Determination of the Time Window of Event-Related Potential Using Multiple-Set Consensus Clustering

Abstract

Clustering is a promising tool for grouping the sequence of similar time-points aimed to identify the attention blocks in spatiotemporal event-related potentials (ERPs) analysis. It is most likely to elicit the appropriate time window for ERP of interest if a suitable clustering method is applied to spatiotemporal ERP. However, how to reliably estimate a proper time window from entire individual subjects' data is still challenging. In this study, we developed a novel multiset consensus clustering method in which several clustering results of multiple subjects were combined to retrieve the best fitted clustering for all the subjects within a group. Then, the obtained clustering was processed by a newly proposed time-window detection method to determine the most suitable time window for identifying the ERP of interest in each condition/group. Applying the proposed method to the simulated ERP data and real data indicated that the brain responses from the individual subjects can be collected to determine a reliable time window for different conditions/groups. Our results revealed more precise time windows to identify N2 and P3 components in the simulated data compared to the state-of-theart methods. Additionally, our proposed method achieved more robust performance and outperformed statistical analysis results in the real data for N300 and prospective positivity components. To conclude, the proposed method successfully estimates the time window for ERP of interest by processing the individual data, offering new venues for spatiotemporal ERP processing.

Brain Evoked Response Qualification Using Multi-Set Consensus Clustering: Toward Single-Trial EEG Analysis

“…Once clustering results were obtained from the individual subjects, a modified version of the time window determination of our previous work (Mahini et al, 2020) was applied for each subject. We modified the time window determination through two criteria in two steps: First, we detected the candidate cluster maps, i.e., the cluster maps with high inner similarity, e.g., > 0.95, in the experimentally interesting interval.…”

“…Other clustering methods such as the Gaussian mixture model for individual subjects (De Lucia et al, 2007b) and single-trial EEG (De Lucia et al, 2007a), and stimulus-related statistical information from single-trial responses (Tzovara, Murray, Plomp, et al, 2012) have been used for EEG data. On the other hand, it has also been shown that consensus clustering can result in consistent and reliable clustering outcomes for biological data (Abu-Jamous et al, 2015;Liu et al, 2017), especially in ERP identification from group-averaged ERP data (Mahini et al, 2020;Mahini et al, 2022). The remaining challenge with the clustering analysis of single-trial EEG is the existing high degree of inconsistency in the EEG data that may lead to uncertain or faulty clustering results.…”

A perspective on electroencephalography sensors for brain-computer interfaces

“…As for all systems, the final performance relies on the performance of the single parts, as well as on their synergy. One of the key performance parameters for BCIs is the accuracy that can be guaranteed by the system within a reasonable latency window [60,61]. The accuracy obtained depends on the chosen paradigm, on the integrated sensor performance in a band or helmet, and on the performance of the decoder system, i.e.…”

Ensemble Deep Clustering Analysis for Time Window Determination of Event-Related Potentials

“…In order to assess the proposed method, we employed two ERP data, simulated and real data. For the simulated data [31], we test the proposed method against our prior knowledge, i.e., about the spatial and temporal properties of pre-defined ERP components when more noise is added to the data. Likewise, for the real ERP data, we test our method for qualifying the ERP of interest in the prior study [19] when the existing noise in the data increases.…”

“…Despite using GFP and the winner-takes-all strategy in determining template maps in the microstates analysis, as argued in some research [11,55], the second group takes whole time points and polarity into account for clustering of spatio-temporal ERP. Recently, we discussed qualifying ERP of interest using consensus clustering as a reliable method for ERP data in different resolutions [31,32,33]. However, cluster analysis of noisy data can result in many noisy clusters and loss of the main components due to being sensitive to the data quality if inappropriate clustering is applied.…”