Unsupervised Clustering of Individuals Sharing Selective Attentional Focus Using Physiological Synchrony

Abstract

Research on brain signals as indicators of a certain attentional state is moving from laboratory environments to everyday settings. Uncovering the attentional focus of individuals in such settings is challenging because there is usually limited information about real-world events, as well as a lack of data from the real-world context at hand that is correctly labeled with respect to individuals' attentional state. In most approaches, such data is needed to train attention monitoring models. We here investigate whether unsupervised clustering can be combined with physiological synchrony in the electroencephalogram (EEG), electrodermal activity (EDA), and heart rate to automatically identify groups of individuals sharing attentional focus without using knowledge of the sensory stimuli or attentional focus of any of the individuals. We used data from an experiment in which 26 participants listened to an audiobook interspersed with emotional sounds and beeps. Thirteen participants were instructed to focus on the narrative of the audiobook and 13 participants were instructed to focus on the interspersed emotional sounds and beeps. We used a broad range of commonly applied dimensionality reduction ordination techniques—further referred to as mappings—in combination with unsupervised clustering algorithms to identify the two groups of individuals sharing attentional focus based on physiological synchrony. Analyses were performed using the three modalities EEG, EDA, and heart rate separately, and using all possible combinations of these modalities. The best unimodal results were obtained when applying clustering algorithms on physiological synchrony data in EEG, yielding a maximum clustering accuracy of 85%. Even though the use of EDA or heart rate by itself did not lead to accuracies significantly higher than chance level, combining EEG with these measures in a multimodal approach generally resulted in higher classification accuracies than when using only EEG. Additionally, classification results of multimodal data were found to be more consistent across algorithms than unimodal data, making algorithm choice less important. Our finding that unsupervised classification into attentional groups is possible is important to support studies on attentional engagement in everyday settings.

Ear-EEG Measures of Auditory Attention to Continuous Speech

“…Thus, especially the combination of cEEGrids with cost-efficient data acquisition platforms such as the OpenBCI provide a setup that could be used for research in everyday life scenarios ( Knierim et al, 2021 ). In addition, ISCs could also be based on a combination of EEG, electrodermal, and heartbeat activity, which has been shown to produce more accurate results than using EEG alone ( Stuldreher et al, 2022 ).…”

Self-Supervised Contrastive Learning for Medical Time Series: A Systematic Review

“…EEG. In all the reviewed papers, we find 31.7% studies [20,21,[28][29][30][31][32][33][34][35][36][37][38][39][40][41][42][43] used EEG. Among these, only one of these studies used intracranial EEG (invasive), and the others used noninvasive EEG.…”

“…ECG. In total, 25% of the reported studies [18,43,[46][47][48][49][50][51][52][53][54][55] worked on ECG data. ECG (also known as EKG) is an effective and simple manner to assess the condition of the human heart.…”

“…We found six studies that used ICU data (10%) [40,43,[58][59][60][61]. ICU datasets typically include vital signs collected by professional medical devices in intensive care at a high time-sensitive level, as well as laboratory measurements and results, medications, admission diagnoses, procedures, chosen treatments, and more.…”

“…In the context of the reviewed articles, two studies have incorporated GSR data into their experiments. Stuldreher et al [43] analyzed the performance of clustering algorithms using EEG, heart rate, and GSR separately, as well as all possible combinations of the three modalities. Another study by Saeed et al [39] performed self-supervised recognition of physiological stress using heart rate and GSR collected from real driving scenarios [68].…”