EEG Artifact Removal System for Depression Using a Hybrid Denoising Approach

被引:6
|
作者
Kaur, Chamandeep [1 ]
Singh, Preeti [1 ]
Sahni, Sukhtej [2 ]
机构
[1] Panjab Univ Chandigarh, Dept Elect & Commun Engn, Chandigarh, India
[2] Cheema Med Complex, Dept Psychiat, Mohali, India
关键词
EEG; Wavelets; Artifacts; Empirical Mode Decomposition (EMD); Depression; EMPIRICAL MODE DECOMPOSITION; OCULAR ARTIFACTS; PERFORMANCE; REDUCTION; DIAGNOSIS; SUPPRESSION; FILTER;
D O I
10.32598/bcn.2021.1388.2
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
Introduction: Several computer-aided diagnosis systems for depression are suggested for use by clinicians to authorize the diagnosis. EEG may be used as an objective analysis tool for identifying depression in the initial stage to avoid 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 denoi sing method based on Empirical Mode Decomposition (EMD) (with Detrended Fluctuation Analysis (DFA) and wavelet packet transform. Initially, real EEG recordings corresponding to depression patients are decomposed into various mode functions by applying EMD. Then, DFA is used as the mode selection criteria. Further Wavelet Packets Decomposition (WPD)-based evaluation is applied to extract the cleaner signal. Results: Simulations were conducted on real EEG databases for depression to demonstrate the effects of the proposed techniques. To conclude the efficacy of the proposed technique, SNR and MAE were identified. The obtained results indicated improved signal-to-noise ratio and lower values of MAE for the combined EMD-DFA-WPD technique. Additionally, Random Forest and SVM (Support Vector Machine)-based classification revealed the improved accuracy of 98.51% and 98.10% for the proposed denoising technique. Whereas the accuracy of the EMD-DFA is 98.01% and 95.81% and EMD combined with DWT technique equaled 98.0% and 97.21% for the EMD-DFA technique for RF and SVM, respectively, compared to the proposed method. Furthermore, the classification performance for both classifiers was compared with and without denoising to highlight the effects of the proposed technique. Conclusion: Proposed denoising system results in better classification of depressed and healthy individuals resulting in a better diagnosing system. These results can be further analyzed using other approaches as a solution to the mode mixing problem of the EMD approach.
引用
收藏
页码:465 / 476
页数:12
相关论文
共 50 条
  • [31] Evaluation of Artifact Subspace Reconstruction for Automatic EEG Artifact Removal
    Chang, Chi-Yuan
    Hsu, Sheng-Hsiou
    Pion-Tonachini, Luca
    Jung, Tzyy-Ping
    2018 40TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2018, : 1242 - 1245
  • [32] Removal of Artifact from EEG Signal using Differential Evolution Algorithm
    Sheniha, S. Femilin
    Priyadharsini, S. Suja
    Rajan, S. Edward
    2013 INTERNATIONAL CONFERENCE ON COMMUNICATIONS AND SIGNAL PROCESSING (ICCSP), 2013, : 134 - 138
  • [33] Artifact Removal from EEG Signals Using the Total Variation Method
    Kim, Min-Ki
    Kim, Sung-Phil
    2015 10TH ASIAN CONTROL CONFERENCE (ASCC), 2015,
  • [34] ECG Artifact Removal of EEG signal using Adaptive Neural Network
    Routray, Lipsa
    Biswal, Pradyut
    Pattanaik, Satya Ranjan
    2018 IEEE 13TH INTERNATIONAL CONFERENCE ON INDUSTRIAL AND INFORMATION SYSTEMS (IEEE ICIIS), 2018, : 116 - 119
  • [35] Real-Time Hybrid Ocular Artifact Detection and Removal for Single Channel EEG
    Majmudar, Charvi A.
    Mahajan, Ruhi
    Morshed, Bashir I.
    2015 IEEE INTERNATIONAL CONFERENCE ON ELECTRO/INFORMATION TECHNOLOGY (EIT), 2015, : 330 - 334
  • [36] Automatic removal of the eye blink artifact from EEG using an ICA-based template matching approach
    Li, YD
    Ma, ZW
    Lu, WK
    Li, YD
    PHYSIOLOGICAL MEASUREMENT, 2006, 27 (04) : 425 - 436
  • [37] Removal of ocular artifact from the EEG: a review
    Croft, RJ
    Barry, RJ
    NEUROPHYSIOLOGIE CLINIQUE-CLINICAL NEUROPHYSIOLOGY, 2000, 30 (01): : 5 - 19
  • [38] Automating muscle artifact removal in ictal EEG
    Vergult, A
    De Clereq, W
    Vanrumste, B
    Van Huffel, S
    Van Hees, J
    Palmini, A
    Van Paesschen, W
    EPILEPSIA, 2005, 46 : 322 - 322
  • [39] Combining TMS and EEG: A touchstone for artifact removal
    Marchesotti, S.
    Plomp, G.
    Herzog, M. H.
    PERCEPTION, 2010, 39 : 133 - 133
  • [40] Artifact Removal Methods in Motor Imagery of EEG
    Zhu, Yanlong
    Wang, Zhongyu
    Dai, Chenglong
    Pi, Dechang
    INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING - IDEAL 2017, 2017, 10585 : 287 - 294