SVM performance is very sensitive to the parameter set. In this paper we propose an automatic and effective model selection method. It is based on evolutionary computation algorithms and use recall, precision and error rate estimated by xialpha-estimate as the optimization targets. Optimized by genetic algorithm (GA) or particle swarm optimization (PSO) algorithm, we demonstrate that SVM could automatically select its multiple parameters and optimize them. Experiments results also verify that by optimizing the bounds estimated by xialpha-estimate we could also improve the practical performance.
{"title":"Evolutionary Computation Based Automatic SVM Model Selection","authors":"Yingqin Zhang","doi":"10.1109/ICNC.2008.4","DOIUrl":"https://doi.org/10.1109/ICNC.2008.4","url":null,"abstract":"SVM performance is very sensitive to the parameter set. In this paper we propose an automatic and effective model selection method. It is based on evolutionary computation algorithms and use recall, precision and error rate estimated by xialpha-estimate as the optimization targets. Optimized by genetic algorithm (GA) or particle swarm optimization (PSO) algorithm, we demonstrate that SVM could automatically select its multiple parameters and optimize them. Experiments results also verify that by optimizing the bounds estimated by xialpha-estimate we could also improve the practical performance.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75075513","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}
In this paper, the Pennes bio-heat transfer equation was simplified in the condition of steady state. Boundary element method was used as the forward solver. It was incorporated with two popular regularization methods for inverse problem. Three well-known methods for selecting regularization parameter were tested, and two experiments were implemented. The first experiment was carried out on a cubic polypropylene whose six faces were free to air, and the second experiment on a cubic polypropylene whose temperature of one face was constant. The inner heat sources and temperature field of the polypropylene in these two experiments were successfully reconstructed.
{"title":"Noninvasive Reconstruction of Temperature Field by Boundary Element Method","authors":"Jinhua Wen, Kaiyang Li, Zhangshen Yu, Daiqiang Yin","doi":"10.1109/ICNC.2008.151","DOIUrl":"https://doi.org/10.1109/ICNC.2008.151","url":null,"abstract":"In this paper, the Pennes bio-heat transfer equation was simplified in the condition of steady state. Boundary element method was used as the forward solver. It was incorporated with two popular regularization methods for inverse problem. Three well-known methods for selecting regularization parameter were tested, and two experiments were implemented. The first experiment was carried out on a cubic polypropylene whose six faces were free to air, and the second experiment on a cubic polypropylene whose temperature of one face was constant. The inner heat sources and temperature field of the polypropylene in these two experiments were successfully reconstructed.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75163597","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 analyses the chaotic characteristics of a large temper rolling millpsilas abnormal vibration signals, and studies phase space reconstruction techniques of the signals. Then, combining the theory of chaotic dynamics and wavelet neural networks, a new vibration model is set up, through inversion method. The property of the model is tested and compared with the model of backpropagation(BP) neural networks, respectively. The result shows that the wavelet neural networks have an advantage over the backpropagation neural networks in rapid convergence and high accuracy.
{"title":"Intelligent Modeling of Abnormal Vibration for Large-Complex Machine Based on Chaos and Wavelet Neural Networks","authors":"Zhonghui Luo","doi":"10.1109/ICNC.2008.715","DOIUrl":"https://doi.org/10.1109/ICNC.2008.715","url":null,"abstract":"This paper analyses the chaotic characteristics of a large temper rolling millpsilas abnormal vibration signals, and studies phase space reconstruction techniques of the signals. Then, combining the theory of chaotic dynamics and wavelet neural networks, a new vibration model is set up, through inversion method. The property of the model is tested and compared with the model of backpropagation(BP) neural networks, respectively. The result shows that the wavelet neural networks have an advantage over the backpropagation neural networks in rapid convergence and high accuracy.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75172088","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}
Harmonic mean is widely used to aggregate central tendency data, which is usually expressed in exact numerical values. In this paper, we investigate the situations where the input data are given in the form of linguistic labels, and develop some linguistic harmonic mean aggregation operators, such as the linguistic weighted harmonic mean (LWHM) operator, the linguistic ordered weighted harmonic mean (LOWHM) operator, and the linguistic hybrid harmonic mean (LHHM) operator for aggregating linguistic information. Some examples are given to illustrate the developed operators.
{"title":"Harmonic Mean Operators for Aggregating Linguistic Information","authors":"Zeshui Xu","doi":"10.1109/ICNC.2008.887","DOIUrl":"https://doi.org/10.1109/ICNC.2008.887","url":null,"abstract":"Harmonic mean is widely used to aggregate central tendency data, which is usually expressed in exact numerical values. In this paper, we investigate the situations where the input data are given in the form of linguistic labels, and develop some linguistic harmonic mean aggregation operators, such as the linguistic weighted harmonic mean (LWHM) operator, the linguistic ordered weighted harmonic mean (LOWHM) operator, and the linguistic hybrid harmonic mean (LHHM) operator for aggregating linguistic information. Some examples are given to illustrate the developed operators.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75460831","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}
In this paper, a neural networks model is established. The existence of non-zero solution pairs for its steady state equation and the local asymptotically stability of non-zero solutions are studied by using the critical point theory, Lusternik-Schnirelmann category theory, and the linearization technology. The similar method can be also used for the more general neural networks and the coupled map lattice system.
{"title":"Existence and Stability of Non-zero Steady State Solutions for Discrete Neutral Networks","authors":"Guang Zhang, Yunling Luo, Liang Bai","doi":"10.1109/ICNC.2008.24","DOIUrl":"https://doi.org/10.1109/ICNC.2008.24","url":null,"abstract":"In this paper, a neural networks model is established. The existence of non-zero solution pairs for its steady state equation and the local asymptotically stability of non-zero solutions are studied by using the critical point theory, Lusternik-Schnirelmann category theory, and the linearization technology. The similar method can be also used for the more general neural networks and the coupled map lattice system.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77849291","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 to develop a hybrid PCA-RBFNN model for financial distress prediction of Chinese listed corporate. The proposed hybrid model integrates the principle component analysis (PCA) method and the radial-basis function neural network (RBFNN). Besides the traditional finance indicators, we introduce the cash-flow indicators which perfectly reflect the real-time financial situation of a corporate. In our proposed model, the PCA method is employed to select indicators and to reduce dimensions, and the RBFNN is used as a predicting tool for corporate financial situation. The experimental results suggest that the model has high prediction accuracy and execution efficiency.
{"title":"Predicting Financial Distress of Chinese Listed Corporate by a Hybrid PCA-RBFNN Model","authors":"Ying Sai, Shiwei Zhu, Zhang Tao","doi":"10.1109/ICNC.2008.778","DOIUrl":"https://doi.org/10.1109/ICNC.2008.778","url":null,"abstract":"This paper is to develop a hybrid PCA-RBFNN model for financial distress prediction of Chinese listed corporate. The proposed hybrid model integrates the principle component analysis (PCA) method and the radial-basis function neural network (RBFNN). Besides the traditional finance indicators, we introduce the cash-flow indicators which perfectly reflect the real-time financial situation of a corporate. In our proposed model, the PCA method is employed to select indicators and to reduce dimensions, and the RBFNN is used as a predicting tool for corporate financial situation. The experimental results suggest that the model has high prediction accuracy and execution efficiency.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78287491","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}
PID control schemes have been widely used in most of control system for a long time. However, it is still a very important problem how to determine or tune the PID parameters, because these parameters have a great influence on the stability and the performance of the control system. On the other hand, in the last ten years, quantum computing is attracted as one method which gives us suitable answers for optimization problems. This paper proposes a novel quantum swarm evolution algorithm, called a quantum-inspired swarm evolution algorithm (QSEA), which is based on the concept and principles of quantum computing. The proposed algorithm adopts quantum angle to express Q-bit and improved particle swarm optimization to update automatically. After the quantum-inspired swarm evolution algorithm is described, the experiment result on the parameters of PID controller is given to show its efficiency.
{"title":"Self-Tuning PID Controller Based on Quantum Swarm Evolution Algorithm","authors":"Yourui Huang, Liguo Qu, Yiming Tian","doi":"10.1109/ICNC.2008.458","DOIUrl":"https://doi.org/10.1109/ICNC.2008.458","url":null,"abstract":"PID control schemes have been widely used in most of control system for a long time. However, it is still a very important problem how to determine or tune the PID parameters, because these parameters have a great influence on the stability and the performance of the control system. On the other hand, in the last ten years, quantum computing is attracted as one method which gives us suitable answers for optimization problems. This paper proposes a novel quantum swarm evolution algorithm, called a quantum-inspired swarm evolution algorithm (QSEA), which is based on the concept and principles of quantum computing. The proposed algorithm adopts quantum angle to express Q-bit and improved particle swarm optimization to update automatically. After the quantum-inspired swarm evolution algorithm is described, the experiment result on the parameters of PID controller is given to show its efficiency.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78448961","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}
Automatic path-oriented test data generation is an undecidable problem and genetic algorithm (GA) has been used to test data generation since 1992. In favor of MATLAB, a multi-population genetic algorithm (MPGA) was implemented, which selects individuals for free migration based on their fitness values. Applying MPGA to generating path-oriented test data generation is a new and meaningful attempt. After depicting how to transform path-oriented test data generation into an optimization problem, basic process flow of path-oriented test data generation using GA was presented. Using a triangle classifier as program under test, experimental results show that MPGA based approach can generate path-oriented test data more effectively and efficiently than simple GA based approach does.
{"title":"Automatic Path-Oriented Test Data Generation Using a Multi-population Genetic Algorithm","authors":"Yong Chen, Yong Zhong","doi":"10.1109/ICNC.2008.388","DOIUrl":"https://doi.org/10.1109/ICNC.2008.388","url":null,"abstract":"Automatic path-oriented test data generation is an undecidable problem and genetic algorithm (GA) has been used to test data generation since 1992. In favor of MATLAB, a multi-population genetic algorithm (MPGA) was implemented, which selects individuals for free migration based on their fitness values. Applying MPGA to generating path-oriented test data generation is a new and meaningful attempt. After depicting how to transform path-oriented test data generation into an optimization problem, basic process flow of path-oriented test data generation using GA was presented. Using a triangle classifier as program under test, experimental results show that MPGA based approach can generate path-oriented test data more effectively and efficiently than simple GA based approach does.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74913826","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}
The analyzing quantitative kinetics gait data is very important in medical diagnostics as well as in early identification of gait asymmetry. The paper investigated the application of kernel-based technique in kinetic gait data with nonlinear property for gait feature extraction and classification. Its basic idea was that Kernel principal component analysis (KPCA) algorithm was employed to extract gait feature for initiating the training set of support vector machines (SVM) via pre-processing, which SVM with better generalization performance recognized gait patterns. Kinetics gait data of 24 young and 24 elderly participants were analyzed, and the receiver operating characteristic (ROC) plots were adopted to evaluate the generalization performance of gait classifier. The result showed that the proposed approach could map the participantpsilas kinetics gait data structure into a linearly separable space with higher dimension, recognizing gait patterns with 90% accuracy, and has considerable potential for future clinical applications.
{"title":"Kernel-Based Feature Extraction for Automated Gait Classification Using Kinetics Data","authors":"Jianning Wu","doi":"10.1109/ICNC.2008.200","DOIUrl":"https://doi.org/10.1109/ICNC.2008.200","url":null,"abstract":"The analyzing quantitative kinetics gait data is very important in medical diagnostics as well as in early identification of gait asymmetry. The paper investigated the application of kernel-based technique in kinetic gait data with nonlinear property for gait feature extraction and classification. Its basic idea was that Kernel principal component analysis (KPCA) algorithm was employed to extract gait feature for initiating the training set of support vector machines (SVM) via pre-processing, which SVM with better generalization performance recognized gait patterns. Kinetics gait data of 24 young and 24 elderly participants were analyzed, and the receiver operating characteristic (ROC) plots were adopted to evaluate the generalization performance of gait classifier. The result showed that the proposed approach could map the participantpsilas kinetics gait data structure into a linearly separable space with higher dimension, recognizing gait patterns with 90% accuracy, and has considerable potential for future clinical applications.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75152250","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}
The cutting stock problem (CSP) with multiple stock lengths is the NP-hard combinatorial optimization problem. In recent years, the CSP is researched by applying evolutionary approaches which includes genetic algorithm, evolutionary programming, et al. In the paper, an ant colony optimization (ACO) algorithm for one-dimensional cutting stock problems with multiple stock lengths (MCSP) is presented, and mutation operation is imported into the ACO in order to avoid the phenomenon of precocity and stagnation emerging. Based on the analysis of the algorithm, the ACO for MCSP has the same time complexity as CSP. Through experiments study, the outcome shows that, compared with other algorithm, the algorithm takes a great improvement in the convergent speed and result optimization.
{"title":"An Ant Colony Optimization Algorithm for the One-Dimensional Cutting Stock Problem with Multiple Stock Lengths","authors":"Q. Lu, Zhiguang Wang, Ming Chen","doi":"10.1109/ICNC.2008.208","DOIUrl":"https://doi.org/10.1109/ICNC.2008.208","url":null,"abstract":"The cutting stock problem (CSP) with multiple stock lengths is the NP-hard combinatorial optimization problem. In recent years, the CSP is researched by applying evolutionary approaches which includes genetic algorithm, evolutionary programming, et al. In the paper, an ant colony optimization (ACO) algorithm for one-dimensional cutting stock problems with multiple stock lengths (MCSP) is presented, and mutation operation is imported into the ACO in order to avoid the phenomenon of precocity and stagnation emerging. Based on the analysis of the algorithm, the ACO for MCSP has the same time complexity as CSP. Through experiments study, the outcome shows that, compared with other algorithm, the algorithm takes a great improvement in the convergent speed and result optimization.","PeriodicalId":6404,"journal":{"name":"2008 Fourth International Conference on Natural Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75211272","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：