Pub Date : 1999-09-23DOI: 10.1109/ICCIMA.1999.798496
H. Diniz, L. de Andrade, A. de Carvalho, M. de Andrade
This paper reports the results of a neural architecture design approach for time series prediction. This approach applies some concepts of the Box-Jenkins (1970) method for data preprocessing and network design. The data used to verify the performance of these approaches were stock market time series of the Brazilian telecommunication company TELEBRAS.
{"title":"Architecture design of artificial neural networks based on Box & Jenkins models for time series prediction","authors":"H. Diniz, L. de Andrade, A. de Carvalho, M. de Andrade","doi":"10.1109/ICCIMA.1999.798496","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798496","url":null,"abstract":"This paper reports the results of a neural architecture design approach for time series prediction. This approach applies some concepts of the Box-Jenkins (1970) method for data preprocessing and network design. The data used to verify the performance of these approaches were stock market time series of the Brazilian telecommunication company TELEBRAS.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"4 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":"128241978","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.1999.798501
V. Karri
In recent years, radial basis function (RBF) neural networks have been shown to be versatile for performance prediction involving nonlinear processes. Machining performance prediction involving various process variables is a nonlinear problem. The conventional mechanics of the cutting approach for predicting thrust and torque in drilling makes use of the oblique cutting theory and an orthogonal cutting databank. The quantitative reliability, in these models, depends on the 'input parameters' along with the 'edge force' components from the orthogonal cutting databank for that given work material. By contrast, neural networks for drilling performance prediction have been shown to be successful for quantitative predictions with minimum number of inputs. In this paper, an RBF neural network architecture is proposed which uses process variables such as tool geometry and operating conditions to estimate thrust and torque in drilling. Extensive drilling tests are carried out to train the RBF network. The developed network is tested over a range of process variables to estimate thrust and torque. It is shown that, using the neural network architecture, the drilling forces are 'simultaneously' predicted to within 5% of the experimental values.
{"title":"RBF neural network for thrust and torque predictions in drilling operations","authors":"V. Karri","doi":"10.1109/ICCIMA.1999.798501","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798501","url":null,"abstract":"In recent years, radial basis function (RBF) neural networks have been shown to be versatile for performance prediction involving nonlinear processes. Machining performance prediction involving various process variables is a nonlinear problem. The conventional mechanics of the cutting approach for predicting thrust and torque in drilling makes use of the oblique cutting theory and an orthogonal cutting databank. The quantitative reliability, in these models, depends on the 'input parameters' along with the 'edge force' components from the orthogonal cutting databank for that given work material. By contrast, neural networks for drilling performance prediction have been shown to be successful for quantitative predictions with minimum number of inputs. In this paper, an RBF neural network architecture is proposed which uses process variables such as tool geometry and operating conditions to estimate thrust and torque in drilling. Extensive drilling tests are carried out to train the RBF network. The developed network is tested over a range of process variables to estimate thrust and torque. It is shown that, using the neural network architecture, the drilling forces are 'simultaneously' predicted to within 5% of the experimental values.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"30 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":"127132459","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.1999.798502
M. Valença, Teresa B Ludermir
Presents a new class of higher-order feedforward neural networks, called self-organized neuron block networks (SNBNs). SNBN networks are based on the inductive learning method (also called self-organization). These new networks are shown to uniformly approximate any continuous function with an arbitrary degree of accuracy. An SNBN provides a natural mechanism for incremental network growth, and we develop a constructive algorithm based on the inductive learning method for the network. Simulation results of forecasting, approximations of nonlinear functions and approximations of multivariate polynomials are given in order to highlight the capability of the network.
{"title":"Self-organization neurons blocks networks [sic]","authors":"M. Valença, Teresa B Ludermir","doi":"10.1109/ICCIMA.1999.798502","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798502","url":null,"abstract":"Presents a new class of higher-order feedforward neural networks, called self-organized neuron block networks (SNBNs). SNBN networks are based on the inductive learning method (also called self-organization). These new networks are shown to uniformly approximate any continuous function with an arbitrary degree of accuracy. An SNBN provides a natural mechanism for incremental network growth, and we develop a constructive algorithm based on the inductive learning method for the network. Simulation results of forecasting, approximations of nonlinear functions and approximations of multivariate polynomials are given in order to highlight the capability of the network.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"32 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":"125220179","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.1999.798516
D. Job, V. Shankararaman, J. Miller
Field programmable gate arrays (FPGAs) are a form of user-programmable logic devices that contain an array of logic gates. As there is no complete set of techniques for designing any FPGA program, researchers have been successful in evolving program designs using genetic algorithms (GAs). However, using GAs to generate software programs for FPGAs faces two main problems, namely scaling and errors. In this paper, we present our on-going research towards overcoming these problems by the integration of GAs with case-based reasoning (CBR). CBR is a problem-solving method that reuses old solutions to solve new problems. Our research work aims to apply CBR to reuse genetically evolved FPGA programs in order to develop larger programs at a reasonable computational expense. This paper describes our preliminary experiments and their results, which are encouraging.
{"title":"Combining CBR and GA for designing FPGAs","authors":"D. Job, V. Shankararaman, J. Miller","doi":"10.1109/ICCIMA.1999.798516","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798516","url":null,"abstract":"Field programmable gate arrays (FPGAs) are a form of user-programmable logic devices that contain an array of logic gates. As there is no complete set of techniques for designing any FPGA program, researchers have been successful in evolving program designs using genetic algorithms (GAs). However, using GAs to generate software programs for FPGAs faces two main problems, namely scaling and errors. In this paper, we present our on-going research towards overcoming these problems by the integration of GAs with case-based reasoning (CBR). CBR is a problem-solving method that reuses old solutions to solve new problems. Our research work aims to apply CBR to reuse genetically evolved FPGA programs in order to develop larger programs at a reasonable computational expense. This paper describes our preliminary experiments and their results, which are encouraging.","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":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132662700","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.1999.798518
M. Harn, V. Berzins, Luqi, B. Shultes
Proposes a formal model with mathematical definitions to represent and explore the complicated hierarchy and multidimensional structure of software evolution. This formalization of software evolution is based on a hypergraph and extended to an evolutionary hypergraph with different software evolution objects. In an evolutionary hypergraph, a top-level software evolution step can be refined into several finer software evolution steps and related top-level software evolution components can be decomposed into finer software evolution components. The hypergraph model, in conjunction with prototyping, can help developers describe and understand software evolution processes. We provide an example of multimedia system evolution to illustrate this formalization.
{"title":"A formal model for software evolution","authors":"M. Harn, V. Berzins, Luqi, B. Shultes","doi":"10.1109/ICCIMA.1999.798518","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798518","url":null,"abstract":"Proposes a formal model with mathematical definitions to represent and explore the complicated hierarchy and multidimensional structure of software evolution. This formalization of software evolution is based on a hypergraph and extended to an evolutionary hypergraph with different software evolution objects. In an evolutionary hypergraph, a top-level software evolution step can be refined into several finer software evolution steps and related top-level software evolution components can be decomposed into finer software evolution components. The hypergraph model, in conjunction with prototyping, can help developers describe and understand software evolution processes. We provide an example of multimedia system evolution to illustrate this formalization.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"8 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":"133109333","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.1999.798550
L. P. Scott, M. Pimentel
HyTime is an ISO standard for the formal specification of the structure of interchangeable documents. OOHyTime has been proposed as an object-oriented view of the standard, with the aim of facilitating both its understanding and use. Initially, this paper introduces HyTime and OOHyTime and follows with details of the OOHyTime view of the modules Measurement and Scheduling, which allow the specification of temporal and spatial relations. Next, the corresponding OOHyTime model for constructors of those HyTime modules that are needed to provide the specification of temporal relations relevant to the process of multimedia synchronization. The usage of the presented work in the context of the World Wide Web is also discussed.
{"title":"OOHyTime from the time-based point of view: the case of synchronization specification in multimedia documents","authors":"L. P. Scott, M. Pimentel","doi":"10.1109/ICCIMA.1999.798550","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798550","url":null,"abstract":"HyTime is an ISO standard for the formal specification of the structure of interchangeable documents. OOHyTime has been proposed as an object-oriented view of the standard, with the aim of facilitating both its understanding and use. Initially, this paper introduces HyTime and OOHyTime and follows with details of the OOHyTime view of the modules Measurement and Scheduling, which allow the specification of temporal and spatial relations. Next, the corresponding OOHyTime model for constructors of those HyTime modules that are needed to provide the specification of temporal relations relevant to the process of multimedia synchronization. The usage of the presented work in the context of the World Wide Web is also discussed.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"5 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":"125385603","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.1999.798530
M. L. Heras, J. Amat
Obtaining of 3D information from image sequences or stereoscopic images is a key problem, not completely solved, and any improvement in its resolution would bring to light a huge quantity of real life applications. The main difficulties lie in the matching of different elements of every image, the so-called correspondence problem. According to the trend of analysing singular points of the scene, we opt for a system based on the labelling and matching of contours and corners of the scene. Those points have some properties that make the method usable for most kinds of images. In order to obtain the contour information, a new algorithm is developed which is hardware implementable, able to autoadapt its parameters to external characteristics (such as as focus, illumination, contrast, etc.), and provides high reliability to the depth obtaining system. A specialised hardware is designed for contour obtaining and labelling with a fast and highly efficient pipeline architecture that gives the system a fast response time.
{"title":"Vision system with depth obtaining capabilities","authors":"M. L. Heras, J. Amat","doi":"10.1109/ICCIMA.1999.798530","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798530","url":null,"abstract":"Obtaining of 3D information from image sequences or stereoscopic images is a key problem, not completely solved, and any improvement in its resolution would bring to light a huge quantity of real life applications. The main difficulties lie in the matching of different elements of every image, the so-called correspondence problem. According to the trend of analysing singular points of the scene, we opt for a system based on the labelling and matching of contours and corners of the scene. Those points have some properties that make the method usable for most kinds of images. In order to obtain the contour information, a new algorithm is developed which is hardware implementable, able to autoadapt its parameters to external characteristics (such as as focus, illumination, contrast, etc.), and provides high reliability to the depth obtaining system. A specialised hardware is designed for contour obtaining and labelling with a fast and highly efficient pipeline architecture that gives the system a fast response time.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"43 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":"130136853","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.1999.798494
M. Ivanović, Z. Budimac
In this paper, a proposition of an agent-oriented workflow framework which merges information flows and maintenance with decision-making processes is presented. The proposed framework can be applied in different institutions, and an application in the agricultural domain is suggested. The amalgamation of agent and workflow technologies is done in order to increase efficiency and to improve the decision-making process.
{"title":"A framework for agent-oriented workflow in agriculture","authors":"M. Ivanović, Z. Budimac","doi":"10.1109/ICCIMA.1999.798494","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798494","url":null,"abstract":"In this paper, a proposition of an agent-oriented workflow framework which merges information flows and maintenance with decision-making processes is presented. The proposed framework can be applied in different institutions, and an application in the agricultural domain is suggested. The amalgamation of agent and workflow technologies is done in order to increase efficiency and to improve the decision-making process.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"89 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":"130951588","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.1999.798575
J. Stanczak, J. Mulawka, B. K. Verma
In this paper we propose a new method of tuning the probabilities of the genetic operators. We assume that every member of the optimized population conducts his own ranking of genetic operator qualities. This ranking becomes a base to compute the probabilities of appearance and execution of genetic operators. This set of probabilities is a base of experience of every individual and according to this it chooses the operator in every iteration of the algorithm. Due to this experience one can maximize the chance of offspring survival.
{"title":"Genetic algorithms with adaptive probabilities of operator selection","authors":"J. Stanczak, J. Mulawka, B. K. Verma","doi":"10.1109/ICCIMA.1999.798575","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798575","url":null,"abstract":"In this paper we propose a new method of tuning the probabilities of the genetic operators. We assume that every member of the optimized population conducts his own ranking of genetic operator qualities. This ranking becomes a base to compute the probabilities of appearance and execution of genetic operators. This set of probabilities is a base of experience of every individual and according to this it chooses the operator in every iteration of the algorithm. Due to this experience one can maximize the chance of offspring survival.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"1 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":"130205158","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.1999.798544
Hong Yu
This paper proposes a new image retrieval scheme that works directly on compressed image (JPEG) databases. As we know, a large percentage of the image databases are stored in compressed image format, such as JPEG format. In addition, about half of the images on the Internet are also in JPEG format. Thus, image retrieval systems that require JPEG decompression greatly limit the speed of image searching. Subsequently, new methodologies for retrieving of images without JPEG decoding is needed for Web image search and compressed image database retrieval. We propose a new metric, Q-distance, that can be utilized to measure the distance between two compressed images. A system that uses Q-distance for fast image retrieval is also presented. Experiment results show that Q-distance is robust against variation and this new retrieval scheme, which directly works in the compressed image domain, is fast to execute and suitable for Web image searching and retrieval.
{"title":"Visual image retrieval on compressed domain with Q-distance","authors":"Hong Yu","doi":"10.1109/ICCIMA.1999.798544","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798544","url":null,"abstract":"This paper proposes a new image retrieval scheme that works directly on compressed image (JPEG) databases. As we know, a large percentage of the image databases are stored in compressed image format, such as JPEG format. In addition, about half of the images on the Internet are also in JPEG format. Thus, image retrieval systems that require JPEG decompression greatly limit the speed of image searching. Subsequently, new methodologies for retrieving of images without JPEG decoding is needed for Web image search and compressed image database retrieval. We propose a new metric, Q-distance, that can be utilized to measure the distance between two compressed images. A system that uses Q-distance for fast image retrieval is also presented. Experiment results show that Q-distance is robust against variation and this new retrieval scheme, which directly works in the compressed image domain, is fast to execute and suitable for Web image searching and retrieval.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"1 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":"127037671","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：