基于深度网络和自适应阈值的脑电信号分类和伪影消除

doi:10.1007/s12204-023-2609-8

J Shanghai Jiaotong Univ Sci ›› 2025, Vol. 30 ›› Issue (4): 693-701.doi: 10.1007/s12204-023-2609-8

基于深度网络和自适应阈值的脑电信号分类和伪影消除

1. Department of Electronics and Communication Engineering, Jawaharlal Nehru Technological University Kakinada, Kakinada 533003, India; 2. Department of Electronics and Communication Engineering, Velagapudi Ramakrishna Siddhartha Engineering College, Vijayawada 520007, India; 3. Department of Electrical, Electronics and Communication Engineering, Gandhi Institute of Technology and Management, Hyderabad 502329, India

收稿日期:2022-02-11 接受日期:2022-07-07 出版日期:2025-07-31 发布日期:2025-07-31

Electroencephalogram Signal Classification and Artifact Removal with Deep Networks and Adaptive Thresholding

MATHE Mariyadasu ^1,3, MIDIDODDI Padmaja ², BATTULA TIRUMALA Krishna ¹

1. Department of Electronics and Communication Engineering, Jawaharlal Nehru Technological University Kakinada, Kakinada 533003, India; 2. Department of Electronics and Communication Engineering, Velagapudi Ramakrishna Siddhartha Engineering College, Vijayawada 520007, India; 3. Department of Electrical, Electronics and Communication Engineering, Gandhi Institute of Technology and Management, Hyderabad 502329, India

Received:2022-02-11 Accepted:2022-07-07 Online:2025-07-31 Published:2025-07-31

摘要/Abstract

摘要： 脑电信号等生理信号在采集和处理过程中经常受到伪影干扰。其中一些伪影可能会恶化与有意义信息相关的信号的基本属性。这些伪影大多是由于人们在获取过程中不自觉的运动或动作而产生的。因此，建议使用信号处理的方法消除这些伪影。本文提出了两种伪影的分类和消除机制。第一阶段使用定制的深度网络对干净的脑电信号和伪影信号进行分类。分类是在特征层上进行的，使用卷积层提取公共空间模式特征，然后使用支持向量机分类器对这些特征进行分类。在第二阶段，对伪影信号进行经验模态分解，并提出自适应阈值消除机制。在该迭代机制中，每个固有模态分解的阈值都会发生改变。

关键词: 伪影消除, 深度网络, 脑电信号分类, 经验模态分解

Abstract: Physiological signals such as electroencephalogram (EEG) signals are often corrupted by artifacts during the acquisition and processing. Some of these artifacts may deteriorate the essential properties of the signal that pertains to meaningful information. Most of these artifacts occur due to the involuntary movements or actions the human does during the acquisition process. So, it is recommended to eliminate these artifacts with signal processing approaches. This paper presents two mechanisms of classification and elimination of artifacts. In the first step, a customized deep network is employed to classify clean EEG signals and artifact-included signals. The classification is performed at the feature level, where common space pattern features are extracted with convolutional layers, and these features are later classified with a support vector machine classifier. In the second stage of the work, the artifact signals are decomposed with empirical mode decomposition, and they are then eliminated with the proposed adaptive thresholding mechanism where the threshold value changes for every intrinsic mode decomposition in the iterative mechanism.

中图分类号:

TN911.7
R318

. 基于深度网络和自适应阈值的脑电信号分类和伪影消除[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(4): 693-701.

MATHE Mariyadasu, MIDIDODDI Padmaja, BATTULA TIRUMALA Krishna. Electroencephalogram Signal Classification and Artifact Removal with Deep Networks and Adaptive Thresholding[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(4): 693-701.

参考文献

[1] SARIN M, VERMA A, MEHTA D H, et al. Automated ocular artifacts identification and removal from EEG data using hybrid machine learning methods[C]//2020 7th International Conference on Signal Processing and Integrated Networks. Noida: IEEE, 2020: 1054-1059.
[2] B ABD RANI M S, BT MANSOR W. Detection of eye blinks from EEG signals for home lighting system activation [C]//2009 6th International Symposium on Mechatronics and its Applications. Sharjah: IEEE, 2009: 1-4.
[3] MUTHUKUMARASWAMY S D. High-frequency brain activity and muscle artifacts in MEG/EEG: A review and recommendations [J]. Frontiers in Human Neuroscience, 2013, 7: 138.
[4] MATHE M, MIDIDODDI P, KRISHNA B T. Artifact removal methods in EEG recordings: A review [J]. Proceedings of Engineering and Technology Innovation, 2022, 20: 35-56.
[5] ZHENG W L, LU B L. Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks [J]. IEEE Transactions on Autonomous Mental Development, 2015, 7(3): 162-175.
[6] SHUKLA S, ROY V, PRAKASH A. Wavelet based empirical approach to mitigate the effect of motion artifacts from EEG signal [C]//2020 IEEE 9th International Conference on Communication Systems and Network Technologies. Gwalior: IEEE, 2020: 323-326.
[7] HASSAN M, BOUDAOUD S, TERRIEN J, et al. Combination of canonical correlation analysis and empirical mode decomposition applied to denoising the labor electrohysterogram [J]. IEEE Transactions on Bio-Medical Engineering, 2011, 58(9): 2441-2447.
[8] AUNG S T, WONGSAWAT Y. Analysis of EEG signals contaminated with motion artifacts using multiscale modified-distribution entropy [J]. IEEE Access, 2021, 9: 33911-33921.
[9] GAJBHIYE P, MINGCHINDA N, CHEN W, et al. Wavelet domain optimized savitzky–golay filter for the removal of motion artifacts from EEG recordings [J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-11.
[10] PHADIKAR S, SINHA N, GHOSH R. Automatic eyeblink artifact removal from EEG signal using wavelet transform with heuristically optimized threshold [J]. IEEE Journal of Biomedical and Health Informatics, 2021, 25(2): 475-484.
[11] ISLAM M K, RASTEGARNIA A. Wavelet-based artifact removal algorithm for EEG data by optimizing mother wavelet and threshold parameters [C]//2020 Emerging Technology in Computing, Communication and Electronics. Bangladesh: IEEE, 2020: 1-6.
[12] MASHHADI N, KHUZANI A Z, HEIDARI M, et al. Deep learning denoising for EOG artifacts removal from EEG signals [C]// 2020 IEEE Global Humanitarian Technology Conference. Seattle: IEEE, 2020: 1-6.
[13] LECUN Y, BENGIO Y, HINTON G. Deep learning [J]. Nature, 2015, 521(7553): 436-444.
[14] TABAR Y R, HALICI U. A novel deep learning approach for classification of EEG motor imagery signals [J]. Journal of Neural Engineering, 2017, 14(1): 016003.
[15] BASHIVAN P, YEASIN M, BIDELMAN G M. Temporal progression in functional connectivity determines individual differences in working memory capacity [C]//2017 International Joint Conference on Neural Networks. Anchorage: IEEE, 2017: 2943-2949.
[16] RADÜNTZ T, SCOUTEN J, HOCHMUTH O, et al. EEG artifact elimination by extraction of ICA-component features using image processing algorithms [J]. Journal of Neuroscience Methods, 2015, 243: 84-93.
[17] LÄNGKVIST M, KARLSSON L, LOUTFI A. A review of unsupervised feature learning and deep learning for time-series modeling [J]. Pattern Recognition Letters, 2014, 42: 11-24.
[18] NGUYEN A, YOSINSKI J, CLUNE J. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images [C]//2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 427-436.
[19] MATHE M, PADMAJA M, TIRUMALA KRISHNA B. Intelligent approach for artifacts removal from EEG signal using heuristic-based convolutional neural network [J]. Biomedical Signal Processing and Control, 2021, 70: 102935.
[20] WAHIBA M, BEKKA R E. New denoising method based on empirical mode decomposition and improved thresholding function [J]. Journal of Physics Conference Series, 2017, 787(1): 012014.
[21] KOPSINIS Y, MCLAUGHLIN S. Development of EMD-based denoising methods inspired by wavelet thresholding [J]. IEEE Transactions on Signal Processing, 2009, 57(4): 1351-1362.
[22] BHATTACHARYYA A, SINGH L, PACHORI R B. Fourier–Bessel series expansion based empirical wavelet transform for analysis of non-stationary signals [J]. Digital Signal Processing, 2018, 78: 185-196.
[23] SREEJA S R, SAHAY R R, SAMANTA D, et al. Removal of eye blink artifacts from EEG signals using sparsity [J]. IEEE Journal of Biomedical and Health Informatics, 2018, 22(5): 1362-1372.
[24] MAMMONE N, LA FORESTA F, MORABITO F C. Automatic artifact rejection from multichannel scalp EEG by wavelet ICA [J]. IEEE Sensors Journal, 2012, 12(3): 533-542.
[25] MAMMONE N, MORABITO F C. Enhanced automatic wavelet independent component analysis for electroencephalographic artifact removal [J]. Entropy, 2014, 16(12): 6553-6572.

基于深度网络和自适应阈值的脑电信号分类和伪影消除

Electroencephalogram Signal Classification and Artifact Removal with Deep Networks and Adaptive Thresholding

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 14

编辑推荐

Metrics

本文评价

[1]	徐寒, 朱三立, 张腾飞, 陈舒, 刘明祥. 低压配电系统剩余电流保护与重合闸逻辑组合优化方法[J]. 上海交通大学学报, 2025, 59(7): 901-911.
[2]	李芬, 孙凌, 王亚维, 屈爱芳, 梅念, 赵晋斌. 基于CEEMDAN-GSA-LSTM和SVR的光伏功率短期区间预测[J]. 上海交通大学学报, 2024, 58(6): 806-818.
[3]	宋立博a，费燕琼b. 新型Lite YOLOv4-Tiny算法及其在裂纹智能检测中的应用[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(3): 528-536.
[4]	孙苗, 杨钧凯, 吴立. 改进希尔伯特-黄变换含噪振动信号时频分析[J]. 上海交通大学学报, 2023, 57(12): 1648-1656.
[5]	郑奕扬, 倪何, 金家善. 基于MSOP的蒸汽动力系统单参数运行稳定性评估方法[J]. 上海交通大学学报, 2021, 55(11): 1438-1444.
[6]	卓鹏程, 严瑾, 郑美妹, 夏唐斌, 奚立峰. 面向滚动轴承全生命周期故障诊断的GA-OIHF Elman神经网络算法[J]. 上海交通大学学报, 2021, 55(10): 1255-1262.
[7]	李春祥, 张浩怡. 基于混合多变量经验模态分解和极限学习机的非平稳过程预测[J]. 上海交通大学学报, 2020, 54(4): 376-386.
[8]	李春祥，裴杨从琪，殷潇. 基于Hermite组合核EMD-WT-LSSVM的非平稳非高斯风压预测[J]. 上海交通大学学报, 2019, 53(10): 1249-1258.
[9]	吴军a, b，黎国强a，吴超勇a，程一伟c，邓超c. 数据驱动的滚动轴承性能衰退状态监测方法[J]. 上海交通大学学报, 2018, 52(5): 538-544.
[10]	江春冬1,2，王景玉1，杜太行1,2，郝静1,3，龙超1. 基于变分模态分解算法的单通道无线电混合信号分离[J]. 上海交通大学学报, 2018, 52(12): 1618-1626.
[11]	刘涛, 杜世昌, 黄德林, 任斐, 梁鑫光. 基于改进的集合经验模态方法振动信号分解[J]. 上海交通大学学报, 2016, 50(9): 1452-1459.
[12]	焦向东, 唐建, 戴波, 丁学鹏. 基于Hilbert-Huang变换的管道超声检测信号处理[J]. 上海交通大学学报, 2016, 50(10): 1646-1650.
[13]	耿超1，王丰华1，黄荣辉2，张君1，张欣2，冯琳1. 基于改进Hilbert-Huang变换算法的电气化铁路谐波检测[J]. 上海交通大学学报（自然版）, 2014, 48(09): 1225-1230.
[14]	李方溪, 陈桂明, 刘希亮, 张倩, 李胜朝. 希尔伯特-黄变换端点效应的自适应端点相位正弦延拓方法 [J]. 上海交通大学学报（自然版）, 2013, 47(04): 594-601.