A Method of Few-shot EEG Artifact Detection Based on the Prototype Network

LI Jingcong; LIN Zhenyuan; PAN Weijian; WU Chaohuang; PAN Jiahui

doi:10.6054/j.jscnun.2022065

Journal of South China Normal University (Natural Science Edition) > 2022 > 54(4): 113-120. > DOI: 10.6054/j.jscnun.2022065

LI Jingcong, LIN Zhenyuan, PAN Weijian, WU Chaohuang, PAN Jiahui. A Method of Few-shot EEG Artifact Detection Based on the Prototype Network[J]. Journal of South China Normal University (Natural Science Edition), 2022, 54(4): 113-120. DOI: 10.6054/j.jscnun.2022065

Citation:

PDF (1162 KB)

A Method of Few-shot EEG Artifact Detection Based on the Prototype Network

School of Software, South China Normal University, Guangzhou 510631, China

More Information

Received Date: August 11, 2021
Available Online: September 21, 2022

Graphical Abstract

Abstract

Abstract

Normal EEG signals are susceptible to contamination by various EEG artifacts, resulting in low signal-to-noise ratios. In order to improve the signal-to-noise ratio of EEG signals, a metric-based few-shot learning method was used to detect EEG artifacts. A few-shot learning model named EEG Artifact Prototype Network (EAPNet) based on a prototype network was proposed to detect artifacts in EEG signals. The model was able to learn a nonlinear mapping from EEG features to the target space, calculate the distance of each class prototype representation and classify them according the distance. In addition, the EAPNet model required only a small number of examples of each new class to train the model to achieve accurate recognition of artifact signals. Artifact recognition experiments were conducted in the public EEG artifact dataset TUAR (TUH EEG Artifact Corpus). The EAPNet model is compared with 2 deep learning models (EEGNet, Fully Connected Neural Network (FNN)) and 7 machine learning models (Gaussian NB, Random Forest (RF), Logistic Regression (LR), Lasso Regression (Lasso), Support Vector Machine (SVM), Ridge Regression (Ridge) and Nearest Neighbor Algorithms (KNN)) in a comparative experiment. The experimental results showed that the EAPNet model was an efficient artifact detection method, with a detection accuracy of 69.44%, 77.21% and 80.01% for 2-way K-shot(K=1, 5, 10) tasks respectively. Among all the compared models, the EAPNet model had the highest recognition accuracy.
- EEG signal,
- EEG artifact,
- few-shot learning,
- prototype network

FullText(HTML)

References (27)

References

[1]	吴朝晖, 俞一鹏, 潘纲, 等. 脑机融合系统综述[J]. 生命科学, 2014, 26(6): 645-649. https://www.cnki.com.cn/Article/CJFDTOTAL-SMKX201406013.htm WU Z H, YU Y P, PAN G, et al. Brain-machine integrated systems[J]. Chinese Bulletin of Life Sciences, 2014, 26(6): 645-649. https://www.cnki.com.cn/Article/CJFDTOTAL-SMKX201406013.htm
[2]	KWON O Y, LEE M H, GUAN C, et al. Subject-indepen-dent brain-computer interfaces based on deep convo-lutional neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 31(10): 3839-3852.
[3]	CHATZICHRISTOS C, DAN J, NARAYANAN A M, et al. Epileptic seizure detection in EEG via fusion of multi-view attention-gated U-net deep neural networks[C]//Proceedings of 2020 IEEE Signal Processing in Medicine and Biology Symposium. Philadelphia: IEEE, 2020: 1-7.
[4]	SUPRATAK A, GUO Y. TinySleepNet: an efficient deep learning model for sleep stage scoring based on raw single-channel EEG[C]//Proceedings of 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society. Montreal: IEEE, 2020: 641-644.
[5]	URIGVEN J A, GARCIA-ZAPIRAIN B. EEG artifact removal—state-of-the-art and guidelines[J]. Journal of Neural Engineering, 2015, 12(3): 031001/1-23. doi: 10.1088/1741-2560/12/3/031001
[6]	FATOURECHI M, BASHASHATI A, WARD R K, et al. EMG and EOG artifacts in brain computer interface systems: a survey[J]. Clinical Neurophysiology, 2007, 118(3): 480-494. doi: 10.1016/j.clinph.2006.10.019
[7]	OCHOA C J, POLICH J. P300 and blink instructions[J]. Clinical Neurophysiology, 2000, 111(1): 93-98. doi: 10.1016/S1388-2457(99)00209-6
[8]	GERLA V, KREMEN V, COVASSIN N, et al. Automatic identification of artifacts and unwanted physiologic signals in EEG and EOG during wakefulness[J]. Biomedical Signal Processing and Control, 2017, 31: 381-390. doi: 10.1016/j.bspc.2016.09.006
[9]	KUMAR P S, ARUMUGANATHAN R, SIVAKUMAR K, et al. Removal of artifacts from EEG signals using adaptive filter through wavelet transform[C]//Proceedings of 2008 9th International Conference on Signal Processing. Beijing: IEEE, 2008: 2138-2141.
[10]	HUANG R, HENG F, HU B, et al. Artifacts reduction method in EEG signals with wavelet transform and adaptive filter[C]//Proceedings of International Conference on Brain Informatics and Health. Warsaw: Springer, 2014: 122-131.
[11]	WANG J W, SU F. A new time-frequency method for EEG artifacts removing[C]//Proceedings of 2014 IEEE 3rd International Conference on Cloud Computing and Intelligence Systems. Shenzhen: IEEE, 2014: 341-346.
[12]	SEJNOWSKI T J. Independent component analysis of electroencephalographic data[C]//Proceedings of the 8th International Conference on Neural Information Processing Systems. Cambridge, MA: IEEE, 1995: 1548-1551.
[13]	IRIARTE J, URRESTARAZU E, VALENCIA M, et al. Independent component analysis as a tool to eliminate artifacts in EEG: a quantitative study[J]. Journal of Clinical Neurophysiology, 2003, 20(4): 249-257. doi: 10.1097/00004691-200307000-00004
[14]	RADVNTZ 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. doi: 10.1016/j.jneumeth.2015.01.030
[15]	RADVNTZ T, SCOUTEN J, HOCHMUTH O, et al. Automated EEG artifact elimination by applying machine learning algorithms to ICA-based features[J]. Journal of Neural Engineering, 2017, 14(4): 046004/1-8.
[16]	LEE S S, LEE K, KANG G. EEG artifact removal by bayesian deep learning & ICA[C]//Proceedings of 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society. Montreal: IEEE, 2020: 932-935.
[17]	KHATWANI M, HOSSEINI M, PANELIYA H, et al. Energy efficient convolutional neural networks for EEG artifact detection[C]//Proceedings of 2018 IEEE Biomedical Circuits and Systems Conference(BioCAS). Cleveland: IEEE, 2018: 1-4.
[18]	MANJUNATH N K, PANELIYA H, HOSSEINI M, et al. A low-power LSTM processor for multi-channel brain EEG artifact detection[C]//Proceedings of 2020 21st International Symposium on Quality Electronic Design (ISQED). Santa Clara: IEEE, 2020: 105-110.
[19]	JUNG H G, LEE S W. Few-shot learning with geometric constraints[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 31(11): 4660-4672. doi: 10.1109/TNNLS.2019.2957187
[20]	KOCH G, ZEMEL R, SALAKHUTDINOV R. Siamese neural networks for one-shot image recognition[C]//Procee-dings of ICML Deep Learning Workshop. Lille: ICML, 2015: 1-8.
[21]	VINYALS O, BLUNDELL C, LILLICRAP T, et al. Mat-ching networks for one shot learning[J]. Advances in Neural Information Processing Systems, 2016, 29: 3630-3638.
[22]	SNELL J, SWERSKY K, ZEMEL R. Prototypical networks for few-shot learning[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach: NIPS, 2017: 4080-4090.
[23]	YANG S, WU S H, LIU T L, et al. Bridging the gap between few-shot and many-shot learning via distribution calibration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021(1): 1-13.
[24]	LAWHERN V J, SOLON A J, WAYTOWICH N R, et al. EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces[J]. Journal of Neural Engineering, 2018, 15(5): 056013/1-30.
[25]	SHAH V, GOLMOHAMMADI M, ZIYABARI S, et al. Optimizing channel selection for seizure detection[C]// Proceedings of 2017 IEEE Signal Processing in Medicine and Biology Symposium(SPMB). Philadelphia: IEEE, 2017: 1-5.
[26]	VANABELLE P, HANDSCHUTTER P D, TAHRY R E, et al. Epileptic seizure detection using EEG signals and extreme gradient boosting[J]. The Journal of Biomedical Research, 2020, 34(3): 228-239. doi: 10.7555/JBR.33.20190016
[27]	SHIM K H, JEONG J H, KWON B H, et al. Assistive robotic arm control based on brain-machine interface with vision guidance using convolution neural network[C]//Proceedings of 2019 IEEE International Conference on Systems, Man and Cybernetics. Bari: IEEE, 2019: 2785-2790.

Cited By

Cited by

Periodical cited type(6)

1.	方艳林，王升帅，张伟，张妮，谢璇，张厚勇. 基于PEMS的非四机械尾气碳排放特征探析. 环境监控与预警. 2025(01): 98-102 .
2.	吴雨涟，杨洁，邵智娟，沈春其，裴程伟，秦龙飞，郑嘉兴，徐婷婷，阚诗烨，宋程璐，崔璀. 苏州市机动车排放清单及特征研究. 环境科学学报. 2024(09): 129-139 .
3.	陈佳昊，项雅静. 基于拥堵系数的上海市道路高分辨率碳排放时空分配方法研究. 环境科学与管理. 2024(11): 16-21 .
4.	石文哲，王峰，付合英，李忠飞，王亮，于海洋，唐忠锋. 基于全生命周期法的矿用柴油重卡碳核算. 环境工程学报. 2023(06): 1907-1914 .
5.	菅月诚，彭娜娜，高艳珊，王强. “双碳”背景下细颗粒物和臭氧污染研究进展. 能源环境保护. 2023(05): 190-200 .
6.	代洪娜，曾煜磊，施庆利，孙婷. 碳达峰与碳中和背景下省域高速公路网碳排放精细化测算方法. 华南师范大学学报(自然科学版). 2023(04): 1-13 .

Other cited types(6)

Get Citation

PDF

XML

Article views PDF downloads Cited by(12)

Turn off MathJax

Article Contents

Abstract

References

A Method of Few-shot EEG Artifact Detection Based on the Prototype Network

Abstract

References

Cited by

Periodical cited type(6)

Other cited types(6)

Catalog

Export File

Citation

Format

Content