compressed sending","authors":"Chunjiang Pang, Xiao Xie","doi":"10.1109/PIC.2010.5687905","DOIUrl":"https://doi.org/10.1109/PIC.2010.5687905","url":null,"abstract":"In order to increase transmission and processing speed, it is essential to compress the non-stationary leakage current in the insulator monitored system. Compressed Sensing (CS) combines sampling and compression with a small amount of sample to reconstruct signal well, which not only reduces hardware requirements, but also improves compression efficiency. However, computational complexity is high in CS recovery process of non-stationary signals. In this paper, CS combines with empirical mode decomposition method (EMD). Decompose Non-stationary leakage current into a finite number of stationary intrinsic mode functions (IMF), and then CS processes stationary IMFs. The experiment results indicate that it enhances not only the speed of process and operational efficiency but also compression ratio and reconstruction accuracy in the case that CS processes leakage current signal by EMD decomposition.","PeriodicalId":142910,"journal":{"name":"2010 IEEE International Conference on Progress in Informatics and Computing","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130135052","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：