T. Higuchi, M. Murakawa, M. Iwata, I. Kajitani, Weixin Liu, M. Salami
{"title":"Evolvable hardware at function level","authors":"T. Higuchi, M. Murakawa, M. Iwata, I. Kajitani, Weixin Liu, M. Salami","doi":"10.1109/ICEC.1997.592293","DOIUrl":"https://doi.org/10.1109/ICEC.1997.592293","url":null,"abstract":"This paper describes a new type of evolvable hardware (EHW). While most EHW research employs hardware evolution at the level of primitive gates (i.e. gate-level evolution), our alternative synthesizes hardware circuits with higher-level functions. We call this evolution \"function-level evolution\". In this paper, two applications of function-level EHW are described. One is for adaptive equalization in digital mobile communication; the other is for lossy data compression.","PeriodicalId":167852,"journal":{"name":"Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116702305","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 study on fuzzy rules discovery using Pseudo-Bacterial Genetic Algorithm with adaptive operator","authors":"N. Nawa, T. Hashiyama, T. Furuhashi, Y. Uchikawa","doi":"10.1109/ICEC.1997.592379","DOIUrl":"https://doi.org/10.1109/ICEC.1997.592379","url":null,"abstract":"This paper presents a new operator called adaptive operator for the Pseudo-Bacterial Genetic Algorithm (PBGA). The PBGA was proposed by the authors as a new approach combining a genetic algorithm (GA) with a local improvement mechanism inspired by a process in bacterial genetics. The PBGA was applied for the discovery of fuzzy rules. The aim of the newly introduced adaptive operator is to improve the quality of the generated fuzzy rules, producing blocks of effective rules and more compact rule bases. The new operator adaptively decides the division points of each chromosome for the bacterial mutation and the cutting points for the crossover. In order to verify the efficiency of the proposed adaptive operator, the PBGA is applied to a simple fuzzy modeling problem. The new operator actuates according to the distribution of degrees of truth values of the rules. The results show the benefits that can be obtained with this operator.","PeriodicalId":167852,"journal":{"name":"Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126756248","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":"Visualizing the evolution of genetic algorithm search processes","authors":"W. B. Shine, C. Eick","doi":"10.1109/ICEC.1997.592337","DOIUrl":"https://doi.org/10.1109/ICEC.1997.592337","url":null,"abstract":"The paper discusses how visualization techniques can facilitate the development of GA-systems. It demonstrates how visualization techniques can be used for the analysis of search space coverage, of convergence behavior, and of the topology of the explored search space. We describe the features of a GA-visualization environment that uses quadcodes to generate search space coverage maps, that employs 2D-distance maps to visualize convergence, and uses contour maps to visualize fitness. We also describe how these maps are generated. Moreover, we discuss how movies are employed for visualizing the evolution of a GA-system. Finally, we discuss the architecture of our GA-visualization system which is implemented on the top of the Khoros visualization package.","PeriodicalId":167852,"journal":{"name":"Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130539314","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":"Generation of optimal fault tolerant locomotion of the hexapod robot over rough terrain using evolutionary programming","authors":"Jung‐Min Yang, Jong-Hwan Kim","doi":"10.1109/ICEC.1997.592360","DOIUrl":"https://doi.org/10.1109/ICEC.1997.592360","url":null,"abstract":"Extends the authors' previous (1996) results on optimal fault-tolerant locomotion of the hexapod walking robot over even terrain by generalizing the shape of the ground. A method of searching for the optimal or near-optimal fault-tolerant sequence of free gaits over rough terrain using evolutionary programming is proposed. Based on the sequence of gaits derived on the even terrain, the proposed algorithm searches for foothold positions that guarantee optimal locomotion and that maintain a non-negative fault stability margin. The effectiveness of the proposed algorithm is demonstrated with computer simulations.","PeriodicalId":167852,"journal":{"name":"Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116479388","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":"Structured learning in recurrent neural network using genetic algorithm with internal copy operator","authors":"T. Kumagai, M. Wada, S. Mikami, R. Hashimoto","doi":"10.1109/ICEC.1997.592395","DOIUrl":"https://doi.org/10.1109/ICEC.1997.592395","url":null,"abstract":"We compose a genetic algorithm that uses an internal copy operator for recurrent neural network learning. The internal copy operator copies one part of a gene to another part of the same gene. We show that the proposed algorithm accelerates learning. We also show that the internal copy operator organizes the structure in the network. The organized structure improves the learning ability and makes it possible to acquire a set of limit cycles easily.","PeriodicalId":167852,"journal":{"name":"Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121800912","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":"Ligation experiments in computing with DNA","authors":"N. Jonoska, S. Karl","doi":"10.1109/ICEC.1997.592308","DOIUrl":"https://doi.org/10.1109/ICEC.1997.592308","url":null,"abstract":"Relative to a short history, the use of DNA in molecular computing applications has received considerable attention. Although several theoretical and computational studies have been considered, descriptions of laboratory studies have been lacking. We detail results from several laboratory experiments that highlight the use of thermostable enzymes in ligation and polymerase chain reactions (LCR and PCR) and explore their utility in DNA-based computing.","PeriodicalId":167852,"journal":{"name":"Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131032315","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":"Genetic algorithms for solving shortest path problems","authors":"Mitsuo Gen, R. Cheng, Dingwei Wang","doi":"10.1109/ICEC.1997.592343","DOIUrl":"https://doi.org/10.1109/ICEC.1997.592343","url":null,"abstract":"In this study, we investigated the possibility of using genetic algorithms to solve shortest path problems. The most thorny and critical task for developing a genetic algorithm to this problem is how to encode a path in a graph into a chromosome. A priority-based encoding method is proposed which can potentially represent all possible paths in a graph. Because a variety of network optimization problems may be solved, either exactly or approximately, by identifying shortest path, this studies will provide a base for constructing efficient solution procedures for shortest path-based network optimization problems. The proposed approach has been tested on three randomly generated problems with different size from 6 nodes to 70 nodes and from 10 edges to 211 edges. The experiment results are very encouraging: it can find the known optimum very rapidly with very high probability. It can be believed that genetic algorithms may hopefully be a new approach for such kinds of difficult-to-solve problems.","PeriodicalId":167852,"journal":{"name":"Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131685846","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":"Learning the local search range for genetic optimisation in nonstationary environments","authors":"Frank Vavak, Ken Jukes, Terence C. Fogarty","doi":"10.1109/ICEC.1997.592335","DOIUrl":"https://doi.org/10.1109/ICEC.1997.592335","url":null,"abstract":"We examine a modification to the genetic algorithm. The variable local search (VLS) operator was designed to enable the genetic algorithm based online optimisers to track optima of time-varying dynamic systems. This feature is not to the detriment of its ability to provide sound results for the stationary environments. The operator matches the level of diversity introduced into the population with the \"degree\" of the environmental change by increasing population diversity only gradually. The paper also shows that the performance of the designed tracking method can be further enhanced by integrating it with a simple exemplar-based incremental learning technique. It is believed that the designed technique will prove beneficial in the application of the genetic algorithm based approaches to industrial control problems.","PeriodicalId":167852,"journal":{"name":"Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131686044","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. Bersano-Begey, J. Daida, J. Vesecky, F.L. Ludwig
{"title":"A Java collaborative interface for genetic programming applications: image analysis for scientific inquiry","authors":"T. Bersano-Begey, J. Daida, J. Vesecky, F.L. Ludwig","doi":"10.1109/ICEC.1997.592358","DOIUrl":"https://doi.org/10.1109/ICEC.1997.592358","url":null,"abstract":"Discusses several key issues involved in designing and using a Java collaborative interface for genetic programming applications over the World Wide Web. We present our implementation that has been used in a new system that assists scientists in classifying and extracting novel features in remotely sensed satellite imagery. This paper also identifies issues in developing a class library that facilitates rapid prototyping of such collaborative graphical user interfaces for genetic programming, and suggests how other researchers could benefit from them.","PeriodicalId":167852,"journal":{"name":"Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115553575","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 neural network that uses evolutionary learning","authors":"Mario K oppen, M. Teunis, B. Nickolay","doi":"10.1109/ICEC.1997.592390","DOIUrl":"https://doi.org/10.1109/ICEC.1997.592390","url":null,"abstract":"This paper proposes a new neural architecture (Nessy) which uses evolutionary optimization for learning. The architecture, the outline of its evolutionary algorithm and the learning laws are given. Nessy is based on several modifications of the multilayer backpropagation neural network. The neurons represent genes of evolutionary optimization, referred to as solutions. Weights represent probabilities and are used for selection. The training value of the output layer is set to zero, the theoretical limit of every cost-oriented optimization, and the crossover operator is replaced by a transduction operator. Mutation is used as usual. Nessy algorithm can be characterized as an individual evolutionary algorithm, but as a neural network too. It was designed for image processing applications. A short example is presented, where the discriminative feature of two images is successfully detected by the proposed evolutionary neural network.","PeriodicalId":167852,"journal":{"name":"Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1997-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114387493","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}