Multilevel Stress Assessment From ECG in a Virtual Reality Environment Using Multimodal Fusion

Abstract

Electrocardiogram (ECG) is an attractive option to assess stress in serious virtual reality (VR) applications due to its noninvasive nature. However, the existing machine learning (ML) models perform poorly. Moreover, existing studies only perform a binary stress assessment, while to develop a more engaging biofeedback-based application, multilevel assessment is necessary. Existing studies annotate and classify a single experience (e.g., watching a VR video) to a single stress level, which again prevents design of dynamic experiences where real-time in-game stress assessment can be utilized. In this article, we report our findings on a new study on VR stress assessment, where three stress levels are assessed. ECG data were collected from nine users experiencing a VR roller coaster. The VR experience was then manually labeled in 10-s segments to three stress levels by three raters. We then propose a novel multimodal deep fusion model utilizing spectrogram and 1-D ECG that can provide a stress prediction from just a 1-s window. The experimental results demonstrate that the proposed model outperforms the classical heart-rate variability (HRV)-based ML models (9% increase in accuracy) and baseline deep learning models (2.5% increase in accuracy). We also report results on the benchmark WESAD dataset to show the supremacy of the model.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 33 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.