Pub Date : 2005-12-15DOI: 10.1109/CIMA.2005.1662323
R. Lahouari, B. Abdelkader, M. Larbi
The recent evolution of radar and sonar is obvious, as that of most of the technical domains, by the extremely fast development of the information processing capacities. To answer for increasing necessities of the users, this evolution led to endow the radar and the sonar of several modes of functioning. In this article, two classical methods of data processing are suggested in detection of radar target domain. The first technique is based on hidden Markov model "HMM", so for the second is based on the neuron network approach "ANN", which inspired originally from intellectual functioning of the human being
{"title":"Application of hidden Markov model and neural network approach for radar target detection","authors":"R. Lahouari, B. Abdelkader, M. Larbi","doi":"10.1109/CIMA.2005.1662323","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662323","url":null,"abstract":"The recent evolution of radar and sonar is obvious, as that of most of the technical domains, by the extremely fast development of the information processing capacities. To answer for increasing necessities of the users, this evolution led to endow the radar and the sonar of several modes of functioning. In this article, two classical methods of data processing are suggested in detection of radar target domain. The first technique is based on hidden Markov model \"HMM\", so for the second is based on the neuron network approach \"ANN\", which inspired originally from intellectual functioning of the human being","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127695876","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 : 2005-12-15DOI: 10.1109/CIMA.2005.1662344
G. Yigitler, O. Ersoy, T. Ibrekei
This paper presents a new approach to the development of multispectral/hyperspectral image enhancement and fusion algorithms. In approaches used up to now for image enhancement, the bands are typically processed separately, and this results in considerable distortion. The amount of information in many bands are also not very efficiently used. The objective of this work is to utilize the amount of information available more effectively, remove such distortions and to improve the appearance of the images. To realize this goal, we developed two new algorithms using transform techniques. In the resulting algorithms developed, image enhancement and image fusion are considered together
{"title":"New transform techniques for enhancement and fusion of multispectral and hyperspectral images","authors":"G. Yigitler, O. Ersoy, T. Ibrekei","doi":"10.1109/CIMA.2005.1662344","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662344","url":null,"abstract":"This paper presents a new approach to the development of multispectral/hyperspectral image enhancement and fusion algorithms. In approaches used up to now for image enhancement, the bands are typically processed separately, and this results in considerable distortion. The amount of information in many bands are also not very efficiently used. The objective of this work is to utilize the amount of information available more effectively, remove such distortions and to improve the appearance of the images. To realize this goal, we developed two new algorithms using transform techniques. In the resulting algorithms developed, image enhancement and image fusion are considered together","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122028668","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 : 2005-12-15DOI: 10.1109/CIMA.2005.1662334
K. Revett, J. Kola
This paper presents a computational model of ischemic stroke that focuses on the role of apoptosis as a mediator of delayed tissue. There is strong evidence that apoptosis (programmed cell death) occurs subsequent to ischemia, but its role as a mediator of delayed cell death has not been examined quantitatively. In this computational study, evidence is presented suggesting that apoptosis can cause tissue damage in a delayed fashion, with a temporal profile similar to that reported in cases of progressive stroke. The results from this study indicate that tissue damage is bi-phasic. In the acute phase (1-3 hours post-ictus), damage in the ischemic focus occurs as a result of severe metabolic insufficiency (necrosis). After a substantial time delay, a second form of cell death becomes apparent - mediated by apoptosis. The combination of necrosis and apoptosis accounts for the final infarct volume occurring in this model of ischemic stroke
{"title":"Apoptosis as a mediator of delayed tissue damage in progressive stroke: a computational study","authors":"K. Revett, J. Kola","doi":"10.1109/CIMA.2005.1662334","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662334","url":null,"abstract":"This paper presents a computational model of ischemic stroke that focuses on the role of apoptosis as a mediator of delayed tissue. There is strong evidence that apoptosis (programmed cell death) occurs subsequent to ischemia, but its role as a mediator of delayed cell death has not been examined quantitatively. In this computational study, evidence is presented suggesting that apoptosis can cause tissue damage in a delayed fashion, with a temporal profile similar to that reported in cases of progressive stroke. The results from this study indicate that tissue damage is bi-phasic. In the acute phase (1-3 hours post-ictus), damage in the ischemic focus occurs as a result of severe metabolic insufficiency (necrosis). After a substantial time delay, a second form of cell death becomes apparent - mediated by apoptosis. The combination of necrosis and apoptosis accounts for the final infarct volume occurring in this model of ischemic stroke","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127537435","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 : 2005-12-15DOI: 10.1109/CIMA.2005.1662359
M. Amasyali, O. Ersoy
Decision trees are often used in pattern recognition and regression problems. They are attractive due to high performance and easy-to-understand rules. Many different decision tree construction algorithms have been developed because of their popularity. In this work, we describe some new heuristic tree construction algorithms and test with 8 benchmark datasets. We compare the new method with other 21 tree induction algorithms. The results show that cline heuristics can be used in all types of classification problems because of its simplicity and acceptable performance
{"title":"Cline: new multivariate decision tree construction heuristics","authors":"M. Amasyali, O. Ersoy","doi":"10.1109/CIMA.2005.1662359","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662359","url":null,"abstract":"Decision trees are often used in pattern recognition and regression problems. They are attractive due to high performance and easy-to-understand rules. Many different decision tree construction algorithms have been developed because of their popularity. In this work, we describe some new heuristic tree construction algorithms and test with 8 benchmark datasets. We compare the new method with other 21 tree induction algorithms. The results show that cline heuristics can be used in all types of classification problems because of its simplicity and acceptable performance","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121119961","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 : 2005-12-15DOI: 10.1109/CIMA.2005.1662346
T.S. Liu, W. Chang
Dealing with voice coil motors, this paper presents reinforcement learning based fuzzy control, which incorporates characteristics of reinforcement learning into fuzzy control. Fuzzy control has excellent characteristics of dealing with model uncertainty and nonlinearity. To complement and improve fuzzy control, reinforcement learning is used to process rough feedback signals. This work constructs fuzzy rules based model based on input-output data of plants and tune fuzzy membership functions by reinforcement learning
{"title":"Fuzzy control based on reinforcement learning for voice coil motor","authors":"T.S. Liu, W. Chang","doi":"10.1109/CIMA.2005.1662346","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662346","url":null,"abstract":"Dealing with voice coil motors, this paper presents reinforcement learning based fuzzy control, which incorporates characteristics of reinforcement learning into fuzzy control. Fuzzy control has excellent characteristics of dealing with model uncertainty and nonlinearity. To complement and improve fuzzy control, reinforcement learning is used to process rough feedback signals. This work constructs fuzzy rules based model based on input-output data of plants and tune fuzzy membership functions by reinforcement learning","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115732719","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 : 2005-12-15DOI: 10.1109/CIMA.2005.1662357
A. Popoola, S. Ahmad, K. Ahmad
Fuzzy systems, also referred to as universal approximators, have been used to model real-world data. In this paper, we examine the prediction performance of fuzzy subtractive-clustering models on time series with trends, seasonalities, and discontinuities. Our results indicate that wavelet preprocessing improves forecast accuracy for time series that exhibit variance changes and other complex local behavior. Conversely, for time series that exhibit no significant structural breaks or variance changes, fuzzy models trained on raw data perform better than hybrid fuzzy-wavelet models. Further work is required to investigate the use of wavelet variance profile of time series to determine the suitability of the application of wavelet-based preprocessing on prediction models
{"title":"Multiscale wavelet preprocessing for fuzzy systems","authors":"A. Popoola, S. Ahmad, K. Ahmad","doi":"10.1109/CIMA.2005.1662357","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662357","url":null,"abstract":"Fuzzy systems, also referred to as universal approximators, have been used to model real-world data. In this paper, we examine the prediction performance of fuzzy subtractive-clustering models on time series with trends, seasonalities, and discontinuities. Our results indicate that wavelet preprocessing improves forecast accuracy for time series that exhibit variance changes and other complex local behavior. Conversely, for time series that exhibit no significant structural breaks or variance changes, fuzzy models trained on raw data perform better than hybrid fuzzy-wavelet models. Further work is required to investigate the use of wavelet variance profile of time series to determine the suitability of the application of wavelet-based preprocessing on prediction models","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115763256","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 : 2005-12-15DOI: 10.1109/CIMA.2005.1662310
T. Ibrikci, A. Çakmak, I. Ersoz, O. Ersoy
Secondary structure prediction of proteins has increasingly been a central research area in bioinformatics. In this paper, support vector machines (SVM) are discussed as a method for the prediction of hemoglobin secondary structures. Different sliding window sizes and different kernels of SVM are comparatively investigated in terms of accuracy of prediction of hemoglobin secondary structure. For this purpose, the training and testing data were obtained from the Protein Data Bank, US with database of secondary structures of protein (DSSP). The results of prediction with different SVM kernels and different window sizes were found to be in the range of 5.93-15.90, 67.76-70.05 , 69.77-73.25, and 74.42-77.64 % for linear kernel, sigmoid kernel, polynomial kernel and Gaussian radial basis kernel, respectively
蛋白质二级结构预测已日益成为生物信息学研究的热点。本文讨论了支持向量机(SVM)作为血红蛋白二级结构预测的一种方法。比较研究了不同滑动窗口大小和不同核数的支持向量机对血红蛋白二级结构的预测精度。为此，训练和测试数据来自美国蛋白质数据库(Protein data Bank, US)和蛋白质二级结构数据库(DSSP)。线性核、s型核、多项式核和高斯径向基核的预测结果分别为5.93 ~ 15.90、67.76 ~ 70.05、69.77 ~ 73.25和74.42 ~ 77.64%
{"title":"Hemoglobin secondary structure predicts with four kernels on support vector machines","authors":"T. Ibrikci, A. Çakmak, I. Ersoz, O. Ersoy","doi":"10.1109/CIMA.2005.1662310","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662310","url":null,"abstract":"Secondary structure prediction of proteins has increasingly been a central research area in bioinformatics. In this paper, support vector machines (SVM) are discussed as a method for the prediction of hemoglobin secondary structures. Different sliding window sizes and different kernels of SVM are comparatively investigated in terms of accuracy of prediction of hemoglobin secondary structure. For this purpose, the training and testing data were obtained from the Protein Data Bank, US with database of secondary structures of protein (DSSP). The results of prediction with different SVM kernels and different window sizes were found to be in the range of 5.93-15.90, 67.76-70.05 , 69.77-73.25, and 74.42-77.64 % for linear kernel, sigmoid kernel, polynomial kernel and Gaussian radial basis kernel, respectively","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124066581","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 : 2005-12-15DOI: 10.1109/CIMA.2005.1662302
X.G. Wang, Y. Ding, X.-F. Zhang, S. Shao
An environment of inhabited region is composed of natural and socio-economic environment, so it should be analyzed from the factors of the two aspects. In this paper, we proposed an integrated assessment index system based on the super-entity immune network model. Considering various factors' influence and their interactions, the model achieves quantitative analysis to the environmental quality assessment in an integrated framework. It also reflects some key factors that affect the environmental quality to a certain extent. Take three inhabited regions as examples, the experimental results demonstrate the rationality and the validity of the assessment model
{"title":"A super-entity-based immune network model for environmental quality assessment of inhabited region","authors":"X.G. Wang, Y. Ding, X.-F. Zhang, S. Shao","doi":"10.1109/CIMA.2005.1662302","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662302","url":null,"abstract":"An environment of inhabited region is composed of natural and socio-economic environment, so it should be analyzed from the factors of the two aspects. In this paper, we proposed an integrated assessment index system based on the super-entity immune network model. Considering various factors' influence and their interactions, the model achieves quantitative analysis to the environmental quality assessment in an integrated framework. It also reflects some key factors that affect the environmental quality to a certain extent. Take three inhabited regions as examples, the experimental results demonstrate the rationality and the validity of the assessment model","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126591222","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 : 2005-12-15DOI: 10.1109/CIMA.2005.1662303
I. Eker, Ş. A. Akınal
Sliding mode control (SMC) method is one of the robust control methods to handle systems with model uncertainties, parameter variations and disturbances. In this study, a sliding mode control system with an integral (SMC+I) operation is adopted to control speed of an electromechanical system. The proposed sliding mode controller is chosen to ensure the stability of overall dynamics during the reaching phase and sliding phase. The stability of the system is guaranteed in the sense of the Lyapunov stability theorem. Chattering problem is overcome using a hyperbolic function. Experimental results verify that the proposed SMC+I controller can achieve favorable tracking performance and is robust with regard to parameter variations and disturbances compared with the conventional sliding mode controller and PID controller
{"title":"Sliding mode control with integral action and experimental application to an electromechanical system","authors":"I. Eker, Ş. A. Akınal","doi":"10.1109/CIMA.2005.1662303","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662303","url":null,"abstract":"Sliding mode control (SMC) method is one of the robust control methods to handle systems with model uncertainties, parameter variations and disturbances. In this study, a sliding mode control system with an integral (SMC+I) operation is adopted to control speed of an electromechanical system. The proposed sliding mode controller is chosen to ensure the stability of overall dynamics during the reaching phase and sliding phase. The stability of the system is guaranteed in the sense of the Lyapunov stability theorem. Chattering problem is overcome using a hyperbolic function. Experimental results verify that the proposed SMC+I controller can achieve favorable tracking performance and is robust with regard to parameter variations and disturbances compared with the conventional sliding mode controller and PID controller","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134034807","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 : 2005-12-15DOI: 10.1109/CIMA.2005.1662322
M. Larbi, B. Aek
We present in this paper a Bayesian classifier, based on neural probabilistic approach using radial basis function (RBF) and based on an improved version of orthogonal least square algorithm (OLS) for fast and incremental learning and automatic creation of hidden neurons. Applied to the famous case like inside a building, this classifier must assure a semantic localization, established on a realistic approach. The will wish to have a discrimination approach in the most possible case by using a generic and powerful representation of knowledge based on conditional and priori probabilities, error costs - case of decision throws etc., this classifier have been generated by neural network. Therefore in place to have a binary decision such as the hard decision like impasse, the mobile robot decides for example 90% of impasse situation
{"title":"Mobile robot recognition using Bayesian penalization with neural approach","authors":"M. Larbi, B. Aek","doi":"10.1109/CIMA.2005.1662322","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662322","url":null,"abstract":"We present in this paper a Bayesian classifier, based on neural probabilistic approach using radial basis function (RBF) and based on an improved version of orthogonal least square algorithm (OLS) for fast and incremental learning and automatic creation of hidden neurons. Applied to the famous case like inside a building, this classifier must assure a semantic localization, established on a realistic approach. The will wish to have a discrimination approach in the most possible case by using a generic and powerful representation of knowledge based on conditional and priori probabilities, error costs - case of decision throws etc., this classifier have been generated by neural network. Therefore in place to have a binary decision such as the hard decision like impasse, the mobile robot decides for example 90% of impasse situation","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"187 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132257218","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：