{"title":"Niches evolving the positioning of a mechanical arm in a 3D environment","authors":"P. Engel, Edson Prestes e Silva","doi":"10.1109/SBRN.1998.731000","DOIUrl":"https://doi.org/10.1109/SBRN.1998.731000","url":null,"abstract":"This paper presents an extension of the traditional genetic algorithms, called cooperative coevolutionary genetic algorithms (CCGA), which is used to evolve the angles of joints of a mechanical arm with N degrees of freedom in a 3D environment. Initially a brief introduction to this new approach will be presented. After this, we show the developed modeling with obtained results. Finally, extensions of this works will be pointed out.","PeriodicalId":401282,"journal":{"name":"Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209)","volume":"52 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115695186","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Implementation of a probabilistic neural network for multi-spectral image classification on an FPGA based custom computing machine","authors":"Marco A. Figueiredo, C. Gloster","doi":"10.1109/SBRN.1998.731021","DOIUrl":"https://doi.org/10.1109/SBRN.1998.731021","url":null,"abstract":"As the demand for higher performance computers for the processing of remote sensing science algorithms increases, the need to investigate new computing paradigms is justified. Field programmable gate arrays (FPGA) enable the implementation of algorithms at the hardware gate level, leading to orders of magnitude performance increase over microprocessor based systems. The automatic classification of space borne multispectral images is an example of a computation intensive application that only tends to increase as instruments start to explore hyperspectral capabilities. A probabilistic neural network is used here to classify pixels of a multispectral LANDSAT-2 image. The implementation described utilizes a commercial-off-the-shelf FPGA based custom computing machine.","PeriodicalId":401282,"journal":{"name":"Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134309634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Safe inclusion of information about rates of variation in a reinforcement learning algorithm","authors":"C. Ribeiro","doi":"10.1109/SBRN.1998.730985","DOIUrl":"https://doi.org/10.1109/SBRN.1998.730985","url":null,"abstract":"There is a need to enhance reinforcement learning techniques by using prior knowledge built into the agent at its inception. The information crudeness upon which those algorithms operate may be interesting from a theoretical point of view, but large scale problems are made too difficult and unrealistic by considering the learning agent as a 'tabula rasa'. None the less, knowledge must be embedded in such a way that the structural, well-studied characteristics of the fundamental algorithms are maintained. A more general formulation of a classical reinforcement learning method is investigated. It allows for a spreading of information derived from single updates towards a neighbourhood of the instantly visited state, and converges to optimality. We show how this new formulation can be used as a mechanism to safely embed prior knowledge about expected rates of variation of action values, and practical studies demonstrate an application of the proposed algorithm.","PeriodicalId":401282,"journal":{"name":"Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130123736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Artificial neural network applied to power system protection","authors":"M. Oleskovicz, D. Coury, A. Carvalho","doi":"10.1109/SBRN.1998.731040","DOIUrl":"https://doi.org/10.1109/SBRN.1998.731040","url":null,"abstract":"The main objective of this paper is the implementation of an alternative protection model to transmission lines applying artificial neural networks (ANN). An improvement in performance to the conventional distance relay is expected, once the ANNs can learn the different fault conditions as well as network changes in order to operate in less time correctly. In this work, the relay protection zone (96% of a transmission line length) was determined by forward and reverse single-line-to-ground fault condition. The input data shows the trip/no trip decision of a protection system. The approach used in this paper utilizes the voltage and current post-fault samples as input to a moving data window. The implemented neural network should capture the knowledge for the correct relay operation facing the different network conditions.","PeriodicalId":401282,"journal":{"name":"Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131245554","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}
M. Rosa, J. Pereira, André Carlos Ponce de Leon Ferreira de Carvalho
{"title":"Evaluation of neural classifiers using statistic methods for identification of laryngeal pathologies","authors":"M. Rosa, J. Pereira, André Carlos Ponce de Leon Ferreira de Carvalho","doi":"10.1109/SBRN.1998.731033","DOIUrl":"https://doi.org/10.1109/SBRN.1998.731033","url":null,"abstract":"The use of statistical elements, like nonparametric tests and principal components analysis, allows the evaluation of the behavior and the performance of artificial neural networks when acoustical measurements are used to identify larynx diseases from which patterns are naturally overlapped. In this work, techniques to improve the results of neural network through the manipulation of the training patterns and convergence control will be discussed.","PeriodicalId":401282,"journal":{"name":"Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114596464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Automatic target recognition using a constructive approach","authors":"E.C. Vargas, H.C. de Sousa, A. de Carvalho","doi":"10.1109/SBRN.1998.731005","DOIUrl":"https://doi.org/10.1109/SBRN.1998.731005","url":null,"abstract":"This paper presents the use of constructive neural networks for pattern recognition. The work presented here is part of the SAPRI project (System for Acquisition, Processing and Image Recognition) which is being developed for the Brazilian Navy. The objective of this paper is to investigate the behavior of constructive neural networks in image recognition tasks, specially with images from the SAPRI project. Constructive neural networks differ from standard networks due to their ability to change their own number of elements, adding or removing units and connections. Four constructive algorithms are presented in this paper: cascade correlation, tower, pyramid and upstart.","PeriodicalId":401282,"journal":{"name":"Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116472829","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}