{"title":"A Perceptive Window for Responsive Environment Applications","authors":"Ching-Wen Hsu, Ya-Chi Huang, Fu-Chun Lu, Jinn-Kwei Guo, Chien-Jen Wang, Chun-Lin Lu","doi":"10.1109/ICNC.2009.679","DOIUrl":"https://doi.org/10.1109/ICNC.2009.679","url":null,"abstract":"This paper demonstrates the implementation of a responsive window which consists of an LCD-TV display and an ultrasonic location system. The window is perceptive because the main controller detects the location of the front observer by an ultrasonic system. The controller also manipulates the remote-end IP-camera to give a proper view which is corresponding to the location of the observer. The designs of both the ultrasonic system and the IP-camera control are described in this paper. Based on the ultrasonic location system, the observer in front of the responsive window needs not to wear anything. The test results show that the observer can manipulate the remote-end IP-camera simply by moving himself in front of the window. It is then verified that the perceptive window is able to be applied in the responsive environments.","PeriodicalId":235382,"journal":{"name":"2009 Fifth International Conference on Natural Computation","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129205580","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":"Random Coefficient Model of Basal Area Growth for Longitudinal Data","authors":"Zhang Qing, Z. Junhui, Kang Xin-gang","doi":"10.1109/ICNC.2009.636","DOIUrl":"https://doi.org/10.1109/ICNC.2009.636","url":null,"abstract":"Basal Area Growth model play an important role in forest management. In the permanent forest plots, the measures of BA growth are taken repeatedly over time, each stand has its individual trajectory. It is necessary to model both main response and individual trajectory of forest stands BA. In this paper, we show how a new random coefficient model of stands Basal Area Growth, which is developed based on longitudinal data. Through comparing the goodness of fit Statistics for different error structures, the optimal model is with AR(1) error structure.","PeriodicalId":235382,"journal":{"name":"2009 Fifth International Conference on Natural Computation","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123965287","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":"The Relationship between Generalization Error and the Training Sample Number of SVM","authors":"Junqing Bai, Guirong Yan, Wentao Mao","doi":"10.1109/ICNC.2009.479","DOIUrl":"https://doi.org/10.1109/ICNC.2009.479","url":null,"abstract":"It is very important to construct the training set and determine the sample number in the regression problem. In this paper, a new idea of constructing the training set is elaborated. The key point of this idea is to choose the hyper-parameters before determining the training set. More importantly, a heuristic approach is proposed to select samples of support vector machine (SVM). Using these methods, the relationship between generalization error and the number of training samples on a given confidence level is computed. The empirical results on benchmark data (Boston Housing) and engineering data indicate that the proposed approach can give a reference to construct the proper training set. Moreover, the proposed approach has practical significance for other parametric learning machine.","PeriodicalId":235382,"journal":{"name":"2009 Fifth International Conference on Natural Computation","volume":"41 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123477490","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":"A Sequential Radial Basis Function Neural Network Modeling Method Based on Partial Cross Validation Error Estimation","authors":"Wen Yao, Xiaoqian Chen","doi":"10.1109/ICNC.2009.352","DOIUrl":"https://doi.org/10.1109/ICNC.2009.352","url":null,"abstract":"Radial Basis Function Neural Network (RBFNN) is widely used in approximating high nonlinear functions. The network complexity and approximation accuracy are directly dominated by the training data. So how to sample data and obtain target system information in design space effectively is one of the key issues in improving RBFNN approximation capability. In this paper, a sequential RBFNN modeling method based on partial cross validation error estimation (PCVEE) criterion is proposed. This method can utilize the sample data as the validation data to test the approximation model accuracy, and expand the sample set purposively and refine the model sequentially according to the error estimation, so as to improve the approximation accuracy effectively. Two mathematical examples are tested to verify the efficiency of this method.","PeriodicalId":235382,"journal":{"name":"2009 Fifth International Conference on Natural Computation","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123488047","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}
Chun-gui Li, Wang Meng, Sun Zi-Gaung, Fei-Ying Lin, Zeng-fang Zhang
{"title":"Urban Traffic Signal Learning Control Using Fuzzy Actor-Critic Methods","authors":"Chun-gui Li, Wang Meng, Sun Zi-Gaung, Fei-Ying Lin, Zeng-fang Zhang","doi":"10.1109/ICNC.2009.374","DOIUrl":"https://doi.org/10.1109/ICNC.2009.374","url":null,"abstract":"Urban traffic control is very complicated, so it is very difficult to build a precise mathematical model. In this paper, we propose a fuzzy Actor-Critic reinforcement leaning algorithm to control the traffic signal, thus the decision can be made dynamically according to real-time traffic state information, and the change of environment can be adapted automatically; In order to solve the curse of the dimensionality problem, we applied fuzzy radial basis function (FRBF) neural network to approximate the state value function. By training self-adapted non-linear processing unit, and realizing online and adaptive constructing of state space, the approximation is improved, thus the control of traffic signal at single intersections is solved. The simulation results show that the effectiveness of the new control algorithm is obviously better than traditional sliced time allocation methods.","PeriodicalId":235382,"journal":{"name":"2009 Fifth International Conference on Natural Computation","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120955357","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":"An Immune Algorithm Based Approach to Inverter Control","authors":"Jiaxin Yuan, Xiaofang Su, Baichao Chen","doi":"10.1109/ICNC.2009.204","DOIUrl":"https://doi.org/10.1109/ICNC.2009.204","url":null,"abstract":"In this paper, a novel nonlinear technique employing Immune Algorithm (IA) as the search method for the optimum control of the inverter was presented. The design problem was converted to an equivalent optimization problem, and the IA was adopted to find the optimal control sequence. IA well fits with on-line microprocessor implementation. An example using a single-phase full-bridge inverter verifies the usefulness of the method. The simulation and experimental results prove the goodness of the presented approach.","PeriodicalId":235382,"journal":{"name":"2009 Fifth International Conference on Natural Computation","volume":"158 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114113102","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":"Simulation of Dynamic Characteristic for Passive Hydraulic Mount","authors":"Z. Yunxia, Fang Zu-hua","doi":"10.1109/ICNC.2009.573","DOIUrl":"https://doi.org/10.1109/ICNC.2009.573","url":null,"abstract":"Dynamic modeling of Passive Hydraulic Engine Mounts (PHEM) is developed with inertia track, decoupler and throttle. Mathematically, the state equations governing vibration isolation behaviors of the PHEMs are presented and solved by means of the lumped parameter method. Numerical results are produced for low and high frequency responses of the engine mounts. It is shown the engine mounts are possessed of better dynamic performance characteristics such as frequency-dependent and amplitude-dependent. The experiments are made for the purpose of parameters designs and validation of the PHEM. It has been shown by comparison of the numerical results with the experimental observations that the present PHEM achieves fairly good performance for the vehicle industry. The work conducted in the paper demonstrates that the methods for simulating the system in the lumped model and the numerical predictions model for modeling PHEM are effective, with which the dynamic characteristic analysis and design optimization of an PHEM can be performed before its prototype development, and this can ensure its low cost and high quality for development.","PeriodicalId":235382,"journal":{"name":"2009 Fifth International Conference on Natural Computation","volume":"500 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116203827","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}
Jie Ma, Dongwei Guo, Kangping Wang, Miao Liu, Sha Chen
{"title":"Colony Evolution in Social Networks Based on Multi-agent System","authors":"Jie Ma, Dongwei Guo, Kangping Wang, Miao Liu, Sha Chen","doi":"10.1109/ICNC.2009.103","DOIUrl":"https://doi.org/10.1109/ICNC.2009.103","url":null,"abstract":"According to the sociological principium, this paper designed a model aimed at social networks and implemented it using the multi-agent system. Based on this model, we established a simulation system to research the evolution of colony in the social networks, analyzed the effects on the evolution by the characteristics of individuals and achieved meaningful conclusions.","PeriodicalId":235382,"journal":{"name":"2009 Fifth International Conference on Natural Computation","volume":"308 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121535546","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":"Application of Bayesian Neural Networks in High Energy Physics Experiments","authors":"Ye Xu, WeiWei Xu, Y. Meng, K. Zhu","doi":"10.1109/ICNC.2009.117","DOIUrl":"https://doi.org/10.1109/ICNC.2009.117","url":null,"abstract":"Some applications of Bayesian neural networks (BNN) in the high energy physics experiments are described in the present paper. They are the applications of BNN to particle identification in the second generation of BEijing Spectrometer experiment (BESII), event identification and event reconstruction in reactor neutrino experiments and supernova location in scintillator detector experiments, respectively. Compared to traditional method, better results are obtained in those experiments using BNN. So we believe that BNN can be also well applied to other fields in other experiments for the high energy physics.","PeriodicalId":235382,"journal":{"name":"2009 Fifth International Conference on Natural Computation","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113978492","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":"Neural Network Sliding Mode Controller for Linear Elevator Using Permanent Magnet Linear Synchronous Motor","authors":"Qing Hu, Hongxia Li, Haiyan Yu, Xin Zhang","doi":"10.1109/ICNC.2009.454","DOIUrl":"https://doi.org/10.1109/ICNC.2009.454","url":null,"abstract":"In order to improve the tracking and robust performances of a linear elevator driving by permanent magnet linear synchronous motor (PMLSM), a stable neural network sliding mode controller (NN-SMC) for a linear motor speed loop control is proposed. The neural network control is highly efficient for some large data sets via self-organizing, learning, and forgetting. Analysis of simulations reveals that proposed method is robust in the presence of uncertainties and bounded external disturbances.","PeriodicalId":235382,"journal":{"name":"2009 Fifth International Conference on Natural Computation","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114802900","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}