Single-trial classification of EEG in a visual object task using ICA and machine learning

Abstract

Presenting different visual object stimuli can elicit detectable changes in EEG recordings, but this is typically observed only after averaging together data from many trials and many participants. We report results from a simple visual object recognition experiment where independent component analysis (ICA) data processing and machine learning classification were able to correctly distinguish presence of visual stimuli at around 87% (0.70 AUC, p<0.0001) accuracy within single trials, using data from single ICs. Seven subjects observed a series of everyday visual object stimuli while EEG was recorded. The task was to indicate whether or not they recognised each object as familiar to them. EEG or IC data from a subset of initial object presentations was used to train support vector machine (SVM) classifiers, which then generated a label for subsequent data. Task-label classifier accuracy gives a proxy measure of task-related information present in the data used to train. This allows comparison of EEG data processing techniques - here, we found selected single ICs that give higher performance than when classifying from any single scalp EEG channel (0.70 AUC vs 0.65 AUC, p<0.0001). Most of these single selected ICs were found in occipital regions. Scoring a sliding analysis window moving through the time-points of the trial revealed that peak accuracy is when using data from +75 to +125 ms relative to the object appearing on screen. We discuss the use of such classification and potential cognitive implications of differential accuracy on IC activations.

Gamma absolute power reveals activation of motor areas after hand immobilization

“…17,18 ICA was applied to the EEG recordings in order to interpret the source of underlying electrocortical signals in the contaminated artifact of electrical potentials on the scalp. Data from individual electrodes exhibiting loss of contact with the scalp or high impedance levels (>10 kΩ) were discarded, and data from single-trial epochs exhibiting excessive movement artifacts (± 100 µV) were also deleted.…”

“…The subjects were instructed not to use tobacco, coffee 15 or alcoholic drinks 16 10 hours before the test because these substances may influence cortical activation recorded by QEEG brain mapping. 17,18 The study was approved by the ethics committee of Veiga de Almeida University and complied with the ethical standards of the Declaration of Helsinki.…”

EEG-based mind driven type writer by fuzzy radial basis function neural classifier

“…Besides these, parietal and motor cortex regions are found to take significantly active participation during the experiment. Additionally, literature [1][2][3][4][5][6] reveals that temporal lobe is highly associated with human speech signal processing. Therefore, we select P3, P4 and Pz (from parietal lobe), T1, T2, T3, T4, T5 and T6 (from temporal lobe) and C3, C4 and Cz (from motor cortex region) for extracting necessary information by applying signal processing techniques.…”

“…There are so many research work based on real time EEG-based human emotion recognition [2], [3] and EEG based stress monitoring is described in paper [4]. In paper [5], one channel of ICA data is taken as input which increases classification accuracy to 87%. Although commercial product level design of MD-TW is still far from reality, the innovations of MD-TW at research level cannot be denied.…”

Optimal determination of wavelet for football player EEG using SVM classifier

“…These changing streams produce electric fields that can be recorded by putting electrodes on the surface of the scalp. The potentials between various electrodes are then amplified and recorded as the EEG; which implies the composition out of the electrical movement of the cerebrum [4]. In this way EEG recordings finish learning about the general movement of a large number of neurons in the mind.…”