摘要
为了提高P300-RSVP目标检测系统的准确率,研究目标视场角对目标检测系统的影响。对5位被试者采用4种不同视场角的目标作为靶刺激进行实验;对被试者大脑产生的脑电波进行预处理,将目标图片对应的脑电信号进行50次叠加平均,发现目标所占视场角为8°左右时P300的峰值最高;采用结构化判别成分分析(HDCA)对单试次脑电信号进行分类,目标所占视场角为8°左右时的目标探测率平均达到82%以上,高于其他目标视场角对应的目标探测率。
In order to improve the accuracy of the P300-RSVP target detection system, the influence of the target perspective on the target detection system is studied. Five subjects are tested using four different angles of view as target stimuli.Brain waves generated by the subjects' brains are preprocessed, and the EEG signals corresponding to the target images are averaged over 50 times. The peak value of P300 is highest when the target's field of view angle is around 8°. Hierarchical Discriminant Component Analysis(HDCA)is used to classify single-trial EEG signals. When the target's angle of view is about 8°, the target detection rate averages over 82%, which is higher than the target detection rate corresponding to the other target perspective.
引文
[1] Polich J,Donchin E.P300 and the word frequency effect[J].Electroencephalography&Clinical Neurophysiology,1988,70(1):33.
[2] Poolman P,Frank R M,Luu P,et al.A single-trial analytic framework for EEG analysis and its application to target detection and classification[J].Neuroimage,2008,42(2):787-798.
[3] Bigdely-Shamlo N,Vankov A,Ramirez R R,et al.Brain activity-based image classification from rapid serial visual presentation[J].IEEE Trans on Neural Syst Rehabil Eng,2008,16(5):432-441.
[4] Sajda P,Pohlmeyer E,Wang J,et al.In a blink of an eye and a switch of a transistor:cortically coupled computer vision[J].Proceedings of the IEEE,2010,98(3):462-478.
[5] Lees S,Dayan N,Cecotti H,et al.A review of rapid serial visual presentation-based brain-computer interfaces[J].Journal of Neural Engineering,2017.
[6] Dias J C,Parra L C.No EEG evidence for subconscious detection during rapid serial visual presentation[C]//Signal Processing in Medicine and Biology Symposium,2011:1-4.
[7] U??umli?M,Chavarriaga R,Millán J D R.An iterative framework for eeg-based image search:robust retrieval with weak classifiers[J].Plos One,2013,8(8):e72018.
[8] Cecotti H,Eckstein M P,Giesbrecht B.Single-trial classification of event-related potentials in rapid serial visual presentation tasks using supervised spatial filtering[J].IEEE Trans on Neural Netw Learn Syst,2014,25(11):2030-2042.
[9]周唯,吴成东.视网膜图像中的黄斑中心检测[J].中国图象图形学报,2018,23(3).
[10]周前祥,姜国华,曲战胜,等.视场角设置对虚拟环境中目标判断的影响[J].航天医学与医学工程,2003,16(4):292-295.
[11] Manor R,Mishali L,Geva A B.Multimodal neural network for rapid serial visual presentation brain computer interface[J].Frontiers in Computational Neuroscience,2016,10:130.
[12] Acqualagna L,Blankertz B.A gaze independent spelling based on rapid serial visual presentation[C]//2011 International Conference of the IEEE Engineering in Medicine and Biology Society,2011:4560-4563.
[13] Liu R,Kwon M.Integrating oculomotor and perceptual training to induce a pseudofovea:a model system for studying central vision loss[J].J Vis,2016,16(6):10.
[14] Marathe A R,Ries A J,Mcdowell K.Sliding HDCA:single-trial EEG classification to overcome and quantify temporal variability[J].IEEE Transactions on Neural Systems&Rehabilitation Engineering A Publication of the IEEE Engineering in Medicine&Biology Society,2014,22(2):201.
[15] Marathe A R,Ries A J,Lawhern V J,et al.The effect of target and non-target similarity on neural classification performance:a boost from confidence[J].Frontiers in Neuroscience,2015,9(270):270.
[16] Kumar S,Sahin F.Brain computer interface for interactive and intelligent image search and retrieval[C]//International Conference on High Capacity Optical Networks and Enabling Technologies,2014:136-140.
[17] Rivet B,Souloumiac A.Optimal linear spatial filters for event-related potentials based on a spatio-temporal model:asymptotical performance analysis[M].[S.l.]:Elsevier NorthHolland,Inc,2013.
[18] Marathe A R,Lawhern V J,Wu D,et al.Improved neural signal classification in a rapid serial visual presentation task using active learning[J].IEEE Trans on Neural Syst Rehabil Eng,2016,24(3):333-343.