EEG Artifact Removal System for Depression Using a Hybrid Denoising Approach

Introduction: Clinicians use several computer-aided diagnostic systems for depression to authorize their diagnosis. An electroencephalogram  (EEG) may be used as an objective tool for early diagnosis of depression and controlling it from reaching a severe and permanent state. However, artifact contamination reduces the accuracy in EEG signal processing systems. Methods: This work proposes a novel denoising method based on empirical mode decomposition (EMD) with detrended fluctuation analysis (DFA) and wavelet packet transform. At first, real EEG recordings corresponding to depressed patients are decomposed into various mode functions by applying EMD. Then, DFA is used as the mode selection criteria. Further wavelet packets decomposition (WPD) evaluation is used to extract the cleaner signals. Results: Simulations were carried out on real EEG databases for depression to demonstrate the effectiveness of the proposed techniques. To conclude the efficacy of the proposed technique, we identified signal-to-noise ratio (SNR) and mean absolute error  (MAE). The results show improved SNR and lower values of MAE for the combined EMD-DFA-WPD technique. Also, random forest and SVM (Support Vector Machine)-based classification showed improved accuracy of 98.51% and 98.10% for the proposed denoising technique, respectively. Whereas the accuracy of the EMD-DFA is 98.01% and 95.81% and EMD combined with DWT technique is 98.0% and 97.21% for the EMD- DFA technique for RF and SVM, respectively, as compared to the proposed method. Also, the classification performance for both classifiers was compared with and without denoising to highlight the effectiveness of the proposed technique. Conclusion: Our proposed denoising system results in a better classification of depressed and healthy individuals. These results can be further analyzed using other approaches to solve the mode mixing problem of the EMD approach.