TY - GEN
T1 - Feature relation network that can identify underlying data structure for effective pattern classification
AU - Zhu, Hai Long
AU - Wang, Hong Qiang
N1 - Copyright:
Copyright 2011 Elsevier B.V., All rights reserved.
PY - 2010
Y1 - 2010
N2 - This paper proposes a feature relation network (FRN) to model the underlying feature relation structures of a set of observations. A pattern classification system is then constructed based on the feature relation network, namely PCS-FRN. During training process, PCS-FRN will form an attractor for each group of samples in order to lower the overall energy states. The attractor, or a feature relation network, reflects the underlying data structure that can discriminate different classes. Parameters of PCS-FRN are estimated by the multi-dimensional evolutionary algorithm. The PCS-FRN system was tested on a synthetic dataset and three real-world medical datasets and compared with conventional classification techniques. Experiment results show that PCS-FRN can achieve better classification accuracies on both binary and multi-class problems.
AB - This paper proposes a feature relation network (FRN) to model the underlying feature relation structures of a set of observations. A pattern classification system is then constructed based on the feature relation network, namely PCS-FRN. During training process, PCS-FRN will form an attractor for each group of samples in order to lower the overall energy states. The attractor, or a feature relation network, reflects the underlying data structure that can discriminate different classes. Parameters of PCS-FRN are estimated by the multi-dimensional evolutionary algorithm. The PCS-FRN system was tested on a synthetic dataset and three real-world medical datasets and compared with conventional classification techniques. Experiment results show that PCS-FRN can achieve better classification accuracies on both binary and multi-class problems.
KW - Data structure
KW - Feature relation network
KW - Pattern classification
UR - http://www.scopus.com/inward/record.url?scp=79952023661&partnerID=8YFLogxK
U2 - 10.1109/BIBMW.2010.5703857
DO - 10.1109/BIBMW.2010.5703857
M3 - Conference proceeding
AN - SCOPUS:79952023661
SN - 9781424483044
T3 - 2010 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2010
SP - 531
EP - 534
BT - 2010 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2010
T2 - 2010 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2010
Y2 - 18 December 2010 through 21 December 2010
ER -