{"title":"Implementation of neural constructivism with programmable hardware","authors":"A. Pérez-Uribe, E. Sanchez","doi":"10.1109/ISNFS.1996.603820","DOIUrl":"https://doi.org/10.1109/ISNFS.1996.603820","url":null,"abstract":"Most neural network models base their \"learning\" capability on changing the strengths of interconnection between computational elements. However, according to \"neural constructivism\", an environmentally-guided neural circuit building offers powerful learning capabilities while minimizing the need for domain-specific structure prespecification. This paper presents a field programmable hardware implementation of an unsupervised constructive neural network with online size adaptation, a form of neural constructivism, and presents a color learning and recognition application.","PeriodicalId":187481,"journal":{"name":"1st International Symposium on Neuro-Fuzzy Systems, AT '96. Conference Report","volume":" 100","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120827276","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":"On the structure of a neuro-fuzzy system to forecast chaotic time series","authors":"L. Studer, F. Masulli","doi":"10.1109/ISNFS.1996.603827","DOIUrl":"https://doi.org/10.1109/ISNFS.1996.603827","url":null,"abstract":"The process of time series forecasting is described in the context of chaotic deterministic complex systems. The Takens-Mane theorem is used to ground the choices of the forecasting function, the number of past values d used and the time interval /spl tau/ between them. We argue that a neuro-fuzzy system (NFS) has the mathematical properties requested by the cited theorem. Moreover, it offers 2 more advantages: 1) a fast convergence, in CPU-time, from a very approximate to a (quasi) perfect forecasting function; 2) the possibility to actually understand, in a linguistic manner, the actual rules learned. These theoretical considerations are applied to the Mackey-Glass synthetic chaotic system (1977) in order to study the sensitivity of the NFS in function of d and /spl tau/. A brief discussion is made on some effects of noise in time series forecasting, and on topological invariants.","PeriodicalId":187481,"journal":{"name":"1st International Symposium on Neuro-Fuzzy Systems, AT '96. Conference Report","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121664706","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":"Performance evaluation of time-delay fuzzy neural networks for isolated word recognition","authors":"K. Oweiss, O. Abdel Alim","doi":"10.1109/ISNFS.1996.603839","DOIUrl":"https://doi.org/10.1109/ISNFS.1996.603839","url":null,"abstract":"A novel structure of fuzzy neural network (FNN) for the recognition of isolated Arabic words is suggested. The performance is evaluated by varying the network topology among several experiments to select the optimum structure for our task. A time delay arrangement is incorporated in the training phase to enable the network to discover useful acoustic-phonetic features without being blurred by shifts in the input. The input speech is processed to obtain a set of linear predictive (LP) derived cepstral coefficients. The input vector to the FNN consists of membership values to linguistic properties of the speech while the output vector is defined in terms of fuzzy class membership values. Three techniques were used to enhance the backpropagation training algorithm used to train the network in order to reduce training time and speed up convergence. The effectiveness of the suggested model is demonstrated on a speech recognition task consisting of Arabic phonemes extracted from a consonant-vowel-consonant (C-V-C) personnel database.","PeriodicalId":187481,"journal":{"name":"1st International Symposium on Neuro-Fuzzy Systems, AT '96. Conference Report","volume":"178 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114003814","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 networks in lightning location systems","authors":"J. Bermudez, A. Piras, M. Rubinstein","doi":"10.1109/ISNFS.1996.603836","DOIUrl":"https://doi.org/10.1109/ISNFS.1996.603836","url":null,"abstract":"In this work, we introduce the use of self organizing Kohonen maps, a type of artificial neural network, for lightning electromagnetic waveform classification. We show how this natural classification can be used to discriminate lightning waveforms in a noisy environment. The utility and functionality of the proposed framework is confirmed by numerical results based on real lightning electric field waveforms from the lightning positioning and tracking system (LPATS) operated by the Swiss Telecom PTT.","PeriodicalId":187481,"journal":{"name":"1st International Symposium on Neuro-Fuzzy Systems, AT '96. Conference Report","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131278992","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":"A Sugeno fuzzy model for knowledge representation in a decision support system","authors":"M. Gorgoglione","doi":"10.1109/ISNFS.1996.603823","DOIUrl":"https://doi.org/10.1109/ISNFS.1996.603823","url":null,"abstract":"Research into the field of decision support systems has been strongly enhanced by the development of artificial intelligence applications. One of the main issues to be tackled in simulating human intelligence and reasoning is how to represent human knowledge in a computing system. In this paper, two main approaches are discussed: the formalization of a sequence of reasoning rules (the expert system approach) and the collection of a set of input-output instructions describing human experience but not the internal mechanisms leading to the decision (the neural network approach). The adoption of a Sugeno fuzzy model for supporting the decision-making processes in a company is proposed, and a case of application is presented for testing the performance of such a model and discussing the organizational implications of fuzzy and neuro-fuzzy approaches.","PeriodicalId":187481,"journal":{"name":"1st International Symposium on Neuro-Fuzzy Systems, AT '96. Conference Report","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124573654","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":"Forecasting financial multivariate time series with neural networks","authors":"Thomas Ankenbrand, M. Tomassini","doi":"10.1109/ISNFS.1996.603826","DOIUrl":"https://doi.org/10.1109/ISNFS.1996.603826","url":null,"abstract":"An integrated approach for modelling the behaviour of financial markets with artificial neural networks (ANNs) is presented. The method allows to forecast financial time series. Its originality lies in the fact that it is based on statistics and macroeconomics principles and it integrates fundamental economic knowledge in a multivariate nonlinear time series ANN model. The core of the work is a feasibility analysis. This is seldom attempted in ANN work and consists in a series of different univariate and multivariate, linear and nonlinear statistical tests. Here we use aggregated input indicators as a new pre-processing step. The feasibility analysis evaluate \"a priori\" chance of forecasting the defined system and help to define the topology of the ANN. The method is applied to a real-life case study, the Swiss bond interest rate forecasting. Results giving out-of-sample performance are discussed.","PeriodicalId":187481,"journal":{"name":"1st International Symposium on Neuro-Fuzzy Systems, AT '96. Conference Report","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125812194","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":"Quality control in die casting with neural networks","authors":"A. Faessler, M. Loher","doi":"10.1109/ISNFS.1996.603832","DOIUrl":"https://doi.org/10.1109/ISNFS.1996.603832","url":null,"abstract":"Die casting is an attractive manufacturing process for metal pieces of complicated shape which are produced in large quantities. In applications of high safety standards comprising parts exposed to high mechanical stress a 100% X-ray examination after production is required. In this paper it is shown that this expensive and time-consuming process can be replaced by employing a classifier based on an artificial neural net. All the process parameters considered as relevant for the quality are input to the net, which then calculates a quality index. The net is trained with a learning base of 120 items. Thereafter, the results obtained by means of a multilayer perceptron, a learning vector quantization and a dynamic learning vector quantization are compared. Our dynamic learning vector quantization, which represents an attractive new approach, is discussed in some detail.","PeriodicalId":187481,"journal":{"name":"1st International Symposium on Neuro-Fuzzy Systems, AT '96. Conference Report","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132785892","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":"Dynamics of pattern formation in cellular neural networks","authors":"Patrick Thiran, G. Setti, C. Serpico","doi":"10.1109/ISNFS.1996.603813","DOIUrl":"https://doi.org/10.1109/ISNFS.1996.603813","url":null,"abstract":"This paper is a partial summary of some recent results that have been obtained to analyze pattern formation in some arrays of first-order dynamical systems. We discuss the dynamics of pattern formation and the way information, introduced as initial condition, is processed by such arrays, either locally or globally.","PeriodicalId":187481,"journal":{"name":"1st International Symposium on Neuro-Fuzzy Systems, AT '96. Conference Report","volume":"282 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116085106","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":"An optimized fuzzy inference system for oestrus detection in dairy cattle","authors":"W. Eradus, H. Scholten, A. T. Cate","doi":"10.1109/ISNFS.1996.603835","DOIUrl":"https://doi.org/10.1109/ISNFS.1996.603835","url":null,"abstract":"A fuzzy inference system has been developed as a tool for oestrus (heat) detection in dairy cattle. It uses signal, which are induced by hormone level changes during oestrus, resulting in physiological and behavioral effects like changes in activity, milk yield and milk temperature. A novelty in this approach is the use of a controlled random optimization method to tune the membership function shapes. Using routinely collected data, the system proves to detect cows in heat with acceptable results.","PeriodicalId":187481,"journal":{"name":"1st International Symposium on Neuro-Fuzzy Systems, AT '96. Conference Report","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130406704","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":"On some industrial applications of fuzzy logic","authors":"I. Vaclavik","doi":"10.1109/ISNFS.1996.603824","DOIUrl":"https://doi.org/10.1109/ISNFS.1996.603824","url":null,"abstract":"This paper presents a fuzzy logic solution for a brake controlled flow of a paper tape from a roll in a printing machine. The fuzzy logic controller is first examined through simulation with an analogic model of the system and the gains are tuned to obtain a well damped response. The fuzzy controller in cascade is then applied to an industrial machine. Compared to the simulation studies the application requires a modification of the membership functions and of the structure of the controller to compensate for the effects of brake hysteresis and for the time delays.","PeriodicalId":187481,"journal":{"name":"1st International Symposium on Neuro-Fuzzy Systems, AT '96. Conference Report","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125561769","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}