Integrating wavelet signal processing and machine learning for EEG-based detection of brain diseases with representative channel selection
Technology and Health Care · 12.11.2026
DOI: 10.1177/09287329261504269 ↗Kurz gefasst
Fachartikel in der Zeitschrift Technology and Health Care, online erschienen am 12.11.2026. Verfasst von Jia Wen Li und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou, China. Die Arbeit nennt 54 Literaturangaben. Gefördert von: Neijiang Philosophy and Social Science Planning Project, Open Research Fund of State Key Laboratory of Digital Medical Engineering, Foundation of the 2023 Higher Education Science Research Plan of the China Association of Higher Education.
Abstract (Originalsprache)
Background
Brain diseases pose a significant global health challenge, and their diagnosis often relies on subjective clinical assessments.
Objective
To this end, this study proposes an integrated wavelet signal processing and machine learning framework for single-channel Electroencephalography (EEG)-based detection of brain diseases with representative channel selection.
Methods
First, EEG signals are decomposed into rhythm-specific sub-bands using the Discrete Wavelet Packet Transform (DWPT). Then, for each rhythm, a multi-dimensional feature matrix (MFM) is constructed by integrating Approximate Entropy (AE), Rhythm Energy Ratio (RER), C0-complexity (C0), and Zero-crossing Rate (ZCR), which comprehensively models the EEG characteristics. Six classifiers were compared under subject-level leave-one-subject-out cross-validation, and Decision Tree (DT) was selected as the representative classifier. Each channel was then evaluated independently as a complete single-channel system, and representative channels were identified from the completed results.
Results
Validated on publicly available datasets for SCHIZ (schizophrenia), UNM (Parkinson's disease), and MPHCE (depression), the method achieves impressive accuracies of 84.52% (F4), 86.54% (F4), and 93.10% (Fp1), respectively, using single-channel EEG electrode.
Conclusions
Such results demonstrate that the proposed approach maintains robust detection performance in each of the three disease-specific tasks. The framework is lightweight by design, using only a single EEG channel and a single simple machine-learning model for classification. It needs no multi-channel feature concatenation or decision-level fusion. This single-channel design suits hardware and data sources with limited resources, and may support the development of low-cost portable EEG systems.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou, China.
- International Joint Research Center for Perception and Control of Intelligent Rehabilitation Systems of Sichuan Province, Chengdu University, Chengdu, China.
- ZUMRI-LYG Joint Laboratory, Zhuhai UM Science and Technology Research Institute, Zhuhai, China.
- Yantai Institute, China Agricultural University, Yantai, China.
- School of Artificial Intelligence, Neijiang Normal University, Neijiang, China.
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China.
ORCID-Profile: Jia Wen Li, Xi Ming Ren, Wei Bin Lin, Yue Heng Peng, Yue Yu, Shuang Zhang, Rong Jun Chen
Förderung
- Neijiang Philosophy and Social Science Planning Project
- Open Research Fund of State Key Laboratory of Digital Medical Engineering
- Foundation of the 2023 Higher Education Science Research Plan of the China Association of Higher Education
- Research Fund of Guangdong Polytechnic Normal University
- Foundation of the Sichuan Research Center of Applied Psychology
- Open Research Fund of International Joint Research Center for Perception and Control of Intelligent Rehabilitation Systems of Sichuan Province
- Graduate Education Demonstration Base Project of Guangdong Polytechnic Normal University
- Sichuan Science and Technology Program
Zitieren
APA
Li, J. W., Ren, X. M., Liu, J. M., Lin, W. B., Peng, Y. H., Huang, Y. S., Yu, Y., Zhang, S., Liu, X., & Chen, R. J. (2026). Integrating wavelet signal processing and machine learning for EEG-based detection of brain diseases with representative channel selection. Technology and Health Care. https://doi.org/10.1177/09287329261504269
Vancouver
Li JW, Ren XM, Liu JM, Lin WB, Peng YH, Huang YS, et al. Integrating wavelet signal processing and machine learning for EEG-based detection of brain diseases with representative channel selection. Technology and Health Care. 2026. doi:10.1177/09287329261504269
BibTeX
@article{Li2026,
author = {Li, Jia Wen and Ren, Xi Ming and Liu, Jin Ming and Lin, Wei Bin and Peng, Yue Heng and Huang, Yue Sheng and Yu, Yue and Zhang, Shuang and Liu, Xin and Chen, Rong Jun},
title = {Integrating wavelet signal processing and machine learning for EEG-based detection of brain diseases with representative channel selection},
journal = {Technology and Health Care},
year = {2026},
doi = {10.1177/09287329261504269}
}
EUVIMED