基于脑电的立体视频加速度的特征识别

doi:10.12068/j.issn.1005-3026.2019.10.004

东北大学学报:自然科学版 ›› 2019, Vol. 40 ›› Issue (10): 1386-1391.DOI: 10.12068/j.issn.1005-3026.2019.10.004

基于脑电的立体视频加速度的特征识别

沈丽丽¹，耿小荃¹，徐礼胜²

(1. 天津大学电气自动化与信息工程学院，天津300072; 2. 东北大学医学与生物信息工程学院，辽宁沈阳110169)

收稿日期:2018-12-27 修回日期:2018-12-27 出版日期:2019-10-15 发布日期:2019-10-10
通讯作者: 沈丽丽
作者简介:沈丽丽(1978-)，女，天津人，天津大学副教授.
基金资助:
国家自然科学基金资助项目(61520106002，61471262，61773110).

EEG-Based Feature Recognition of Stereoscopic Video Acceleration

SHEN Li-li¹， GENG Xiao-quan¹， XU Li-sheng²

1. School of Electrical and Information Engineering， Tianjin University， Tianjin 300072，China; 2. School of Medicine & Biological Information Engineering， Northeastern University， Shenyang 110169， China.

Received:2018-12-27 Revised:2018-12-27 Online:2019-10-15 Published:2019-10-10
Contact: SHEN Li-li
About author:-
Supported by:
-

摘要/Abstract

摘要： 构建一种能够自适应提取脑电特征的PMEMD-2JSD-CSP模型，明确了立体视频的两类匀加速深度运动的可分性.利用部分噪声辅助多变量经验模态分解(PNA-MEMD)对脑电(EEG)信号进行分解得到本征模态函数(IMF)，应用基于詹森-香农散度(JSD)的有效因子对IMF进行两次不同范围的自适应筛选，筛选结果按照权重叠加构成重构信号.利用共空间模式(CSP)对重构信号进行空域特征提取，支持向量机(SVM)对特征进行分类，分类正确率最高为73.16%，证明了该模型对两类EEG信号特征提取的有效性.

关键词: 脑电, 立体深度匀加速运动, 视觉不舒适, 多变量经验模态分解, 共空间模式

Abstract: A PMEMD-2JSD-CSP model capable of adaptively extracting EEG features was established to clarify the separability of two classes uniform acceleration motion in deep of stereoscopic video. EEG signals were decomposed by the partial noise assisted multivariate empirical mode decomposition(PNA-MEMD)algorithm to obtain the intrinsic mode function(IMF)at each scale. An effective factor based on Jensen-Shannon distance(JSD)was used to select IMF adaptively from two different ranges， and the screening results were combined according to the weights to form a reconstructed signal. At last， the common spatial pattern(CSP)approach was applied to extract spatial features of the reconstructed signals， and the support vector machine(SVM)algorithm was employed to classify the spatial features. The best classification correct rate is 73.16%， which proves the validity of the feature extraction model for two classes of EEG signals.

Key words: EEG, stereoscopic uniform acceleration motion in deep, visual uncomfortable, MEMD(multivariate empirical mode decomposition), CSP(common spatial pattern)

中图分类号:

TN911.6

沈丽丽，耿小荃，徐礼胜. 基于脑电的立体视频加速度的特征识别[J]. 东北大学学报:自然科学版, 2019, 40(10): 1386-1391.

SHEN Li-li， GENG Xiao-quan， XU Li-sheng. EEG-Based Feature Recognition of Stereoscopic Video Acceleration[J]. Journal of Northeastern University Natural Science, 2019, 40(10): 1386-1391.

参考文献

[1]Yano S，Emoto M，Mitsuhashi T.Two factors in visual fatigue caused by stereoscopic HDTV images［J］.Displays，2004，25(4):141-150.
[2]Jung Y J，Lee S I，Sohn H，et al.Visual comfort assessment metric based on salient object motion［J］.Journal of Electronic Imaging，2012，21(1):011008.
[3]Speranza F，Tam W J，Renaud R，et al.Effect of disparity and motion on visual comfort of stereoscopic images［C］//Proceedings of SPIE.San Jose，2006:6055.
[4]Shen L L，Du W R，Wang C.Event-related potentials measurement of perception to 3D motion in depth［J］.China Communications，2015，12(5):93-96.
[5]Park C，Looney D，Rehman N U，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.
[6]Huang N E，Zheng S，Steven R，et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear non-stationary time series analysis［J］.Proceedings of the Royal Society A—Mathematical Physical and Engineering Sciences，1998，454(1971):903-995.
[7]Rehman N，Mandic D P.Multivariate empirical mode decomposition［J］.Proceedings of the Royal Society A-Mathematical Physical and Engineering Sciences，2010，466(2117):1291-1302.
[8]Rehman N，Mandic D P.Filter bank property of multivariate empirical mode decomposition［J］.IEEE Transactions on Signal Processing，2011，59(5):2421-2426.
[9]Gaur P，Pachori R B，Wang H，et al.A multivariate empirical mode decomposition based filtering for subject independent BCI［C］//The 27th Irish Signals and Systems Conference(ISSC).Derry:IEEE，2016:1-7.
[10]韩笑，佘青山，高云园，等.基于NA-MEMD和互信息的脑电特征提取方法［J］.传感技术学报，2016，29(8)，1140-1148.(Han Xiao，She Qing-shan，Gao Yun-yuan，et al.Feature extraction of EEG based on NA-MEMD and mutual imformatin［J］.Chinese Journal of Sensors and Actuators，2016，29(8):1140-1148.)
[11]Du S P，Masia B，Hu S M，et al.A metric of visual comfort for stereoscopic motion［J］.ACM Transactions on Graphics，2013，32(6):1-9.
[12]Huang W P，Zeng J，Wang Z Y，et al.Partial noise assisted multivariate EMD:an improved noise assisted method for multivariate signals decomposition［J］.Biomedical Signal Processing and Control，2017，36:205-220.
[13]She Q S，Ma Y L，Meng M，et al.Noise assisted MEMD based relevant IMFs identification and EEG classification［J］.Journal of Central South University，2017，24(3):599-608.
[14]Li M A，Ma J Y，Jia S M.Optimal combination of channels selection based on common spatial pattern algorithm［C］//IEEE International Conference on Mechatronics and Automation.Beijing:IEEE，2011:295-300.
[15]Chen C X，Li K，Wu Q Y，et al.EEG-based detection and evaluation of fatigue caused by watching 3DTV［J］.Displays，2013，34(2):81-88.
[16]Malik A S，Khairuddin R N，Amin H U，et al. EEG based evaluation of stereoscopic 3D displays for viewer discomfort［J］.Biomedical Engineering Online，2015，14(12):21.(上接第1380页)
[2]Hu W，Yang J，Bai L，et al.A new approach for vehicle color recognition based on specular-free image［C］//Proceedings of SPIE.Shanghai:The International Society for Optical Engineering，2013:9067.
[3]Zhang B.Reliable classification of vehicle types based on cascade classifier ensembles［J］. IEEE Transactions on Intelligent Transportation Systems，2013，14(1):322-332.
[4]Zhang Z，Tan T，Huang K，et al.Three-dimensional deformable-model-based localization and recognition of road vehicles［J］.IEEE Transactions on Image Processing，2012，21(1):1-13.
[5]Pepik B，Stark M，Gehler P，et al.Multi-view and 3D deformable part models［J］.IEEE Transactions on Pattern Analysis & Machine Intelligence，2015，37(11):2232-2245.
[6]Lin Y L，Morariu V I，Hsu W，et al.Jointly optimizing 3D model fitting and fine-grained classification［C］//European Conference on Computer Vision.Zurich，2014:466-480.
[7]Hu C，Bai X，Qi L，et al.Vehicle color recognition with spatial pyramid deep learning［J］.IEEE Transactions on Intelligent Transportation Systems，2015，16(5):2925-2934.
[8]Liu M，Yu C，Ling H，et al.Hierarccal joint CNN-based models for fine-grained cars recognition［C］//International Conference on Cloud Computing & Security.Singapore，2016:337-347.
[9]Rachmadi R F，Purnama I.Vehicle color recognition using convolutional neural network［J］.ArXiv Preprint ArXiv，2015，1510:07391.
[10]Yang L，Luo P，Loy C C，et al.A large-scale car data set for fine-grained categorization and verification［C］//IEEE Conference on Computer Vision and Pattern Recognition.Boston，2015:3973-3981.
[11]Naikal N，Yang A Y，Sastry S S.Informative feature selection for object recognition via sparse PCA［C］//International Conference on Computer Vision.Barcelona，2011:818-825.
[12]Wu L，Shen C，Hengel A V D.Deep linear discriminant analysis on fisher networks:a hybrid architecture for person re-identification［J］.Pattern Recognition，2017，65:238-250.
[13]Gawehns D，Wilderjans T F，Putten C M V.The statistical analysis of neuronal data:comparing algorithms for independent component analysis［J］.ISME Journal，2016，7(2):317-336.
[14]Chen S B，Wang J，Liu C Y，et al.Two-dimensional discriminant locality preserving projection based on 1-norm maximization［J］.Pattern Recognition Letters，2017，87:147-154.
[15]吴成东，樊玉泉，张云洲，等.基于改进KPCA算法的车牌字符识别方法［J］.东北大学学报(自然科学版)，2008，29(5):629-632.(Wu Cheng-dong，Fan Yu-quan，Zhang Yun-zhou，et al.License plate recognition method based on improved KPCA algorithm［J］.Journal of Northeastern University(Natural Science)，2008，29(5):629-632.)
[16]Lee D D，Seung H S.Learning the parts of objects by non-negative matrix factorization［J］.Nature，1999，401(6755):788-791.
[17]Liu Q.Kernel local sparse representation based classifier［J］.Neural Processing Letters，2016，60(1):1684-1695.

基于脑电的立体视频加速度的特征识别

EEG-Based Feature Recognition of Stereoscopic Video Acceleration

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	段志豪，刘冲，陈杰，陆志国. 数据区间优化对SSVEP算法性能的影响[J]. 东北大学学报（自然科学版）, 2021, 42(8): 1092-1097.
[2]	王翘秀，王宏，胡佛，化成城. 基于脑区社团结构的恐高程度识别模型[J]. 东北大学学报（自然科学版）, 2021, 42(3): 381-388.
[3]	常文文，王宏，化成城，王翘秀. 基于有向网络的人物信息诱发脑电信号特征[J]. 东北大学学报:自然科学版, 2019, 40(1): 1-6.
[4]	王琳，化成城，姜鑫，王宏. 基于颈腰部肌电及脑电信号的疲劳驾驶检测[J]. 东北大学学报:自然科学版, 2018, 39(1): 102-107.
[5]	张驰，卢绍文，王宏，王宏*. 磨矿过程控制中专家操作人员脑电特征分析[J]. 东北大学学报:自然科学版, 2017, 38(6): 828-833.
[6]	黄璐，王宏. 基于盲反卷积的脑电信号盲分离研究[J]. 东北大学学报:自然科学版, 2016, 37(8): 1100-1103.
[7]	刘冲，于清文，陆志国，王宏. 基于最小二乘支持向量机的脑电信号分类[J]. 东北大学学报:自然科学版, 2016, 37(5): 634-637.
[8]	韩凌，王宏，李春胜. 基于多变量希尔伯特频域模型的癫痫发作预测[J]. 东北大学学报:自然科学版, 2015, 36(10): 1383-1387.
[9]	付荣荣，王宏，王琳，张驰. 基于无线体域网中多生理信号驾驶疲劳检测[J]. 东北大学学报:自然科学版, 2014, 35(6): 850-853.
[10]	黄璐，王宏. 基于约束独立分量分析的脑电特征提取[J]. 东北大学学报:自然科学版, 2014, 35(3): 419-423.
[11]	王福旺，王宏，罗旭. 基于EEG与EOG信号的疲劳驾驶状态综合分析[J]. 东北大学学报:自然科学版, 2014, 35(2): 175-178.
[12]	叶柠;孙宇舸;. 基于EEG小波包子带能量比的疲劳驾驶检测方法[J]. 东北大学学报(自然科学版), 2012, 33(8): 1088-1092.
[13]	颜世玉;王宏;刘冲;赵海滨;. 基于小波方差的运动想象脑电信号特征提取[J]. 东北大学学报(自然科学版), 2012, 33(7): 934-937.
[14]	刘冲;李春胜;赵海滨;王宏;. 特征选择算法在ECoG分类中的应用[J]. 东北大学学报(自然科学版), 2011, 32(5): 658-661.
[15]	刘冲;赵海滨;李春胜;王宏;. 基于CSP与SVM算法的运动想象脑电信号分类[J]. 东北大学学报(自然科学版), 2010, 31(8): 1098-1101.