Ant Colony Optimization Based Feature Selection Method for QEEG Data Classification.
作者： Turker Tekin Erguzel , Serhat Ozekes , Selahattin Gultekin , Nevzat Tarhan
关键词: Feature selection 、 Data classification 、 Psychology 、 Minimum redundancy feature selection 、 Data mining 、 Sensitivity (control systems) 、 Selection (genetic algorithm) 、 Ant colony optimization algorithms 、 Feature (computer vision) 、 Artificial neural network
摘要: OBJECTIVE Many applications such as biomedical signals require selecting a subset of the input features in order to represent whole set features. A feature selection algorithm has recently been proposed new approach for selection. METHODS Feature process using ant colony optimization (ACO) 6 channel pre-treatment electroencephalogram (EEG) data from theta and delta frequency bands is combined with back propagation neural network (BPNN) classification method 147 major depressive disorder (MDD) subjects. RESULTS BPNN classified R subjects 91.83% overall accuracy 95.55% detection sensitivity. Area under ROC curve (AUC) value after increased 0.8531 0.911. The selected by were Fp1, Fp2, F7, F8, F3 band eliminated 7 12 5 subset. CONCLUSION ACO improves BPNN. Using other algorithms or classifiers compare performance each important underline validity versatility designed combination.
sci-hub.se 参考文章(61)
Adham Atyabi, Martin H. Luerssen, Sean P. Fitzgibbon, David M. W. Powers, The impact of PSO based dimension reduction on EEG classification Brain Informatics. pp. 220- 231 ,(2012) , 10.1007/978-3-642-35139-6_21
Rami N. Khushaba, Ahmed Al-Ani, Akram AlSukker, Adel Al-Jumaily, A Combined Ant Colony and Differential Evolution Feature Selection Algorithm ant colony optimization and swarm intelligence. pp. 1- 12 ,(2008) , 10.1007/978-3-540-87527-7_1
Sue Ellen Haupt, Randy L. Haupt, Practical Genetic Algorithms ,(2004)
D. Flotzinger, M. Pregenzer, G. Pfurtscheller, Feature selection with distinction sensitive learning vector quantisation and genetic algorithms world congress on computational intelligence. ,vol. 6, pp. 3448- 3451 ,(1994) , 10.1109/ICNN.1994.374888
Miroslav Bursa, Lenka Lhotska, Ant Colony Cooperative Strategy in Electrocardiogram and Electroencephalogram Data Clustering Nature Inspired Cooperative Strategies for Optimization (NICSO 2007). pp. 323- 333 ,(2008) , 10.1007/978-3-540-78987-1_29
Laurene Fausett, Fundamentals of neural networks: architectures, algorithms, and applications Prentice Hall. ,(1994)
Shinsuke Kito, Takashi Hasegawa, Yoshihiko Koga, Cerebral blood flow ratio of the dorsolateral prefrontal cortex to the ventromedial prefrontal cortex as a potential predictor of treatment response to transcranial magnetic stimulation in depression. Brain Stimulation. ,vol. 5, pp. 547- 553 ,(2012) , 10.1016/J.BRS.2011.09.004
Yifei Wang, Naim Dahnoun, Alin Achim, A novel system for robust lane detection and tracking Signal Processing. ,vol. 92, pp. 319- 334 ,(2012) , 10.1016/J.SIGPRO.2011.07.019
Martin Bares, Martin Brunovsky, Tomas Novak, Miloslav Kopecek, Pavla Stopkova, Peter Sos, Vladimir Krajca, Cyril Höschl, The change of prefrontal QEEG theta cordance as a predictor of response to bupropion treatment in patients who had failed to respond to previous antidepressant treatments European Neuropsychopharmacology. ,vol. 20, pp. 459- 466 ,(2010) , 10.1016/J.EURONEURO.2010.03.007
Martijn Arns, Wilhelmus H. Drinkenburg, Paul B. Fitzgerald, J. Leon Kenemans, Neurophysiological predictors of non-response to rTMS in depression Brain Stimulation. ,vol. 5, pp. 569- 576 ,(2012) , 10.1016/J.BRS.2011.12.003