A new approach to interconnecting multilayer feedforward neural networks for tackling the problems of texture classification is proposed. The resulting classification system classifies textures via two stages; one to compress original co-occurrence feature patterns of high dimensionality to lower dimensional principal feature patterns, and the other to perform actual classification of textures using the principal features. Each stage is efficiently implemented by a trained multilayer feedforward neural network. Such a cascaded use of neural networks significantly reduces the computational complexity that is otherwise encountered in classifying large-scale texture images. Two practical applications of the system are provided, showing the direct applicability of the approach for real problem-solving.
{"title":"Neural network based classification system for texture images with its applications","authors":"C. Shang, K. Brown","doi":"10.1049/ISE.1994.0004","DOIUrl":"https://doi.org/10.1049/ISE.1994.0004","url":null,"abstract":"A new approach to interconnecting multilayer feedforward neural networks for tackling the problems of texture classification is proposed. The resulting classification system classifies textures via two stages; one to compress original co-occurrence feature patterns of high dimensionality to lower dimensional principal feature patterns, and the other to perform actual classification of textures using the principal features. Each stage is efficiently implemented by a trained multilayer feedforward neural network. Such a cascaded use of neural networks significantly reduces the computational complexity that is otherwise encountered in classifying large-scale texture images. Two practical applications of the system are provided, showing the direct applicability of the approach for real problem-solving.","PeriodicalId":55165,"journal":{"name":"Engineering Intelligent Systems for Electrical Engineering and Communications","volume":"229 1","pages":"27-36"},"PeriodicalIF":0.0,"publicationDate":"1994-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72672196","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 paper proposes a neural network technique to classify numerals using Zernike moments that are invariant to rotation only. In order to make them invariant to scale and shift, we introduce modified Zernike moments based on regular moments. Owing to the large number of Zernike moments used, it is computationally more efficient to select a subset of them that can discriminate as well as the original set. The subset is determined using stepwise discriminant analysis. The performance of a subset is examined through its comparison to the original set. The results are shown of using such a scheme to classify scaled, rotated, and shifted binary images and images that have been perturbed with random noise. In addition to the neural network approach, the Fisher's classifier is also used, which is a parametric classifier. A comparative study of their performances shows that the neural network approach produces better classification accuracy than the Fisher's classifier. When a suitable subset of Zernike moments is used, the classifiers perform well, just like the original set. The performance of the classifiers is also examined. The computational time is greatly reduced when a suitable subset of Zernike moments is used.
{"title":"Neuro-pattern classification using Zernike moments and its reduced set of features","authors":"P. Raveendran, S. Omatu, S. Ong","doi":"10.1049/ISE.1994.0024","DOIUrl":"https://doi.org/10.1049/ISE.1994.0024","url":null,"abstract":"The paper proposes a neural network technique to classify numerals using Zernike moments that are invariant to rotation only. In order to make them invariant to scale and shift, we introduce modified Zernike moments based on regular moments. Owing to the large number of Zernike moments used, it is computationally more efficient to select a subset of them that can discriminate as well as the original set. The subset is determined using stepwise discriminant analysis. The performance of a subset is examined through its comparison to the original set. The results are shown of using such a scheme to classify scaled, rotated, and shifted binary images and images that have been perturbed with random noise. In addition to the neural network approach, the Fisher's classifier is also used, which is a parametric classifier. A comparative study of their performances shows that the neural network approach produces better classification accuracy than the Fisher's classifier. When a suitable subset of Zernike moments is used, the classifiers perform well, just like the original set. The performance of the classifiers is also examined. The computational time is greatly reduced when a suitable subset of Zernike moments is used.","PeriodicalId":55165,"journal":{"name":"Engineering Intelligent Systems for Electrical Engineering and Communications","volume":"13 1","pages":"230-235"},"PeriodicalIF":0.0,"publicationDate":"1994-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77310639","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":"Intelligent Structural Systems","authors":"J. R. Stone","doi":"10.1049/ise.1994.0007","DOIUrl":"https://doi.org/10.1049/ise.1994.0007","url":null,"abstract":"","PeriodicalId":55165,"journal":{"name":"Engineering Intelligent Systems for Electrical Engineering and Communications","volume":"53 1","pages":"49"},"PeriodicalIF":0.0,"publicationDate":"1994-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87364184","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":"Editorial: ESPRIT results in the area of intelligent systems in engineering","authors":"P. Corsi","doi":"10.1049/ISE.1994.0013","DOIUrl":"https://doi.org/10.1049/ISE.1994.0013","url":null,"abstract":"","PeriodicalId":55165,"journal":{"name":"Engineering Intelligent Systems for Electrical Engineering and Communications","volume":"61 1","pages":"101"},"PeriodicalIF":0.0,"publicationDate":"1994-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80634602","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":"Robotic Systems: Advanced Techniques and Applications","authors":"R. Vepa","doi":"10.1049/ISE.1994.0006","DOIUrl":"https://doi.org/10.1049/ISE.1994.0006","url":null,"abstract":"","PeriodicalId":55165,"journal":{"name":"Engineering Intelligent Systems for Electrical Engineering and Communications","volume":"56 1","pages":"48"},"PeriodicalIF":0.0,"publicationDate":"1994-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76642519","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 comparative performance of rule-based and fuzzy-logic-based power system stabilisers is described. The stabilising signal in these stabilisers is computed using two parameters depending on the speed/acceleration state of the generator in the phase plane. The required measurement is the speed deviation. The comparison of different stabilisers is demonstrated by a practical implementation using a digital signal processor mounted on a PC-AT. Results of experimental tests on a physical model of a simple power system are presented.
{"title":"Laboratory evaluation and test results for rule-based and fuzzy logic-based power system stabilisers: a comparative study","authors":"M.A.M. Hassan, O. Malik","doi":"10.1049/ISE.1993.0006","DOIUrl":"https://doi.org/10.1049/ISE.1993.0006","url":null,"abstract":"A comparative performance of rule-based and fuzzy-logic-based power system stabilisers is described. The stabilising signal in these stabilisers is computed using two parameters depending on the speed/acceleration state of the generator in the phase plane. The required measurement is the speed deviation. The comparison of different stabilisers is demonstrated by a practical implementation using a digital signal processor mounted on a PC-AT. Results of experimental tests on a physical model of a simple power system are presented.","PeriodicalId":55165,"journal":{"name":"Engineering Intelligent Systems for Electrical Engineering and Communications","volume":"42 1","pages":"52-60"},"PeriodicalIF":0.0,"publicationDate":"1993-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74217573","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, techniques for machine learning of real-time control strategies are presented and reviewed from a control engineer's point of view. The objective is to present a consolidated view, both in the context of classical control theory and modern artificial intelligence practice. The review seeks to present the principal contributions to the field and the impact of these contributions on control engineering, particularly from the machine learning point of view. >
{"title":"A review of techniques for machine learning of real-time control strategies","authors":"R. Vepa","doi":"10.1049/ISE.1993.0009","DOIUrl":"https://doi.org/10.1049/ISE.1993.0009","url":null,"abstract":"In this paper, techniques for machine learning of real-time control strategies are presented and reviewed from a control engineer's point of view. The objective is to present a consolidated view, both in the context of classical control theory and modern artificial intelligence practice. The review seeks to present the principal contributions to the field and the impact of these contributions on control engineering, particularly from the machine learning point of view. >","PeriodicalId":55165,"journal":{"name":"Engineering Intelligent Systems for Electrical Engineering and Communications","volume":"15 1","pages":"77-90"},"PeriodicalIF":0.0,"publicationDate":"1993-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83598460","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 life-cycle of complex engineering products involves many disciplines, each of which is responsible for a stage, or phase, in the design-to-production process. Concurrent engineering principles are capable of bringing together the traditionally disparate groups involved. However, in order to facilitate the essential sharing of product and process information, there is a need to provide a common environment capable of supporting the various requirements of designers, production workers and managers while ensuring that communication and appropriate support is maintained. This paper describes model-based planning research in the construction industry. At the heart of the system are a central generic computer model of a certain type of construction and a knowledge-based system able to apply engineering knowledge in the constraint satisfaction process, leading to a planned sequence of construction activities. The environment comprises the central representation and reasoning mechanism, a symbolic computer-aided design facility, and a commercial project planning and management system. The paper details our experiences in developing and applying the environment in the planning of ‘real-life’ construction projects.
{"title":"An integrated project planning environment","authors":"G. Winstanley, Michael A. Chacon, R. Levitt","doi":"10.1049/ISE.1993.0010","DOIUrl":"https://doi.org/10.1049/ISE.1993.0010","url":null,"abstract":"The life-cycle of complex engineering products involves many disciplines, each of which is responsible for a stage, or phase, in the design-to-production process. Concurrent engineering principles are capable of bringing together the traditionally disparate groups involved. However, in order to facilitate the essential sharing of product and process information, there is a need to provide a common environment capable of supporting the various requirements of designers, production workers and managers while ensuring that communication and appropriate support is maintained. This paper describes model-based planning research in the construction industry. At the heart of the system are a central generic computer model of a certain type of construction and a knowledge-based system able to apply engineering knowledge in the constraint satisfaction process, leading to a planned sequence of construction activities. The environment comprises the central representation and reasoning mechanism, a symbolic computer-aided design facility, and a commercial project planning and management system. The paper details our experiences in developing and applying the environment in the planning of ‘real-life’ construction projects.","PeriodicalId":55165,"journal":{"name":"Engineering Intelligent Systems for Electrical Engineering and Communications","volume":"19 1","pages":"91-106"},"PeriodicalIF":0.0,"publicationDate":"1993-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72675919","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}
L. Travé-Massuyès, K. Bousson, J. Evrard, F. Guerrin, B. Lucas, A. Missier, M. Tomasena, L. Zimmer
Qualitative models of dynamical systems fall into noncausal or causal approaches. The noncausal approach is widely used in part because traditional physics describes phenomena by means of symmetric functional relations. It supports the idea that causality can be ignored or inferred from the model itself. Nevertheless, when people explain how things work, they use causal relations. Representing causality explicitly makes it possible to take advantage of exogenous knowledge necessary for understanding the phenomena and supporting self-explanatory simulation. The basic concepts used in both approaches, in addition to the representation formalisms and algorithms, are discussed. >
{"title":"Non-causal versus causal qualitative modelling and simulation","authors":"L. Travé-Massuyès, K. Bousson, J. Evrard, F. Guerrin, B. Lucas, A. Missier, M. Tomasena, L. Zimmer","doi":"10.1049/ISE.1993.0015","DOIUrl":"https://doi.org/10.1049/ISE.1993.0015","url":null,"abstract":"Qualitative models of dynamical systems fall into noncausal or causal approaches. The noncausal approach is widely used in part because traditional physics describes phenomena by means of symmetric functional relations. It supports the idea that causality can be ignored or inferred from the model itself. Nevertheless, when people explain how things work, they use causal relations. Representing causality explicitly makes it possible to take advantage of exogenous knowledge necessary for understanding the phenomena and supporting self-explanatory simulation. The basic concepts used in both approaches, in addition to the representation formalisms and algorithms, are discussed. >","PeriodicalId":55165,"journal":{"name":"Engineering Intelligent Systems for Electrical Engineering and Communications","volume":"86 1","pages":"159-182"},"PeriodicalIF":0.0,"publicationDate":"1993-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78230794","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 concept for distributed control systems is outlined. The concept is based on a plant database containing descriptions of the plant and the control system. The database is object-based and supports multiple view of an objects. A demonstrator is presented where a DCS of this type is emulated. The demonstrator contains a number of control, monitoring and diagnosis applications that execute in real time against a simulation of a Steritherm sterilisation process.< >
{"title":"Using multi-view objects for structuring plant databases","authors":"Karl-Erik Årzén","doi":"10.1049/ISE.1993.0016","DOIUrl":"https://doi.org/10.1049/ISE.1993.0016","url":null,"abstract":"A concept for distributed control systems is outlined. The concept is based on a plant database containing descriptions of the plant and the control system. The database is object-based and supports multiple view of an objects. A demonstrator is presented where a DCS of this type is emulated. The demonstrator contains a number of control, monitoring and diagnosis applications that execute in real time against a simulation of a Steritherm sterilisation process.<\u0000 >","PeriodicalId":55165,"journal":{"name":"Engineering Intelligent Systems for Electrical Engineering and Communications","volume":"1 1","pages":"183-200"},"PeriodicalIF":0.0,"publicationDate":"1993-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72754727","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：