In the paper the experimental study of the influence of parameters on the final results of the rule extraction method from neural network for classification problem is described. The method is based on evolutionary approach, where for each class evolves separate population. The paper starts on the presentation of the basic concepts of the method. Next, the results of experiments are described. They examine the influence of genetic parameters. Then, the parameters that affect the rule extraction efficiency are tested. All experiments are made with using UCI data sets. At the end, some general conclusion concerning the role of the parameters and their influence on the final results are formulated.
{"title":"The influence of parameters in evolutionary based rule extraction method from neural network","authors":"Urszula Markowska-Kaczmar","doi":"10.1109/ISDA.2005.91","DOIUrl":"https://doi.org/10.1109/ISDA.2005.91","url":null,"abstract":"In the paper the experimental study of the influence of parameters on the final results of the rule extraction method from neural network for classification problem is described. The method is based on evolutionary approach, where for each class evolves separate population. The paper starts on the presentation of the basic concepts of the method. Next, the results of experiments are described. They examine the influence of genetic parameters. Then, the parameters that affect the rule extraction efficiency are tested. All experiments are made with using UCI data sets. At the end, some general conclusion concerning the role of the parameters and their influence on the final results are formulated.","PeriodicalId":345842,"journal":{"name":"5th International Conference on Intelligent Systems Design and Applications (ISDA'05)","volume":"258 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":"121348127","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 term visual arts data mining defines a framework for Data Mining techniques applied to learn and discover patterns in visual arts collections. Its results can be widely used by visual arts market, museums and art galleries. This paper proposes a multi-label voting algorithm to identify similar visual arts objects studied using neuro-fuzzy classifiers. The algorithm integrates predictions of experts trained on clusters of heterogeneous collections of data. It combines predictions of the modular ensemble of classifiers by identifying hierarchical votes for most similar classes. Experimental results show better performances than individual global models. Relationships between some visual arts patterns are inferred. We also compare the results obtained for few fusion versions of our algorithm with other methods applied on IRIS and Glass benchmarks. The results show that our algorithm has at least similar performance to other schemes on all data sets and adds flexibility to cases where classifiers' expertise overlaps on unions of disjunctive sets of the universe of discourse.
{"title":"A multi-label voting algorithm for neuro-fuzzy classifier ensembles with applications in visual arts data mining","authors":"D. Neagu, Shuai Zhang, C. Balescu","doi":"10.1109/ISDA.2005.10","DOIUrl":"https://doi.org/10.1109/ISDA.2005.10","url":null,"abstract":"The term visual arts data mining defines a framework for Data Mining techniques applied to learn and discover patterns in visual arts collections. Its results can be widely used by visual arts market, museums and art galleries. This paper proposes a multi-label voting algorithm to identify similar visual arts objects studied using neuro-fuzzy classifiers. The algorithm integrates predictions of experts trained on clusters of heterogeneous collections of data. It combines predictions of the modular ensemble of classifiers by identifying hierarchical votes for most similar classes. Experimental results show better performances than individual global models. Relationships between some visual arts patterns are inferred. We also compare the results obtained for few fusion versions of our algorithm with other methods applied on IRIS and Glass benchmarks. The results show that our algorithm has at least similar performance to other schemes on all data sets and adds flexibility to cases where classifiers' expertise overlaps on unions of disjunctive sets of the universe of discourse.","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":"127393066","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 aim of this paper is to present some remarks on computing maximal consistent extensions of dynamic information systems. Dynamic information systems can be used as a tool for description of concurrent systems. In this case, they include the knowledge about global states and transitions between them observed in given concurrent systems. The task of creating a maximal consistent extension is to find all global states and all transitions between them which are consistent with the knowledge included in data tables representing a dynamic information system. A method for computing such an extension is given. The method presented here seems to be more efficient than methods presented earlier in the literature. Our approach is based on the rough set theory.
{"title":"Some remarks on computing consistent extensions of dynamic information systems","authors":"Z. Suraj, K. Pancerz","doi":"10.1109/ISDA.2005.84","DOIUrl":"https://doi.org/10.1109/ISDA.2005.84","url":null,"abstract":"The aim of this paper is to present some remarks on computing maximal consistent extensions of dynamic information systems. Dynamic information systems can be used as a tool for description of concurrent systems. In this case, they include the knowledge about global states and transitions between them observed in given concurrent systems. The task of creating a maximal consistent extension is to find all global states and all transitions between them which are consistent with the knowledge included in data tables representing a dynamic information system. A method for computing such an extension is given. The method presented here seems to be more efficient than methods presented earlier in the literature. Our approach is based on the rough set theory.","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":"131081190","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}
Iris detection is a crucial part of an iris recognition system. One of the main issues in iris segmentation is coping with occlusions that happen due to eyelids and eyelashes. In this paper, only the lower part of the iris is utilized for recognition. Wavelet based texture features along with a mixed Hamming; harmonic mean distance classifier is used for identification. It is observed that relying in a smaller but more reliable part of the iris, though reducing the net amount of information, improves the overall performance. Experimental results on CASIA database show that the method has a promising performance with an accuracy of more than 99%.
{"title":"A half-eye wavelet based method for iris recognition","authors":"A. Poursaberi, Babak Nadjar Araabi","doi":"10.1109/ISDA.2005.6","DOIUrl":"https://doi.org/10.1109/ISDA.2005.6","url":null,"abstract":"Iris detection is a crucial part of an iris recognition system. One of the main issues in iris segmentation is coping with occlusions that happen due to eyelids and eyelashes. In this paper, only the lower part of the iris is utilized for recognition. Wavelet based texture features along with a mixed Hamming; harmonic mean distance classifier is used for identification. It is observed that relying in a smaller but more reliable part of the iris, though reducing the net amount of information, improves the overall performance. Experimental results on CASIA database show that the method has a promising performance with an accuracy of more than 99%.","PeriodicalId":345842,"journal":{"name":"5th International Conference on Intelligent Systems Design and Applications (ISDA'05)","volume":"15 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":"122349784","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}
Implementation of data mining applications is a challenging and complicated task, and the applications are often built from scratch. In this paper, a component-based application framework, called smart archive (SA) designed for implementing data mining applications, is presented. SA provides functionality common to most data mining applications and components for utilizing history information. Using SA, it is possible to build high-quality applications with shorter development times by configuring the framework to process application-specific data. The architecture, the components, the implementation and the design principles of the framework are presented. The advantages of a framework-based implementation are demonstrated by presenting a case study which compares the framework approach to implementing a real-world application with the option of building an equivalent application from scratch. In conclusion, the paper presents a lucid framework for creating data mining applications and illustrates the importance and advantages of using the presented approach.
{"title":"Smart archive: a component-based data mining application framework","authors":"P. Laurinen, L. Tuovinen, J. Röning","doi":"10.1109/ISDA.2005.83","DOIUrl":"https://doi.org/10.1109/ISDA.2005.83","url":null,"abstract":"Implementation of data mining applications is a challenging and complicated task, and the applications are often built from scratch. In this paper, a component-based application framework, called smart archive (SA) designed for implementing data mining applications, is presented. SA provides functionality common to most data mining applications and components for utilizing history information. Using SA, it is possible to build high-quality applications with shorter development times by configuring the framework to process application-specific data. The architecture, the components, the implementation and the design principles of the framework are presented. The advantages of a framework-based implementation are demonstrated by presenting a case study which compares the framework approach to implementing a real-world application with the option of building an equivalent application from scratch. In conclusion, the paper presents a lucid framework for creating data mining applications and illustrates the importance and advantages of using the presented approach.","PeriodicalId":345842,"journal":{"name":"5th International Conference on Intelligent Systems Design and Applications (ISDA'05)","volume":"44 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":"122017194","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}
Neural networks are widely used in time-series forecasting. One of the issues that arise in neural networks applications is that when a neural network is trained for too long the quality of the predictions tends to deteriorate. To overcome this problem various methods of early stopping are employed. This paper proposes a new approach to early stopping issue in neural network training. In the approach presented the validation series is chosen based on its mean dynamic correlation with forecasted series. The approach is verified by application to macroeconomic data where suitable sets of series are commonly available.
{"title":"Dynamic correlation approach to early stopping in artificial neural network training: macroeconomic forecasting example","authors":"Krzysztof Michalak, R. Raciborski","doi":"10.1109/ISDA.2005.41","DOIUrl":"https://doi.org/10.1109/ISDA.2005.41","url":null,"abstract":"Neural networks are widely used in time-series forecasting. One of the issues that arise in neural networks applications is that when a neural network is trained for too long the quality of the predictions tends to deteriorate. To overcome this problem various methods of early stopping are employed. This paper proposes a new approach to early stopping issue in neural network training. In the approach presented the validation series is chosen based on its mean dynamic correlation with forecasted series. The approach is verified by application to macroeconomic data where suitable sets of series are commonly available.","PeriodicalId":345842,"journal":{"name":"5th International Conference on Intelligent Systems Design and Applications (ISDA'05)","volume":"63 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":"123369287","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}
Bayesian techniques are attractive and viable tools for modeling complex stochastic processes in general and the groundwater contamination process in particular. This is mainly because these techniques do not only emphasize the stochastic nature of this process but also the precision and the accuracy of the tested methods used by environmental laboratories. In this work, we describe the development and application of a prototype dynamic Bayesian network (DBN) that models groundwater quality in order to assess and predict the impact of pollutants on the water column.
{"title":"Modeling groundwater quality with Bayesian techniques","authors":"K. Shihab","doi":"10.1109/ISDA.2005.65","DOIUrl":"https://doi.org/10.1109/ISDA.2005.65","url":null,"abstract":"Bayesian techniques are attractive and viable tools for modeling complex stochastic processes in general and the groundwater contamination process in particular. This is mainly because these techniques do not only emphasize the stochastic nature of this process but also the precision and the accuracy of the tested methods used by environmental laboratories. In this work, we describe the development and application of a prototype dynamic Bayesian network (DBN) that models groundwater quality in order to assess and predict the impact of pollutants on the water column.","PeriodicalId":345842,"journal":{"name":"5th International Conference on Intelligent Systems Design and Applications (ISDA'05)","volume":"13 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":"122773278","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 accurate input-output universe of discourse (UOD) on which membership functions are defined is hard to acquire, especially for nonlinear multi-input and multi-output (MIMO) systems, and control accuracy will reduce greatly in the steady state due to limited fuzzy control rules. This paper presents a design scheme for the adaptive fuzzy logic controllers to control a MIMO system with online changeable input-output UOD of the controller, which could solve two problems mentioned above to a great extent. We obtain fuzzy inference rules that are defined by the error and change of error to describe the variation law of the input-output UOD according to the current trend of the controlled process, so the proper widths of the UOD can be derived from the fuzzy inference rules dynamically in real-time. Simulation results for the nonlinear MIMO system show the effectiveness of the proposed fuzzy logic controller.
{"title":"Adaptive fuzzy logic controller with rule-based changeable universe of discourse for a nonlinear MIMO system","authors":"Yi Wang, Huiwen Deng, Zheng Chen","doi":"10.1109/ISDA.2005.18","DOIUrl":"https://doi.org/10.1109/ISDA.2005.18","url":null,"abstract":"The accurate input-output universe of discourse (UOD) on which membership functions are defined is hard to acquire, especially for nonlinear multi-input and multi-output (MIMO) systems, and control accuracy will reduce greatly in the steady state due to limited fuzzy control rules. This paper presents a design scheme for the adaptive fuzzy logic controllers to control a MIMO system with online changeable input-output UOD of the controller, which could solve two problems mentioned above to a great extent. We obtain fuzzy inference rules that are defined by the error and change of error to describe the variation law of the input-output UOD according to the current trend of the controlled process, so the proper widths of the UOD can be derived from the fuzzy inference rules dynamically in real-time. Simulation results for the nonlinear MIMO system show the effectiveness of the proposed fuzzy logic controller.","PeriodicalId":345842,"journal":{"name":"5th International Conference on Intelligent Systems Design and Applications (ISDA'05)","volume":"28 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":"131618428","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the paper a concept of active hypercontours as well as a formalized description of contextual classification and relationship between them are presented. The idea of active hypercontours generalizes traditional active contour methods which are extensively developed in image analysis. The proposed concepts can enable an incorporation of techniques specific for traditional contextual and non-contextual classification problems to active contour approach and vice versa.
{"title":"Active hypercontours and contextual classification","authors":"Arkadiusz Tomczyk","doi":"10.1109/ISDA.2005.16","DOIUrl":"https://doi.org/10.1109/ISDA.2005.16","url":null,"abstract":"In the paper a concept of active hypercontours as well as a formalized description of contextual classification and relationship between them are presented. The idea of active hypercontours generalizes traditional active contour methods which are extensively developed in image analysis. The proposed concepts can enable an incorporation of techniques specific for traditional contextual and non-contextual classification problems to active contour approach and vice versa.","PeriodicalId":345842,"journal":{"name":"5th International Conference on Intelligent Systems Design and Applications (ISDA'05)","volume":"30 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":"129977914","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 presents an attempt to match signal processing derived features to the higher-level (linguistic) description of timbre in order to support the timbre driven retrieval of violins. The experiments are performed on a set of 53 instruments recorded during the 10/sup th/ Henryk Wieniawski International Violinmakers Competition held in Poznan, Poland, in 2001. The results add to the recent research approach to apply computational intelligence to bridge the semantic and conceptual gap, which exists between the low level description and higher-level interpretation of multimedia. The taxonomy used for violin voices is correlated with objective attributes of entirely distinct character so that semantically disjoint categories are created, providing supportive cues for further analysis. The results should deliver new, enriching aspect to the design of methodology of inferring preference models from the objective characteristics of digital media.
{"title":"Towards timbre-driven semantic retrieval of violins","authors":"E. Lukasik","doi":"10.1109/ISDA.2005.94","DOIUrl":"https://doi.org/10.1109/ISDA.2005.94","url":null,"abstract":"The paper presents an attempt to match signal processing derived features to the higher-level (linguistic) description of timbre in order to support the timbre driven retrieval of violins. The experiments are performed on a set of 53 instruments recorded during the 10/sup th/ Henryk Wieniawski International Violinmakers Competition held in Poznan, Poland, in 2001. The results add to the recent research approach to apply computational intelligence to bridge the semantic and conceptual gap, which exists between the low level description and higher-level interpretation of multimedia. The taxonomy used for violin voices is correlated with objective attributes of entirely distinct character so that semantically disjoint categories are created, providing supportive cues for further analysis. The results should deliver new, enriching aspect to the design of methodology of inferring preference models from the objective characteristics of digital media.","PeriodicalId":345842,"journal":{"name":"5th International Conference on Intelligent Systems Design and Applications (ISDA'05)","volume":"41 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":"132941775","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：