Pub Date : 2016-08-01DOI: 10.1109/FSKD.2016.7603511
Qingling Lu, Zhihui Wang, Wei Zhang, Yanbin Zhao
With the increase of vehicles ownership in the society, traffic security problem stands out. This paper proposes a warning strategy of vehicles' driving safety based on the vehicles networking. Receive the motion information sent from the adjacent vehicles through network and determine the position of the adjacent vehicles relative to the local vehicle when they have a higher speed. The people can use the danger value to evaluate the possibility of vehicle collision. If danger value exceeds the threshold, the warning comes into being. This strategy makes the vehicles acquire adjacent vehicles' information through the network. It has advantages of a wider range and stronger predictability. The warning system for safe driving of vehicles is composed of vehicle-mounted intelligent nodes and servers. The vehicle-mounted intelligent nodes obtain the motion information of vehicles through the OBD, GPS/inertial navigation and other sensors, and because of its connecting motors under steering wheel or seats, it will remind the driver by shaking when the warning produces, at the same time, dangerous vehicles and their motion information will be displayed on the navigation map.
{"title":"The warning system of vehicles' driving safety based on network","authors":"Qingling Lu, Zhihui Wang, Wei Zhang, Yanbin Zhao","doi":"10.1109/FSKD.2016.7603511","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603511","url":null,"abstract":"With the increase of vehicles ownership in the society, traffic security problem stands out. This paper proposes a warning strategy of vehicles' driving safety based on the vehicles networking. Receive the motion information sent from the adjacent vehicles through network and determine the position of the adjacent vehicles relative to the local vehicle when they have a higher speed. The people can use the danger value to evaluate the possibility of vehicle collision. If danger value exceeds the threshold, the warning comes into being. This strategy makes the vehicles acquire adjacent vehicles' information through the network. It has advantages of a wider range and stronger predictability. The warning system for safe driving of vehicles is composed of vehicle-mounted intelligent nodes and servers. The vehicle-mounted intelligent nodes obtain the motion information of vehicles through the OBD, GPS/inertial navigation and other sensors, and because of its connecting motors under steering wheel or seats, it will remind the driver by shaking when the warning produces, at the same time, dangerous vehicles and their motion information will be displayed on the navigation map.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126928574","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 : 2016-08-01DOI: 10.1109/FSKD.2016.7603154
G. Yu, Jin Tian, Minqiang Li
With the increasing size of big data, classifiers usually suffer from intractable computing and storage issues. Moreover, decision boundaries in complex classification problems are usually complicated and circuitous. Modeling on too many instances can sometimes cause oversensitivity to noise and degrade the learning accuracies. Instance selection offers an effective way to improve classification performance based on partial but significant data. This paper presents a novel instance selection algorithm based on nearest enemy information. The dataset is divided into several partitions corresponding to instances' nearest enemies. In every partition, representative instances are selected based on the distribution information to represent both sides of decision boundary. A support vector machine (SVM) is then adopted to conduct the classification model based on these representative instances. Experimental results illustrate that the proposed algorithm outperforms some conventional instance selection methods with higher classification accuracy and smaller size of selected instances.
{"title":"Nearest neighbor-based instance selection for classification","authors":"G. Yu, Jin Tian, Minqiang Li","doi":"10.1109/FSKD.2016.7603154","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603154","url":null,"abstract":"With the increasing size of big data, classifiers usually suffer from intractable computing and storage issues. Moreover, decision boundaries in complex classification problems are usually complicated and circuitous. Modeling on too many instances can sometimes cause oversensitivity to noise and degrade the learning accuracies. Instance selection offers an effective way to improve classification performance based on partial but significant data. This paper presents a novel instance selection algorithm based on nearest enemy information. The dataset is divided into several partitions corresponding to instances' nearest enemies. In every partition, representative instances are selected based on the distribution information to represent both sides of decision boundary. A support vector machine (SVM) is then adopted to conduct the classification model based on these representative instances. Experimental results illustrate that the proposed algorithm outperforms some conventional instance selection methods with higher classification accuracy and smaller size of selected instances.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115040208","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 : 2016-08-01DOI: 10.1109/FSKD.2016.7603443
Yaqi Li, Chun Yan, W. Liu, Maozhen Li
Automobile insurance fraud is gradually spreading in the global scope, and mining automobile insurance fraud is more and more concerned by the society. Concerning that the number of samples in the actual automobile insurance claims data is not balance and the amount of data is large, the real data of a automobile insurance company were selected to establish the random forest fraud mining model based on the theory of automobile insurance fraud mining. The data were processed to screen the index and the importance analysis of each input variable to the output variable was obtained. The error of the model was analyzed. Finally the method has been verified by empirical analysis. The empirical results show that: compared with the traditional model, the automobile insurance fraud mining model introducing Random Forest is suitable for large data sets and unbalanced data. It can be better used for the classification and prediction of the automobile insurance claims data and mining fraud rules. And it has the better accuracy and robustness.
{"title":"Research and application of random forest model in mining automobile insurance fraud","authors":"Yaqi Li, Chun Yan, W. Liu, Maozhen Li","doi":"10.1109/FSKD.2016.7603443","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603443","url":null,"abstract":"Automobile insurance fraud is gradually spreading in the global scope, and mining automobile insurance fraud is more and more concerned by the society. Concerning that the number of samples in the actual automobile insurance claims data is not balance and the amount of data is large, the real data of a automobile insurance company were selected to establish the random forest fraud mining model based on the theory of automobile insurance fraud mining. The data were processed to screen the index and the importance analysis of each input variable to the output variable was obtained. The error of the model was analyzed. Finally the method has been verified by empirical analysis. The empirical results show that: compared with the traditional model, the automobile insurance fraud mining model introducing Random Forest is suitable for large data sets and unbalanced data. It can be better used for the classification and prediction of the automobile insurance claims data and mining fraud rules. And it has the better accuracy and robustness.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115328442","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 : 2016-08-01DOI: 10.1109/FSKD.2016.7603272
Xinwei Chang, Feng Luo
This paper introduces design of a complete CAN Calibration Protocol (CCP) System, including Electronic Control Unit (ECU) driver, Computer calibration software design and an improvement on transfer mechanism. CCP driver is developed as an independent software component with interfaces compatible with different embedded system. Computer software is developed in Microsoft Visual Studio using API of a common Controller Area Network (CAN) tool. A modification in transfer mechanism is introduced to achieve better real-time performance. The CCP system is proved to be effective and efficient to meet the requirement of common calibration task.
{"title":"CAN calibration system design and transfer mechanism optimization","authors":"Xinwei Chang, Feng Luo","doi":"10.1109/FSKD.2016.7603272","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603272","url":null,"abstract":"This paper introduces design of a complete CAN Calibration Protocol (CCP) System, including Electronic Control Unit (ECU) driver, Computer calibration software design and an improvement on transfer mechanism. CCP driver is developed as an independent software component with interfaces compatible with different embedded system. Computer software is developed in Microsoft Visual Studio using API of a common Controller Area Network (CAN) tool. A modification in transfer mechanism is introduced to achieve better real-time performance. The CCP system is proved to be effective and efficient to meet the requirement of common calibration task.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115524050","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 : 2016-08-01DOI: 10.1109/FSKD.2016.7603209
Qingpeng Liu, Hua Cai, Guangqiu Chen, Shuang Dou, Yong Yang
In the traditional image mosaic algorithm based on seam line, the line is searched by making the color and neighborhood structure difference as small as possible in the overlap region of the images. However, when a small object with single color and symmetrical structure appears, the color and the neighborhood structure difference are not able to restrain the direction of the seam line. The appearance of the seam line crossing the object leads to the deformity of the crossed object in the mosaic image. Aiming at this problem, the image contour energy based on the above two parts is proposed to punish seam line in this paper, which can change the direction of seam line. Experimental results show that the new energy formula used in this paper can effectively avoid the crossing and the deformity.
{"title":"An image mosaic method based on improving seam line","authors":"Qingpeng Liu, Hua Cai, Guangqiu Chen, Shuang Dou, Yong Yang","doi":"10.1109/FSKD.2016.7603209","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603209","url":null,"abstract":"In the traditional image mosaic algorithm based on seam line, the line is searched by making the color and neighborhood structure difference as small as possible in the overlap region of the images. However, when a small object with single color and symmetrical structure appears, the color and the neighborhood structure difference are not able to restrain the direction of the seam line. The appearance of the seam line crossing the object leads to the deformity of the crossed object in the mosaic image. Aiming at this problem, the image contour energy based on the above two parts is proposed to punish seam line in this paper, which can change the direction of seam line. Experimental results show that the new energy formula used in this paper can effectively avoid the crossing and the deformity.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"111 3S 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115542111","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 : 2016-08-01DOI: 10.1109/FSKD.2016.7603456
Xin Wang, Wen Li, Zhijie Song
The study bases on the peculiarity of the emergency events in the college life and the particular characters of the college students. We carry out the study by using the suitable new, which can induce emotion and the suitable respondent. The study divides into three parts. The first part is the study about the spread process of the emotion, we can get that the process developed in the order as “emotion sharing-emotional contagion-emotion sharing once again”. The second part is the study about the spread ways of the emotion, we can get that the intimacy and the trust can forecast the spread of the emotion. The third part is the study of the model building of interpersonal relationship, using the data we get from the survey. After the summarization, we give our conclusion in the end of the study.
{"title":"Research on mechanisms of emotional transmission among university students in emergencies","authors":"Xin Wang, Wen Li, Zhijie Song","doi":"10.1109/FSKD.2016.7603456","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603456","url":null,"abstract":"The study bases on the peculiarity of the emergency events in the college life and the particular characters of the college students. We carry out the study by using the suitable new, which can induce emotion and the suitable respondent. The study divides into three parts. The first part is the study about the spread process of the emotion, we can get that the process developed in the order as “emotion sharing-emotional contagion-emotion sharing once again”. The second part is the study about the spread ways of the emotion, we can get that the intimacy and the trust can forecast the spread of the emotion. The third part is the study of the model building of interpersonal relationship, using the data we get from the survey. After the summarization, we give our conclusion in the end of the study.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122771266","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 : 2016-08-01DOI: 10.1109/FSKD.2016.7603263
Dan Liu, Xin Sui, Li Li
The article puts forward an algorithm that combines Genetic Algorithm (GA) with Simulated Annealing (SA) which lower the energy consumption of the cloud data center. The energy-efficient virtual machine placement algorithm primarily accomplishes the population initialization according to the virtual machine placement rule and crossover, variation and correction. Finally, filter the new population on the basis of the metropolis rule. Experimental results show that the energy-efficient algorithm combines the advantages of GA and SA which have been improved a lot on global optimal solutions.
{"title":"An energy-efficient virtual machine placement algorithm in cloud data center","authors":"Dan Liu, Xin Sui, Li Li","doi":"10.1109/FSKD.2016.7603263","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603263","url":null,"abstract":"The article puts forward an algorithm that combines Genetic Algorithm (GA) with Simulated Annealing (SA) which lower the energy consumption of the cloud data center. The energy-efficient virtual machine placement algorithm primarily accomplishes the population initialization according to the virtual machine placement rule and crossover, variation and correction. Finally, filter the new population on the basis of the metropolis rule. Experimental results show that the energy-efficient algorithm combines the advantages of GA and SA which have been improved a lot on global optimal solutions.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122571749","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 : 2016-08-01DOI: 10.1109/FSKD.2016.7603385
Hongpu Hu, Yue Zhang, Fan Yu, Yao He, Yanli Wan
To increase work efficiency of administration transaction, we have designed the Information-based management system of CHS. The system includes four subsidiary systems: The administration management handing system, evaluating system, searching system and statistics analytical system. The administration management handling system includes the application system of the CHS station(center), the examine system of the CHS center, the examination and approval system of district public health bureau and the record system of municipal public health bureau. The contents include installation, registering, checking-up, alteration and logging-off. The system of automatic evaluation can compute automated synthetically index numbers of evaluated units and display the best and the worst items according to the evaluation system which are set up in the computer in advance; it could rank the order of units of the same kind according to the synthesized index numbers and the order of the individual items. The searching system included basic data searching, personnel searching, administrations results searching. The system of statistics and analysis can make statistics and analyze the basic circumstance about CHS, by which researchers can accurately master the condition of the CHS resources, and can constitute statistics charts meeting different requests. It could provide basis decision for the administrative departments so as to allot hygiene resources reasonably. By carrying out the system, the compliance management definitely be strengthened so that CHS sector will enter the information age of standardized and automated operation, complying with laws and regulation. CHS can be improved by management.
{"title":"On the functionalities of an information-based management system of community health service in China","authors":"Hongpu Hu, Yue Zhang, Fan Yu, Yao He, Yanli Wan","doi":"10.1109/FSKD.2016.7603385","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603385","url":null,"abstract":"To increase work efficiency of administration transaction, we have designed the Information-based management system of CHS. The system includes four subsidiary systems: The administration management handing system, evaluating system, searching system and statistics analytical system. The administration management handling system includes the application system of the CHS station(center), the examine system of the CHS center, the examination and approval system of district public health bureau and the record system of municipal public health bureau. The contents include installation, registering, checking-up, alteration and logging-off. The system of automatic evaluation can compute automated synthetically index numbers of evaluated units and display the best and the worst items according to the evaluation system which are set up in the computer in advance; it could rank the order of units of the same kind according to the synthesized index numbers and the order of the individual items. The searching system included basic data searching, personnel searching, administrations results searching. The system of statistics and analysis can make statistics and analyze the basic circumstance about CHS, by which researchers can accurately master the condition of the CHS resources, and can constitute statistics charts meeting different requests. It could provide basis decision for the administrative departments so as to allot hygiene resources reasonably. By carrying out the system, the compliance management definitely be strengthened so that CHS sector will enter the information age of standardized and automated operation, complying with laws and regulation. CHS can be improved by management.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122872674","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 : 2016-08-01DOI: 10.1109/FSKD.2016.7603484
Ling-Yuan Hsu, Hwai-Tsu Hu, Hsien-Hsin Chou
Watermarks are used to protect the copyright of multimedia and help us to identify legitimate ownership. Imperceptibility and robustness are always prime concern for the watermarking researchers. Therefore, a simple but effective blind watermarking scheme would be what we expect. In this study, we present a kind of blind watermarking technique, which is based on inter-blocks estimation of the discrete cosine transform (DCT) coefficients. To satisfy both imperceptibility and robustness requirements while maintaining a sufficient payload capacity, a quantization index modulation technique (QIM) DCT-based scheme is employed. This technique substantial reduces the effect of host data interference, thus having significant advantage over previously proposed DCT-based watermarking schemes. Experimental results show that the proposed scheme to embedding watermarks can effectively to defense various image attacks, especially in image compression attacks and Gaussian noise.
{"title":"An effective blind image watermarking based on inter-blocks estimation and quantization index modulation","authors":"Ling-Yuan Hsu, Hwai-Tsu Hu, Hsien-Hsin Chou","doi":"10.1109/FSKD.2016.7603484","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603484","url":null,"abstract":"Watermarks are used to protect the copyright of multimedia and help us to identify legitimate ownership. Imperceptibility and robustness are always prime concern for the watermarking researchers. Therefore, a simple but effective blind watermarking scheme would be what we expect. In this study, we present a kind of blind watermarking technique, which is based on inter-blocks estimation of the discrete cosine transform (DCT) coefficients. To satisfy both imperceptibility and robustness requirements while maintaining a sufficient payload capacity, a quantization index modulation technique (QIM) DCT-based scheme is employed. This technique substantial reduces the effect of host data interference, thus having significant advantage over previously proposed DCT-based watermarking schemes. Experimental results show that the proposed scheme to embedding watermarks can effectively to defense various image attacks, especially in image compression attacks and Gaussian noise.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114466081","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 : 2016-08-01DOI: 10.1109/FSKD.2016.7603531
Shuhui Huang, Xin Yan, Zhengtao Yu, Qingling Lei
It is hard to solve the problem of considerable segmentation error caused by out-of-vocabulary words, so for segmentation task based on Constrained Conditional Random Fields Model, the Precision is relatively low. To solve this problem, Constrained Conditional Random Fields Model, which exploits constraints on the Khmer word segmentation and named entity recognition, is proposed in this paper. With a series of segmentation, POS tagging and NER tasks, the Khmer entity annotation corpus which contains more entities is constructed. Several groups of experiments are set up in each link of construction entity annotation corpus. These experimental data have proven that the proposed method is feasible.
{"title":"Construction of Khmer entity annotation corpus based on constrained conditional random fields","authors":"Shuhui Huang, Xin Yan, Zhengtao Yu, Qingling Lei","doi":"10.1109/FSKD.2016.7603531","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603531","url":null,"abstract":"It is hard to solve the problem of considerable segmentation error caused by out-of-vocabulary words, so for segmentation task based on Constrained Conditional Random Fields Model, the Precision is relatively low. To solve this problem, Constrained Conditional Random Fields Model, which exploits constraints on the Khmer word segmentation and named entity recognition, is proposed in this paper. With a series of segmentation, POS tagging and NER tasks, the Khmer entity annotation corpus which contains more entities is constructed. Several groups of experiments are set up in each link of construction entity annotation corpus. These experimental data have proven that the proposed method is feasible.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116873731","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：