Deep-seeded Clustering for Emotion Recognition from Wearable Physiological Sensors
This addresses the problem of cumbersome ground truth label collection for emotion recognition in naturalistic settings, though it appears incremental as it builds on existing unsupervised and clustering methods.
The paper tackled emotion recognition from wearable physiological sensors by proposing a deep-seeded clustering algorithm that combines an autoencoder for unsupervised feature representation and c-means clustering, achieving accuracies of 80.7% on WESAD, 64.2% on Stress-Predict, and 61.0% on CEAP360-VR datasets.
According to the circumplex model of affect, an emotional response could characterized by a level of pleasure (valence) and intensity (arousal). As it reflects on the autonomic nervous system (ANS) activity, modern wearable wristbands can record non-invasively and during our everyday lives peripheral end-points of this response. While emotion recognition from physiological signals is usually achieved using supervised machine learning algorithms that require ground truth labels for training, collecting it is cumbersome and particularly unfeasible in naturalistic settings, and extracting meaningful insights from these signals requires domain knowledge and might be prone to bias. Here, we propose and test a deep-seeded clustering algorithm that automatically extracts and classifies features from those physiological signals with minimal supervision - combining an autoencoder (AE) for unsupervised feature representation and c-means clustering for fine-grained classification. We also show that the model obtains good performance results across three different datasets frequently used in affective computing studies (accuracies of 80.7% on WESAD, 64.2% on Stress-Predict and 61.0% on CEAP360-VR).