2013 |
Luckner, Marcin; Szyszko, Krzysztof RBF ensemble based on reduction of DAG structure Inproceedings Proceedings of the 2013 Federated Conference on Computer Science and Information Systems, pp. 99–105, IEEE, Kraków, 2013. Abstract | Links | BibTeX | Tagi: Accuracy, binary classifiers, Chebyshev approximation, classes similarity, Classification, classification cost reduction, DAG structure reduction, Directed Acyclic Graph, directed graphs, Euclidean distance, Glass, Kernel, learning (artificial intelligence), pattern classification, Radial Basis Function, radial basis function ensemble, radial basis function networks, RBF ensemble, recognition accuracy, Support Vector Machines, UCI repository @inproceedings{Luckner2013a, title = {RBF ensemble based on reduction of DAG structure}, author = {Marcin Luckner and Krzysztof Szyszko}, url = {https://fedcsis.org/proceedings/2013/pliks/334.pdf}, year = {2013}, date = {2013-01-01}, booktitle = {Proceedings of the 2013 Federated Conference on Computer Science and Information Systems}, pages = {99--105}, publisher = {IEEE}, address = {Kraków}, abstract = {Binary classifiers are grouped into an ensemble to solve multi-class problems. One of proposed ensemble structure is a directed acyclic graph. In this structure, a classifier is created for each pair of classes. The number of classifiers can be reduced if groups of classes will be separated instead of individual classes. The proposed method is based on the similarity of classes defined as a distance between classes. For near classes the structure of DAG stays immutable. For the distant classes more than one is separated with a single classifier. In this paper, the proposed method is tested in variants based on various metrics. For the tests, several datasets from UCI repository was used and the results were compared with published works. The tests proved that grouping of radial basis functions into such ensemble reduces the classification cost and the recognition accuracy is not reduced significantly.}, keywords = {Accuracy, binary classifiers, Chebyshev approximation, classes similarity, Classification, classification cost reduction, DAG structure reduction, Directed Acyclic Graph, directed graphs, Euclidean distance, Glass, Kernel, learning (artificial intelligence), pattern classification, Radial Basis Function, radial basis function ensemble, radial basis function networks, RBF ensemble, recognition accuracy, Support Vector Machines, UCI repository}, pubstate = {published}, tppubtype = {inproceedings} } Binary classifiers are grouped into an ensemble to solve multi-class problems. One of proposed ensemble structure is a directed acyclic graph. In this structure, a classifier is created for each pair of classes. The number of classifiers can be reduced if groups of classes will be separated instead of individual classes. The proposed method is based on the similarity of classes defined as a distance between classes. For near classes the structure of DAG stays immutable. For the distant classes more than one is separated with a single classifier. In this paper, the proposed method is tested in variants based on various metrics. For the tests, several datasets from UCI repository was used and the results were compared with published works. The tests proved that grouping of radial basis functions into such ensemble reduces the classification cost and the recognition accuracy is not reduced significantly. |
Luckner, Marcin; Szyszko, Krzysztof RBF ensemble based on reduction of DAG structure Inproceedings Proceedings of the 2013 Federated Conference on Computer Science and Information Systems, pp. 99–105, IEEE, Kraków, 2013. Abstract | Links | BibTeX | Tagi: Accuracy, binary classifiers, Chebyshev approximation, classes similarity, Classification, classification cost reduction, DAG structure reduction, Directed Acyclic Graph, directed graphs, Euclidean distance, Glass, Kernel, learning (artificial intelligence), pattern classification, Radial Basis Function, radial basis function ensemble, radial basis function networks, RBF ensemble, recognition accuracy, Support Vector Machines, UCI repository @inproceedings{Luckner2013ab, title = {RBF ensemble based on reduction of DAG structure}, author = {Marcin Luckner and Krzysztof Szyszko}, url = {https://fedcsis.org/proceedings/2013/pliks/334.pdf}, year = {2013}, date = {2013-01-01}, booktitle = {Proceedings of the 2013 Federated Conference on Computer Science and Information Systems}, pages = {99--105}, publisher = {IEEE}, address = {Kraków}, abstract = {Binary classifiers are grouped into an ensemble to solve multi-class problems. One of proposed ensemble structure is a directed acyclic graph. In this structure, a classifier is created for each pair of classes. The number of classifiers can be reduced if groups of classes will be separated instead of individual classes. The proposed method is based on the similarity of classes defined as a distance between classes. For near classes the structure of DAG stays immutable. For the distant classes more than one is separated with a single classifier. In this paper, the proposed method is tested in variants based on various metrics. For the tests, several datasets from UCI repository was used and the results were compared with published works. The tests proved that grouping of radial basis functions into such ensemble reduces the classification cost and the recognition accuracy is not reduced significantly.}, keywords = {Accuracy, binary classifiers, Chebyshev approximation, classes similarity, Classification, classification cost reduction, DAG structure reduction, Directed Acyclic Graph, directed graphs, Euclidean distance, Glass, Kernel, learning (artificial intelligence), pattern classification, Radial Basis Function, radial basis function ensemble, radial basis function networks, RBF ensemble, recognition accuracy, Support Vector Machines, UCI repository}, pubstate = {published}, tppubtype = {inproceedings} } Binary classifiers are grouped into an ensemble to solve multi-class problems. One of proposed ensemble structure is a directed acyclic graph. In this structure, a classifier is created for each pair of classes. The number of classifiers can be reduced if groups of classes will be separated instead of individual classes. The proposed method is based on the similarity of classes defined as a distance between classes. For near classes the structure of DAG stays immutable. For the distant classes more than one is separated with a single classifier. In this paper, the proposed method is tested in variants based on various metrics. For the tests, several datasets from UCI repository was used and the results were compared with published works. The tests proved that grouping of radial basis functions into such ensemble reduces the classification cost and the recognition accuracy is not reduced significantly. |
2006 |
ł, W{ł}adys; Luckner, Marcin Automatic Knowledge Acquisition: Recognizing Music Notation with Methods of Centroids and Classifications Trees Inproceedings The 2006 IEEE International Joint Conference on Neural Network Proceedings, pp. 3382–3388, IEEE, 2006, ISSN: 10987576. Abstract | Links | BibTeX | Tagi: centroids, Classification tree analysis, classifications trees, classifiers, Decision trees, feature extraction, Knowledge acquisition, Multiple signal classification, music, music notation recognition, music symbols recognition, Neural networks, Optical character recognition software, Ordinary magnetoresistance, pattern classification, Pattern recognition, Printing, Text recognition, Tiles @inproceedings{Homenda2006, title = {Automatic Knowledge Acquisition: Recognizing Music Notation with Methods of Centroids and Classifications Trees}, author = {W{ł}adys{ł}aw Homenda and Marcin Luckner}, url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=1716561}, doi = {10.1109/IJCNN.2006.247339}, issn = {10987576}, year = {2006}, date = {2006-01-01}, booktitle = {The 2006 IEEE International Joint Conference on Neural Network Proceedings}, pages = {3382--3388}, publisher = {IEEE}, abstract = {This paper presents a pattern recognition study aimed al music symbols recognition. The study is focused on classification methods of music symbols based on decision trees and clustering method applied to classes of music symbols that face classification problems. Classification is made on the basis of extracted features. A comparison of selected classifiers was made on some classes of nutation symbols distorted by a variety of factors as image noise, printing defects, different fonts, skew and curvature of scanning, overlapped symbols.}, keywords = {centroids, Classification tree analysis, classifications trees, classifiers, Decision trees, feature extraction, Knowledge acquisition, Multiple signal classification, music, music notation recognition, music symbols recognition, Neural networks, Optical character recognition software, Ordinary magnetoresistance, pattern classification, Pattern recognition, Printing, Text recognition, Tiles}, pubstate = {published}, tppubtype = {inproceedings} } This paper presents a pattern recognition study aimed al music symbols recognition. The study is focused on classification methods of music symbols based on decision trees and clustering method applied to classes of music symbols that face classification problems. Classification is made on the basis of extracted features. A comparison of selected classifiers was made on some classes of nutation symbols distorted by a variety of factors as image noise, printing defects, different fonts, skew and curvature of scanning, overlapped symbols. |
ł, W{ł}adys; Luckner, Marcin Automatic Knowledge Acquisition: Recognizing Music Notation with Methods of Centroids and Classifications Trees Inproceedings The 2006 IEEE International Joint Conference on Neural Network Proceedings, pp. 3382–3388, IEEE, 2006, ISSN: 10987576. Abstract | Links | BibTeX | Tagi: centroids, Classification tree analysis, classifications trees, classifiers, Decision trees, feature extraction, Knowledge acquisition, Multiple signal classification, music, music notation recognition, music symbols recognition, Neural networks, Optical character recognition software, Ordinary magnetoresistance, pattern classification, Pattern recognition, Printing, Text recognition, Tiles @inproceedings{Homenda2006b, title = {Automatic Knowledge Acquisition: Recognizing Music Notation with Methods of Centroids and Classifications Trees}, author = {W{ł}adys{ł}aw Homenda and Marcin Luckner}, url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=1716561}, doi = {10.1109/IJCNN.2006.247339}, issn = {10987576}, year = {2006}, date = {2006-01-01}, booktitle = {The 2006 IEEE International Joint Conference on Neural Network Proceedings}, pages = {3382--3388}, publisher = {IEEE}, abstract = {This paper presents a pattern recognition study aimed al music symbols recognition. The study is focused on classification methods of music symbols based on decision trees and clustering method applied to classes of music symbols that face classification problems. Classification is made on the basis of extracted features. A comparison of selected classifiers was made on some classes of nutation symbols distorted by a variety of factors as image noise, printing defects, different fonts, skew and curvature of scanning, overlapped symbols.}, keywords = {centroids, Classification tree analysis, classifications trees, classifiers, Decision trees, feature extraction, Knowledge acquisition, Multiple signal classification, music, music notation recognition, music symbols recognition, Neural networks, Optical character recognition software, Ordinary magnetoresistance, pattern classification, Pattern recognition, Printing, Text recognition, Tiles}, pubstate = {published}, tppubtype = {inproceedings} } This paper presents a pattern recognition study aimed al music symbols recognition. The study is focused on classification methods of music symbols based on decision trees and clustering method applied to classes of music symbols that face classification problems. Classification is made on the basis of extracted features. A comparison of selected classifiers was made on some classes of nutation symbols distorted by a variety of factors as image noise, printing defects, different fonts, skew and curvature of scanning, overlapped symbols. |
Publikacje
2013 |
RBF ensemble based on reduction of DAG structure Inproceedings Proceedings of the 2013 Federated Conference on Computer Science and Information Systems, pp. 99–105, IEEE, Kraków, 2013. |
RBF ensemble based on reduction of DAG structure Inproceedings Proceedings of the 2013 Federated Conference on Computer Science and Information Systems, pp. 99–105, IEEE, Kraków, 2013. |
2006 |
Automatic Knowledge Acquisition: Recognizing Music Notation with Methods of Centroids and Classifications Trees Inproceedings The 2006 IEEE International Joint Conference on Neural Network Proceedings, pp. 3382–3388, IEEE, 2006, ISSN: 10987576. |
Automatic Knowledge Acquisition: Recognizing Music Notation with Methods of Centroids and Classifications Trees Inproceedings The 2006 IEEE International Joint Conference on Neural Network Proceedings, pp. 3382–3388, IEEE, 2006, ISSN: 10987576. |