Eye blink artifact detection based on multi-dimensional EEG feature fusion and optimization

被引:13
作者
Wang, Meng [1 ,2 ]
Cui, Xiaonan [1 ,2 ]
Wang, Tianlei [1 ,2 ]
Jiang, Tiejia [2 ,4 ]
Gao, Feng [2 ,4 ]
Cao, Jiuwen [1 ,2 ,3 ]
机构
[1] Hangzhou Dianzi Univ, Machine Learning & I Hlth Int Cooperat Base Zhejia, Hangzhou 310018, Peoples R China
[2] Hangzhou Dianzi Univ, Artificial Intelligence Inst, Hangzhou 310018, Zhejiang, Peoples R China
[3] Hangzhou Neuro Sci & Technol Co Ltd, Res & Dev Dept, Hangzhou, Peoples R China
[4] Zhejiang Univ, Childrens Hosp, Natl Clin Res Ctr Child Hlth, Dept Neurol,Sch Med, Hangzhou 310003, Peoples R China
基金
中国国家自然科学基金;
关键词
Eye blink detection; Empirical mode decomposition; Common spatial pattern; Particle swarm optimization; REMOVAL; SIGNALS; ELECTROOCULOGRAM;
D O I
10.1016/j.bspc.2023.104657
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Eye blink is the most common artifact in electroencephalogram (EEG), which usually affects the performance of EEG-based applications, such as neurological aided diagnostic analysis. For low spatial resolution EEG signals, current methods generally lack of spatial filtering, leading to a degraded performance. In this paper, a novel eye blink artifact detection algorithm based on multiple EEG feature fusion and PSO optimization is proposed in a few-channel data environment. The forehead FP1 and FP2 electrodes EEGs are decomposed based on empirical mode decomposition (EMD) through autocorrelation coefficients for signal filtering. The EEG variance features are extracted by the Common Spatial Pattern (CSP) filtering to enhance the feature discrimination. The particle swarm optimization (PSO) combined with support vector machine (SVM) is applied for feature fusion and optimization. We evaluate the performance on real recorded EEG dataset by the Children's Hospital of Zhejiang University School of Medicine (CHZU). There contain EEGs with eye blink artifacts of 20 subjects. The results show that the proposed method can achieve the highest accuracy, recall rate, precision and F1 value.
引用
收藏
页数:11
相关论文
共 50 条
[21]   DWT-EMD Feature Level Fusion Based Approach over Multi and Single Channel EEG Signals for Seizure Detection [J].
Jana, Gopal Chandra ;
Agrawal, Anupam ;
Pattnaik, Prasant Kumar ;
Sain, Mangal .
DIAGNOSTICS, 2022, 12 (02)
[22]   Eye blink detection based on multiple Gabor response waves [J].
Li, Jiang-Wei .
PROCEEDINGS OF 2008 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2008, :2852-2856
[23]   Multi-dimensional particle swarm optimization in dynamic environments [J].
Kiranyaz, Serkan ;
Pulkkinen, Jenni ;
Gabbouj, Moncef .
EXPERT SYSTEMS WITH APPLICATIONS, 2011, 38 (03) :2212-2223
[24]   MULTI-DIMENSIONAL PARTICLE SWARM OPTIMIZATION FOR DYNAMIC CLUSTERING [J].
Kiranyaz, Serkan ;
Ince, Turker ;
Yildirim, Alper ;
Gabbouj, Moncef .
EUROCON 2009: INTERNATIONAL IEEE CONFERENCE DEVOTED TO THE 150 ANNIVERSARY OF ALEXANDER S. POPOV, VOLS 1- 4, PROCEEDINGS, 2009, :1398-1405
[25]   Adaptive Particle Swarm Optimization with Multi-dimensional Mutation [J].
Nishio, Toshiki ;
Kushida, Junichi ;
Hara, Akira ;
Takahama, Tetsuyuki .
2015 IEEE 8TH INTERNATIONAL WORKSHOP ON COMPUTATIONAL INTELLIGENCE AND APPLICATIONS (IWCIA) PROCEEDINGS, 2015, :131-136
[26]   Wavelet Design for Automatic Real-Time Eye Blink Detection and Recognition in EEG Signals [J].
Miranda, M. ;
Salinas, R. ;
Raff, U. ;
Magna, O. .
INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL, 2019, 14 (03) :375-387
[27]   EEG decoding method based on multi-feature information fusion for spinal cord injury [J].
Xu, Fangzhou ;
Li, Jincheng ;
Dong, Gege ;
Li, Jianfei ;
Chen, Xinyi ;
Zhu, Jianqun ;
Hu, Jinglu ;
Zhang, Yang ;
Yue, Shouwei ;
Wen, Dong ;
Leng, Jiancai .
NEURAL NETWORKS, 2022, 156 :135-151
[28]   Multi-Dimensional Medical Image Fusion With Complex Sparse Representation [J].
Chen, Yuhang ;
Liu, Aiping ;
Liu, Yu ;
He, Zhiyang ;
Liu, Cong ;
Chen, Xun .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2024, 71 (09) :2728-2739
[29]   Single Channel EEG Artifact Identification Using Two-Dimensional Multi-Resolution Analysis [J].
Taherisadr, Mojtaba ;
Dehzangi, Omid ;
Parsaei, Hossein .
SENSORS, 2017, 17 (12)
[30]   Robust Eye Blink Detection Based on Eye Landmarks and Savitzky-Golay Filtering [J].
Al-gawwam, Sarmad ;
Benaissa, Mohammed .
INFORMATION, 2018, 9 (04)