Emerging Trends in EEG Signal Processing: A Systematic Review

被引：7
作者：
Ramnivas Sharma
Hemant Kumar Meena
机构：
[1] Department of Electrical Engineering, Malaviya National Institute of Technology, Rajasthan, Jaipur
来源：
SN Computer Science | / 5卷 / 4期
关键词：
Classification models; EEG signals; Feature extraction; Graph signal processing; Signal processing;
D O I：
10.1007/s42979-024-02773-w
中图分类号：
学科分类号：
摘要：
This review investigates cutting-edge electroencephalography (EEG) signal processing techniques, focusing on noise reduction, artifact removal, and feature extraction. The study also explores emerging trends such as graph signal processing (GSP), deep learning-based methods, and real-time processing, highlighting their potential in enhancing EEG signal analysis accuracy and efficiency. This research extensively reviews state-of-the-art EEG signal processing techniques and advanced feature extraction methods. Approaches in time, frequency, and time-frequency domains are examined, with applications in cognitive neuroscience, brain–computer interfaces, and clinical diagnostics. The study also explores novel methods like GSP and deep learning, analyzing their impact on EEG signal analysis. The paper presents a comparative analysis of existing methodologies, identifying research gaps and future directions. It emphasizes the significance of GSP in exploring intricate brain networks and dynamic interactions. These findings enhance understanding of brain communication, offering insights into neurological disorders and cognitive functions. Advanced techniques showcased in this study address challenges related to non-stationary and noisy EEG signals, significantly improving accuracy and efficiency in EEG signal analysis. In summary, this review underscores the vital role of EEG signal processing in unraveling the complexities of the human brain. The study’s emphasis on robust algorithms and exploration of innovative methods advances EEG signal analysis. This research sets the stage for future developments, fostering progress in the field of EEG signal processing. © The Author(s).
引用
收藏
相关论文
共 86 条
[1]  
Subasi A., Practical Guide for Biomedical Signals Analysis Using Machine Learning Techniques: A MATLAB Based Approach, (2019)
[2]  
Beres A.M., Time is of the essence: A review of electroencephalog-raphy (EEG) and event-related brain potentials (erps) in language research, Appl Psychophysiol Biofeedback., 42, pp. 247-255, (2017)
[3]  
Novik O., Smirnov F., Volgin M., Novik O., Smirnov F., Volgin M., Structures of the brain, Electromagnetic Geophysical Fields: Precursors to Earthquakes and Tsunamis
[4]  
Impacts on the Brain and Heart, pp. 69-89, (2019)
[5]  
Das S., Tripathy D., Raheja J.L., Real-Time BCI System Design to Control Arduino Based Speed Controllable Robot Using EEG, (2019)
[6]  
Subasi A., EEG signal classification using wavelet feature extraction and a mixture of expert model, Expert Syst Appl, 32, 4, pp. 1084-1093, (2007)
[7]  
Ahmed M.I.B., Alotaibi S., Dash S., Nabil M., Alturki A.O., A review on machine learning approaches in identification of pediatric epilepsy, SN Comput Sci, 3, 6, (2022)
[8]  
Mumtaz W., Ali S.S.A., Yasin M.A.M., Malik A.S., A machine learning framework involving EEG-based functional connectivity to diagnose major depressive disorder (mdd), Med Biol Eng Com-Put, 56, pp. 233-246, (2018)
[9]  
Acharya U.R., Oh S.L., Hagiwara Y., Tan J.H., Adeli H., Subha D.P., Automated EEG-based screening of depression using deep convolutional neural network, Comput Methods Programs Biomed, 161, pp. 103-113, (2018)
[10]  
Anuragi A., Sisodia D.S., Alcohol use disorder detection using EEG signal features and flexible analytical wavelet transform, Biomed Signal Process Control, 52, pp. 384-393, (2019)
123456789