Convolutional Neural Network - Wavelet Transform Fusion for EEG Signal Processing: Explorations and Perspectives
DOI:
https://doi.org/10.53469/wjimt.2025.08(05).20Keywords:
Convolutional Neural Networks, Wavelet Transform, Electroencephalogram Signals, Multimodal DataAbstract
This paper systematically explores the research progress and application potential of the integration of Convolutional Neural Networks (CNNs) and Wavelet Transform (WT) techniques in electroencephalogram (EEG) signal processing. By combining the time-frequency localization analysis of wavelet transforms with the deep feature learning capabilities of CNNs, this approach effectively addresses the traditional challenges of EEG signal processing, such as non-stationarity and subtle signal characteristics. The study identifies core challenges, including insufficient real-time performance due to model complexity, variability in cross-subject generalization, and subjective biases in annotated data. Future directions focus on lightweight dynamic fusion architectures, multimodal data collaborative learning, and enhanced clinical interpretability techniques. Through algorithmic innovations and interdisciplinary collaboration between engineering and medicine, breakthroughs in fields such as brain-machine interfaces and precise diagnosis of neurological diseases are expected.
References
Geng S, Zhou W, Yuan Q, et al. EEG non-linear feature extraction using correlation dimension and Hurst exponent[J]. Neurological research, 2011, 33(9): 908-912.
Stanyard R A, Mason D, Ellis C, et al. Aperiodic and Hurst EEG exponents across early human brain development: A systematic review[J]. Developmental Cognitive Neuroscience, 2024: 101402.
Valdés P, Bosch J, Grave R, et al. Frequency domain models of the EEG[J]. Brain topography, 1992, 4: 309-319.
Al-Fahoum A S, Al-Fraihat A A. Methods of EEG Signal Features Extraction Using Linear Analysis in Frequency and Time‐Frequency Domains[J]. International Scholarly Research Notices, 2014, 2014(1): 730218.
Albera L, Kachenoura A, Comon P, et al. ICA-based EEG denoising: a comparative analysis of fifteen methods[J]. Bulletin of the Polish Academy of Sciences: Technical Sciences, 2012, 60(3 Special issue on Data Mining in Bioengineering): 407-418.
Klug M, Berg T, Gramann K. Optimizing EEG ICA decomposition with data cleaning in stationary and mobile experiments[J]. Scientific Reports, 2024, 14(1): 14119.
Shen M, Yang F, Wen P, et al. A real-time epilepsy seizure detection approach based on EEG using short-time Fourier transform and Google-Net convolutional neural network[J]. Heliyon, 2024, 10(11).
Sadiq M T, Yousaf A, Siuly S, et al. Fast fractional Fourier transform-aided novel graphical Approach for EEG Alcoholism Detection[J]. Bioengineering, 2024, 11(5): 464.
Yao X, Li T, Ding P, et al. Emotion classification based on transformer and CNN for EEG spatial–temporal feature learning[J]. Brain sciences, 2024, 14(3): 268.
Srivastava A, Singh A, Tiwari A K. An efficient hybrid approach for the prediction of epilepsy using CNN with LSTM[J]. International Journal of Artificial Intelligence and Soft Computing, 2022, 7(3): 179-193.
Chen J X, Zhang P W, Mao Z J, et al. Accurate EEG-based emotion recognition on combined features using deep convolutional neural networks[J]. Ieee Access, 2019, 7: 44317-44328.
Madhavan S, Tripathy R K, Pachori R B. Time-frequency domain deep convolutional neural network for the classification of focal and non-focal EEG signals[J]. IEEE Sensors Journal, 2019, 20(6): 3078-3086.
Xin Q, Hu S, Liu S, et al. An attention-based wavelet convolution neural network for epilepsy EEG classification[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022, 30: 957-966.
Hsu W Y, Cheng Y W. EEG-channel-temporal-spectral-attention correlation for motor imagery EEG classification[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023, 31: 1659-1669.
Purwono P, Ma'arif A, Rahmaniar W, et al. Understanding of convolutional neural network (cnn): A review[J]. International Journal of Robotics and Control Systems, 2022, 2(4): 739-748.
Kattenborn T, Leitloff J, Schiefer F, et al. Review on Convolutional Neural Networks (CNN) in vegetation remote sensing[J]. ISPRS journal of photogrammetry and remote sensing, 2021, 173: 24-49.
Azzerboni B, Carpentieri M, La Foresta F, et al. Neural-ICA and wavelet transform for artifacts removal in surface EMG[C]//2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No. 04CH37541). IEEE, 2004, 4: 3223-3228.
Wang X, Wang Y, Liu D, et al. Automated recognition of epilepsy from EEG signals using a combining space–time algorithm of CNN-LSTM[J]. Scientific Reports, 2023, 13(1): 14876.