A Low-Cost Computational Method for Characterizing Event-Related Potentials for BCI Applications and Beyond

Abstract

Event-related potentials (ERPs) are important neurophysiological markers widely used in scientific, medical and engineering contexts. Proper ERP detection contributes to widening the scope of use and, in general, improving functionality. The morphology and latency of ERPs are variable among subject sessions, which complicates their detection. Although variability is an intrinsic feature of neuronal activity, it can be addressed with novel views on ERP detection techniques. In this paper, we propose an agile method for characterizing and thus detecting variable ERPs, which keeps track of their temporal and spatial information through the continuous measurement of the area under the curve in ERP components. We illustrate the usefulness of the proposed ERP characterization for electrode selection in brain-computer interfaces (BCIs) and compare the results with other standard methods. We assess ERP classification for BCI use with Bayesian linear discriminant analysis (BLDA) and cross-validation. We also evaluate performance with both the information transfer rate and BCI utility. The results of our validation tests show that this characterization helps to take advantage of the information on the evolution of positive and negative ERP components and, therefore, to efficiently select electrodes for optimized ERP detection. The proposed method improves the classification accuracy and bitrate of all sets of electrodes analyzed. Furthermore, the method is robust between different day sessions. Our work contributes to the efficient detection of ERPs, manages inter-and intrasubject variability, decreases the computational cost of classic detection methods and contributes to promoting low-cost personalized brain-computer interfaces.

Predicting Working Memory performance based on specific individual EEG spatiotemporal features

“…This can be explained thanks to the extraction of characteristics used in this work, through power spectrum that has shown its robustness in the extraction of spectral patterns in EEG signals [67]. In addition to the selection of electrodes, which is understood as a feature selection technique, which has been satisfactorily tested and widely used in BCI [45, 46]. Among the main advantages of the selection of electrodes are the ability to eliminate redundant information, to reduce the number of parameters to optimize the classifier, and to identify characteristics related to the targeted mental states.…”

“…By using all the electrodes we have data with high dimensionality and noise which contains redundant information that slows down the classifier due to a positive correlation between the number of parameters to be optimized by the classifier and the number of features. The best choice of electrodes as a selection of features has been presented as an efficient alternative [47, 45, 46], but not habitually in WM tasks. Currently, ML algorithms can help a characterise and predict WM performance, and although few works have been done to date, none consider the temporal and spatial characterization in a WM task to improve the prediction in each subject.…”

“…In several of them taking all the brain regions or where the bibliography shows related activity. However, involving all electrodes from all regions is inefficient, in fact it is known that the use of a large number of electrodes does not always guarantee improved performance [44, 45, 46]. By using all the electrodes we have data with high dimensionality and noise which contains redundant information that slows down the classifier due to a positive correlation between the number of parameters to be optimized by the classifier and the number of features.…”

Single-trial extraction of event-related potentials (ERPs) and classification of visual stimuli by ensemble use of discrete wavelet transform with Huffman coding and machine learning techniques

“…This kind of application requires accurate and fast detections of physical motor events corresponding with neuronal activity, which could be achievable with the use of machine learning. Many analysis methods and machine learning tools are reported to be used to achieve such accuracy in ERPs [21][22][23]. However, the ERP responses achieved through visual stimuli are less regular and also have a low signal-to-noise ratio as compared to the motor control task signals.…”

Brain-Computer Interface: Advancement and Challenges

“…The temporal resolution of event-related potentials is remarkable, but it has a low spatial resolution. ERPs were used by Changoluisa, V. et al [271] to build an adaptive strategy for identifying and detecting changeable ERPs. Continuous monitoring of the curve in ERP components takes account of their temporal and spatial information.…”