Title: SportVAE: athletic heart rate anomaly detection via wearable sensors using enhanced variational autoencoders

Authors: Peng Liu; Yang Yu

Addresses: Jilin University of Chemical Technology, No. 45, Chengde Street, Longtan District, Jilin City, Jilin Province, China ' Changchun University, No. 6543, Satellite Road, Changchun City, Jilin Province, China

Abstract: Traditional HRV analysis struggles to distinguish exercise-induced variations from genuine cardiac irregularities, especially in high-intensity activities. To address these issues, this study proposes SportVAE, an enhanced variational autoencoder (VAE) for detecting heart rate anomalies of athletes during physical activities via wearable sensors. The proposed model incorporates temporal attention, a bidirectional LSTM encoder for capturing heart rate dynamics, and an adaptive weighting mechanism to balance reconstruction error and KL divergence based on intensity. Tested on the public PPG-DaLiA dataset and a proprietary dataset from 20 professional athletes, it achieved a 90.4% F1-score (on PPG-DaLiA) and 89.8% F1-score (on our proprietary dataset), outperforming existing methods. The model handles varying intensities, and is efficient enough for wearable devices, contributing to both theory and practice in athletic health monitoring.

Keywords: variational autoencoder; VAE; athletic heart rate monitoring; anomaly detection; deep learning; temporal attention mechanism; wearable technology.

DOI: 10.1504/IJBIDM.2026.155238

International Journal of Business Intelligence and Data Mining, 2026 Vol.28 No.4/5/6, pp.261 - 275

Received: 31 May 2025
Accepted: 13 Jan 2026
Published online: 29 Jul 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article