Classification of Event-Related Potentials Associated with Response Errors in Actors and Observers Based on Autoregressive Modeling

Abstract

Event-Related Potentials (ERPs) provide non-invasive measurements of the electrical activity on the scalp related to the processing of stimuli and preparation of responses by the brain. In this paper an ERP-signal classification method is proposed for discriminating between ERPs of correct and incorrect responses of actors and of observers seeing an actor making such responses. The classification method targeted signals containing error-related negativity (ERN) and error positivity (Pe) components, which are typically associated with error processing in the human brain. Feature extraction consisted of Multivariate Autoregressive modeling combined with the Simulated Annealing technique. The resulting information was subsequently classified by means of an Artificial Neural Network (ANN) using back-propagation algorithm under the "leave-one-out cross-validation" scenario and the Fuzzy C-Means (FCM) algorithm. The ANN consisted of a multi-layer perceptron (MLP). The approach yielded classification rates of up to 85%, both for the actors' correct and incorrect responses and the corresponding ERPs of the observers. The electrodes needed for such classifications were situated mainly at central and frontal areas. Results provide indications that the classification of the ERN is achievable. Furthermore, the availability of the Pe signals, in addition to the ERN, improves the classification, and this is more pronounced for observers' signals. The proposed ERP-signal classification method provides a promising tool to study error detection and observational-learning mechanisms in performance monitoring and joint-action research, in both healthy and patient populations.

Detection of Error-Related Potentials in Stroke Patients from EEG Using an Artificial Neural Network

“…Moreover, it may not be needed to use as many ErrP and NonErrP epochs as were utilized in this study; it has been reported that a steep increase in classification accuracies was observed after ~50–100 ErrPs were used for calibration [ 33 , 36 , 40 ]. The classification accuracies based on within-day calibration are in agreement with findings in several other studies which have reported a detection performance in the range of roughly 70–90% [ 12 , 13 , 15 , 16 , 17 , 22 , 28 , 30 , 32 , 33 , 56 ]; it should be noted that different classification metrics have been reported. This was the case when using either features or the entire epoch as input for the ANN classifier.…”

“…A 5-layer MLP ANN was used [ 28 , 52 ] with an input layer equal to the number of features (number of channels x number of samples in epoch), three hidden layers of the size 100-50-25, and an output layer of size 1 with a sigmoid activation function. The scaled conjugate gradient descent method was used for training the neural network with a maximum number of epochs of 200.…”

“…Moreover, it could be used to transfer from a generalized classifier that could be used initially to avoid collecting user-specific training data for the BCI before the actual rehabilitation training starts to an individualized classifier. It has been shown in several studies that ErrPs can be decoded (see [ 9 , 10 ] for a review about decoding ErrPs) and how the performance of the decoder can be optimized using different types of features [ 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 , 21 ], classifiers [ 11 , 12 , 17 , 18 , 22 , 23 ], time windows [ 24 , 25 , 26 ], and channels [ 17 , 25 , 27 , 28 ]. Moreover, it has been shown that generalized ErrP detectors can be transferred across different tasks and types of ErrPs such as observation and interaction ErrPs, across participants, and time which eliminates the need for calibration (see, e.g., [ 11 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 ]).…”

Prediction of Human Inhibition Brain Function with Inter-Subject and Intra-Subject Variability

“…ERP analysis provides non-invasive measurements of electrical activity in the human brain. It is associated with the response to stimuli [ 45 , 46 , 47 ]. The previous study yielded a higher classification accuracy of 93.75% using ERP input features in machine learning techniques [ 45 , 46 , 47 ].…”

“…It is associated with the response to stimuli [ 45 , 46 , 47 ]. The previous study yielded a higher classification accuracy of 93.75% using ERP input features in machine learning techniques [ 45 , 46 , 47 ]. In our article, using PSD with the QDA classifier achieved the highest classification precision of 97.61% than in ERP features commonly used in former machine learning algorithms.…”