Sebastián A. Ríos, J. D. Velásquez, Eduardo S. Vera, H. Yasuda, T. Aoki
Web systems have reached a very important role in today's business world. Every day organizations fight to keep their present clients and to gain new ones. In order to accomplish this goal it is very important to make precise changes in the Web site content. However, the development of these improvements is a complex and specialized task because of the nature of the Web data itself. We propose a novel approach to successfully make changes to improve the Web site content using text mining. We use a self organizing feature map (SOFM) to find the most relevant text content, and then we propose a reverse clustering analysis in order to extract the most significant pages of the whole Web site. The effectiveness of this method was experimentally tested in a real Web site.
{"title":"Improving the Web text content by extracting significant pages into a Web site","authors":"Sebastián A. Ríos, J. D. Velásquez, Eduardo S. Vera, H. Yasuda, T. Aoki","doi":"10.1109/ISDA.2005.55","DOIUrl":"https://doi.org/10.1109/ISDA.2005.55","url":null,"abstract":"Web systems have reached a very important role in today's business world. Every day organizations fight to keep their present clients and to gain new ones. In order to accomplish this goal it is very important to make precise changes in the Web site content. However, the development of these improvements is a complex and specialized task because of the nature of the Web data itself. We propose a novel approach to successfully make changes to improve the Web site content using text mining. We use a self organizing feature map (SOFM) to find the most relevant text content, and then we propose a reverse clustering analysis in order to extract the most significant pages of the whole Web site. The effectiveness of this method was experimentally tested in a real Web site.","PeriodicalId":345842,"journal":{"name":"5th International Conference on Intelligent Systems Design and Applications (ISDA'05)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129024071","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}
Clustering is a classification process in data mining, very used mainly for grouping of continuous values. The traditional techniques of clustering such as fuzzy C-means clustering (FCM), create groups that don't have, many times, practical sense to the user. Relative information gain has been used with success in classification applications, for instance the induction of decision tree. Our goal is to modify the way how the distance is calculated among elements in the FCM algorithm, adding to the calculation the relative information gain. The elements are grouped according to a categorical field selected from the own training dataset. Therefore groups are created and induced according to the gain criterion calculated among the elements and the categorical field.
{"title":"Using gain ratio distance (GRD) to induce clustering","authors":"Claudio Ratke, D. Andrade","doi":"10.1109/ISDA.2005.97","DOIUrl":"https://doi.org/10.1109/ISDA.2005.97","url":null,"abstract":"Clustering is a classification process in data mining, very used mainly for grouping of continuous values. The traditional techniques of clustering such as fuzzy C-means clustering (FCM), create groups that don't have, many times, practical sense to the user. Relative information gain has been used with success in classification applications, for instance the induction of decision tree. Our goal is to modify the way how the distance is calculated among elements in the FCM algorithm, adding to the calculation the relative information gain. The elements are grouped according to a categorical field selected from the own training dataset. Therefore groups are created and induced according to the gain criterion calculated among the elements and the categorical field.","PeriodicalId":345842,"journal":{"name":"5th International Conference on Intelligent Systems Design and Applications (ISDA'05)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125166565","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 presents a method for enforcing image segmentation. Method presented here is a part of a wider research - an image understanding system. Regions of the image, extracted by a basic segmentation process, belong to certain classes. Spatial relations are calculated for extracted regions of the image, according to the declared knowledge. Declarative knowledge in the form of semantic rules is used as a second step to eliminate errors in the basic segmentation process. The approach is generic, but in this case it is used for melanoma skin lesions diagnosis.
{"title":"Melanocytic lesion images segmentation enforcing by spatial relations based declarative knowledge","authors":"H. Kwasnicka, M. Paradowski","doi":"10.1109/ISDA.2005.63","DOIUrl":"https://doi.org/10.1109/ISDA.2005.63","url":null,"abstract":"This paper presents a method for enforcing image segmentation. Method presented here is a part of a wider research - an image understanding system. Regions of the image, extracted by a basic segmentation process, belong to certain classes. Spatial relations are calculated for extracted regions of the image, according to the declared knowledge. Declarative knowledge in the form of semantic rules is used as a second step to eliminate errors in the basic segmentation process. The approach is generic, but in this case it is used for melanoma skin lesions diagnosis.","PeriodicalId":345842,"journal":{"name":"5th International Conference on Intelligent Systems Design and Applications (ISDA'05)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126016733","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}
Protein function is closely related to the structure of interaction site of the protein. Proteins that have similar structure at interaction sites often bind to the same compound. We have proposed a method for retrieving similar interaction protein using profiles that represent the features of the interaction site binding to a certain compound. Since it takes a long time to extract a profile manually, automatic extraction of a profile from the protein structure data is highly required. This paper presents a method for automatic profile extraction based on frequency distribution of atoms. The profile extracted by using the proposed method was closely similar to the profile extracted manually. Retrieval experiment shows that the accuracy of identifying correct interaction sites using a profile generated by the proposed method is equivalent to the result using a manually constructed profile.
{"title":"Automatic profile extraction based on frequency distribution of atoms for retrieving similar interaction protein","authors":"Mariko Matsumoto, Yusuke Nonomura, T. Ohkawa","doi":"10.1109/ISDA.2005.29","DOIUrl":"https://doi.org/10.1109/ISDA.2005.29","url":null,"abstract":"Protein function is closely related to the structure of interaction site of the protein. Proteins that have similar structure at interaction sites often bind to the same compound. We have proposed a method for retrieving similar interaction protein using profiles that represent the features of the interaction site binding to a certain compound. Since it takes a long time to extract a profile manually, automatic extraction of a profile from the protein structure data is highly required. This paper presents a method for automatic profile extraction based on frequency distribution of atoms. The profile extracted by using the proposed method was closely similar to the profile extracted manually. Retrieval experiment shows that the accuracy of identifying correct interaction sites using a profile generated by the proposed method is equivalent to the result using a manually constructed profile.","PeriodicalId":345842,"journal":{"name":"5th International Conference on Intelligent Systems Design and Applications (ISDA'05)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131655204","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}
Many studies of man-machine interaction using eye trackers have been tackled over recent decades. In this paper, we present a new learning system to estimate user interest with gaze sensory information. In short, a statistical learning scheme, especially the variational Bayes (VB), is incorporated for building probabilistic model parameters, dealing with the uncertainty of estimated user interest. Several computational results show how the VB can cope with user interest estimation, by selectively modeling their uncertainty.
{"title":"Learning to estimate user interest utilizing the variational Bayes estimator","authors":"Taiji Suzuki, T. Koshizen, K. Aihara, H. Tsujino","doi":"10.1109/ISDA.2005.59","DOIUrl":"https://doi.org/10.1109/ISDA.2005.59","url":null,"abstract":"Many studies of man-machine interaction using eye trackers have been tackled over recent decades. In this paper, we present a new learning system to estimate user interest with gaze sensory information. In short, a statistical learning scheme, especially the variational Bayes (VB), is incorporated for building probabilistic model parameters, dealing with the uncertainty of estimated user interest. Several computational results show how the VB can cope with user interest estimation, by selectively modeling their uncertainty.","PeriodicalId":345842,"journal":{"name":"5th International Conference on Intelligent Systems Design and Applications (ISDA'05)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131243774","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 distribution of the genetic programming algorithm improves the efficiency of the search for the solution, but additional parameters of this distribution are undesirable. This paper presents the analysis of early experimental results of using flocking to control interactions among the distributed subpopulations so less human intervention is needed The possibility to set up migration parameters dynamically at the run time brings the distributed genetic programming algorithm to the same level of automation as standard genetic programming while keeping the increased performance of the distributed GP. The paper discusses the nature of the required additional computations of the GP algorithm when adapting flocking for migration control. The positive empirical results support the idea of mixing both search techniques together.
{"title":"Flocking of subpopulations in distributed genetic programming","authors":"Giedrius Paulikas, D. Rubliauskas","doi":"10.1109/ISDA.2005.46","DOIUrl":"https://doi.org/10.1109/ISDA.2005.46","url":null,"abstract":"The distribution of the genetic programming algorithm improves the efficiency of the search for the solution, but additional parameters of this distribution are undesirable. This paper presents the analysis of early experimental results of using flocking to control interactions among the distributed subpopulations so less human intervention is needed The possibility to set up migration parameters dynamically at the run time brings the distributed genetic programming algorithm to the same level of automation as standard genetic programming while keeping the increased performance of the distributed GP. The paper discusses the nature of the required additional computations of the GP algorithm when adapting flocking for migration control. The positive empirical results support the idea of mixing both search techniques together.","PeriodicalId":345842,"journal":{"name":"5th International Conference on Intelligent Systems Design and Applications (ISDA'05)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127814275","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}
Our paper presents a modular architecture for a natural dialogue system. The architecture is applied in the construction of Logo - a dialogue system for Polish, based on the Discourse Representation theory, implementing some aspects of the pragmatic analysis and enabling communication with an agent acting in the virtual reality of a blocks world. Logo deals also with the selected issues of coreference resolution. The proposed architecture is intended to be flexible and open for utilisation of diverged language resources.
{"title":"Logo - the modular conversational agent understanding Polish","authors":"Maciej Piasecki, Ireneusz Matysiak, A. Rusak","doi":"10.1109/ISDA.2005.60","DOIUrl":"https://doi.org/10.1109/ISDA.2005.60","url":null,"abstract":"Our paper presents a modular architecture for a natural dialogue system. The architecture is applied in the construction of Logo - a dialogue system for Polish, based on the Discourse Representation theory, implementing some aspects of the pragmatic analysis and enabling communication with an agent acting in the virtual reality of a blocks world. Logo deals also with the selected issues of coreference resolution. The proposed architecture is intended to be flexible and open for utilisation of diverged language resources.","PeriodicalId":345842,"journal":{"name":"5th International Conference on Intelligent Systems Design and Applications (ISDA'05)","volume":"234 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126966502","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}
J. Grzymala-Busse, Z. Hippe, T. Mroczek, E. Rój, B. Skowronski
Our objective was to investigate an influence of some factors contributing to the bed caking tendency during the hop extraction process. It is important to keep the process free of bed caking since it prolongs extraction. In our research, three data sets describing the extraction process were used for knowledge discovery using rule induction and generation of belief networks. Experts analyzed discovered knowledge from the view point of potential applications. Finally, an error rate for all used methods was estimated using ten-fold cross validation.
{"title":"Data mining analysis of granular bed caking during hop extraction","authors":"J. Grzymala-Busse, Z. Hippe, T. Mroczek, E. Rój, B. Skowronski","doi":"10.1109/ISDA.2005.36","DOIUrl":"https://doi.org/10.1109/ISDA.2005.36","url":null,"abstract":"Our objective was to investigate an influence of some factors contributing to the bed caking tendency during the hop extraction process. It is important to keep the process free of bed caking since it prolongs extraction. In our research, three data sets describing the extraction process were used for knowledge discovery using rule induction and generation of belief networks. Experts analyzed discovered knowledge from the view point of potential applications. Finally, an error rate for all used methods was estimated using ten-fold cross validation.","PeriodicalId":345842,"journal":{"name":"5th International Conference on Intelligent Systems Design and Applications (ISDA'05)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130923468","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}
K. Grudzień, A. Romanowski, D. Sankowski, R. Aykroyd, Richard A. Williams
Advanced statistical modelling such as Bayesian framework is a powerful methodology and gives great flexibility in terms of physical phenomena modelling. Unfortunately it is usually associated with very time and resource consuming computing. Therefore it was avoided by engineers in the past. Nowadays, rapid development of computer capabilities enables use of such methods. Algorithms reported here are based on Markov chain Monte Carlo (MCMC) methods applied to Bayesian modelling. The important factor is highly iterative approach enabling direct desired parameters estimation, hence omitting the phase of image reconstruction. This property has an important feature of making feasible implementation of automatic industrial process control systems based on process tomography.
{"title":"Advanced statistical computing for capacitance tomography as a monitoring and control tool","authors":"K. Grudzień, A. Romanowski, D. Sankowski, R. Aykroyd, Richard A. Williams","doi":"10.1109/ISDA.2005.19","DOIUrl":"https://doi.org/10.1109/ISDA.2005.19","url":null,"abstract":"Advanced statistical modelling such as Bayesian framework is a powerful methodology and gives great flexibility in terms of physical phenomena modelling. Unfortunately it is usually associated with very time and resource consuming computing. Therefore it was avoided by engineers in the past. Nowadays, rapid development of computer capabilities enables use of such methods. Algorithms reported here are based on Markov chain Monte Carlo (MCMC) methods applied to Bayesian modelling. The important factor is highly iterative approach enabling direct desired parameters estimation, hence omitting the phase of image reconstruction. This property has an important feature of making feasible implementation of automatic industrial process control systems based on process tomography.","PeriodicalId":345842,"journal":{"name":"5th International Conference on Intelligent Systems Design and Applications (ISDA'05)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126625313","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 development of the mass flow rate measurements in the industrial systems using a twin-planes electrical capacitance tomography (ECT) system is presented. The mass flow measurement is based on cross-section decomposition into homogenous regions and virtual channel is then defined as connecting of two homogenous regions of different sensor planes. The decomposition has been obtained by using a stochastic flow model. As a result the set of virtual channels is obtained instead the complex flow inside a single physical channel. The authors present the results of investigation for turbulent flow propagation using the virtual channel concept also.
{"title":"Mass flow measurements based on a virtual channel concept","authors":"D. Sankowski, V. Mosorov, K. Grudzień","doi":"10.1109/ISDA.2005.62","DOIUrl":"https://doi.org/10.1109/ISDA.2005.62","url":null,"abstract":"The development of the mass flow rate measurements in the industrial systems using a twin-planes electrical capacitance tomography (ECT) system is presented. The mass flow measurement is based on cross-section decomposition into homogenous regions and virtual channel is then defined as connecting of two homogenous regions of different sensor planes. The decomposition has been obtained by using a stochastic flow model. As a result the set of virtual channels is obtained instead the complex flow inside a single physical channel. The authors present the results of investigation for turbulent flow propagation using the virtual channel concept also.","PeriodicalId":345842,"journal":{"name":"5th International Conference on Intelligent Systems Design and Applications (ISDA'05)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126511923","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：