The paper describes an investigation of the problem of identifying objects, in particular ships at sea, in infrared images obtained at a variety of angles and scales. The paper covers theoretical and experimental work relating to the choice of feature vectors to describe the images and the application of the this work to the development of a demonstration system.<>
{"title":"All-aspect ship recognition in infrared images","authors":"Cara DeSilva, G. Lee, R. Johnson","doi":"10.1109/ETD.1995.403472","DOIUrl":"https://doi.org/10.1109/ETD.1995.403472","url":null,"abstract":"The paper describes an investigation of the problem of identifying objects, in particular ships at sea, in infrared images obtained at a variety of angles and scales. The paper covers theoretical and experimental work relating to the choice of feature vectors to describe the images and the application of the this work to the development of a demonstration system.<<ETX>>","PeriodicalId":302763,"journal":{"name":"Proceedings Electronic Technology Directions to the Year 2000","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132606971","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}
There is a tremendous interest in the development of the evolutionary computation techniques as they are well suited to deal with optimization of functions containing a large number of variables. This paper presents a brief review of evolutionary computing techniques. It also discusses briefly the hybridization of evolutionary computation and neural networks and presents a solution of a classical problem using neural computing and evolutionary computing techniques.<>
{"title":"Integrating evolutionary computation with neural networks","authors":"E. Vonk, L. Jain, L. Veelenturf, R. Hibbs","doi":"10.1109/ETD.1995.403480","DOIUrl":"https://doi.org/10.1109/ETD.1995.403480","url":null,"abstract":"There is a tremendous interest in the development of the evolutionary computation techniques as they are well suited to deal with optimization of functions containing a large number of variables. This paper presents a brief review of evolutionary computing techniques. It also discusses briefly the hybridization of evolutionary computation and neural networks and presents a solution of a classical problem using neural computing and evolutionary computing techniques.<<ETX>>","PeriodicalId":302763,"journal":{"name":"Proceedings Electronic Technology Directions to the Year 2000","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123380253","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}
An adaptive control procedure utilising neural networks is presented. The method is based on the model reference control technique and can be applied to discrete-time nonlinear systems of unknown structure. Multi-layered neural networks are used to approximate the plant Jacobian and synthesise the controller. A sufficient condition for the convergence of the tracking error between the desired output and controlled output is presented. Lyapunov theory is used to show that the overall system is stable. Simulation studies show that the proposed scheme performs well even in the presence of dynamic perturbations.<>
{"title":"Investigation of stability and convergence issues for an enhanced model reference neural adaptive control scheme","authors":"S. Mazumdar, C. Lim","doi":"10.1109/ETD.1995.403487","DOIUrl":"https://doi.org/10.1109/ETD.1995.403487","url":null,"abstract":"An adaptive control procedure utilising neural networks is presented. The method is based on the model reference control technique and can be applied to discrete-time nonlinear systems of unknown structure. Multi-layered neural networks are used to approximate the plant Jacobian and synthesise the controller. A sufficient condition for the convergence of the tracking error between the desired output and controlled output is presented. Lyapunov theory is used to show that the overall system is stable. Simulation studies show that the proposed scheme performs well even in the presence of dynamic perturbations.<<ETX>>","PeriodicalId":302763,"journal":{"name":"Proceedings Electronic Technology Directions to the Year 2000","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127350153","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}
There is a tremendous interest in the development of the theory and applications of evolutionary computing techniques both in industry and universities. Evolutionary computation is the name given to collection of algorithms based on the evolution of a population towards a solution of a certain problem. These algorithms are used successfully in many applications requiring the optimization of a certain multidimensional function. The population of possible solutions evolves from one generation to the next, ultimately arriving at a satisfactory solution to the problem. These algorithms differ in the way a new population is generated from the present one and in the way the members are represented within the algorithm. Three types of evolutionary computing techniques are widely reported recently. These are genetic algorithms (GAs), genetic programming (GP) and evolutionary algorithms (EAs). The EAs can be divided into evolutionary strategies (ES) and evolutionary programming (EP). All three of these algorithms in some way are modelled after the evolutionary processes occurring in nature.<>
{"title":"Introduction to evolutionary computing techniques","authors":"L. Jain, C. L. Karr","doi":"10.1109/ETD.1995.403482","DOIUrl":"https://doi.org/10.1109/ETD.1995.403482","url":null,"abstract":"There is a tremendous interest in the development of the theory and applications of evolutionary computing techniques both in industry and universities. Evolutionary computation is the name given to collection of algorithms based on the evolution of a population towards a solution of a certain problem. These algorithms are used successfully in many applications requiring the optimization of a certain multidimensional function. The population of possible solutions evolves from one generation to the next, ultimately arriving at a satisfactory solution to the problem. These algorithms differ in the way a new population is generated from the present one and in the way the members are represented within the algorithm. Three types of evolutionary computing techniques are widely reported recently. These are genetic algorithms (GAs), genetic programming (GP) and evolutionary algorithms (EAs). The EAs can be divided into evolutionary strategies (ES) and evolutionary programming (EP). All three of these algorithms in some way are modelled after the evolutionary processes occurring in nature.<<ETX>>","PeriodicalId":302763,"journal":{"name":"Proceedings Electronic Technology Directions to the Year 2000","volume":"36 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":"133450142","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}
Kristof Van Laerhoven, kristof mis.tu-darmstadt.de, Warren S. McCulloch, W. Pitts
A general introduction to the subject of artificial neural networks is given and the tenuous relationship of neural networks to the biological neuron structure of the brain is also briefly outlined. The development of artificial neural networks has been marked by periods of considerable optimism and others of disillusionment. A realistic assessment of the potential of artificial neural networks is attempted and some of the unrealistic expectations which has grown around a new and developing subject are dispelled. The study of artificial neural networks originally grew out of a desire to understand the function of the biological brain. This relationship between the biological neuron and the artificial neuron has been of great importance in past research but at the present time it does not appear to be a fruitful field. A basic description of the biological neural network is included so that the debt the artificial neural network owes to the biological neural network may be appreciated.<>
{"title":"Introduction to artificial neural networks","authors":"Kristof Van Laerhoven, kristof mis.tu-darmstadt.de, Warren S. McCulloch, W. Pitts","doi":"10.1109/ETD.1995.403491","DOIUrl":"https://doi.org/10.1109/ETD.1995.403491","url":null,"abstract":"A general introduction to the subject of artificial neural networks is given and the tenuous relationship of neural networks to the biological neuron structure of the brain is also briefly outlined. The development of artificial neural networks has been marked by periods of considerable optimism and others of disillusionment. A realistic assessment of the potential of artificial neural networks is attempted and some of the unrealistic expectations which has grown around a new and developing subject are dispelled. The study of artificial neural networks originally grew out of a desire to understand the function of the biological brain. This relationship between the biological neuron and the artificial neuron has been of great importance in past research but at the present time it does not appear to be a fruitful field. A basic description of the biological neural network is included so that the debt the artificial neural network owes to the biological neural network may be appreciated.<<ETX>>","PeriodicalId":302763,"journal":{"name":"Proceedings Electronic Technology Directions to the Year 2000","volume":"91 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131776417","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}
Fuzzy logic was first developed by Zadeh in the mid 1960s for representing uncertain and imprecise knowledge. In the classical Boolean logic truth is represented by the 1 state and falsity is by the 0 state. Boolean algebra has no provision for approximate reasoning. Fuzzy logic is an extension of Boolean logic in the sense that it also provides a platform for handling uncertain and imprecise knowledge. Fuzzy logic uses fuzzy set theory, in which a variable is a member of one or more sets, with a specified degree of membership, usually denoted by the Greek letter /spl mu/. The paper provides an introduction to fuzzy systems.<>
{"title":"Introduction to fuzzy systems","authors":"L. Jain, C. L. Karr","doi":"10.1109/ETD.1995.403485","DOIUrl":"https://doi.org/10.1109/ETD.1995.403485","url":null,"abstract":"Fuzzy logic was first developed by Zadeh in the mid 1960s for representing uncertain and imprecise knowledge. In the classical Boolean logic truth is represented by the 1 state and falsity is by the 0 state. Boolean algebra has no provision for approximate reasoning. Fuzzy logic is an extension of Boolean logic in the sense that it also provides a platform for handling uncertain and imprecise knowledge. Fuzzy logic uses fuzzy set theory, in which a variable is a member of one or more sets, with a specified degree of membership, usually denoted by the Greek letter /spl mu/. The paper provides an introduction to fuzzy systems.<<ETX>>","PeriodicalId":302763,"journal":{"name":"Proceedings Electronic Technology Directions to the Year 2000","volume":"28 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":"133411049","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}
This paper reports the application of evolutionary computation in the automatic generation of a neural network architecture. It is a usual practice to use trial and error to find a suitable neural network architecture. This is not only time consuming but may not generate an optimal solution for a given problem. The use of evolutionary computation is a step towards automation in architecture generation. In this paper a brief introduction to the field is given as well as an implementation of automatic neural network generation using genetic programming.<>
{"title":"Automatic generation of a neural network architecture using evolutionary computation","authors":"E. Vonk, L. Jain, L. Veelenturf, R. P. Johnson","doi":"10.1109/ETD.1995.403479","DOIUrl":"https://doi.org/10.1109/ETD.1995.403479","url":null,"abstract":"This paper reports the application of evolutionary computation in the automatic generation of a neural network architecture. It is a usual practice to use trial and error to find a suitable neural network architecture. This is not only time consuming but may not generate an optimal solution for a given problem. The use of evolutionary computation is a step towards automation in architecture generation. In this paper a brief introduction to the field is given as well as an implementation of automatic neural network generation using genetic programming.<<ETX>>","PeriodicalId":302763,"journal":{"name":"Proceedings Electronic Technology Directions to the Year 2000","volume":"2011 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":"131764756","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}
The technological advances that have taken place in microelectronics, telecommunication and computer technologies have revolutionised the instrumentation used for measurement and control in today's industries. These applications being largely nonelectrical in nature, the impact has been even more tremendous. Mechanical and chemical engineers have suddenly to grapple with advanced electronic technologies in terms of communications, electronic hardware and computer software developments. On the other hand electrical engineers have to contend with ingenious ways of integrating modem semiconductor and communications technology into designs for instruments which are primarily mechanical in the front end and purpose. With the tremendous size of the market in the industrial measurement and control sector, the momentum given by the advances in electronics and communications is even more felt in this sector than in many other sectors. The impact of all these factors is to make the field of instrumentation for measurement and control ever more interdisciplinary and with endless challenges thrown open especially by the developments in microelectronics, computer software and the ever increasing demand of industrial processes.<>
{"title":"Control instrumentation-a survey of current practice and some future trends","authors":"R. Devanathan, D. Mital, L. Jain","doi":"10.1109/ETD.1995.403463","DOIUrl":"https://doi.org/10.1109/ETD.1995.403463","url":null,"abstract":"The technological advances that have taken place in microelectronics, telecommunication and computer technologies have revolutionised the instrumentation used for measurement and control in today's industries. These applications being largely nonelectrical in nature, the impact has been even more tremendous. Mechanical and chemical engineers have suddenly to grapple with advanced electronic technologies in terms of communications, electronic hardware and computer software developments. On the other hand electrical engineers have to contend with ingenious ways of integrating modem semiconductor and communications technology into designs for instruments which are primarily mechanical in the front end and purpose. With the tremendous size of the market in the industrial measurement and control sector, the momentum given by the advances in electronics and communications is even more felt in this sector than in many other sectors. The impact of all these factors is to make the field of instrumentation for measurement and control ever more interdisciplinary and with endless challenges thrown open especially by the developments in microelectronics, computer software and the ever increasing demand of industrial processes.<<ETX>>","PeriodicalId":302763,"journal":{"name":"Proceedings Electronic Technology Directions to the Year 2000","volume":"64 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":"133553894","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 the last decade or so, expert systems also called knowledge-based systems have made their way from research laboratories into the real world. Applications have been, and are continuing to be, developed in areas as diverse as business, medicine, manufacturing, defence, astronomy, science and engineering. Such applications perform tasks that include interpretation, prediction, diagnosis, design, planning, monitoring, debugging, repairing, instruction and control. The expert systems are the offshoots of artificial intelligence which is concerned with using computers to simulate human intelligence in a limited way. Some researchers define artificial intelligence (AI) as the science of making machines do things that would require intelligence if done by men. In the last few decades, AI has spread into major subfields including expert systems, artificial neural networks, fuzzy systems, evolutionary computation and chaos theory. Some researchers do not differentiate between expert systems and knowledge-based systems. The key issue behind all these developments is the knowledge acquisition, knowledge representation and knowledge processing.<>
{"title":"Introduction to knowledge-based systems","authors":"L. Jain","doi":"10.1109/ETD.1995.403493","DOIUrl":"https://doi.org/10.1109/ETD.1995.403493","url":null,"abstract":"In the last decade or so, expert systems also called knowledge-based systems have made their way from research laboratories into the real world. Applications have been, and are continuing to be, developed in areas as diverse as business, medicine, manufacturing, defence, astronomy, science and engineering. Such applications perform tasks that include interpretation, prediction, diagnosis, design, planning, monitoring, debugging, repairing, instruction and control. The expert systems are the offshoots of artificial intelligence which is concerned with using computers to simulate human intelligence in a limited way. Some researchers define artificial intelligence (AI) as the science of making machines do things that would require intelligence if done by men. In the last few decades, AI has spread into major subfields including expert systems, artificial neural networks, fuzzy systems, evolutionary computation and chaos theory. Some researchers do not differentiate between expert systems and knowledge-based systems. The key issue behind all these developments is the knowledge acquisition, knowledge representation and knowledge processing.<<ETX>>","PeriodicalId":302763,"journal":{"name":"Proceedings Electronic Technology Directions to the Year 2000","volume":"34 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":"114830488","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}
Using the definitions of the Academic Press Dictionary of Science and Technology 1992, microelectronics refers to the special methods and techniques used in producing miniature circuits, and engineering is the profession that creates all of the artifacts making up the modern world. Microelectronic engineering then describes a subset of the whole. The article gives an overview of microelectronic engineering research.<>
{"title":"Microelectronic engineering","authors":"W. Marwood, L. Jain","doi":"10.1109/ETD.1995.403468","DOIUrl":"https://doi.org/10.1109/ETD.1995.403468","url":null,"abstract":"Using the definitions of the Academic Press Dictionary of Science and Technology 1992, microelectronics refers to the special methods and techniques used in producing miniature circuits, and engineering is the profession that creates all of the artifacts making up the modern world. Microelectronic engineering then describes a subset of the whole. The article gives an overview of microelectronic engineering research.<<ETX>>","PeriodicalId":302763,"journal":{"name":"Proceedings Electronic Technology Directions to the Year 2000","volume":"7 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":"115554585","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：