基于感興趣腦區(qū)LASSO-Granger因果關(guān)系的腦電特征提取算法
doi: 10.11999/JEIT150851
基金項(xiàng)目:
國家自然科學(xué)基金(61201302, 61172134),國家留學(xué)基金(201308330297),浙江省自然科學(xué)基金(LY15F010009)
Feature Extraction of Electroencephalography Based on LASSO-Granger Causality Between Brain Region of Interest
Funds:
The National Natural Science Foundation of China (61201302, 61172134), State Scholarship Fund of China (201308330297), Natural Science Foundation of Zhejiang Province (LY15F010009)
-
摘要: 該文將腦功能網(wǎng)絡(luò)引入到腦電特征提取的研究中,提出一種基于感興趣腦區(qū)LASSO-Granger因果關(guān)系的新方法,克服了當(dāng)前基于孤立腦區(qū)的研究方法的不足。先利用主成分分析提取各感興趣區(qū)的最大主成分,然后計算它們之間的LASSO-Granger因果度量,并將其作為特征向量,最后輸入支持向量機(jī)分類器,對BCI Competition IV dataset 1中的4組數(shù)據(jù)進(jìn)行分類識別。結(jié)果表明,基于感興趣腦區(qū)間LASSO-Granger因果關(guān)系分析和支持向量機(jī)分類器的方法對不同的運(yùn)動想象任務(wù)識別率較高,提供了新的研究思路。
-
關(guān)鍵詞:
- 腦功能網(wǎng)絡(luò) /
- LASSO-Granger /
- 感興趣腦區(qū) /
- 特征提取
Abstract: Brain functional network is introduced to feature extraction of ElectroEncephaloGraphy (EEG), and a novel method is proposed based on Least Absolute Shrinkage and Selection Operator (LASSO)-Granger causality between Region Of Interest (ROI) in the brain, in order to overcome the inherent deficiencies of research methods based on isolated brain region. Firstly, the maximum principal component of ROIs is extracted by Principal Component Analysis (PCA), and then causality values between ROIs are calculated by LASSO-Granger. Finally, the values are used as the input vector for Support Vector Machine (SVM), and then four datasets of BCI Competition IV Dataset 1 are used for classification.Experimental results show that different motor imagery tasks are successfully identified by the method of SVM classifier combined with feature extraction which is based on LASSO-Granger causality between the brain region of interest (ROIs). This method provides a new idea for the study of extracting EEG features.-
Key words:
- Brain functional network /
- LASSO-Granger /
- Region Of Interest (ROI) /
- Feature extraction
-
ARBONELL F, NAGANO-SAITO A, LEYTON M, et al. Dopamine precursor depletion impairs structure and efficiency of resting state brain functional networks[J]. Neuropharmacology, 2014, 84: 90-100. 閆錚, 高小榕, 應(yīng)俊. 基于認(rèn)知功能連接的信息流增益計算方法及應(yīng)用[J]. 電子與信息學(xué)報, 2014, 36(11): 2756-2761. doi: 10.3724/SP.J.1146.2013.02019. YAN Zheng, GAO Xiaorong, and YING Jun. The flow gain methods and applications based on cognition functional connectivity[J]. Journal of Electronics Information Technology, 2014, 36(11): 2756-2761. doi: 10.3724/SP.J.1146. 2013.02019. GRABBERR L, JOLA C, BERRA G, et al. Motor imagery training improves precision of an upper limb movement in patients with hemiparesis[J]. NeuroRehabilitation, 2015, 37(2): 263-271. DING M, CHEN Y, and BRESSLER S L. Granger causality: basic theory and application to neuroscience[J]. Handbook of Time Series Analysis: Recent Theoretical Developments and Applications, 2006, 17: 437-460. 吳明權(quán), 李海峰, 馬琳. 單通道腦電信號中眼電干擾的自動分離方法[J]. 電子與信息學(xué)報, 2015, 37(2): 367-372. doi: 10.11999/JEIT140602. WU Mingquan, LI Haifeng, and MA Lin. Automatic electrooculogram separation method for single channel electroencephalogram signals[J]. Journal of Electronics Information Technology, 2015, 37(2): 367-372. doi: 10.11999 /JEIT140602. 呂俊, 謝勝利, 章晉龍. 腦-機(jī)接口中基于ERS/ERD的自適應(yīng)空間濾波算法[J]. 電子與信息學(xué)報, 2009, 31(2): 314-318. Jun, XIE Shengli, and ZHANG Jinlong. Adaptive spatial filter based on ERD/ERS for brain-computer interfaces[J]. Journal of Electronics Information Technology, 2009, 31(2): 314-318. 李衛(wèi)娜, 鄭小林, 吳南, 等. 應(yīng)用因果分析方法對癲癇發(fā)作間期頭皮腦電信號進(jìn)行致癇灶定側(cè)[J]. 國際生物醫(yī)學(xué)工程雜志, 2013, 36(5): 261-265. LI Weina, ZHENG Xiaolin, WU Nan, et al. Epileptic foci lateralization from interictal scalp EEG by applying causal analysis[J]. International Journal of Biomedical Engineering, 2013, 36(5): 261-265. EPSTEIN C M, ADHIKARI B M, GROSS R, et al. Application of high-frequency Granger causality to analysis of epileptic seizures and surgical decision making[J]. Epilepsia, 2014, 55(12): 2038-2047. NICOLAOU N, HOURR S, ALEXANDROU P, et al. EEG- based automatic classification of awake versus anesthetized state in general anesthesia using Granger causality[J]. PLoS One, 2012, 7(3): e33869. ARNOLD A, LIU Y, and ABE N. Temporal causal modeling with graphical granger methods[C]. Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, 2007: 66-75. BENJAMIN B, DORNHERE G, KRAUEDAT M, et al. The non-invasive Berlin brain-computer interface: fast acquisition of effective performance in untrained subjects[J]. NeuroImage, 2007, 37(2): 539-550. JOHN S . Cortical functions[Z]. Routledge, 1999: 30-45. GAO Qing, DUAN Xujun, and CHEN Huafu. Evaluation of effective connectivity of motor areas during motor imagery and execution using conditional Granger causality[J]. NeuroImage, 2011, 54(2): 1280-1288. FRASER A M and SWINNEY H L. Independent coordinates for strange attractors from mutual information[J]. Physical Review A, 1986, 33(2): 1134-1140. ZHANG H, CHIN Z Y, ANG K K, et al. Optimum spatio- spectral filtering network for braincomputer interface[J]. IEEE Transactions on Neural Networks, 2011, 22(1): 52-63. PARK C, LOONEY D, AHRABIAN A, et al. Classification of motor imagery BCI using multivariate empirical mode decomposition[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2013, 21(1): 10-22. -
計量
- 文章訪問數(shù): 1860
- HTML全文瀏覽量: 231
- PDF下載量: 482
- 被引次數(shù): 0