Pub Date : 1999-11-09DOI: 10.1109/ICCIMA.1999.798511
Pabitra Mitra, S. Mitra, S. Pal
The article describes a way of designing a hybrid system for classification and rule generation, integrating rough set theory with a fuzzy MLP using an evolutionary algorithm. An l-class classification problem is split into l two-class problems. Crude subnetworks are initially obtained for each of these two-class problems via rough set theory. These subnetworks are then combined and the final network is evolved using a GA with restricted mutation operator which utilizes the knowledge of the modular structure already generated, for faster convergence.
{"title":"Modular rough fuzzy MLP: evolutionary design","authors":"Pabitra Mitra, S. Mitra, S. Pal","doi":"10.1109/ICCIMA.1999.798511","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798511","url":null,"abstract":"The article describes a way of designing a hybrid system for classification and rule generation, integrating rough set theory with a fuzzy MLP using an evolutionary algorithm. An l-class classification problem is split into l two-class problems. Crude subnetworks are initially obtained for each of these two-class problems via rough set theory. These subnetworks are then combined and the final network is evolved using a GA with restricted mutation operator which utilizes the knowledge of the modular structure already generated, for faster convergence.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130271424","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}
Pub Date : 1999-09-23DOI: 10.1109/ICCIMA.1999.798505
M. Prashant, R. Siddharth, R. Kumar
We introduce a novel approach to cryptography by amalgamating two cryptic concepts: molecular genetics and image patterning. The genetic code for an organism is unique and yet to be cracked. Formed on the basis of just four nucleotide bases, numerous variations of characteristics are produced. At the same time, encoding using images gives rise to millions of patterns. We draw a parallel between a combination of these and cryptography, thereby attempting to achieve a high level of data security. The first phase of our encryption process deals with concepts from molecular genetics involving meiosis, fertilization, translation and mutation. Our next phase involves the encryption of data in the form of images. We have tested the algorithm to encode data and image files. Results are presented in the form of sample images.
{"title":"Formulation of an encryption algorithm on the basis of molecular genetics and image patterns","authors":"M. Prashant, R. Siddharth, R. Kumar","doi":"10.1109/ICCIMA.1999.798505","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798505","url":null,"abstract":"We introduce a novel approach to cryptography by amalgamating two cryptic concepts: molecular genetics and image patterning. The genetic code for an organism is unique and yet to be cracked. Formed on the basis of just four nucleotide bases, numerous variations of characteristics are produced. At the same time, encoding using images gives rise to millions of patterns. We draw a parallel between a combination of these and cryptography, thereby attempting to achieve a high level of data security. The first phase of our encryption process deals with concepts from molecular genetics involving meiosis, fertilization, translation and mutation. Our next phase involves the encryption of data in the form of images. We have tested the algorithm to encode data and image files. Results are presented in the form of sample images.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114993500","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}
Pub Date : 1999-09-23DOI: 10.1109/ICCIMA.1999.798497
A. Adami, G.B. Lazzarotto, E.F. Foppa, D.A. Couto Barone
This paper presents an implementation of a security system for elevators using speaker identification. The system uses a model of an artificial neural network called a multi-layer perceptron as a classifier. In this work, some features, such as pitch, formants, perceptual linear prediction coefficients, mel-cepstral coefficients and cepstral coefficients, are used to obtain the best results in the classification process.
{"title":"A comparison between features for a residential security prototype based on speaker identification with a model of artificial neural network","authors":"A. Adami, G.B. Lazzarotto, E.F. Foppa, D.A. Couto Barone","doi":"10.1109/ICCIMA.1999.798497","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798497","url":null,"abstract":"This paper presents an implementation of a security system for elevators using speaker identification. The system uses a model of an artificial neural network called a multi-layer perceptron as a classifier. In this work, some features, such as pitch, formants, perceptual linear prediction coefficients, mel-cepstral coefficients and cepstral coefficients, are used to obtain the best results in the classification process.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123807233","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}
Pub Date : 1999-09-23DOI: 10.1109/ICCIMA.1999.798507
D.G. Li, A. Watson
Optical thin films are used in a wide variety of optical components. An important aspect of modern thin film design work is the use of computers to match the multilayer parameters to a set of optical specifications such as a desired reflectance curve. There are several basic approaches to the design of thin film multilayer coatings. These include graphical, analytical and digital design methods. The latter, representing both local and global minimum seeking algorithms, are particularly powerful because they lend themselves to the design of coatings with much more complicated properties than is possible with the other methods. Many traditional optimization techniques, including simplex, gradient, and damped least squares method, have been used in this field. However, up to now it has not been possible to say if one of these techniques gives the optimal solution of the problem to be solved. A genetic algorithm is introduced to search for the optimal optical thin film design. The paper discusses the problem of thin film design in greater detail. It shows how a genetic algorithm can evolve the design for better performance. Examples of designs obtained by GA optimization techniques are given.
{"title":"Genetic algorithms in optical thin film optimisation design","authors":"D.G. Li, A. Watson","doi":"10.1109/ICCIMA.1999.798507","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798507","url":null,"abstract":"Optical thin films are used in a wide variety of optical components. An important aspect of modern thin film design work is the use of computers to match the multilayer parameters to a set of optical specifications such as a desired reflectance curve. There are several basic approaches to the design of thin film multilayer coatings. These include graphical, analytical and digital design methods. The latter, representing both local and global minimum seeking algorithms, are particularly powerful because they lend themselves to the design of coatings with much more complicated properties than is possible with the other methods. Many traditional optimization techniques, including simplex, gradient, and damped least squares method, have been used in this field. However, up to now it has not been possible to say if one of these techniques gives the optimal solution of the problem to be solved. A genetic algorithm is introduced to search for the optimal optical thin film design. The paper discusses the problem of thin film design in greater detail. It shows how a genetic algorithm can evolve the design for better performance. Examples of designs obtained by GA optimization techniques are given.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125277331","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}
Pub Date : 1999-09-23DOI: 10.1109/ICCIMA.1999.798571
M.C. Agarwal, K. Arvind, R. Kumar, L. Behera, I.J. Nagrath
This paper deals with the formulation of a height profile model for a vibratory tactile display unit using the concept of fractal dimensions and fractal Brownian motion. The paper discusses, in brief, the theory of fractals and the imaging process. The fractal dimension from image data is calculated using second-order statistics and the Fourier power spectrum. The image fractal model is then used to separate out the homogeneous and inhomogeneous regions. An algorithm is presented to compute the fractal dimension of various blocks; second-order statistics for homogeneous regions and another method for inhomogeneous regions. The algorithm is implemented on synthetic textures as well as on real images.
{"title":"Vibratory tactile display: a fractal Brownian approach","authors":"M.C. Agarwal, K. Arvind, R. Kumar, L. Behera, I.J. Nagrath","doi":"10.1109/ICCIMA.1999.798571","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798571","url":null,"abstract":"This paper deals with the formulation of a height profile model for a vibratory tactile display unit using the concept of fractal dimensions and fractal Brownian motion. The paper discusses, in brief, the theory of fractals and the imaging process. The fractal dimension from image data is calculated using second-order statistics and the Fourier power spectrum. The image fractal model is then used to separate out the homogeneous and inhomogeneous regions. An algorithm is presented to compute the fractal dimension of various blocks; second-order statistics for homogeneous regions and another method for inhomogeneous regions. The algorithm is implemented on synthetic textures as well as on real images.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122578619","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}
Pub Date : 1999-09-23DOI: 10.1109/ICCIMA.1999.798580
A. Bhaumik, S. Banerjee, J. Sil
The paper proposes a new supervised training algorithm for feedforward neural networks. Instead of applying single valued input-output information, multivalued information in the form of a K-dimensional vector (K>1) is applied to each node of the input-output layer. Weights are adjusted using the gradient decent approximation method in order to minimise the sum-squared error value at each node of the output layer. The training algorithm has been studied for wide range of input-output values and gives worthy results especially when the output vector is small enough compared to the input vector. The paper suggests a judicious method for choosing the bias component of the sigmoidal activation function used in the training algorithm.
{"title":"A new supervised training algorithm for generalised learning","authors":"A. Bhaumik, S. Banerjee, J. Sil","doi":"10.1109/ICCIMA.1999.798580","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798580","url":null,"abstract":"The paper proposes a new supervised training algorithm for feedforward neural networks. Instead of applying single valued input-output information, multivalued information in the form of a K-dimensional vector (K>1) is applied to each node of the input-output layer. Weights are adjusted using the gradient decent approximation method in order to minimise the sum-squared error value at each node of the output layer. The training algorithm has been studied for wide range of input-output values and gives worthy results especially when the output vector is small enough compared to the input vector. The paper suggests a judicious method for choosing the bias component of the sigmoidal activation function used in the training algorithm.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124122005","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}
Pub Date : 1999-09-23DOI: 10.1109/ICCIMA.1999.798504
A. Wu, P. Tam
According to the basic optimization principle of artificial neural networks, a novel kind of neural network model for solving the quadratic programming problem is presented. The methodology is based on the Lagrange multiplier theory in optimization and seeks to provide solutions satisfying the necessary conditions of optimality. The equilibrium point of the network satisfies the Kuhn-Tucker condition for the problem. The stability and convergency of the neural network is investigated and the strategy of the neural optimization is discussed. The feasibility of the neural network method is verified with computation examples. Results of the simulation of the neural network to solve optimum problems are presented to illustrate the computational power of the neural network method.
{"title":"Using neural network method computes quadratic optimization problems","authors":"A. Wu, P. Tam","doi":"10.1109/ICCIMA.1999.798504","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798504","url":null,"abstract":"According to the basic optimization principle of artificial neural networks, a novel kind of neural network model for solving the quadratic programming problem is presented. The methodology is based on the Lagrange multiplier theory in optimization and seeks to provide solutions satisfying the necessary conditions of optimality. The equilibrium point of the network satisfies the Kuhn-Tucker condition for the problem. The stability and convergency of the neural network is investigated and the strategy of the neural optimization is discussed. The feasibility of the neural network method is verified with computation examples. Results of the simulation of the neural network to solve optimum problems are presented to illustrate the computational power of the neural network method.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114760235","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}
Pub Date : 1999-09-23DOI: 10.1109/ICCIMA.1999.798540
P. Piamsa-nga, N. Alexandridis, S. Srakaew, G. Blankenship, S. Subramanya
Researchers are currently more interested in searching for fragments that are similar to a query, than a total data item that is similar to a query; the search interest is for "contains", not "is". The paper presents an O(logn) algorithm, called the "generalized virtual node (GVN)" algorithm; the GVN algorithm is a search algorithm for data fragments that have similar contents to that of a query. An example of the use of the GVN algorithm is in the search of a database of audio recordings for a few measures of a melody. Each audio clip is transformed into characteristic features and these features are stored in a hierarchical multidimensional structure, called a "k-tree". The k-tree is exploited to build a unified retrieval model for any types of multimedia data. The experimental results of this "in-clip" search algorithm on an audio database demonstrate a search quality is qualitatively and quantitatively acceptable, with a retrieval time faster than other algorithms, such as brute-force and partial matching.
{"title":"In-clip search algorithm for content-based audio retrieval","authors":"P. Piamsa-nga, N. Alexandridis, S. Srakaew, G. Blankenship, S. Subramanya","doi":"10.1109/ICCIMA.1999.798540","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798540","url":null,"abstract":"Researchers are currently more interested in searching for fragments that are similar to a query, than a total data item that is similar to a query; the search interest is for \"contains\", not \"is\". The paper presents an O(logn) algorithm, called the \"generalized virtual node (GVN)\" algorithm; the GVN algorithm is a search algorithm for data fragments that have similar contents to that of a query. An example of the use of the GVN algorithm is in the search of a database of audio recordings for a few measures of a melody. Each audio clip is transformed into characteristic features and these features are stored in a hierarchical multidimensional structure, called a \"k-tree\". The k-tree is exploited to build a unified retrieval model for any types of multimedia data. The experimental results of this \"in-clip\" search algorithm on an audio database demonstrate a search quality is qualitatively and quantitatively acceptable, with a retrieval time faster than other algorithms, such as brute-force and partial matching.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130062594","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}
Pub Date : 1999-09-23DOI: 10.1109/ICCIMA.1999.798553
R. Manivasakan, U. Desai, A. Karandikar
In this paper, we model the background network traffic by CIPP in an ATM multiplexer while simulating the end-to-end transport of real world VBR traffic over ATM networks. CIPP has been proposed by Manivasakan et al. (1999) for modeling broadband teletraffic. It was shown that, an empirical relationship exists between the parameter /spl rho/ of CIPP and estimated local Hurst parameter H. This feature is made use of to study the effect of degree of self-similarity of background network traffic on various performance measures. The modeling and simulation results show the effect of self-similarity of the background process (as measured by /spl rho/ of CIPP) on various performance measures parameterised by ATM multiplexer buffer size and decoder buffer size.
{"title":"End-to-end simulation of VBR traffic over ATM networks using CIPP network traffic model","authors":"R. Manivasakan, U. Desai, A. Karandikar","doi":"10.1109/ICCIMA.1999.798553","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798553","url":null,"abstract":"In this paper, we model the background network traffic by CIPP in an ATM multiplexer while simulating the end-to-end transport of real world VBR traffic over ATM networks. CIPP has been proposed by Manivasakan et al. (1999) for modeling broadband teletraffic. It was shown that, an empirical relationship exists between the parameter /spl rho/ of CIPP and estimated local Hurst parameter H. This feature is made use of to study the effect of degree of self-similarity of background network traffic on various performance measures. The modeling and simulation results show the effect of self-similarity of the background process (as measured by /spl rho/ of CIPP) on various performance measures parameterised by ATM multiplexer buffer size and decoder buffer size.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114338732","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}
Pub Date : 1999-09-23DOI: 10.1109/ICCIMA.1999.798533
L. Polkowski, A. Skowron
A logical calculus of granules is presented. This calculus provides a framework for the approximate synthesis of solutions under uncertainty by distributed systems. The presented calculus is based on rough mereology, a paradigm for approximate reasoning developed by the authors which blends together and relies on the mereology ideas of St. Lesniewski (see L. Polkowski and A. Skowron, Intell. Automation and Soft Comput., vol. 2, no. 2, 1996), rough set theory and fuzzy set theory.
{"title":"Logical calculi of rough-set granules in problems of approximate synthesis in distributed systems","authors":"L. Polkowski, A. Skowron","doi":"10.1109/ICCIMA.1999.798533","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798533","url":null,"abstract":"A logical calculus of granules is presented. This calculus provides a framework for the approximate synthesis of solutions under uncertainty by distributed systems. The presented calculus is based on rough mereology, a paradigm for approximate reasoning developed by the authors which blends together and relies on the mereology ideas of St. Lesniewski (see L. Polkowski and A. Skowron, Intell. Automation and Soft Comput., vol. 2, no. 2, 1996), rough set theory and fuzzy set theory.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125804248","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：