Ant Colony Optimization Based Feature Selection Method for QEEG Data Classification

다국어 초록 (Multilingual Abstract)

Objective-Many applications such as biomedical signals require selecting a subset of the input features in order to represent the whole set of features. A feature selection algorithm has recently been proposed as a new approach for feature subset selection.

Methods-Feature selection process using ant colony optimization (ACO) for 6 channel pre-treatment electroencephalogram (EEG) data from theta and delta frequency bands is combined with back propagation neural network (BPNN) classification method for 147 major depressive disorder (MDD) subjects.

Results-BPNN classified R subjects with 91.83% overall accuracy and 95.55% subjects detection sensitivity. Area under ROC curve (AUC) value after feature selection increased from 0.8531 to 0.911. The features selected by the optimization algorithm were Fp1, Fp2, F7, F8, F3 for theta frequency band and eliminated 7 features from 12 to 5 feature subset.

Conclusion-ACO feature selection algorithm improves the classification accuracy of BPNN. Using other feature selection algorithms or classifiers to compare the performance for each approach is important to underline the validity and versatility of the designed combination.

목차 (Table of Contents)

• INTRODUCTION
• METHODS
• RESULTS
• DISCUSSION
• ACKNOWLEDGEMENTS
• REFERENCES

참고문헌 (Reference)

1 Khodayari A, "Using pretreatment electroencephalography data to predict response to transcranial magnetic stimulation therapy for major depression" 2011

2 Basiri ME, "Using ant colony optimization-based selected features for predicting post-synaptic activity in proteins" 4973 : 12-23, 2008

3 Atyabi A, "The impact of PSO based dimension reduction in EEG study" 2012

4 Bares M, "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" 20 : 459-466, 2010

5 Chiang Y, "The application of ant colony optimization for gene selection in microarray-based cancer classification" 2008

6 Trivedi MH, "Symptom clusters as predictors of late response to antidepressant treatment" 66 : 1064-1074, 2005

7 Sabeti M, "Selection of relevant features for EEG signal classification of schizophrenic patients" 2 : 122-134, 2007

8 Z Hong, "Recognition of epileptic EEG signals based on BP neural networks" 35 : 18-23, 2009

9 Coutin-Churchman P, "Quantitative spectral analysis of EEG in psychiatry revisited:drawing signs out of numbers in a clinical setting" 114 : 2294-2306, 2003

10 Richieri R, "Predictive value of brain perfusion SPECT for rTMS response in pharmacoresistant depression" 38 : 1715-1722, 2011

11 Haupt RL, "Practical Genetic Algorithms, 2nd Edition" John Wiley & Sons, Inc 2004

12 Roda A, "Perceptual tests and feature extraction: Toward a novel methodology for the assessment of the digitization of old ethnic music records" 90 : 1000-1007, 2010

13 Brakemeier EL, "Patterns of response to repetitive transcranial magnetic stimulation (rTMS) in major depression: replication study in drug-free patients" 108 : 59-70, 2008

14 Micoulaud-Franchi JA, "Parieto-temporal alpha EEG band power at baseline as a predictor of antidepressant treatment response with repetitive transcranial magnetic stimulation: a preliminary study" 137 : 156-160, 2012

15 Ocak H, "Optimal classification of epileptic seizures in EEG using wavelet analysis and genetic algorithm" 88 : 1858-1867, 2008

16 Arns M, "Neurophysiological predictors of non-response to rTMS in depression" 5 : 569-576, 2012

17 Arns M, "Neurophysiological predictors of non-response to rTMS in depression" 5 : 569-576, 2012

18 Zhang GP, "Neural networks for classification: A Survey" 30 : 451-462, 2000

19 Haykin S, "Neural Networks: A Comprehensive Foundation" Macmillan 1994

20 Subbotin S, "Modifications of ant colony optimization method for feature selection" 2007

21 Polat K, "Medical decision support system based on artificial immune recognition immune system, fuzzy weighted pre-processing and feature selection" 33 : 484-490, 2007

22 Micheli-Tzanakou E, "Medical Devices and Systems" CRC Press LLC 7.1-7.14, 2000

23 Leuchter AF, "Mandelkern M. Relationship between brain electrical activity and cortical perfusion in normal subjects" 90 : 125-140, 1999

24 Tsai JS, "Joint robustness and security enhancement for feature-based image watermarking using invariant feature regions" 92 : 1431-1445, 2012

25 Khushaba, RN, "Intelligent artificial ants based feature extraction from wavelet packet coefficients for biomedical signal classification" 2008

26 Choi SI, "Input variable selection for feature extraction in classification problems" 92 : 636-648, 2012

27 Huang K, "Information theoretic wavelet packet sub-band selection for texture classification" 86 : 1410-1420, 2006

28 Fausett L, "Fundamentals of Neural Networks Architectures, Algorithms, and Applications" Prentice Hall 1994

29 Flotzinger D, "Feature selection with distinction sensitive learning vector quantisation and genetic algorithms" 1994

30 Lu JJ, "Feature selection based-on genetic algorithm for image annotation" 21 : 887-891, 2008

31 Yeh YC, "Feature selection algorithm for ECG signals using range-overlaps method" 37 : 3499-3512, 2010

32 Liao TW, "Feature extraction and selection from acoustic emission signals with an application in grinding wheel condition monitoring" 23 : 74-84, 2010

33 Ververidis D, "Fast and accurate sequential floating forward feature selection with the Bayes classifier applied to speech emotion recognition" 88 : 2956-2970, 2008

34 Chen B, "Efficient ant colony optimization for image feature selection" 93 : 1566-1576, 2013

35 O’Reardon JP, "Efficacy and safety of transcranial magnetic stimulation in the acute treatment of major depression: a multisite randomized controlled trial" 62 : 1208-1216, 2007

36 Khodayari A, "Diagnosis of psychiatric disorders using EEG data and employing a statistical decision model" 2010

37 Leuchter AF, "Cordance: a new method for assessment of cerebral perfusion and metabolism using quantitative electroencephalography" 1 : 208-219, 1994

38 Hyun TK, "Computerized recognition of Alzheimer disease-EEG using genetic algorithms and neural network" ELSEVIER SCIENCE BV 21 : 1124-1130, 2005

39 Im CH, "Computer-aided performance evaluation of a multichannel transcranial magnetic stimulation system" 42 : 3803-3808, 2006

40 Garrett D, "Comparison of linear, nonlinear, and feature selection methods for EEG signal classification" 11 : 141-144, 2003

41 Jensen R, "Combining Rough and Fuzzy Sets for Feature Selection" University of Edinburgh 2005

42 Li YJ, "Classification of Schizophrenia and depression by EEG with ANNs" In Medicine and Biology Society 2005

43 Kito S, "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" 5 : 547-553, 2012

44 Lek S, "Artificial neural networks as a tool in ecological modeling, an introduction" 120 : 65-73, 1999

45 Price GW, "Appraisal of sessional EEG features as a correlate of clinical changes in an rTMS treatment of depression" 39 : 131-138, 2008

46 Aghdam MH, "Application of ant colony optimization for feature selection in text categorization" IEEE Press 2008

47 Dorigo M, "Ant colony system: a cooperative learning approach to the traveling salesman problem" 1 : 53-66, 1997

48 Huang H, "Ant colony optimization-based feature selection method for surface electromyography signals classification" 42 : 30-38, 2012

49 Karnan M, "Ant colony optimization for feature selection and classification of microcalcifications in digital mammograms" ADCOM 2006

50 Bursa M, "Ant colony cooperative Strategy clustering in Electrocardiogram and electroencephalogram data clustering" 2007

51 Guyon I, "An introduction to variable and feature selection" 3 : 1157-1182, 2003

52 Kanan HR, "An improved feature selection method based on ant colony optimization (ACO) evaluated on face recognition system" 205 : 716-725, 2008

53 Saeys Y, "A review of feature selection techniques in bioinformatics" 23 : 2507-2517, 2007

54 Khodayari-Rostamabad A, "A pilot study to determine whether machine learning methodologies using Pre-treatment electroencephalography can predict the symptomatic response to clozapine therapy" 121 : 1998-2006, 2010

55 Nemati S, "A novel text-independent speaker verification system using ant colony optimization algorithm" 5099 : 421-429, 2008

56 Wang Y, "A novel system for robust lane detection and tracking" 92 : 319-334, 2012

57 Nemati S, "A novel ACO-GA hybrid algorithm for feature selection in protein function prediction" 36 : 12086-12094, 2009

58 Awaidah SM, "A multiple feature/resolution scheme to Arabic (Indian) numerals recognition using hidden Markov models" 89 : 1176-1184, 2009

59 Patricia EN, "A decision rule-based method for feature selection in predictive data mining" 37 : 602-609, 2010

60 Khushaba, RN, "A combined ant colony and differential evolution feature selection algorithm" 5217 : 1-12, 2008