Exploiting Feature-driven Approximation to Preserve Privacy in Machine Learning based Health Monitoring Systems

Real-time health monitoring systems generate massive biometric sensor data, placing substantial demands on memory, computation, and power resources. Additionally, the sensitive nature of such data raises critical privacy concerns related to attributes like gender, age, and body mass index. To address these challenges, this work proposes FAxC—a novel feature-driven approximation framework that performs multi-dimensional data reduction by leveraging the biometric features of sensor signals. Unlike prior approximation techniques that operate on isolated signals or uniformly sample data, FAxC intelligently selects and masks segments to preserve human activity recognition performance while enhancing user privacy. Our case study shows that, compared to existing privacy-aware approaches, FAxC reduces the disparity in gender-distinguishable biometric features in human activity recognition, decreasing Z-direction peak acceleration from 56% to 22% and stride root mean square from 31% to 3%. Our FAxC enhances the privacy-preserving rate by up to $5.6 \times$ over the baseline and outperforms existing methods by a factor ranging from $1.2 \times$ to $5.4 \times$. The proposed method has also been validated on the TAME Pain dataset for a voice-based pain level detection system. FAxC reduces the risk of gender leakage by 50% compared to using raw data, while maintaining pain level detection accuracy.