Heuristic Feature Extraction Method for BCI with Harmony Search and DiscreteWavelet Transform

다국어 초록 (Multilingual Abstract)

For the brain-computer interface system (BCI), pre-processing has an important role to ensure systemperformance. However, the speech recognition system using electroencephalogram (EEG) is weak against temporaleffects. Therefore, in general cases, wavelet transform has been used to cope with the temporal effects and nonstationarycharacteristic of EEG. The discrete version of wavelet transform, called DWT, requires a filter of thesystem for use in downsampling the signal. In other words, it is important to determine the suitable type of filter. Inmany cases, it is difficult to find an adequate filter for DWT because of differences in the characteristics of the inputsignal. In this paper, we proposed a heuristic approach to finding the optimal filter of the system for EEG signals.
The harmony search algorithm (HSA) was used for finding of the optimal filter. In the learning process with theEEG system, the optimal wavelet filter could be found, which is automatically designed for subject personality.

참고문헌 (Reference)

1 V. J. Samar, "Wavelet analysis of neuroelectric waveforms : a conceptual tutorial" 66 (66): 7-60, 1999

2 Y. Chae, "Toward brain-actuated humanoid robots : asynchronous direct control using an EEGbased BCI" 28 (28): 1131-1144, 2012

3 D. Zhang, "Toward a minimally invasive brain–computer interface using a single subdural channel : A visual speller study" 71 : 30-41, 2013

4 R. Polikar, "TheWavelet Tutorial"

5 I. Iturrate, "Synchronous EEG brain-actuated wheelchair with automated navigation" Universidad de Zaragoza 2009

6 Junchang Zhai, "Robust Pole Assignment for Linear Control Systems in a Circular Region Using Novel Global Harmony Search Algorithm" 제어·로봇·시스템학회 14 (14): 713-722, 2016

7 L. R. Hochberg, "Reach and grasp by people with tetraplegia using a neurally controlled robotic arm" 485 (485): 372-375, 2012

8 R. Fazel-Rezai, "P300 brain computer interface : current challenges and emerging trends" 5 : 1-30, 2012

9 G. G. Roy, "On optimal feature selection using modified harmony search for power quality disturbance classification" 1355-1360, 2009

10 T. -J. Lee, "Electroencephalography signal grouping and feature classification using harmony search for BCI" 2013 (2013): 1-9, 2013

11 A. Porbadnigk, "EEG-based speech recognition : Impact of temporal effects" Karlsruhe Institute of Technology 376-381, 2009

12 L. Bi, "EEG-based brain-controlled mobile robots : a survey" 43 (43): 161-176, 2013

13 T. K. Gandhi, "Discrete harmony search based expert model for epileptic seizure detection in electroencephalography" 39 (39): 4055-4062, 2012

14 C. Song, "Decoding of Chinese phoneme clusters using ECoG" Tsinghua University 1278-1281, 2014

15 C. Heil, "Continuous and discrete wavelet transforms" 31 (31): 628-666, 1989

16 R. Bogue, "Brain-computer interfaces : control by thought" 37 (37): 126-132, 2010

17 Kyeong-Jun Mun, "Active Contour Model Based Object Contour Detection Using Genetic Algorithm with Wavelet Based Image Preprocessing" 제어·로봇·시스템학회 2 (2): 100-106, 2004

18 Z. W. Geem, "A new heuristic optimization algorithm : harmony search" 76 (76): 60-68, 2001