Julio Cesar Ramos Fernández, V. L. Morales, Omar López Ortega
This paper proposes a novel methodology for modelling nonlinear systems based on fuzzy clustering and cubic splines. The Gustafson-Kessel algorithm (G-K) is used in order to classify, in a database of input/output (I/O) measurements, the clusters with linear trends. Every three different and ordered consecutive clusters, contain a maximum and/or a minimum, which can be taken as the points of inflexion. Then, for every three clusters a cubic spline is figure out. Also, the intersection with the next cluster is smoothed with fuzzy submodels. An automation of the whole modelling process with a minimized number of rules with respect to linear submodels is then achieved, which is a clear improvement on the classical Takagi-Sugeno (T-S) models. By means of a simple example, the modelling algorithm is illustrated
{"title":"Modelling of Nonlinear Systems Based on Fuzzy Clustering and Cubic Splines","authors":"Julio Cesar Ramos Fernández, V. L. Morales, Omar López Ortega","doi":"10.1109/CERMA.2006.64","DOIUrl":"https://doi.org/10.1109/CERMA.2006.64","url":null,"abstract":"This paper proposes a novel methodology for modelling nonlinear systems based on fuzzy clustering and cubic splines. The Gustafson-Kessel algorithm (G-K) is used in order to classify, in a database of input/output (I/O) measurements, the clusters with linear trends. Every three different and ordered consecutive clusters, contain a maximum and/or a minimum, which can be taken as the points of inflexion. Then, for every three clusters a cubic spline is figure out. Also, the intersection with the next cluster is smoothed with fuzzy submodels. An automation of the whole modelling process with a minimized number of rules with respect to linear submodels is then achieved, which is a clear improvement on the classical Takagi-Sugeno (T-S) models. By means of a simple example, the modelling algorithm is illustrated","PeriodicalId":179210,"journal":{"name":"Electronics, Robotics and Automotive Mechanics Conference (CERMA'06)","volume":"38 10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133375196","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}
Some procedures carried out in the National University of Colombia physics laboratories involved in the electrical characterization of thin films are highly troublesome and comprise several inaccuracies in the measurements that expose the results to misunderstandings. The following electrical characterization system is a real-time software-controlled data acquisition environment specially designed for the measurement of voltage and current in thin films using the four-probe testing method. The system also allows the study of the thermal behavior of thin films using a heating source and provides measurements storage in a plain-text archive for further research
{"title":"Electrical Characterization of Thin Films Using Measurements of Electrical Resistivity","authors":"A.J.C. Vanegasa, German D Molina","doi":"10.1109/CERMA.2006.41","DOIUrl":"https://doi.org/10.1109/CERMA.2006.41","url":null,"abstract":"Some procedures carried out in the National University of Colombia physics laboratories involved in the electrical characterization of thin films are highly troublesome and comprise several inaccuracies in the measurements that expose the results to misunderstandings. The following electrical characterization system is a real-time software-controlled data acquisition environment specially designed for the measurement of voltage and current in thin films using the four-probe testing method. The system also allows the study of the thermal behavior of thin films using a heating source and provides measurements storage in a plain-text archive for further research","PeriodicalId":179210,"journal":{"name":"Electronics, Robotics and Automotive Mechanics Conference (CERMA'06)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129570163","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 new algorithm of two stage vector quantization for joint source-channel speech coding for any transmission channels is presented. The computational complexity is only slightly higher than the most widely used multi stage vector quantization algorithm (MSVQ). This new algorithm improves the characteristics and the results of a sequential quantizer of two stages. The base of this algorithm is the modification of the well-known GS-RGSKAepsiv algorithm (reduced complexity generalized stochastic K-means algorithm of great speed) for a non-stationary channel. This new algorithm is optimal for the joint construction of two stages. The main features of the proposed algorithm are as follows: 1) Due to its stochastic nature it avoids being trapped in poor local minimums. 2) Initial codebooks are not needed; the codevectors move away from the gravity center of the training vectors towards their final position. 3) Source coding and channel coding are jointly optimized to obtain robust codebooks for different levels of noise in transmission channels. 4) The reduction of calculation time is based on geometric considerations and memory management. This algorithm allows to design the codebook orderly due to its advantageous convergence properties. The results showed that the algorithm needs only 8 to 16% of the number of mathematical operations in comparison with the operations required by others propositions for full search of MSQV, either stationary or non-stationary channels
{"title":"New Fast and Robust Stochastic Algorithm of Two Stage Vector Quantization for Joint Source-Channel Speech Coding for Any Transmission Channel","authors":"V. Garcia, A. Ramirez","doi":"10.1109/CERMA.2006.117","DOIUrl":"https://doi.org/10.1109/CERMA.2006.117","url":null,"abstract":"A new algorithm of two stage vector quantization for joint source-channel speech coding for any transmission channels is presented. The computational complexity is only slightly higher than the most widely used multi stage vector quantization algorithm (MSVQ). This new algorithm improves the characteristics and the results of a sequential quantizer of two stages. The base of this algorithm is the modification of the well-known GS-RGSKAepsiv algorithm (reduced complexity generalized stochastic K-means algorithm of great speed) for a non-stationary channel. This new algorithm is optimal for the joint construction of two stages. The main features of the proposed algorithm are as follows: 1) Due to its stochastic nature it avoids being trapped in poor local minimums. 2) Initial codebooks are not needed; the codevectors move away from the gravity center of the training vectors towards their final position. 3) Source coding and channel coding are jointly optimized to obtain robust codebooks for different levels of noise in transmission channels. 4) The reduction of calculation time is based on geometric considerations and memory management. This algorithm allows to design the codebook orderly due to its advantageous convergence properties. The results showed that the algorithm needs only 8 to 16% of the number of mathematical operations in comparison with the operations required by others propositions for full search of MSQV, either stationary or non-stationary channels","PeriodicalId":179210,"journal":{"name":"Electronics, Robotics and Automotive Mechanics Conference (CERMA'06)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133611098","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.L.F. Giraldo, T.E. Delgado, J. Riano, D.G. Castellanos
For a given set of samples, a new model is proposed to reduce input feature space, which decreases the learning time of classifiers, but also, improves the prediction accuracy according to the chosen relevance criterion. This model is constructed by decision trees and genetic algorithms, which evaluates by means of k nearest neighbor rule for classification, allowing the evolution model parameters of used genetic algorithm. The training set corresponds to the extracted features from pathological (hypernasality) and non-pathological (normal) speech, acquired from 90 children, 45 examples per class. A comparative analysis between different approaches about feature selection is performed upon experimental results, showing the feasibility of this approach in such a cases involving pathologies recognition
{"title":"Feature Selection Using Hybrid Evaluation Approaches Based on Genetic Algorithms","authors":"T.L.F. Giraldo, T.E. Delgado, J. Riano, D.G. Castellanos","doi":"10.1109/CERMA.2006.113","DOIUrl":"https://doi.org/10.1109/CERMA.2006.113","url":null,"abstract":"For a given set of samples, a new model is proposed to reduce input feature space, which decreases the learning time of classifiers, but also, improves the prediction accuracy according to the chosen relevance criterion. This model is constructed by decision trees and genetic algorithms, which evaluates by means of k nearest neighbor rule for classification, allowing the evolution model parameters of used genetic algorithm. The training set corresponds to the extracted features from pathological (hypernasality) and non-pathological (normal) speech, acquired from 90 children, 45 examples per class. A comparative analysis between different approaches about feature selection is performed upon experimental results, showing the feasibility of this approach in such a cases involving pathologies recognition","PeriodicalId":179210,"journal":{"name":"Electronics, Robotics and Automotive Mechanics Conference (CERMA'06)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115271676","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}
It is presented the development of algorithm for microcalcifications detection in mammography images using wavelet transform. We have proposed a computerized scheme detection microcalcifications clusters in the mammography images. The experimental results have shown the advantages and drawbacks of the detection algorithm. There are used images of the MIAS database with microcalcifications presence that permits to prove the proposed algorithm
{"title":"Detection of Microcalcifications in Digital Mammograms Images Using Wavelet Transform","authors":"C. Juarez, V. Ponomaryov","doi":"10.1109/CERMA.2006.36","DOIUrl":"https://doi.org/10.1109/CERMA.2006.36","url":null,"abstract":"It is presented the development of algorithm for microcalcifications detection in mammography images using wavelet transform. We have proposed a computerized scheme detection microcalcifications clusters in the mammography images. The experimental results have shown the advantages and drawbacks of the detection algorithm. There are used images of the MIAS database with microcalcifications presence that permits to prove the proposed algorithm","PeriodicalId":179210,"journal":{"name":"Electronics, Robotics and Automotive Mechanics Conference (CERMA'06)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115368927","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 we propose representing solutions in evolutionary algorithms for power distribution network expansion planning problems using the edge-set encoding technique, and we describe recombination and mutation operators for this representation. We demonstrate the usefulness of this encoding technique in a genetic algorithm designed to deal with the planning problem formulated as a single-objective optimization problem: to find the best location and size of substations and lines to minimize a cost function of the network. The algorithm was tested on a real power distribution network and the results were compared with the results from other heuristic methods. We concluded that the edge-set encoding and its genetic operators in evolutionary algorithms for power distribution network expansion planning offer strong locality and heritability, and computational efficiency. In the companion paper, the edge-set encoding technique is tested on a multi-objective power distribution network planning problem
{"title":"The Edge-set Encoding in Evolutionary Algorithms for Power Distribution Network Planning Problem Part I: Single-objective Optimization Planning","authors":"F. Rivas-Dávalos, M. Irving","doi":"10.1109/CERMA.2006.90","DOIUrl":"https://doi.org/10.1109/CERMA.2006.90","url":null,"abstract":"In this paper we propose representing solutions in evolutionary algorithms for power distribution network expansion planning problems using the edge-set encoding technique, and we describe recombination and mutation operators for this representation. We demonstrate the usefulness of this encoding technique in a genetic algorithm designed to deal with the planning problem formulated as a single-objective optimization problem: to find the best location and size of substations and lines to minimize a cost function of the network. The algorithm was tested on a real power distribution network and the results were compared with the results from other heuristic methods. We concluded that the edge-set encoding and its genetic operators in evolutionary algorithms for power distribution network expansion planning offer strong locality and heritability, and computational efficiency. In the companion paper, the edge-set encoding technique is tested on a multi-objective power distribution network planning problem","PeriodicalId":179210,"journal":{"name":"Electronics, Robotics and Automotive Mechanics Conference (CERMA'06)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115398772","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}
Binary decision diagrams have been successful forms to represent Boolean functions, and associative memories have been one of the most important models for pattern recognition, being the alpha-beta associative memories the best available model today. In this paper we propose the use of binary decision diagrams to represent alpha-beta associative memories. By doing so, we are able to merge two important and very active areas of contemporary scientific research, and improve on both models
{"title":"Using Binary Decision Diagrams to Efficiently Represent Alpha-Beta Associative Memories","authors":"I. López-Yáñez, C. Yáñez-Márquez","doi":"10.1109/CERMA.2006.96","DOIUrl":"https://doi.org/10.1109/CERMA.2006.96","url":null,"abstract":"Binary decision diagrams have been successful forms to represent Boolean functions, and associative memories have been one of the most important models for pattern recognition, being the alpha-beta associative memories the best available model today. In this paper we propose the use of binary decision diagrams to represent alpha-beta associative memories. By doing so, we are able to merge two important and very active areas of contemporary scientific research, and improve on both models","PeriodicalId":179210,"journal":{"name":"Electronics, Robotics and Automotive Mechanics Conference (CERMA'06)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125212906","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}
J.V. Lopez, J.C.S. Garcia, H. Meana, M. R. Macías, T.A. Ruiz
In this paper a modification to the mean square algorithm (LMS) appears, with the objective to reduce the floating point operations. This reduction allows to obtain a simple implementation of a digital adaptive filter, inside an integrated circuit, because a reduction of the floating point operations is made. The obtained advantages with this modification are the over adaptation of LMS algorithm, in order to increase the speed of convergence or higher frequency signals processing
{"title":"Over Adapted LMS Algorithm with Codified Error","authors":"J.V. Lopez, J.C.S. Garcia, H. Meana, M. R. Macías, T.A. Ruiz","doi":"10.1109/CERMA.2006.70","DOIUrl":"https://doi.org/10.1109/CERMA.2006.70","url":null,"abstract":"In this paper a modification to the mean square algorithm (LMS) appears, with the objective to reduce the floating point operations. This reduction allows to obtain a simple implementation of a digital adaptive filter, inside an integrated circuit, because a reduction of the floating point operations is made. The obtained advantages with this modification are the over adaptation of LMS algorithm, in order to increase the speed of convergence or higher frequency signals processing","PeriodicalId":179210,"journal":{"name":"Electronics, Robotics and Automotive Mechanics Conference (CERMA'06)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125510338","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 nonlinear benchmark problem, very interesting due to interaction between translational and rotational movements is the RTAC system (also called TORA). Diverse control techniques in several previous papers have been dedicated to it. The present work proposes, by means of a straightforward procedure, a controller design based on an approach of RTAC system, using numerical methods, so that the system tends to origin after being displaced of this position. The control signal is calculated through the resolution of a linear equations system. Computer simulations show that the performance is comparable and in some aspects better than the one obtained with more complicated controllers
{"title":"Controller Designed by Means of Numeric Methods for a Benchmark Problem: RTAC (Rotational Translational Actuator)","authors":"A. Rosales, G. Scaglia, V. Mut, F. di Sciascio","doi":"10.1109/CERMA.2006.30","DOIUrl":"https://doi.org/10.1109/CERMA.2006.30","url":null,"abstract":"A nonlinear benchmark problem, very interesting due to interaction between translational and rotational movements is the RTAC system (also called TORA). Diverse control techniques in several previous papers have been dedicated to it. The present work proposes, by means of a straightforward procedure, a controller design based on an approach of RTAC system, using numerical methods, so that the system tends to origin after being displaced of this position. The control signal is calculated through the resolution of a linear equations system. Computer simulations show that the performance is comparable and in some aspects better than the one obtained with more complicated controllers","PeriodicalId":179210,"journal":{"name":"Electronics, Robotics and Automotive Mechanics Conference (CERMA'06)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125583254","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}
Shape-of-object representation has always been an important topic in image processing and pattern recognition. This work deals with representation of shape of objects, and approaches to recognize objects. Several invariant techniques are widely used to represent an object because they preserve information and allow considerable data reduction. In this paper, a new approach based on a code representation and testor theory is presented. The proposed method is invariant under translation, scaling and rotation. Also, the paper discusses the capabilities of the method in recognizing objects. In addition, results using simple figures classes are show
{"title":"An Invariant Approach for Image Recognition","authors":"E. Zuniga-Segura, G. Sánchez-Díaz","doi":"10.1109/CERMA.2006.14","DOIUrl":"https://doi.org/10.1109/CERMA.2006.14","url":null,"abstract":"Shape-of-object representation has always been an important topic in image processing and pattern recognition. This work deals with representation of shape of objects, and approaches to recognize objects. Several invariant techniques are widely used to represent an object because they preserve information and allow considerable data reduction. In this paper, a new approach based on a code representation and testor theory is presented. The proposed method is invariant under translation, scaling and rotation. Also, the paper discusses the capabilities of the method in recognizing objects. In addition, results using simple figures classes are show","PeriodicalId":179210,"journal":{"name":"Electronics, Robotics and Automotive Mechanics Conference (CERMA'06)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122894578","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：