EEG Peak Detection in Cognitive Conflict Processing Using Summit Navigator and Clustering-Based Ranking
IEEE Transactions on Neural Systems and Rehabilitation Engineering - Tập 30 - Trang 1548-1556 - 2022
Tóm tắt
Correct detection of peaks in electroencephalogram (EEG) signals is of essence due to the significant correlation of those potentials with cognitive performance and disorders. This paper proposes a novel and non-parametric approach to detect prediction error negativity (PEN) in cognitive conflict processing. The PEN candidates are first located from the input signal via an adaptation of a recent effective method for local maxima extraction, processed in a multi-scale manner. The found candidates are then fused and ranked based on their shape and location-based features. False positives caused by candidates’ magnitude are eliminated by rotating the sorted candidate list where the one with the second-best ranking score will be identified as PEN. The EEG data collected from a 3D object selection task have been used to verify the efficacy of the proposed approach. Compared with the state-of-the-art peak detection techniques, the proposed method shows an improvement of at least 2.67% in accuracy and 6.27% in sensitivity while requires only about 4 ms to process an epoch. The accuracy and computational efficiency of the proposed technique in the detection of PEN in cognitive conflict processing would lead to promising applications in performance improvement of brain-computer interfaces (BCIs).
Từ khóa
#Summit navigator #peak detection #spike detection #electroencephalogram (EEG) #cognitive conflict #prediction error negativity (PEN) #error-related positive potential (Pe) #clusteringTài liệu tham khảo
macqueen, 1967, Some methods for classification and analysis of multivariate observations, Proc 5th Berkeley Symp Math Statist Probab, 1, 281
10.1126/science.1242072
10.1109/MLSP.2010.5589217
10.1145/3290605.3300657
10.1038/s41598-018-30609-0
10.1109/TIP.2019.2932501
ester, 1996, A density-based algorithm for discovering clusters in large spatial databases with noise, Proc KDD, 96, 226
10.1145/235968.233324
10.1016/j.neucom.2005.12.108
makeig, 1995, Independent component analysis of electroencephalographic data, Proc Adv Neural Inf Process Syst, 8, 1
10.1109/TBME.2007.908083
10.1088/1741-2552/abfa70
10.1016/j.brainres.2007.04.024
10.1109/TCDS.2020.2991301
10.1016/j.neuroimage.2020.117578
10.1016/j.cpr.2008.07.003
10.1016/j.neucom.2013.12.006
10.1109/ACCESS.2018.2875487
10.1016/S1350-4533(99)00092-2
10.1016/j.compbiomed.2007.03.005
10.1109/TNSRE.2013.2282153
10.1155/2018/5081258
10.1016/0301-0511(88)90021-X
10.1016/S1388-2457(99)00122-4
10.1109/ACCESS.2018.2832089
10.1016/0013-4694(91)90062-9
singh, 2020, EnK: Encoding time-information in convolution, arXiv 2006 04198
10.1016/0301-0511(88)90014-2
10.1111/j.1467-9280.1993.tb00586.x
falkenstein, 1990, Effects of errors in choice reaction tasks on the ERP under focused and divided attention, Psychophysiological Brain Research, 192
10.1109/ICRA.2019.8793748
10.1016/j.tics.2014.02.009
10.1016/j.physbeh.2021.113369
10.1016/0013-4694(76)90063-8
10.1109/TIM.2018.2862078
10.1109/TKDE.2015.2492558
ac?r, 2004, Automatic spike detection in EEG by a two-stage procedure based on support vector machines, Comput Biol Med, 34, 561, 10.1016/j.compbiomed.2003.08.003
10.1109/ICNC.2009.639
10.1088/1741-2552/ab5247
10.1088/1741-2552/ab4896