In order to protect pipeline transportation and prevent from leakage incident for manmade damage or natural factors, it is very important to carry out such researches as active protecting and accurate positioning. Designed the pipeline prevention monitoring and leak detecting system based on calculating LPCC (linear prediction cepstrum coefficient) and using HMM (hidden Markov models) to recognise damage acoustic signals. The continuous non-steady time-variety process was sub-framed and described with a series of short steady sequences on the basis of acoustic signal characteristic analysed. LPCC which represents accurately each short-time acoustic signal was selected as the acoustic signal characteristic parameters and extracted effectively using Durbin algorithm; HMM was established to recognise damage types by Baum-Welch revaluation algorithm with the state-transfer probability and observing time sequences characteristic parameters; using Viterbi decoding algorithm realized the search of best transfer route and achieved the corresponding export probability. The results show that the acoustic singles recognition rate is improved effectively based on sound spectrum LPCC and HMM,and can be up to 97%
{"title":"Pipeline Damage and Leak Detection Based on Sound Spectrum LPCC and HMM","authors":"C. Ai, Honghua Zhao, R. Ma, Xueren Dong","doi":"10.1109/ISDA.2006.215","DOIUrl":"https://doi.org/10.1109/ISDA.2006.215","url":null,"abstract":"In order to protect pipeline transportation and prevent from leakage incident for manmade damage or natural factors, it is very important to carry out such researches as active protecting and accurate positioning. Designed the pipeline prevention monitoring and leak detecting system based on calculating LPCC (linear prediction cepstrum coefficient) and using HMM (hidden Markov models) to recognise damage acoustic signals. The continuous non-steady time-variety process was sub-framed and described with a series of short steady sequences on the basis of acoustic signal characteristic analysed. LPCC which represents accurately each short-time acoustic signal was selected as the acoustic signal characteristic parameters and extracted effectively using Durbin algorithm; HMM was established to recognise damage types by Baum-Welch revaluation algorithm with the state-transfer probability and observing time sequences characteristic parameters; using Viterbi decoding algorithm realized the search of best transfer route and achieved the corresponding export probability. The results show that the acoustic singles recognition rate is improved effectively based on sound spectrum LPCC and HMM,and can be up to 97%","PeriodicalId":116729,"journal":{"name":"Sixth International Conference on Intelligent Systems Design and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130192129","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 : 2006-10-16DOI: 10.1109/ISDA.2006.253882
Shulin Wang, Ji Wang, Huowang Chen, Wensheng Tang
Gene expression data that is being used to gather information from tissue samples is expected to significantly improve the development of efficient tumor diagnosis and to provide understanding and insight into tumor related cellular processes. In this paper, we propose a novel feature selection approach which integrates the feature score criterion with factor analysis to further improve the SVM-based classification performance of gene expression data. We examine two sets of published gene expression data to validate the novel feature selection method by means of SVM classifier with different parameters. Experiments show that the proposed hybrid method can select a small quantity of principal factors to represent a large number of genes and SVM has a superior classification performance with the common factors which are extracted from gene expression data. Moreover, experiment results demonstrate successful cross-validation accuracy of 92% for the colon dataset and 100% for the leukemia dataset
{"title":"The Classification of Tumor Using Gene Expression Profile Based on Support Vector Machines and Factor Analysis","authors":"Shulin Wang, Ji Wang, Huowang Chen, Wensheng Tang","doi":"10.1109/ISDA.2006.253882","DOIUrl":"https://doi.org/10.1109/ISDA.2006.253882","url":null,"abstract":"Gene expression data that is being used to gather information from tissue samples is expected to significantly improve the development of efficient tumor diagnosis and to provide understanding and insight into tumor related cellular processes. In this paper, we propose a novel feature selection approach which integrates the feature score criterion with factor analysis to further improve the SVM-based classification performance of gene expression data. We examine two sets of published gene expression data to validate the novel feature selection method by means of SVM classifier with different parameters. Experiments show that the proposed hybrid method can select a small quantity of principal factors to represent a large number of genes and SVM has a superior classification performance with the common factors which are extracted from gene expression data. Moreover, experiment results demonstrate successful cross-validation accuracy of 92% for the colon dataset and 100% for the leukemia dataset","PeriodicalId":116729,"journal":{"name":"Sixth International Conference on Intelligent Systems Design and Applications","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130268589","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 : 2006-10-16DOI: 10.1109/ISDA.2006.253720
Shuping Yao, Chang-zhen Hu
To improve the predication accuracy for server load, a novel predication method was proposed based on the integration of wavelet analysis and support vector regression. The server load time series, which is nonlinear and non-stationary, was decomposed and then, reconstructed into several branches by the wavelet method. Of these branches, the lowest scale high frequency signal was forecasted by moving average model, the others were predicted by support vector regression respectively and the final value was the combination of these predicted results. Theoretical analysis and experiment results show that wavelet analysis can decompose the original load series into several time series that have simpler frequency components and are easier to be forecasted; support vector regression has greater generation ability and guarantees global minima for given training data, it performs well for non-stationary time series prediction. So the method has higher predictive precision than traditional prediction approaches
{"title":"Prediction of Server Load Based on Wavelet-Support Vector Regression-Moving Average","authors":"Shuping Yao, Chang-zhen Hu","doi":"10.1109/ISDA.2006.253720","DOIUrl":"https://doi.org/10.1109/ISDA.2006.253720","url":null,"abstract":"To improve the predication accuracy for server load, a novel predication method was proposed based on the integration of wavelet analysis and support vector regression. The server load time series, which is nonlinear and non-stationary, was decomposed and then, reconstructed into several branches by the wavelet method. Of these branches, the lowest scale high frequency signal was forecasted by moving average model, the others were predicted by support vector regression respectively and the final value was the combination of these predicted results. Theoretical analysis and experiment results show that wavelet analysis can decompose the original load series into several time series that have simpler frequency components and are easier to be forecasted; support vector regression has greater generation ability and guarantees global minima for given training data, it performs well for non-stationary time series prediction. So the method has higher predictive precision than traditional prediction approaches","PeriodicalId":116729,"journal":{"name":"Sixth International Conference on Intelligent Systems Design and Applications","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131582566","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}
T. Srinivasan, S. Shivashankar, V. Archana, B. Rakesh
In this paper, we present a novel adaptively automated fingerprint classification scheme, which is computationally efficient and resolves both intra-class diversities and inter-class similarities. Initially, preprocessing of fingerprint images is carried out to enhance the image. For classification based on global shape, directional image is computed. Principal component analysis is employed in first stage for dimensionality reduction and to get feature space that accounts for as much of the total variation as possible. In second stage, self-organizing maps are involved for further dimension reduction and data clustering. We use the Kohonen topological map for pattern classification. The learning process takes into account the large intra class diversity and the continuum of fingerprint pattern types. Finally LVQ2 maps the class separated fingerprint images into their respective class, the winner and runner-up neuron are trained in such a way that they take into account the inter-class similarities. Experimental results show that AAFFC achieves an accuracy of around 89 % for five-class classification tested on NIST 4 without rejection
{"title":"AAFFC: An Adaptively Automated Five-Class Fingerprint Classification Scheme Using Kohonens Feature Map","authors":"T. Srinivasan, S. Shivashankar, V. Archana, B. Rakesh","doi":"10.1109/ISDA.2006.82","DOIUrl":"https://doi.org/10.1109/ISDA.2006.82","url":null,"abstract":"In this paper, we present a novel adaptively automated fingerprint classification scheme, which is computationally efficient and resolves both intra-class diversities and inter-class similarities. Initially, preprocessing of fingerprint images is carried out to enhance the image. For classification based on global shape, directional image is computed. Principal component analysis is employed in first stage for dimensionality reduction and to get feature space that accounts for as much of the total variation as possible. In second stage, self-organizing maps are involved for further dimension reduction and data clustering. We use the Kohonen topological map for pattern classification. The learning process takes into account the large intra class diversity and the continuum of fingerprint pattern types. Finally LVQ2 maps the class separated fingerprint images into their respective class, the winner and runner-up neuron are trained in such a way that they take into account the inter-class similarities. Experimental results show that AAFFC achieves an accuracy of around 89 % for five-class classification tested on NIST 4 without rejection","PeriodicalId":116729,"journal":{"name":"Sixth International Conference on Intelligent Systems Design and Applications","volume":"33 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131730323","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 use of monolithic neural networks (such as a multilayer perceptron) has some drawbacks: e.g. slow learning, weight coupling, the black box effect. These can be alleviated by the use of a modular neural network. The creation of a MNN has three steps: task decomposition, module creation and decision integration. In this paper we propose the use of an entropic clustering algorithm as a way of performing task decomposition. We present experiments on several real world classification problems that show the performance of this approach
{"title":"Modular Neural Network Task Decomposition Via Entropic Clustering","authors":"Jorge M. Santos, Luís A. Alexandre, J. M. D. Sá","doi":"10.1109/ISDA.2006.198","DOIUrl":"https://doi.org/10.1109/ISDA.2006.198","url":null,"abstract":"The use of monolithic neural networks (such as a multilayer perceptron) has some drawbacks: e.g. slow learning, weight coupling, the black box effect. These can be alleviated by the use of a modular neural network. The creation of a MNN has three steps: task decomposition, module creation and decision integration. In this paper we propose the use of an entropic clustering algorithm as a way of performing task decomposition. We present experiments on several real world classification problems that show the performance of this approach","PeriodicalId":116729,"journal":{"name":"Sixth International Conference on Intelligent Systems Design and Applications","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132615137","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 : 2006-10-16DOI: 10.1109/ISDA.2006.253822
X. Ruan, Shao-bai Zhang, Xin-yuan Li
The cerebellum has long been thought to play a crucial role in the forming of graceful movements, and it is viewed as a set of modules, each of which can be added to a control system to improve smooth coordinated movement, with improvements continuing and improving over time. The present paper combines the microcomplex view of the cerebellum's role in motor control with a modification of the Marr-Albus view of cerebellar plasticity to exemplify this by a model of the role of cerebellum in adaptation to the effects of wearing prism glasses on throwing at a target
{"title":"A model of the role of cerebellum in adaptation to the effects of wearing prism glasses on throwing at a target","authors":"X. Ruan, Shao-bai Zhang, Xin-yuan Li","doi":"10.1109/ISDA.2006.253822","DOIUrl":"https://doi.org/10.1109/ISDA.2006.253822","url":null,"abstract":"The cerebellum has long been thought to play a crucial role in the forming of graceful movements, and it is viewed as a set of modules, each of which can be added to a control system to improve smooth coordinated movement, with improvements continuing and improving over time. The present paper combines the microcomplex view of the cerebellum's role in motor control with a modification of the Marr-Albus view of cerebellar plasticity to exemplify this by a model of the role of cerebellum in adaptation to the effects of wearing prism glasses on throwing at a target","PeriodicalId":116729,"journal":{"name":"Sixth International Conference on Intelligent Systems Design and Applications","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131049876","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}
A turbocharged diesel engine dominated integrated starter generator (ISG) hybrid electric vehicle (HEV) is proposed. In order to achieve good fuel economy and low emissions performance, a cost function which is the function of fuel economy and emissions is defined and the optimal operation line (OOL) of engine is determined through selecting the minimal value of the cost function. The baseline based fuzzy logic control strategy (BL-FLC) presented here can optimize both the fuel economy and emissions by making this compress-ignition direct-injection (CIDI) engine work at or near its OOL all the time. Also, a baseline control strategy is presented with simulation results. Compared with baseline control strategy, the BL-FLC presented in this paper can obtain 11.7% decrease in fuel consumption on the given drive cycle without sacrificing dynamic performance
{"title":"Fuzzy Logic Based Control for ISG Hybrid Electric Vehicle","authors":"Guoqiang Ao, H. Zhong, L. Yang, J. Qiang, B. Zhuo","doi":"10.1109/ISDA.2006.156","DOIUrl":"https://doi.org/10.1109/ISDA.2006.156","url":null,"abstract":"A turbocharged diesel engine dominated integrated starter generator (ISG) hybrid electric vehicle (HEV) is proposed. In order to achieve good fuel economy and low emissions performance, a cost function which is the function of fuel economy and emissions is defined and the optimal operation line (OOL) of engine is determined through selecting the minimal value of the cost function. The baseline based fuzzy logic control strategy (BL-FLC) presented here can optimize both the fuel economy and emissions by making this compress-ignition direct-injection (CIDI) engine work at or near its OOL all the time. Also, a baseline control strategy is presented with simulation results. Compared with baseline control strategy, the BL-FLC presented in this paper can obtain 11.7% decrease in fuel consumption on the given drive cycle without sacrificing dynamic performance","PeriodicalId":116729,"journal":{"name":"Sixth International Conference on Intelligent Systems Design and Applications","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130739102","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 : 2006-10-16DOI: 10.1109/ISDA.2006.253864
Ruiguo Yu, Pilian He, Xinrong Zhang, Gaofeng Bai
Authentication watermarking is a hidden data inserted into an image, in order to detect alterations. This paper introduces a technique of fragile halftone watermark towards static images which is not good enough in the aspect of visual effect. Aiming at this, this paper brings out two ways to improve: evaluate all of the reversible pixels in the image using the characteristic of human's eyes; in the conversing process from color image or gray scale image to binary image, generate more reversible pixels by using HVS model. Some experiments are brought out, and the result shows that, after adding watermark, the visual effect of the image is improved effectively, and the shortages of the original method are conquered
{"title":"An Improved Fragile Halftone Watermark Method","authors":"Ruiguo Yu, Pilian He, Xinrong Zhang, Gaofeng Bai","doi":"10.1109/ISDA.2006.253864","DOIUrl":"https://doi.org/10.1109/ISDA.2006.253864","url":null,"abstract":"Authentication watermarking is a hidden data inserted into an image, in order to detect alterations. This paper introduces a technique of fragile halftone watermark towards static images which is not good enough in the aspect of visual effect. Aiming at this, this paper brings out two ways to improve: evaluate all of the reversible pixels in the image using the characteristic of human's eyes; in the conversing process from color image or gray scale image to binary image, generate more reversible pixels by using HVS model. Some experiments are brought out, and the result shows that, after adding watermark, the visual effect of the image is improved effectively, and the shortages of the original method are conquered","PeriodicalId":116729,"journal":{"name":"Sixth International Conference on Intelligent Systems Design and Applications","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130978753","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}
Air fuel ratio is a key index affecting power performance and fuel economy and exhaust emissions of the gasoline engine, whose accurate model is the foundation of accuracy air fuel ratio control. Taking HL495 engine as experimental device, a method of indenting air fuel ratio based on Elman neural network was provided in this paper. Experiment results show the air fuel ratio model based on Elman neural network has simple structure and can accurately approximate the air fuel ratio transient process and average relative error is less than 1 %. The air fuel ratio based on Elman neural network is better than the air fuel ratio model based on BP neural network
{"title":"Air Fuel Ratio Identification of Gasoline Engine during Transient Conditions Based on Elman Neural Networks","authors":"Z. Hou, Quntai Sen, Yihu Wu","doi":"10.1109/ISDA.2006.86","DOIUrl":"https://doi.org/10.1109/ISDA.2006.86","url":null,"abstract":"Air fuel ratio is a key index affecting power performance and fuel economy and exhaust emissions of the gasoline engine, whose accurate model is the foundation of accuracy air fuel ratio control. Taking HL495 engine as experimental device, a method of indenting air fuel ratio based on Elman neural network was provided in this paper. Experiment results show the air fuel ratio model based on Elman neural network has simple structure and can accurately approximate the air fuel ratio transient process and average relative error is less than 1 %. The air fuel ratio based on Elman neural network is better than the air fuel ratio model based on BP neural network","PeriodicalId":116729,"journal":{"name":"Sixth International Conference on Intelligent Systems Design and Applications","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132784788","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}
Using the theory that the coupling ratio of fiber coupler changes periodically with center distance of two optical fibers, in the fabrication process of fiber coupler, the fiber is fused but not stretched when light begin to split. The reduction of diameter of fiber is dependent of the theological characteristic of the fused fiberglass, and the light continues to split. A new manufacturing method of optical fiber couplers is developed with fused biconical taper experimental system. The tested results show that the performance of the novel optical fiber coupler complies with the performance indexes of fused biconical taper coupler, and its diameter of coupling region is double of classical fused biconical taper coupler.
{"title":"Development of a Novel Optical Fiber Coupler","authors":"Shuai Ci-jun, Duan Ji-an, Zhong Jue","doi":"10.1109/ISDA.2006.22","DOIUrl":"https://doi.org/10.1109/ISDA.2006.22","url":null,"abstract":"Using the theory that the coupling ratio of fiber coupler changes periodically with center distance of two optical fibers, in the fabrication process of fiber coupler, the fiber is fused but not stretched when light begin to split. The reduction of diameter of fiber is dependent of the theological characteristic of the fused fiberglass, and the light continues to split. A new manufacturing method of optical fiber couplers is developed with fused biconical taper experimental system. The tested results show that the performance of the novel optical fiber coupler complies with the performance indexes of fused biconical taper coupler, and its diameter of coupling region is double of classical fused biconical taper coupler.","PeriodicalId":116729,"journal":{"name":"Sixth International Conference on Intelligent Systems Design and Applications","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132861149","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：