Pub Date : 2011-10-13DOI: 10.1109/CCIS.2011.6045143
Fang Zhu, Zongtian Liu, Juanli Yang, Ping Zhu
This paper provides a new method combining Maximum Entropy with rules for identify event place phrase. Firstly, all phrases which not include event trigger are extracted from event mention, and a rule base about event place phrases analyzes and filters these phrases for obtaining the phrase candidate set. Secondly, we explore some rich text features from three kinds of linguistics features that contain phrase, event trigger and context information. Thirdly, in order to establish a train set, we use some feature words representing these text features to build feature vector space. Then, a machine learning model to identify event place phrase is trained by using L-BFGS functions algorithm. At last, this predictive model is used to classify the test set. The result shows that the method is efficient. In open test, the recall, precision and F-measure reach 0.6296296, 0.8095238 and 0.7083333 respectively.
{"title":"Chinese event place phrase recognition of emergency event using Maximum Entropy","authors":"Fang Zhu, Zongtian Liu, Juanli Yang, Ping Zhu","doi":"10.1109/CCIS.2011.6045143","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045143","url":null,"abstract":"This paper provides a new method combining Maximum Entropy with rules for identify event place phrase. Firstly, all phrases which not include event trigger are extracted from event mention, and a rule base about event place phrases analyzes and filters these phrases for obtaining the phrase candidate set. Secondly, we explore some rich text features from three kinds of linguistics features that contain phrase, event trigger and context information. Thirdly, in order to establish a train set, we use some feature words representing these text features to build feature vector space. Then, a machine learning model to identify event place phrase is trained by using L-BFGS functions algorithm. At last, this predictive model is used to classify the test set. The result shows that the method is efficient. In open test, the recall, precision and F-measure reach 0.6296296, 0.8095238 and 0.7083333 respectively.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"30 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121092664","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 : 2011-10-13DOI: 10.1109/CCIS.2011.6045109
Jun Wang, Lei Li, F. Ren
Social network plays an important role in this network age. With development of social network, people hope more attribute and more precise description about relation which is the key element of network. This paper proposes an improved method of extracting emotional attribute of relations from Chinese events based on syntactical analysis. In our work, we improved the defect of previous method that can not deal with multiple entities in one sentence. In addition, a large-scale Chinese emotional dictionary not only emotional verbs was used in the extraction of emotional attribute. Experiment showed our method achieved satisfied performance.
{"title":"An improved method of extracting emotional attribute of relations based on syntactical analysis","authors":"Jun Wang, Lei Li, F. Ren","doi":"10.1109/CCIS.2011.6045109","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045109","url":null,"abstract":"Social network plays an important role in this network age. With development of social network, people hope more attribute and more precise description about relation which is the key element of network. This paper proposes an improved method of extracting emotional attribute of relations from Chinese events based on syntactical analysis. In our work, we improved the defect of previous method that can not deal with multiple entities in one sentence. In addition, a large-scale Chinese emotional dictionary not only emotional verbs was used in the extraction of emotional attribute. Experiment showed our method achieved satisfied performance.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121375970","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 : 2011-10-13DOI: 10.1109/CCIS.2011.6045121
Wenchong Shi, Maohua Liu
The paper is intended to ascertain the emphases and difficulties of data processing in Internet of things (IoT) so as to identify the technical strategy. It first analyzed the characteristics of data in IoT, and then analyzed the various properties' requirements in data processing. The authors thought, the data in IoT are polymorphous, heterogeneous, large in quantity and time-limited, there are also some difficulties in data transmitting, they proposed database and middleware technology is the key to solve the polymorphism and heterogeneity, cloud computing or sea computing is the key to resolve data's largeness, the development of high quality devices for data source is the key to data's transmitting. The paper's innovation is that the author has considered the common challenges of data's transmitting in IoT and the application of sea computing.
{"title":"Tactics of handling data in Internet of things","authors":"Wenchong Shi, Maohua Liu","doi":"10.1109/CCIS.2011.6045121","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045121","url":null,"abstract":"The paper is intended to ascertain the emphases and difficulties of data processing in Internet of things (IoT) so as to identify the technical strategy. It first analyzed the characteristics of data in IoT, and then analyzed the various properties' requirements in data processing. The authors thought, the data in IoT are polymorphous, heterogeneous, large in quantity and time-limited, there are also some difficulties in data transmitting, they proposed database and middleware technology is the key to solve the polymorphism and heterogeneity, cloud computing or sea computing is the key to resolve data's largeness, the development of high quality devices for data source is the key to data's transmitting. The paper's innovation is that the author has considered the common challenges of data's transmitting in IoT and the application of sea computing.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121206744","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 : 2011-10-13DOI: 10.1109/CCIS.2011.6045145
Xuesong Dai, Yuan Ma
The intent waned value is a connection between concepts. In this article a kind of incremental algorithm of concept lattice formation calculated by waned value altogether with extent and intent is provided. As in this algorithm the intend waned value is contained in intermediate result so it is easy and rapid to determine if the concept is a “top element” and the speed of “top element” checking will be very quick. Therefore the speed of concept lattice formation is improved obviously.
{"title":"An incremental algorithm for formation a concept lattice based on the intent waned value","authors":"Xuesong Dai, Yuan Ma","doi":"10.1109/CCIS.2011.6045145","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045145","url":null,"abstract":"The intent waned value is a connection between concepts. In this article a kind of incremental algorithm of concept lattice formation calculated by waned value altogether with extent and intent is provided. As in this algorithm the intend waned value is contained in intermediate result so it is easy and rapid to determine if the concept is a “top element” and the speed of “top element” checking will be very quick. Therefore the speed of concept lattice formation is improved obviously.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127561048","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 : 2011-10-13DOI: 10.1109/CCIS.2011.6045115
Hang Yin, Xiaojun Jing, Songlin Sun
Fingerprint recognition is a widely used biometric identification mechanism. The singular points of fingerprints are important referential points for the fingerprint classification and fingerprint matching. In this paper, we propose a novel algorithm for detecting the singular points. The method is based on vector orthogonal theory and the fact that the singular points have special pattern of the orientation field. We use the same mask to detect the core points and delta points in different field. After applying the special mask, the core points and delta points will be detected in the orientation field and double orientation field respectively. To substantiate the performance of our approach, we have experimented with fvc2002 and fvc2004 database. Experimental results show that our algorithm is accurate and robust, giving better results than competing approaches.
{"title":"A novel algorithm for fingerprint singular points detection based on vecrot orthogonal theory","authors":"Hang Yin, Xiaojun Jing, Songlin Sun","doi":"10.1109/CCIS.2011.6045115","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045115","url":null,"abstract":"Fingerprint recognition is a widely used biometric identification mechanism. The singular points of fingerprints are important referential points for the fingerprint classification and fingerprint matching. In this paper, we propose a novel algorithm for detecting the singular points. The method is based on vector orthogonal theory and the fact that the singular points have special pattern of the orientation field. We use the same mask to detect the core points and delta points in different field. After applying the special mask, the core points and delta points will be detected in the orientation field and double orientation field respectively. To substantiate the performance of our approach, we have experimented with fvc2002 and fvc2004 database. Experimental results show that our algorithm is accurate and robust, giving better results than competing approaches.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127347672","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}
Web page clustering based on semantic or topic promises improved search and browsing on the web. Intuitively, tags from social bookmarking websites such as del.icio.us can be used as a complementary source to document thus improving clustering of web pages. In this paper, we present a novel model which employs topic model to associate annotated document with a distribution of topics, and then constructs a graph including tags, document and topics by performing a Random Walks for clustering. We examine the performance of our model on a real-world data set, illustrating that our model provides improved clustering performance than algorithm utilizing page text alone.
{"title":"Annotation-aware web clustering based on topic model and random walks","authors":"Jiashen Sun, Xiaojie Wang, Caixia Yuan, Guannan Fang","doi":"10.1109/CCIS.2011.6045023","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045023","url":null,"abstract":"Web page clustering based on semantic or topic promises improved search and browsing on the web. Intuitively, tags from social bookmarking websites such as del.icio.us can be used as a complementary source to document thus improving clustering of web pages. In this paper, we present a novel model which employs topic model to associate annotated document with a distribution of topics, and then constructs a graph including tags, document and topics by performing a Random Walks for clustering. We examine the performance of our model on a real-world data set, illustrating that our model provides improved clustering performance than algorithm utilizing page text alone.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134001191","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 : 2011-10-13DOI: 10.1109/CCIS.2011.6045039
Yun Liu, Ling Zhao
Aimed at the problem of credibility and accuracy exiting in multi-sensor data for bridge health monitoring, this paper presents a model based on two-dimensional data processing. To make reliability of the measurements, first asynchronous data are equalized by the least square algorithm, and through the geometric coordinate transformation algorithm, measurements will be placed in the same space-time coordinates system. To improve accuracy of the measurements, Kalman filter is applied to reduce the system error after the data registration. The simulation results show that the methods significantly improve the credibility and accuracy of data in multi-sensor networks for bridge health monitoring.
{"title":"Multi-sensor data registration for bridge health monitoring","authors":"Yun Liu, Ling Zhao","doi":"10.1109/CCIS.2011.6045039","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045039","url":null,"abstract":"Aimed at the problem of credibility and accuracy exiting in multi-sensor data for bridge health monitoring, this paper presents a model based on two-dimensional data processing. To make reliability of the measurements, first asynchronous data are equalized by the least square algorithm, and through the geometric coordinate transformation algorithm, measurements will be placed in the same space-time coordinates system. To improve accuracy of the measurements, Kalman filter is applied to reduce the system error after the data registration. The simulation results show that the methods significantly improve the credibility and accuracy of data in multi-sensor networks for bridge health monitoring.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116842665","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 : 2011-10-13DOI: 10.1109/CCIS.2011.6045140
Jie Yang, Yongshi Xu, R. Xu
Taking full advantage of limited number of trains to obtain the best transport efficiency is the foremost question in Urban Rail Transit (URT) operation. The paper analyzes the deficiencies in current theory of URT train running program, and then puts forward its objective: comparing and optimizing the operating projects according to average passenger waiting time and total trainload. Firstly, the paper establishes a platform-train-passengers interchange model, set up corresponding real-time arithmetic for average waiting time and total trainload. Secondly, this article advances a double-target optimum model for URT train running program, and then figure out the optimu m solution by using artificial intelligence technique. Finally, an example is given to validate the optimu m method.
{"title":"Optimization method of Urban Rail Transit train running scheme","authors":"Jie Yang, Yongshi Xu, R. Xu","doi":"10.1109/CCIS.2011.6045140","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045140","url":null,"abstract":"Taking full advantage of limited number of trains to obtain the best transport efficiency is the foremost question in Urban Rail Transit (URT) operation. The paper analyzes the deficiencies in current theory of URT train running program, and then puts forward its objective: comparing and optimizing the operating projects according to average passenger waiting time and total trainload. Firstly, the paper establishes a platform-train-passengers interchange model, set up corresponding real-time arithmetic for average waiting time and total trainload. Secondly, this article advances a double-target optimum model for URT train running program, and then figure out the optimu m solution by using artificial intelligence technique. Finally, an example is given to validate the optimu m method.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131077409","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 : 2011-10-13DOI: 10.1109/CCIS.2011.6045047
Songqing Duan, Bin Wu, Bai Wang, Juan Yang
The rapid growth of data promotes the development of parallel computing. MapReduce, which is a simplified programming model of distributed parallel computing, is becoming more and more popular. In this paper, we design and implementation of parallel statistical algorithm based on Hadoop's MapReduce model. The algorithm, which is used to grasp the overall characteristics of massive data, involves the calculation of central tendency, dispersion and distribution tendency. By experiment, we come to the conclusion that the algorithm is suitable for dealing with large-scale data.
{"title":"Design and implementation of parallel statiatical algorithm based on Hadoop's MapReduce model","authors":"Songqing Duan, Bin Wu, Bai Wang, Juan Yang","doi":"10.1109/CCIS.2011.6045047","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045047","url":null,"abstract":"The rapid growth of data promotes the development of parallel computing. MapReduce, which is a simplified programming model of distributed parallel computing, is becoming more and more popular. In this paper, we design and implementation of parallel statistical algorithm based on Hadoop's MapReduce model. The algorithm, which is used to grasp the overall characteristics of massive data, involves the calculation of central tendency, dispersion and distribution tendency. By experiment, we come to the conclusion that the algorithm is suitable for dealing with large-scale data.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131702852","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 : 2011-10-13DOI: 10.1109/CCIS.2011.6045033
Ke Zhang, Xiaojie Wang, Yixin Zhong
Spatial directional relation is an important content of spatial relation research, but its fundamental theories were still not perfect; most of the relevant references gave their emphasis to formal description models of directional relation but neglected the fundamental theories system based on directional relation itself. To make deeper investigation into the issue, this paper in detail proposes definition, reference frame, properties, influence factors, and classification of directional relation; these conceptual issues provide theory basis for formal description models of directional relation and applications of relevant research.
{"title":"Reserch on fundamental theory of spatial directional relation","authors":"Ke Zhang, Xiaojie Wang, Yixin Zhong","doi":"10.1109/CCIS.2011.6045033","DOIUrl":"https://doi.org/10.1109/CCIS.2011.6045033","url":null,"abstract":"Spatial directional relation is an important content of spatial relation research, but its fundamental theories were still not perfect; most of the relevant references gave their emphasis to formal description models of directional relation but neglected the fundamental theories system based on directional relation itself. To make deeper investigation into the issue, this paper in detail proposes definition, reference frame, properties, influence factors, and classification of directional relation; these conceptual issues provide theory basis for formal description models of directional relation and applications of relevant research.","PeriodicalId":128504,"journal":{"name":"2011 IEEE International Conference on Cloud Computing and Intelligence Systems","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131774426","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：