Pub Date : 2010-11-01DOI: 10.1109/YCICT.2010.5713130
Yuanyuan Jin, Bao-jian Gao, Ziran Zhang
This paper presents an automatic topic segmentation approach based on subwords normalized cut (Ncut) for Chinese broadcast news, since the classical Ncut has a limitation that the number of segments has to be set as a prior. We abstract a text into a weighted undirected graph, where the nodes correspond to sentences and the weights of edges describe inter-sentence lexical similarities at Chinese subwords level, thus the segmentation task is formalized as a graph-partitioning problem under the Ncut criterion. In order to break through the limitation, we proposed a text dotplotting inspired method, which can evaluate the segmentation results and select the optimal number of segments automatically. Lastly, we put the whole approach into a machine learning framework, learning the best arguments on train set. Our method achieved relative improvement of 3% over non-automatic subwords Ncut, also the previous best method.
{"title":"An automatic normalized cut topic segmentation approach","authors":"Yuanyuan Jin, Bao-jian Gao, Ziran Zhang","doi":"10.1109/YCICT.2010.5713130","DOIUrl":"https://doi.org/10.1109/YCICT.2010.5713130","url":null,"abstract":"This paper presents an automatic topic segmentation approach based on subwords normalized cut (Ncut) for Chinese broadcast news, since the classical Ncut has a limitation that the number of segments has to be set as a prior. We abstract a text into a weighted undirected graph, where the nodes correspond to sentences and the weights of edges describe inter-sentence lexical similarities at Chinese subwords level, thus the segmentation task is formalized as a graph-partitioning problem under the Ncut criterion. In order to break through the limitation, we proposed a text dotplotting inspired method, which can evaluate the segmentation results and select the optimal number of segments automatically. Lastly, we put the whole approach into a machine learning framework, learning the best arguments on train set. Our method achieved relative improvement of 3% over non-automatic subwords Ncut, also the previous best method.","PeriodicalId":179847,"journal":{"name":"2010 IEEE Youth Conference on Information, Computing and Telecommunications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124162479","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 : 2010-11-01DOI: 10.1109/YCICT.2010.5713124
Wang Xin, Yu Hongliang, Zhang Lin
As the shortcomings of BP neural network slow convergence rate, falling into local minimum easily and difficult to determine the number of hidden nodes accurately, the number of hidden nodes, weights and threshold of BP neural network were optimized, using binary and real number hybrid coding based on genetic algorithms with global searching ability. Finally, the method tested with WD615 diesel engine valve fault diagnosis data. Experimental results showed that this algorithm has obvious advantages, it is able to overcome the deficiencies of BP neural network, and improves the network's learning ability.
{"title":"Improved genetic algorithm and neural network method and the application in fault diagnosis of valve diesel engine","authors":"Wang Xin, Yu Hongliang, Zhang Lin","doi":"10.1109/YCICT.2010.5713124","DOIUrl":"https://doi.org/10.1109/YCICT.2010.5713124","url":null,"abstract":"As the shortcomings of BP neural network slow convergence rate, falling into local minimum easily and difficult to determine the number of hidden nodes accurately, the number of hidden nodes, weights and threshold of BP neural network were optimized, using binary and real number hybrid coding based on genetic algorithms with global searching ability. Finally, the method tested with WD615 diesel engine valve fault diagnosis data. Experimental results showed that this algorithm has obvious advantages, it is able to overcome the deficiencies of BP neural network, and improves the network's learning ability.","PeriodicalId":179847,"journal":{"name":"2010 IEEE Youth Conference on Information, Computing and Telecommunications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126791038","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 : 2010-11-01DOI: 10.1109/YCICT.2010.5713071
Ji-hua Cao
A guaranteed cost control method for autonomous vehicle platoon with communication constraints (such as quantization, time-delay and packet-losses) is developed in this paper. Firstly, a vehicle model is established for the platoon's longitudinal movement, which is shown to be a great improvement of the existing models in that networked communication constraints are considered. Then, a guaranteed cost control algorithm is presented to overcome the communication constraints on the platoon. Under this controller, the platoon can be stable. The effectiveness of the proposed robust controller is demonstrated by simulation studies.
{"title":"A guaranteed cost control for autonomous vehicle platoon with communication constraints","authors":"Ji-hua Cao","doi":"10.1109/YCICT.2010.5713071","DOIUrl":"https://doi.org/10.1109/YCICT.2010.5713071","url":null,"abstract":"A guaranteed cost control method for autonomous vehicle platoon with communication constraints (such as quantization, time-delay and packet-losses) is developed in this paper. Firstly, a vehicle model is established for the platoon's longitudinal movement, which is shown to be a great improvement of the existing models in that networked communication constraints are considered. Then, a guaranteed cost control algorithm is presented to overcome the communication constraints on the platoon. Under this controller, the platoon can be stable. The effectiveness of the proposed robust controller is demonstrated by simulation studies.","PeriodicalId":179847,"journal":{"name":"2010 IEEE Youth Conference on Information, Computing and Telecommunications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126808858","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 : 2010-11-01DOI: 10.1109/YCICT.2010.5713051
Errong Pei, Sheng Wang, Zhizhong Zhang
Unlike traditional spectrum sharing model with a predetermined fixed interference threshold at the primary receiver, in the paper we consider a new spectrum sharing model with a elastic controllable interference varying between 0 and bottom threshold that is maximum the primary receiver can tolerated, and we introduce a seller's market trading mechanism in order to fully exploit the interference room, as has very important practical significance. In the context, we investigate the secondary user's (SU's) maximal gross profit and optimal power allocation scheme in Rayleigh fading environment, and also study the interference price and average revenue of SU's impact on them. Numerical calculation results are conducted to verify our theoretical results.
{"title":"Gross profit maximization and optimal power allocation for spectrum-sharing based on elastic controllable interference in Rayleigh fading channels","authors":"Errong Pei, Sheng Wang, Zhizhong Zhang","doi":"10.1109/YCICT.2010.5713051","DOIUrl":"https://doi.org/10.1109/YCICT.2010.5713051","url":null,"abstract":"Unlike traditional spectrum sharing model with a predetermined fixed interference threshold at the primary receiver, in the paper we consider a new spectrum sharing model with a elastic controllable interference varying between 0 and bottom threshold that is maximum the primary receiver can tolerated, and we introduce a seller's market trading mechanism in order to fully exploit the interference room, as has very important practical significance. In the context, we investigate the secondary user's (SU's) maximal gross profit and optimal power allocation scheme in Rayleigh fading environment, and also study the interference price and average revenue of SU's impact on them. Numerical calculation results are conducted to verify our theoretical results.","PeriodicalId":179847,"journal":{"name":"2010 IEEE Youth Conference on Information, Computing and Telecommunications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130485003","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 : 2010-11-01DOI: 10.1109/YCICT.2010.5713091
R. Han, Xuewen Zeng, Peng Sun
Video streaming applications have implementation issues when the transmission rate is much less than the video playback rate. Caching the beginning part of the video in large storage device before playing is a common solution. In this paper, we propose a bandwidth allocation scheme on video content distribution servers. This algorithm is aim to control the server sending rate with efficient bandwidth resource allocation. In order to reduce the impact of network rate jitter, we present a client cache scheme considering the average receiving rate. On servers, on-line clients are grouped into three queues based on different serving stages: playing, downloading or waiting to play. The sending rate is allocated to each client dynamically. Clients who are watching video have the highest priority. For the waiting clients, a weighted bandwidth allocation approach is presented to minimize users' waiting time. The simulation results show that the proposed bandwidth allocation scheme can achieve a high performance.
{"title":"Bandwidth allocation on video content distribution servers","authors":"R. Han, Xuewen Zeng, Peng Sun","doi":"10.1109/YCICT.2010.5713091","DOIUrl":"https://doi.org/10.1109/YCICT.2010.5713091","url":null,"abstract":"Video streaming applications have implementation issues when the transmission rate is much less than the video playback rate. Caching the beginning part of the video in large storage device before playing is a common solution. In this paper, we propose a bandwidth allocation scheme on video content distribution servers. This algorithm is aim to control the server sending rate with efficient bandwidth resource allocation. In order to reduce the impact of network rate jitter, we present a client cache scheme considering the average receiving rate. On servers, on-line clients are grouped into three queues based on different serving stages: playing, downloading or waiting to play. The sending rate is allocated to each client dynamically. Clients who are watching video have the highest priority. For the waiting clients, a weighted bandwidth allocation approach is presented to minimize users' waiting time. The simulation results show that the proposed bandwidth allocation scheme can achieve a high performance.","PeriodicalId":179847,"journal":{"name":"2010 IEEE Youth Conference on Information, Computing and Telecommunications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131992169","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 : 2010-11-01DOI: 10.1109/YCICT.2010.5713132
Qianbin Chen, Haijun Hu, Ya-Lai Zhao, Rong Chai
Group mobility in WSN is of particular importance as it is can be found in many practical application scenarios. In this paper, we propose to combine HIP and NEMO protocol for supporting group mobility in WSN. The overview of HIP and NEMO protocol is introduced and the new network architecture for applying HIP and NEMO protocol in WSN is proposed, which enhances mobility management, network security and host multi-homing for WSN. The corresponding group mobility management mechanism and signaling process are discussed.
{"title":"HIP-based network mobility management for WSN","authors":"Qianbin Chen, Haijun Hu, Ya-Lai Zhao, Rong Chai","doi":"10.1109/YCICT.2010.5713132","DOIUrl":"https://doi.org/10.1109/YCICT.2010.5713132","url":null,"abstract":"Group mobility in WSN is of particular importance as it is can be found in many practical application scenarios. In this paper, we propose to combine HIP and NEMO protocol for supporting group mobility in WSN. The overview of HIP and NEMO protocol is introduced and the new network architecture for applying HIP and NEMO protocol in WSN is proposed, which enhances mobility management, network security and host multi-homing for WSN. The corresponding group mobility management mechanism and signaling process are discussed.","PeriodicalId":179847,"journal":{"name":"2010 IEEE Youth Conference on Information, Computing and Telecommunications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133903925","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 : 2010-11-01DOI: 10.1109/YCICT.2010.5713102
Guoru Ding, Qi-hui Wu, Jinlong Wang, Xiao Zhang
In this paper, a joint cooperative spectrum sensing (CSS) and resource scheduling scheme for cognitive radio networks (CRN) is investigated. The soft sensing information instead of 1 bit hard decision information is directly used for decision-making to further exploit spectrum opportunities. To find the global optimal solution of a non-convex multi-carrier resource scheduling problem, a distributive scheduling algorithm based on duality theory is proposed. Simulation results reveal the substantial performance gain of the proposed scheme over the previous designs.
{"title":"Joint cooperative spectrum sensing and resource scheduling for cognitive radio networks with soft sensing information","authors":"Guoru Ding, Qi-hui Wu, Jinlong Wang, Xiao Zhang","doi":"10.1109/YCICT.2010.5713102","DOIUrl":"https://doi.org/10.1109/YCICT.2010.5713102","url":null,"abstract":"In this paper, a joint cooperative spectrum sensing (CSS) and resource scheduling scheme for cognitive radio networks (CRN) is investigated. The soft sensing information instead of 1 bit hard decision information is directly used for decision-making to further exploit spectrum opportunities. To find the global optimal solution of a non-convex multi-carrier resource scheduling problem, a distributive scheduling algorithm based on duality theory is proposed. Simulation results reveal the substantial performance gain of the proposed scheme over the previous designs.","PeriodicalId":179847,"journal":{"name":"2010 IEEE Youth Conference on Information, Computing and Telecommunications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132737596","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 : 2010-11-01DOI: 10.1109/YCICT.2010.5713129
Xiaopeng Gao, Zhiqiang Wang, Han Wan, Xiang Long
Physic-based fluid simulation is used extensively nowadays; however the traditional serial algorithm can't satisfy the real-time requirement due to its complexity and computeintensive. The development of modern GPU makes this possible. In this paper, a Smoothed Particle Hydrodynamics (SPH) method for incompressible fluid was implemented using CUDA on GPU. Since the algorithm was executed on the GPU entirely, the method can take full advantage of massive computational power of modern graphics hardware. The experiment results show that our GPU based SPH implementation can achieve the rate of 89 frames per second in the simulation of 102K particles and gain nearly 140× speedups compared with the serial algorithm.
{"title":"Accelerate Smoothed Particle Hydrodynamics using GPU","authors":"Xiaopeng Gao, Zhiqiang Wang, Han Wan, Xiang Long","doi":"10.1109/YCICT.2010.5713129","DOIUrl":"https://doi.org/10.1109/YCICT.2010.5713129","url":null,"abstract":"Physic-based fluid simulation is used extensively nowadays; however the traditional serial algorithm can't satisfy the real-time requirement due to its complexity and computeintensive. The development of modern GPU makes this possible. In this paper, a Smoothed Particle Hydrodynamics (SPH) method for incompressible fluid was implemented using CUDA on GPU. Since the algorithm was executed on the GPU entirely, the method can take full advantage of massive computational power of modern graphics hardware. The experiment results show that our GPU based SPH implementation can achieve the rate of 89 frames per second in the simulation of 102K particles and gain nearly 140× speedups compared with the serial algorithm.","PeriodicalId":179847,"journal":{"name":"2010 IEEE Youth Conference on Information, Computing and Telecommunications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121466285","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 : 2010-11-01DOI: 10.1109/YCICT.2010.5713079
Zhou Weihong, Xiong Shunqing, Ma Ting
Most of the fuzzy classifiers are created by fuzzy rules based on apriori knowledge and expert's knowledge, but in many applications, it's difficult to obtain fuzzy rules without apriori knowledge of the data. To solve this problem, a new way of creating Mamdani fuzzy classifier based on Mamdani fuzzy logical system is proposesed in this paper, and the new fuzzy classifier is improved with the genetic algorithm further. The result of data simulation with Iris data shows the new Mamdani fuzzy classifier has minimum number of features, minimum number of fuzzy rules and better precision.
{"title":"A fuzzy classifier based on Mamdani fuzzy logic system and genetic algorithm","authors":"Zhou Weihong, Xiong Shunqing, Ma Ting","doi":"10.1109/YCICT.2010.5713079","DOIUrl":"https://doi.org/10.1109/YCICT.2010.5713079","url":null,"abstract":"Most of the fuzzy classifiers are created by fuzzy rules based on apriori knowledge and expert's knowledge, but in many applications, it's difficult to obtain fuzzy rules without apriori knowledge of the data. To solve this problem, a new way of creating Mamdani fuzzy classifier based on Mamdani fuzzy logical system is proposesed in this paper, and the new fuzzy classifier is improved with the genetic algorithm further. The result of data simulation with Iris data shows the new Mamdani fuzzy classifier has minimum number of features, minimum number of fuzzy rules and better precision.","PeriodicalId":179847,"journal":{"name":"2010 IEEE Youth Conference on Information, Computing and Telecommunications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125267945","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}
This paper is an initial explore to Chinese-Uyghur statistical machine translation. We experimented on three systems, which are based on moses framework, on Uyghur word-level corpus and morpheme-level corpus, then combine their 1-best translation hypothesis by constructing consensus network using TER alignment. The experiments show the combination of hypothesis that are from different systems can obtain a better result.
{"title":"Moses-based Chinese-Uyghur statistical machine translation systems","authors":"Xinghua Dong, Yating Yang, Xiaoping Zhou, Junlin Zhou","doi":"10.1109/YCICT.2010.5713076","DOIUrl":"https://doi.org/10.1109/YCICT.2010.5713076","url":null,"abstract":"This paper is an initial explore to Chinese-Uyghur statistical machine translation. We experimented on three systems, which are based on moses framework, on Uyghur word-level corpus and morpheme-level corpus, then combine their 1-best translation hypothesis by constructing consensus network using TER alignment. The experiments show the combination of hypothesis that are from different systems can obtain a better result.","PeriodicalId":179847,"journal":{"name":"2010 IEEE Youth Conference on Information, Computing and Telecommunications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124487967","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}