International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications最新文献
Pub Date : 2012-05-29DOI: 10.1109/ICNC.2012.6234772
Xueji Wang, Linlin Zhao, Shuang Wang
For the problems of fuzzy object's edges and computation complexity for video object segmentation, an improved SVM algorithm is proposed in this paper. We have adopted the adaptive change detection method to get the original video object, whose pixels constitute the samples set for SVM training, and then we improved the SVM by using the idea of active learning, and finally we built the video object segmentation model from the improved SVM. Experimental results show that both the spatial accuracy and the temporal coherency of this algorithm are much better than before. This algorithm achieves the goal of automatic segmentation, and overcomes the disadvantage of supervision learning, and it can reduce the computation complexity.
{"title":"A novel SVM video object extraction technology","authors":"Xueji Wang, Linlin Zhao, Shuang Wang","doi":"10.1109/ICNC.2012.6234772","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234772","url":null,"abstract":"For the problems of fuzzy object's edges and computation complexity for video object segmentation, an improved SVM algorithm is proposed in this paper. We have adopted the adaptive change detection method to get the original video object, whose pixels constitute the samples set for SVM training, and then we improved the SVM by using the idea of active learning, and finally we built the video object segmentation model from the improved SVM. Experimental results show that both the spatial accuracy and the temporal coherency of this algorithm are much better than before. This algorithm achieves the goal of automatic segmentation, and overcomes the disadvantage of supervision learning, and it can reduce the computation complexity.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"24 1","pages":"44-48"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82230930","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234607
Yuan Wang, Yu Zhenjun, Jia Yongxing
To improve the accuracy of lip-reading recognition, an emotions and topic-related mixed language model has been researched. On the basis of the key words, the topic is divided by subject words, improved scene training corpus design and parameter estimation methods are used, the scene training corpus of different topics is expressed as the fuzzy subset of the whole scene training corpus, parameter estimated which can be got is also based on the fuzzy training set of different topics. The problem of sparse data which is introduced by less of training corpus in traditional language model has been eased by improved methods, quantitative description about the relationship of scene training corpus and topics has been presented, and full use of the image identification techniques for expression recognition in lipreading recognition area, auxiliary emotional factors language model to carry out lip-reading recognition.
{"title":"Research of emotions and topic-related mixed language model about lip-reading recognition","authors":"Yuan Wang, Yu Zhenjun, Jia Yongxing","doi":"10.1109/ICNC.2012.6234607","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234607","url":null,"abstract":"To improve the accuracy of lip-reading recognition, an emotions and topic-related mixed language model has been researched. On the basis of the key words, the topic is divided by subject words, improved scene training corpus design and parameter estimation methods are used, the scene training corpus of different topics is expressed as the fuzzy subset of the whole scene training corpus, parameter estimated which can be got is also based on the fuzzy training set of different topics. The problem of sparse data which is introduced by less of training corpus in traditional language model has been eased by improved methods, quantitative description about the relationship of scene training corpus and topics has been presented, and full use of the image identification techniques for expression recognition in lipreading recognition area, auxiliary emotional factors language model to carry out lip-reading recognition.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"106 1","pages":"540-545"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90449169","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}
Human can only feel spatial information within three-dimensional space. However, there are more than three attributes in economic statistical data and other data sets generally. When studying the inherent structural characteristics of these data such as clustering and distribution, researchers need to reduce multi-dimensional information to three-dimensional space or less to achieve multi-dimensional visualization. There are many dimension reduction methods, whose results are different from each other because of different mathematics theories and application ranges. In the paper, authors analyze economic statistical data of Sichuan province in 2007 by using Multidimensional Scaling (MDS) which is a nonlinear method and Support Vector Machines (SVM) which is a supervised classification method. The classification result of MDS is consistent with the status of economic development of Sichuan in general, but details of the result cannot be verified itself; the output results of SVM by selecting different kernel functions are very similar to the classification result of MDS, which can validate these results. And considering the advantages and the solid mathematical theory, authors believe that the combination of these two methods is scientific.
{"title":"A multi-dimensional visualization method combining MDS and SVM","authors":"Xing-Ling Wang, Liyuan Zhang, Cheng-Wei Dong, X. Rui","doi":"10.1109/ICNC.2012.6234736","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234736","url":null,"abstract":"Human can only feel spatial information within three-dimensional space. However, there are more than three attributes in economic statistical data and other data sets generally. When studying the inherent structural characteristics of these data such as clustering and distribution, researchers need to reduce multi-dimensional information to three-dimensional space or less to achieve multi-dimensional visualization. There are many dimension reduction methods, whose results are different from each other because of different mathematics theories and application ranges. In the paper, authors analyze economic statistical data of Sichuan province in 2007 by using Multidimensional Scaling (MDS) which is a nonlinear method and Support Vector Machines (SVM) which is a supervised classification method. The classification result of MDS is consistent with the status of economic development of Sichuan in general, but details of the result cannot be verified itself; the output results of SVM by selecting different kernel functions are very similar to the classification result of MDS, which can validate these results. And considering the advantages and the solid mathematical theory, authors believe that the combination of these two methods is scientific.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"81 1","pages":"436-439"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86734281","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}
{"title":"Adopting genetic algorithm for portfolio management","authors":"Tak-Chung Fu, Chak-man Ng, Chi-pang Chung, Fu-Lai Chung","doi":"10.1109/ICNC.2012.6234511","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234511","url":null,"abstract":"","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"32 1","pages":"1151-1155"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78924826","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234572
Jing-wei Deng, Kai Deng, Yong-sheng Li, Ying-xing Li
Although there have been recent extensive research cooperation network and online community, have very limited knowledge of the actual development of online social networks. In the paper, we consider the structural evolution of a large online social networks. The theoretical analysis and simulation results show that, the evolution of the social networks model with scale-free and small-world properties. A new social network is close to the real-world social networks more exactly and can simulate the real-world social networks. It is generated by improving the Barabasi-Albert networks.
{"title":"Study on evolution model and simulation based on social networks","authors":"Jing-wei Deng, Kai Deng, Yong-sheng Li, Ying-xing Li","doi":"10.1109/ICNC.2012.6234572","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234572","url":null,"abstract":"Although there have been recent extensive research cooperation network and online community, have very limited knowledge of the actual development of online social networks. In the paper, we consider the structural evolution of a large online social networks. The theoretical analysis and simulation results show that, the evolution of the social networks model with scale-free and small-world properties. A new social network is close to the real-world social networks more exactly and can simulate the real-world social networks. It is generated by improving the Barabasi-Albert networks.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"46 1","pages":"1238-1241"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75682383","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234567
Yingcong Zeng, Jinhua Zheng
For hybrid wireless sensor networks with mobile nodes, to optimize the coverage performance, a control strategy based on SA-MODE (Self Adaptive-Multi Objective Differential Evolutionary Algorithm) for mobile nodes is proposed. Simulation results have shown the validity of the algorithm.
{"title":"A genetic algorithm-based wireless sensor network coverage-enhancing approach","authors":"Yingcong Zeng, Jinhua Zheng","doi":"10.1109/ICNC.2012.6234567","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234567","url":null,"abstract":"For hybrid wireless sensor networks with mobile nodes, to optimize the coverage performance, a control strategy based on SA-MODE (Self Adaptive-Multi Objective Differential Evolutionary Algorithm) for mobile nodes is proposed. Simulation results have shown the validity of the algorithm.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"50 1","pages":"1069-1073"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73583725","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234757
Yulong Liu, N. Li
Multimedia synchronization is a significant requirement for distributed multimedia applications. In this paper, a multimedia dynamic timed synchronization model based on Petri nets is presented (MDTSPN), which can describe the temporal synchronization accurately, and has stronger interactive ability. The backtracking algorithm is introduced to ensure the whole synchronization under the users' interactive control, and describe the dynamic behaviors of multimedia.
{"title":"A multimedia synchronization MDTSPN model based on Petri nets","authors":"Yulong Liu, N. Li","doi":"10.1109/ICNC.2012.6234757","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234757","url":null,"abstract":"Multimedia synchronization is a significant requirement for distributed multimedia applications. In this paper, a multimedia dynamic timed synchronization model based on Petri nets is presented (MDTSPN), which can describe the temporal synchronization accurately, and has stronger interactive ability. The backtracking algorithm is introduced to ensure the whole synchronization under the users' interactive control, and describe the dynamic behaviors of multimedia.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"13 1","pages":"497-501"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80299281","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234683
Q. Si, Mingchang Li, Guangyu Zhang, S. Liang, Zhaochen Sun
With the development of the exploitation in Tianjin coastal District, study on carrying capacity and its dynamic changes are the key methods for improving the scientific management level and for realizing sustainable development. This paper presents a data-driven neural network method to establish comprehensive carrying capacity assessment model by the nonlinear relationship between impact factors and level of carrying capacity. The calibration results work well in Tianjin Binhai District.
{"title":"Research on comprehensive carrying capacity assessment method with data-driven neural network","authors":"Q. Si, Mingchang Li, Guangyu Zhang, S. Liang, Zhaochen Sun","doi":"10.1109/ICNC.2012.6234683","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234683","url":null,"abstract":"With the development of the exploitation in Tianjin coastal District, study on carrying capacity and its dynamic changes are the key methods for improving the scientific management level and for realizing sustainable development. This paper presents a data-driven neural network method to establish comprehensive carrying capacity assessment model by the nonlinear relationship between impact factors and level of carrying capacity. The calibration results work well in Tianjin Binhai District.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"10 1","pages":"458-460"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73935465","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234668
Lin Huang, Tiejun Yang
License plate recognition is an important part of intelligent transportation systems, and image feature extraction and recognition are the key processes. This paper describes a method of license plate identification. Firstly, wavelet transform modulus maxima is used to detect edges for the segmented characters of the plate, then the features of relative moment are extracted. Secondly, the features are fed into BP neural network for classification. Experiment results show that the method is efficient and has good recognition rate.
{"title":"Vehicle license plate recognition based on wavelet transform modulus maxima and BP neural network","authors":"Lin Huang, Tiejun Yang","doi":"10.1109/ICNC.2012.6234668","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234668","url":null,"abstract":"License plate recognition is an important part of intelligent transportation systems, and image feature extraction and recognition are the key processes. This paper describes a method of license plate identification. Firstly, wavelet transform modulus maxima is used to detect edges for the segmented characters of the plate, then the features of relative moment are extracted. Secondly, the features are fed into BP neural network for classification. Experiment results show that the method is efficient and has good recognition rate.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"95 S91","pages":"295-297"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/ICNC.2012.6234668","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72408177","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234519
Jingwei Zhu, Ting Rui, Husheng Fang, Jinlin Zhang, Ming Liao
A simulated annealing ant colony algorithm(ASAC) is presented to tackle the quadratic assignment problem (QAP). The simulated annealing method is introduced to the ant colony algorithm. The temperature which declines with the iterations is set in the algorithm. After each round of searching, the solution set got by the colony is treated as the candidate set. Base on the simulated annealing method, the solution in the candidate set is chosen to join the update set with possibility which determined by the temperature. The update set is used to update the trail information matrix. And also the current best solution is used to enhance the tail information. The pheromone trails matrix is reset when the algorithm is in the stagnant state. The computer experiments demonstrate this algorithm has high calculation stability and converging speed.
{"title":"Simulated annealing ant colony algorithm for QAP","authors":"Jingwei Zhu, Ting Rui, Husheng Fang, Jinlin Zhang, Ming Liao","doi":"10.1109/ICNC.2012.6234519","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234519","url":null,"abstract":"A simulated annealing ant colony algorithm(ASAC) is presented to tackle the quadratic assignment problem (QAP). The simulated annealing method is introduced to the ant colony algorithm. The temperature which declines with the iterations is set in the algorithm. After each round of searching, the solution set got by the colony is treated as the candidate set. Base on the simulated annealing method, the solution in the candidate set is chosen to join the update set with possibility which determined by the temperature. The update set is used to update the trail information matrix. And also the current best solution is used to enhance the tail information. The pheromone trails matrix is reset when the algorithm is in the stagnant state. The computer experiments demonstrate this algorithm has high calculation stability and converging speed.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"31 1","pages":"789-793"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77054678","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}
International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications
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：