International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications最新文献
Pub Date : 2011-07-26DOI: 10.1109/ICNC.2011.6022070
B. Buren
Area MT+ is a patch of middle temporal cortex that plays a critical role in our ability to perceive motion in the visual modality. Recent neuroimaging studies of congenitally blind adults suggest that this brain area can “learn” to represent auditory motion, but only when individuals are deprived of visual input from birth. Here I present a parallel distributed processing network that behaves similarly to area MT+. Its internal connection weights are such that it is able to compute the direction of motion by comparing the locations of two sequentially-presented visual inputs. Trained on visual + auditory input, it continues to respond only to visual motion. In the absence of visual inputs, it learns to detect motion in auditory inputs. My network is characterized by innate processing biases, coupled with a capacity for flexibility. I argue that this implementation is a plausible model of the neural network that constitutes area MT+.
{"title":"Modeling the functional development of human visual motion area MT+","authors":"B. Buren","doi":"10.1109/ICNC.2011.6022070","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022070","url":null,"abstract":"Area MT+ is a patch of middle temporal cortex that plays a critical role in our ability to perceive motion in the visual modality. Recent neuroimaging studies of congenitally blind adults suggest that this brain area can “learn” to represent auditory motion, but only when individuals are deprived of visual input from birth. Here I present a parallel distributed processing network that behaves similarly to area MT+. Its internal connection weights are such that it is able to compute the direction of motion by comparing the locations of two sequentially-presented visual inputs. Trained on visual + auditory input, it continues to respond only to visual motion. In the absence of visual inputs, it learns to detect motion in auditory inputs. My network is characterized by innate processing biases, coupled with a capacity for flexibility. I argue that this implementation is a plausible model of the neural network that constitutes area MT+.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"34 1","pages":"320-324"},"PeriodicalIF":0.0,"publicationDate":"2011-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83159019","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 : 2011-07-26DOI: 10.1109/ICNC.2011.6022398
Xiao-fei Zhang, Xianfeng Huai, Shouyi Li, Bo-Ren Yang
According to the randomness of thermal parameters of laboratory test and the defects of traditional back analysis method which is easy to fall into premature and has low efficiency and great computational complexity, the back analysis method based on parallel particle swarm optimization is developed. The back analysis steps of thermal parameters of mass concrete structure is demonstrated detailedly. When three-dimensional finite element relocating mesh method and improved BP neural network method are used to inverse thermal parameters based on the measured temperature, the parameters which reflect the true performance can be obtained. The results show that this method has a better stability and convergency and is feasible to inverse thermal parameters.
{"title":"Back analysis of thermal parameters of roller compacted concrete dam based on parallel particle swarm optimization","authors":"Xiao-fei Zhang, Xianfeng Huai, Shouyi Li, Bo-Ren Yang","doi":"10.1109/ICNC.2011.6022398","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022398","url":null,"abstract":"According to the randomness of thermal parameters of laboratory test and the defects of traditional back analysis method which is easy to fall into premature and has low efficiency and great computational complexity, the back analysis method based on parallel particle swarm optimization is developed. The back analysis steps of thermal parameters of mass concrete structure is demonstrated detailedly. When three-dimensional finite element relocating mesh method and improved BP neural network method are used to inverse thermal parameters based on the measured temperature, the parameters which reflect the true performance can be obtained. The results show that this method has a better stability and convergency and is feasible to inverse thermal parameters.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"65 1","pages":"2011-2014"},"PeriodicalIF":0.0,"publicationDate":"2011-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80696594","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 : 2011-07-26DOI: 10.1109/ICNC.2011.6022390
Lu Tan, Yanrong Chi
Introducing the topological structure and regular topology structure, the purpose is to seek with regular topological structure of low dimensional data set, the structural topological structure regularity, and puts forward the measure to keep data set topology structure of local rules embedding method. Compared to nuclear feature mapping methods, such as Locally Linear Embedding, Laplacian Eigenmap and so on, low dimensional embedded result is approximately regular, and data classification has more natural connection. The last results prove the theory results show that this technique can greatly discover the topological structure of data, compared to the LLE and Laplacian Eigenmap.
{"title":"Notice of Retraction Locally regular embedding","authors":"Lu Tan, Yanrong Chi","doi":"10.1109/ICNC.2011.6022390","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022390","url":null,"abstract":"Introducing the topological structure and regular topology structure, the purpose is to seek with regular topological structure of low dimensional data set, the structural topological structure regularity, and puts forward the measure to keep data set topology structure of local rules embedding method. Compared to nuclear feature mapping methods, such as Locally Linear Embedding, Laplacian Eigenmap and so on, low dimensional embedded result is approximately regular, and data classification has more natural connection. The last results prove the theory results show that this technique can greatly discover the topological structure of data, compared to the LLE and Laplacian Eigenmap.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"38 1","pages":"2133-2136"},"PeriodicalIF":0.0,"publicationDate":"2011-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73752234","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 : 2011-07-26DOI: 10.1109/ICNC.2011.6022143
Jingyao Wang, Heli Liu, Mei Song
The quality of service (QoS) is an important factor for networks; guarantee the QoS in network is then very important for the network performance. Anyway, the research on the accurately evaluation on QoS is still lacked. In this paper, we employ the computational learning theory to study this problem and present the QoS evaluation model. Then the QoS evaluation scheme base on support vector machine (SVM) is proposed. Simulation results show that our propose scheme is more effective and improve the performance of the QoS evaluation.
{"title":"A novel QoS evaluation scheme based on support vector machine","authors":"Jingyao Wang, Heli Liu, Mei Song","doi":"10.1109/ICNC.2011.6022143","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022143","url":null,"abstract":"The quality of service (QoS) is an important factor for networks; guarantee the QoS in network is then very important for the network performance. Anyway, the research on the accurately evaluation on QoS is still lacked. In this paper, we employ the computational learning theory to study this problem and present the QoS evaluation model. Then the QoS evaluation scheme base on support vector machine (SVM) is proposed. Simulation results show that our propose scheme is more effective and improve the performance of the QoS evaluation.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"337 1","pages":"724-727"},"PeriodicalIF":0.0,"publicationDate":"2011-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77476242","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 : 2011-07-26DOI: 10.1109/ICNC.2011.6022110
Lei Li, Yang Duan
The regression analysis is a method in mathematical statistics to solve many practical problem. Support Vector Regression (SVR) is an effective method for resolving regression problem. However, the traditional SVR impose many of the limitations, the SVR parameters need optimizing, but there is not a mature theoretic for choosing the parameters of SVR, which causes much discommodity to the appliance of SVR. This paper proposes and investigates the use of a genetic algorithm approach for simultaneously select an optimal feature subset and optimize SVR parameters.
{"title":"A GA-based feature selection and parameters optimization for support vector regression","authors":"Lei Li, Yang Duan","doi":"10.1109/ICNC.2011.6022110","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022110","url":null,"abstract":"The regression analysis is a method in mathematical statistics to solve many practical problem. Support Vector Regression (SVR) is an effective method for resolving regression problem. However, the traditional SVR impose many of the limitations, the SVR parameters need optimizing, but there is not a mature theoretic for choosing the parameters of SVR, which causes much discommodity to the appliance of SVR. This paper proposes and investigates the use of a genetic algorithm approach for simultaneously select an optimal feature subset and optimize SVR parameters.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"779 1","pages":"335-339"},"PeriodicalIF":0.0,"publicationDate":"2011-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76915792","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 : 2011-07-26DOI: 10.1109/ICNC.2011.6022104
Xiang Hui, Y. Gang
Credit scoring has gained increasing attentions from banks, which can benefit from reducing possible risks of default. Based on the analysis of relationship between the performance of ensemble model and that of base classifiers, this paper proposes a selective neural network ensemble model for credit scoring, In which Artificial neural networks and ensemble learning methods are firstly employed to build a base classifiers pool, then hierarchical clustering algorithm is used to divide those base classifiers into several clusters, then the classifiers with highest accuracy in each cluster are chose to vote for the final decision. Three real world credit datasets are selected as the experimental data to demonstrate the accuracy of the model. The results show that selective neural network ensemble model can significantly improved the efficiency in selection of base classifiers and generalization ability and thereby show enough attractive features for credit risk management system.
{"title":"Credit scoring model based on selective neural network ensemble","authors":"Xiang Hui, Y. Gang","doi":"10.1109/ICNC.2011.6022104","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022104","url":null,"abstract":"Credit scoring has gained increasing attentions from banks, which can benefit from reducing possible risks of default. Based on the analysis of relationship between the performance of ensemble model and that of base classifiers, this paper proposes a selective neural network ensemble model for credit scoring, In which Artificial neural networks and ensemble learning methods are firstly employed to build a base classifiers pool, then hierarchical clustering algorithm is used to divide those base classifiers into several clusters, then the classifiers with highest accuracy in each cluster are chose to vote for the final decision. Three real world credit datasets are selected as the experimental data to demonstrate the accuracy of the model. The results show that selective neural network ensemble model can significantly improved the efficiency in selection of base classifiers and generalization ability and thereby show enough attractive features for credit risk management system.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"33 1","pages":"513-516"},"PeriodicalIF":0.0,"publicationDate":"2011-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89429298","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 : 2011-07-26DOI: 10.1109/ICNC.2011.6022118
Zhenzhen Yuan, Shuang Liu, Linyan Xue, Xiu-e Yuan
Power system load is a nonlinear time series, for the complexity and nonlinear of power systems loads, this paper combines the idea of chaos theory, make full use of data in the reconstruction phase space power load based on the load of forecast, due to the approximation capability of neural networks with superior predictive ability, the use of RBF neural network-based method and Matlab simulation, the simulation shows that such a prediction algorithm to obtain good results.
{"title":"Short-term load forecasting based on chaos theory and RBF neural network","authors":"Zhenzhen Yuan, Shuang Liu, Linyan Xue, Xiu-e Yuan","doi":"10.1109/ICNC.2011.6022118","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022118","url":null,"abstract":"Power system load is a nonlinear time series, for the complexity and nonlinear of power systems loads, this paper combines the idea of chaos theory, make full use of data in the reconstruction phase space power load based on the load of forecast, due to the approximation capability of neural networks with superior predictive ability, the use of RBF neural network-based method and Matlab simulation, the simulation shows that such a prediction algorithm to obtain good results.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"25 1","pages":"526-529"},"PeriodicalIF":0.0,"publicationDate":"2011-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78209019","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 : 2011-07-26DOI: 10.1109/ICNC.2011.6022225
Gang Huang, Yuanming Long, Jinhang Li
There has been a growing interest in studying of random search strategies. In many industries including manufacturing, logistics, computer etc., researchers use evolutionary algorithms to solve sophisticated optimization problems which have stationary or shifty optimal values. These problems could hardly be solved with precise mathematical methods, called non-deterministic Polynomial-time hard (NP-hard) problems. Particle swarm optimization (PSO) is one of those algorithm and attracts extra attention. In this paper, we put forward a new model to explore the step length of search process of PSO, via statistics methods. Typical two-dimensional and multi-dimensional benchmark functions are used to generate empirical data for further analysis. Levy flight search patterns finally proved to play an important role in the searching process. Then the relationship between the values of scaling parameters in power law distributions and the efficiency of PSO is discussed. More interesting results are given in discussion.
{"title":"Lévy flight search patterns in particle swarm optimization","authors":"Gang Huang, Yuanming Long, Jinhang Li","doi":"10.1109/ICNC.2011.6022225","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022225","url":null,"abstract":"There has been a growing interest in studying of random search strategies. In many industries including manufacturing, logistics, computer etc., researchers use evolutionary algorithms to solve sophisticated optimization problems which have stationary or shifty optimal values. These problems could hardly be solved with precise mathematical methods, called non-deterministic Polynomial-time hard (NP-hard) problems. Particle swarm optimization (PSO) is one of those algorithm and attracts extra attention. In this paper, we put forward a new model to explore the step length of search process of PSO, via statistics methods. Typical two-dimensional and multi-dimensional benchmark functions are used to generate empirical data for further analysis. Levy flight search patterns finally proved to play an important role in the searching process. Then the relationship between the values of scaling parameters in power law distributions and the efficiency of PSO is discussed. More interesting results are given in discussion.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"21 1","pages":"1185-1189"},"PeriodicalIF":0.0,"publicationDate":"2011-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76906155","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 : 2011-07-26DOI: 10.1109/ICNC.2011.6022189
T. Teoh, Siu-Yeung Cho
This paper presents an attempt of using Hidden Markov Model to model the high level emotions (such as, encouraging, interest, unsure, disagreeing and discouraging) through low level facial expressions (such as, happy, sad, surprise and neutral). The rationale behind using HMM is that the HMM models human brain as human emotion is quite complex, naturally a human instinct contain hidden layer as well (like sub conscious mind). In addition, Markov state chain property is good to model human emotion as our emotion is also through our mind state that it is always dependent on our previous state of our emotion and current event will end up our current emotion state. Our proposed work is to develop an emotion indexer acting as a higher level analysis to interpret more advanced emotional states out of the basic emotions.
{"title":"Human emotional states modeling by Hidden Markov Model","authors":"T. Teoh, Siu-Yeung Cho","doi":"10.1109/ICNC.2011.6022189","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022189","url":null,"abstract":"This paper presents an attempt of using Hidden Markov Model to model the high level emotions (such as, encouraging, interest, unsure, disagreeing and discouraging) through low level facial expressions (such as, happy, sad, surprise and neutral). The rationale behind using HMM is that the HMM models human brain as human emotion is quite complex, naturally a human instinct contain hidden layer as well (like sub conscious mind). In addition, Markov state chain property is good to model human emotion as our emotion is also through our mind state that it is always dependent on our previous state of our emotion and current event will end up our current emotion state. Our proposed work is to develop an emotion indexer acting as a higher level analysis to interpret more advanced emotional states out of the basic emotions.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"56 1","pages":"908-912"},"PeriodicalIF":0.0,"publicationDate":"2011-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84698851","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 : 2011-07-26DOI: 10.1109/ICNC.2011.6022228
Tran Xuan Truong, L. Lan, Nguyễn Duy Việt, Mai Vinh Du
The use of internet services for time sensitive applications like voice and video, requires the forecasting quality of service. The TCP/IP differentiated services structure is given to achieve this target. However, network congestion control is limited and comes from the high priority. Some studies are still seeking a replacement techniques such as random early detection (RED) and its modification to manage congestion. In this paper we present neural network control research results to implement RED, called NRED. We found that with neural network we can perform better for discrimination acts to cancel the packets for gathering traffic flow, and also provide better quality services to all types different traffic while ensuring high utilization.
{"title":"Congestion control in TCP/IP differentiated services network using neural network","authors":"Tran Xuan Truong, L. Lan, Nguyễn Duy Việt, Mai Vinh Du","doi":"10.1109/ICNC.2011.6022228","DOIUrl":"https://doi.org/10.1109/ICNC.2011.6022228","url":null,"abstract":"The use of internet services for time sensitive applications like voice and video, requires the forecasting quality of service. The TCP/IP differentiated services structure is given to achieve this target. However, network congestion control is limited and comes from the high priority. Some studies are still seeking a replacement techniques such as random early detection (RED) and its modification to manage congestion. In this paper we present neural network control research results to implement RED, called NRED. We found that with neural network we can perform better for discrimination acts to cancel the packets for gathering traffic flow, and also provide better quality services to all types different traffic while ensuring high utilization.","PeriodicalId":87274,"journal":{"name":"International Conference on Computing, Networking, and Communications : [proceedings]. International Conference on Computing, Networking and Communications","volume":"1 1","pages":"686-690"},"PeriodicalIF":0.0,"publicationDate":"2011-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90077479","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：