Pub Date : 1999-12-01DOI: 10.1109/IJCNN.1999.830762
I. Silva, A. Souza, M. E. Bordon
This paper describes a novel approach for mapping lightning models using artificial neural networks. The networks acts as identifier of structural features of the lightning models so that output parameters can be estimated and generalised from an input parameter set. Simulation examples are presented to validate the proposed approach. More specifically, the neural networks are used to compute electrical field intensity and critical disruptive voltage taking into account several atmospheric and structural factors, such as pressure, temperature, humidity, distance between phases, height of bus bars, and wave forms. A comparative analysis with other approaches is also provided to illustrate this new methodology.
{"title":"Evaluation and identification of lightning models by artificial neural networks","authors":"I. Silva, A. Souza, M. E. Bordon","doi":"10.1109/IJCNN.1999.830762","DOIUrl":"https://doi.org/10.1109/IJCNN.1999.830762","url":null,"abstract":"This paper describes a novel approach for mapping lightning models using artificial neural networks. The networks acts as identifier of structural features of the lightning models so that output parameters can be estimated and generalised from an input parameter set. Simulation examples are presented to validate the proposed approach. More specifically, the neural networks are used to compute electrical field intensity and critical disruptive voltage taking into account several atmospheric and structural factors, such as pressure, temperature, humidity, distance between phases, height of bus bars, and wave forms. A comparative analysis with other approaches is also provided to illustrate this new methodology.","PeriodicalId":157719,"journal":{"name":"IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129287695","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 : 1999-12-01DOI: 10.1109/IJCNN.1999.831042
Y. Osana, M. Hagiwara
We propose a knowledge processing system using chaotic associative memory (KPCAM). The proposed KPCAM is based on a chaotic associative memory (CAM) composed of chaotic neurons. In the conventional chaotic neural network, when a stored pattern is given to the network as an external input continuously, the input pattern is searched. The CAM makes use of this property in order to separate the superimposed patterns and to deal with many-to-many associations. In this research, the CAM is applied to knowledge processing in which the knowledge is represented in a form of semantic network. The proposed KPCAM has the following features: 1) it can deal with the knowledge which is represented in a form of semantic network; 2) it can deal with characteristics inheritance; and 3) it is robust for noisy input. A series of computer simulations shows the effectiveness of the proposed system.
{"title":"Knowledge processing system using chaotic associative memory","authors":"Y. Osana, M. Hagiwara","doi":"10.1109/IJCNN.1999.831042","DOIUrl":"https://doi.org/10.1109/IJCNN.1999.831042","url":null,"abstract":"We propose a knowledge processing system using chaotic associative memory (KPCAM). The proposed KPCAM is based on a chaotic associative memory (CAM) composed of chaotic neurons. In the conventional chaotic neural network, when a stored pattern is given to the network as an external input continuously, the input pattern is searched. The CAM makes use of this property in order to separate the superimposed patterns and to deal with many-to-many associations. In this research, the CAM is applied to knowledge processing in which the knowledge is represented in a form of semantic network. The proposed KPCAM has the following features: 1) it can deal with the knowledge which is represented in a form of semantic network; 2) it can deal with characteristics inheritance; and 3) it is robust for noisy input. A series of computer simulations shows the effectiveness of the proposed system.","PeriodicalId":157719,"journal":{"name":"IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339)","volume":"214 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123840685","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 : 1999-12-01DOI: 10.1109/IJCNN.1999.836267
Yuan-Hsiang Chang, B. Zheng, Xiao-Hui Wang, W. Good
The authors investigated computer-aided diagnosis (CAD) schemes to determine the probability for the presence of breast cancer using artificial neural networks (ANNs) that were trained by a backpropagation (BP) algorithm or by a genetic algorithm (GA). A clinical database of 418 previously verified patient cases was employed and randomly partitioned into two independent sets for CAD training and testing. During training, the BP and the GA were independently applied to optimize, or to evolve the inter-connecting weights of the ANNs. Both the BP/GA-trained CAD performances were then compared using the receiver-operating characteristics (ROC) analysis. In the training set, both the BP/GA-trained CAD schemes yielded the areas under ROC curves of 0.91 and 0.93, respectively. In the testing set, both the BP/GA-trained ANNs yielded the areas under ROC curves of approximately 0.83. These results demonstrated that the GA performed slightly better, although not significantly, than BP for the training of the CAD schemes.
{"title":"Computer-aided diagnosis of breast cancer using artificial neural networks: comparison of backpropagation and genetic algorithms","authors":"Yuan-Hsiang Chang, B. Zheng, Xiao-Hui Wang, W. Good","doi":"10.1109/IJCNN.1999.836267","DOIUrl":"https://doi.org/10.1109/IJCNN.1999.836267","url":null,"abstract":"The authors investigated computer-aided diagnosis (CAD) schemes to determine the probability for the presence of breast cancer using artificial neural networks (ANNs) that were trained by a backpropagation (BP) algorithm or by a genetic algorithm (GA). A clinical database of 418 previously verified patient cases was employed and randomly partitioned into two independent sets for CAD training and testing. During training, the BP and the GA were independently applied to optimize, or to evolve the inter-connecting weights of the ANNs. Both the BP/GA-trained CAD performances were then compared using the receiver-operating characteristics (ROC) analysis. In the training set, both the BP/GA-trained CAD schemes yielded the areas under ROC curves of 0.91 and 0.93, respectively. In the testing set, both the BP/GA-trained ANNs yielded the areas under ROC curves of approximately 0.83. These results demonstrated that the GA performed slightly better, although not significantly, than BP for the training of the CAD schemes.","PeriodicalId":157719,"journal":{"name":"IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125431186","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 : 1999-12-01DOI: 10.1109/IJCNN.1999.833531
Shailesh Kumar, M. Crawford, Joydeep Ghosh
Conventional methods for feature selection use some kind of separability criteria or classification accuracy for computing the relevance of a feature subset to the classification task. In two-class problems, this approach may be suitable, but for problems such as character recognition with 26 classes, these feature selection algorithms are often faced with complex tradeoffs among efficacy of features for separating different subsets of classes. We propose a class-pair based feature selection algorithm which, in conjunction with mixture modeling technique, provides significantly superior results for differentiating a large number of classes, even when the class priors vary considerably. This technique is applied to multisensor NASA/JPL remote sensing AIRSAR data for characterizing 11 types of land cover. The proposed polychotomous approach not only gives improved test accuracy, but also reduces the number of features used. Important domain information can be derived from the features selected for different class pairs and the distance measure between these class pairs.
{"title":"A versatile framework for labelling imagery with a large number of classes","authors":"Shailesh Kumar, M. Crawford, Joydeep Ghosh","doi":"10.1109/IJCNN.1999.833531","DOIUrl":"https://doi.org/10.1109/IJCNN.1999.833531","url":null,"abstract":"Conventional methods for feature selection use some kind of separability criteria or classification accuracy for computing the relevance of a feature subset to the classification task. In two-class problems, this approach may be suitable, but for problems such as character recognition with 26 classes, these feature selection algorithms are often faced with complex tradeoffs among efficacy of features for separating different subsets of classes. We propose a class-pair based feature selection algorithm which, in conjunction with mixture modeling technique, provides significantly superior results for differentiating a large number of classes, even when the class priors vary considerably. This technique is applied to multisensor NASA/JPL remote sensing AIRSAR data for characterizing 11 types of land cover. The proposed polychotomous approach not only gives improved test accuracy, but also reduces the number of features used. Important domain information can be derived from the features selected for different class pairs and the distance measure between these class pairs.","PeriodicalId":157719,"journal":{"name":"IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127603130","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 : 1999-12-01DOI: 10.1109/IJCNN.1999.832715
K. Hirasawa, Jinglu Hu, J. Murata, C. Jin, Kazuaki Yotsumoto, H. Katagiri
A method for identifying nonlinear dynamic systems with noise is proposed by using probabilistic universal learning networks (PrULNs). PrULNs are extensions of universal learning networks (ULNs). ULNs form a superset of neural networks and were proposed to provide a universal framework for modeling and control of nonlinear large-scale complex systems. But the ULN does not provide any stochastic characteristics of the signals propagating through it. The PrULNs are equipped with machinery to calculate stochastic properties of signals and to train network parameters so that the signals behave with the pre-specified stochastic properties. On the other hand it is generally recognized that there exists an overfitting problem when identification of nonlinear dynamic systems with noise is done by neural networks. In this paper, it is shown from simulation results of identification of a nonlinear robot dynamics that PrULNs are useful for avoiding the overfitting.
{"title":"Identification of nonlinear dynamic systems by using probabilistic universal learning networks","authors":"K. Hirasawa, Jinglu Hu, J. Murata, C. Jin, Kazuaki Yotsumoto, H. Katagiri","doi":"10.1109/IJCNN.1999.832715","DOIUrl":"https://doi.org/10.1109/IJCNN.1999.832715","url":null,"abstract":"A method for identifying nonlinear dynamic systems with noise is proposed by using probabilistic universal learning networks (PrULNs). PrULNs are extensions of universal learning networks (ULNs). ULNs form a superset of neural networks and were proposed to provide a universal framework for modeling and control of nonlinear large-scale complex systems. But the ULN does not provide any stochastic characteristics of the signals propagating through it. The PrULNs are equipped with machinery to calculate stochastic properties of signals and to train network parameters so that the signals behave with the pre-specified stochastic properties. On the other hand it is generally recognized that there exists an overfitting problem when identification of nonlinear dynamic systems with noise is done by neural networks. In this paper, it is shown from simulation results of identification of a nonlinear robot dynamics that PrULNs are useful for avoiding the overfitting.","PeriodicalId":157719,"journal":{"name":"IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339)","volume":"155 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122503462","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 : 1999-12-01DOI: 10.1109/IJCNN.1999.831043
Y. Osana, M. Hagiwara
We propose a chaotic associative memory for sequential patterns (CAMSP). The proposed CAMSP is based on a chaotic associative memory composed of chaotic neurons. In the conventional chaotic neural network, when a stored pattern is given to the network as an external input continuously, the input pattern is searched. The CAM makes use of this property in order to separate the superimposed patterns. In this research, the CAM is applied to associations for sequential patterns. The proposed model has the following features: 1) it can deal with associations for the sequential patterns; 2) it can realize associations by considering patterns' history; and 3) it is robust for noisy input. A series of computer simulations shows the effectiveness of the proposed model.
{"title":"Chaotic associative memory for sequential patterns","authors":"Y. Osana, M. Hagiwara","doi":"10.1109/IJCNN.1999.831043","DOIUrl":"https://doi.org/10.1109/IJCNN.1999.831043","url":null,"abstract":"We propose a chaotic associative memory for sequential patterns (CAMSP). The proposed CAMSP is based on a chaotic associative memory composed of chaotic neurons. In the conventional chaotic neural network, when a stored pattern is given to the network as an external input continuously, the input pattern is searched. The CAM makes use of this property in order to separate the superimposed patterns. In this research, the CAM is applied to associations for sequential patterns. The proposed model has the following features: 1) it can deal with associations for the sequential patterns; 2) it can realize associations by considering patterns' history; and 3) it is robust for noisy input. A series of computer simulations shows the effectiveness of the proposed model.","PeriodicalId":157719,"journal":{"name":"IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132449634","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 : 1999-12-01DOI: 10.1109/IJCNN.1999.831504
Ryuta Fukuda, J. Hara, W. Shankle, T. Inui, M. Tomita
Connectivity between language related Brodmann areas derived from analyses of data source provided by Conel (1939-1967) has been proposed. The analysis consists of computing the correlation coefficients between each layer of one cortical area to each layer of another cortical area over the 8 age points. A "connection" was created between two layers of two cortical areas if: 1) its z-score have significance level less than 20%, and 2) the two layers began myelinating at the same age point. Predicted connections are consistent with neural network models derived neuro-imaging, psychological tests, and also support some seemingly unusual findings reported by others.
{"title":"Predicting human cortical connectivity for language areas using the Conel database","authors":"Ryuta Fukuda, J. Hara, W. Shankle, T. Inui, M. Tomita","doi":"10.1109/IJCNN.1999.831504","DOIUrl":"https://doi.org/10.1109/IJCNN.1999.831504","url":null,"abstract":"Connectivity between language related Brodmann areas derived from analyses of data source provided by Conel (1939-1967) has been proposed. The analysis consists of computing the correlation coefficients between each layer of one cortical area to each layer of another cortical area over the 8 age points. A \"connection\" was created between two layers of two cortical areas if: 1) its z-score have significance level less than 20%, and 2) the two layers began myelinating at the same age point. Predicted connections are consistent with neural network models derived neuro-imaging, psychological tests, and also support some seemingly unusual findings reported by others.","PeriodicalId":157719,"journal":{"name":"IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115397110","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 : 1999-12-01DOI: 10.1109/IJCNN.1999.831485
H. Kume, Y. Osana, M. Hagiwara
We propose a neural network model of visual system based on the feature integration theory. The proposed model has a structure based on the hierarchical structure of visual system and selectiveness of information by visual attention. The proposed model consists of two stages: the feature recognition stage and the feature integration stage. In the feature recognition stage, there are two modules: the form recognition module and the color recognition module. In these modules, information of form and color is separately processed in parallel. The form recognition module is constructed using the neocognitron, and the color recognition module is based on the LVQ neural network. The feature integration stage is based on the feature integration theory, which is a representative theory for explaining all phenomena occurring in visual system as a consistent process. We carried out computer simulations and confirmed that the proposed model can recognize plural objects and solve the binding problem.
{"title":"Solving the binding problem with feature integration theory","authors":"H. Kume, Y. Osana, M. Hagiwara","doi":"10.1109/IJCNN.1999.831485","DOIUrl":"https://doi.org/10.1109/IJCNN.1999.831485","url":null,"abstract":"We propose a neural network model of visual system based on the feature integration theory. The proposed model has a structure based on the hierarchical structure of visual system and selectiveness of information by visual attention. The proposed model consists of two stages: the feature recognition stage and the feature integration stage. In the feature recognition stage, there are two modules: the form recognition module and the color recognition module. In these modules, information of form and color is separately processed in parallel. The form recognition module is constructed using the neocognitron, and the color recognition module is based on the LVQ neural network. The feature integration stage is based on the feature integration theory, which is a representative theory for explaining all phenomena occurring in visual system as a consistent process. We carried out computer simulations and confirmed that the proposed model can recognize plural objects and solve the binding problem.","PeriodicalId":157719,"journal":{"name":"IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129614378","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 : 1999-09-01DOI: 10.1109/IJCNN.1999.831080
J. Kwok
In this paper, we extend the use of moderated outputs to the support vector machine (SVM) by making use of a relationship between SVM and the evidence framework. The moderated output is more in line with the Bayesian idea that the posterior weight distribution should be taken into account upon prediction, and it also alleviates the usual tendency of assigning overly high confidence to the estimated class memberships of the test patterns. Moreover, the moderated output derived here can be taken as an approximation to the posterior class probability. Hence, meaningful rejection thresholds can be assigned and outputs from several networks can be directly compared. Experimental results on both artificial and real-world data are also discussed.
{"title":"Moderating the outputs of support vector machine classifiers","authors":"J. Kwok","doi":"10.1109/IJCNN.1999.831080","DOIUrl":"https://doi.org/10.1109/IJCNN.1999.831080","url":null,"abstract":"In this paper, we extend the use of moderated outputs to the support vector machine (SVM) by making use of a relationship between SVM and the evidence framework. The moderated output is more in line with the Bayesian idea that the posterior weight distribution should be taken into account upon prediction, and it also alleviates the usual tendency of assigning overly high confidence to the estimated class memberships of the test patterns. Moreover, the moderated output derived here can be taken as an approximation to the posterior class probability. Hence, meaningful rejection thresholds can be assigned and outputs from several networks can be directly compared. Experimental results on both artificial and real-world data are also discussed.","PeriodicalId":157719,"journal":{"name":"IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122924986","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 : 1999-07-10DOI: 10.1109/IJCNN.1999.833453
Y. Boniface, F. Alexandre, S. Vialle
Hardware developments have led to the use of shared memory as an efficient parallel programming method. The main goals of the work reported here are to speed up executions and to decrease development time of parallel neural network implementations. To allow for such implementations, a library has been defined, as a bridge between neural networks and general purpose MIMD computer parallelisms.
{"title":"A bridge between two paradigms for parallelism: neural networks and general purpose MIMD computers","authors":"Y. Boniface, F. Alexandre, S. Vialle","doi":"10.1109/IJCNN.1999.833453","DOIUrl":"https://doi.org/10.1109/IJCNN.1999.833453","url":null,"abstract":"Hardware developments have led to the use of shared memory as an efficient parallel programming method. The main goals of the work reported here are to speed up executions and to decrease development time of parallel neural network implementations. To allow for such implementations, a library has been defined, as a bridge between neural networks and general purpose MIMD computer parallelisms.","PeriodicalId":157719,"journal":{"name":"IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114981163","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：