A Kalman Filter Based Methodology for EEG Spike Enhancement
Overview
Authors
Affiliations
In this work, we present a methodology for spike enhancement in electroencephalographic (EEG) recordings. Our approach takes advantage of the non-stationarity nature of the EEG signal using a time-varying autoregressive model. The time-varying coefficients of autoregressive model are estimated using the Kalman filter. The results show considerable improvement in signal-to-noise ratio and significant reduction of the number of false positives.
Magnetoencephalography-based approaches to epilepsy classification.
Pan R, Yang C, Li Z, Ren J, Duan Y Front Neurosci. 2023; 17:1183391.
PMID: 37502686 PMC: 10368885. DOI: 10.3389/fnins.2023.1183391.
Classification of the Epileptic Seizure Onset Zone Based on Partial Annotation.
Zhao X, Zhao Q, Tanaka T, Sole-Casals J, Zhou G, Mitsuhashi T Cogn Neurodyn. 2023; 17(3):703-713.
PMID: 37265654 PMC: 10229525. DOI: 10.1007/s11571-022-09857-4.
Human Recognition Using Deep Neural Networks and Spatial Patterns of SSVEP Signals.
Oikonomou V Sensors (Basel). 2023; 23(5).
PMID: 36904629 PMC: 10006983. DOI: 10.3390/s23052425.
Epileptic seizure focus detection from interictal electroencephalogram: a survey.
Islam M, Zhao X, Miao Y, Sugano H, Tanaka T Cogn Neurodyn. 2023; 17(1):1-23.
PMID: 36704629 PMC: 9871145. DOI: 10.1007/s11571-022-09816-z.
Navigating the Statistical Minefield of Model Selection and Clustering in Neuroscience.
Kiraly B, Hangya B eNeuro. 2022; 9(4).
PMID: 35835556 PMC: 9282170. DOI: 10.1523/ENEURO.0066-22.2022.