Automated EEG sentence classification using novel dynamic-sized binary pattern and multilevel discrete wavelet transform techniques with TSEEG database
Article
Article Title | Automated EEG sentence classification using novel dynamic-sized binary pattern and multilevel discrete wavelet transform techniques with TSEEG database |
---|---|
ERA Journal ID | 3391 |
Article Category | Article |
Authors | Barua, Prabal Datta, Keles, Tugce, Dogan, Sengul, Baygin, Mehmet, Tuncer, Turker, Demir, Caner Feyzi, Fujita, Hamido, Tan, Ru-San, Ooi, Chui Ping and Acharya, U. Rajendra |
Journal Title | Biomedical Signal Processing and Control |
Journal Citation | 79 (Part 1) |
Article Number | 104055 |
Number of Pages | 13 |
Year | 2023 |
Publisher | Elsevier |
Place of Publication | Netherlands |
ISSN | 1746-8094 |
Digital Object Identifier (DOI) | https://doi.org/10.1016/j.bspc.2022.104055 |
Web Address (URL) | https://www.sciencedirect.com/science/article/pii/S1746809422005274 |
Abstract | Electroencephalography (EEG) signal is an important physiological signal commonly used in machine learning to decode brain activities, including imagined words and sentences. We aimed to develop an automated lightweight EEG signal-based sentence classification model using a novel dynamic-sized binary pattern (DSBP) textural feature extractor and iterative multi-classifiers based majority voting (IMCMV) algorithm for iterative voting of results calculated using different classifiers for multi-channel EEG signal inputs. A new Turkish sentence EEG(TSEEG) was prospectively acquired. It comprised of 15-second 14-channel EEG signals recorded when 40 volunteers (for each dataset, we collected EEG signals from 20 participants) were either shown or read corresponding to demonstration or listening modes, respectively. Hence, 20 standardized commonly used sentences were obtained in their native Turkish language. The developed sentence classification model extracted 5,400 multilevel deep features from each channel EEG signal segment using the novel DSBP, statistical features, and multilevel discrete wavelet transform (MDWT). 512 features were then chosen using the neighborhood component analysis selection function. k-nearest neighbor and support vector machine classifiers were used to calculate two prediction vectors from the selected features using tenfold cross-validation, i.e., 28 vectors were generated for each 14-channel EEG recording. Finally, the best general voted results were determined for increasing numbers of iteratively calculated prediction vectors using the novel IMCMV algorithm. Channel-wise and voted results were found to be excellent for sentence classification for the TSEEG dataset in both demonstration and listening modes. The DSBP-IMCMV-based model attained the best general classification rates of 98.81% and 98.19% in the demonstration and listening modes, respectively. |
Keywords | Dynamic sized binary pattern; EEG sentence classification; Iterative multi-classifiers based majority voting; Machine learning; Neighborhood component analysis |
Contains Sensitive Content | Does not contain sensitive content |
Public Notes | File reproduced in accordance with the copyright policy of the publisher/author. |
Funder | Türkiye Bilimsel ve Teknolojik Araştırma Kurumu |
Byline Affiliations | School of Business |
University of Technology Sydney | |
Firat University, Turkey | |
Ardahan University, Turkiye | |
HUTECH University of Technology, Vietnam | |
University of Granada, Spain | |
Iwate Prefectural University, Japan | |
National Heart Centre, Singapore | |
Duke-NUS Medical School, Singapore | |
Singapore University of Social Sciences (SUSS), Singapore | |
School of Mathematics, Physics and Computing | |
Institute for Life Sciences and the Environment | |
Centre for Health Research |
https://research.usq.edu.au/item/yy8y3/automated-eeg-sentence-classification-using-novel-dynamic-sized-binary-pattern-and-multilevel-discrete-wavelet-transform-techniques-with-tseeg-database
Download files
Published Version
65
total views122
total downloads0
views this month0
downloads this month