Physically Plausible Data Augmentations for Wearable IMU-based Human Activity Recognition Using Physics Simulation

2025-08-18

AI Summary

In wearable inertial measurement unit (IMU)-based human activity recognition (HAR), high-quality labeled data are scarce, and conventional signal-transform-based data augmentation (STDA) often generates physically implausible synthetic IMU sequences. To address this, we propose the first physically grounded data augmentation framework for HAR. Our method leverages a physics simulation engine to jointly model human dynamics, sensor spatial pose, and hardware response characteristics; it drives synthesis of realistic IMU time-series using motion-capture or video-based pose estimates. Evaluated on three public HAR benchmarks, our approach achieves an average macro-F1 improvement of 3.7 percentage points over STDA baselines (up to +13), while requiring only 40% of the original subject data to match baseline performance. This demonstrates substantially enhanced model generalizability and practical deployability in real-world wearable applications.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Humans and AI: Human-in-the-loop Machine Learning
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

The scarcity of high-quality labeled data in sensor-based Human Activity Recognition (HAR) hinders model performance and limits generalization across real-world scenarios. Data augmentation is a key strategy to mitigate this issue by enhancing the diversity of training datasets. Signal Transformation-based Data Augmentation (STDA) techniques have been widely used in HAR. However, these methods are often physically implausible, potentially resulting in augmented data that fails to preserve the original meaning of the activity labels. In this study, we introduce and systematically characterize Physically Plausible Data Augmentation (PPDA) enabled by physics simulation. PPDA leverages human body movement data from motion capture or video-based pose estimation and incorporates various realistic variabilities through physics simulation, including modifying body movements, sensor placements, and hardware-related effects. We compare the performance of PPDAs with traditional STDAs on three public datasets of daily activities and fitness workouts. First, we evaluate each augmentation method individually, directly comparing PPDAs to their STDA counterparts. Next, we assess how combining multiple PPDAs can reduce the need for initial data collection by varying the number of subjects used for training. Experiments show consistent benefits of PPDAs, improving macro F1 scores by an average of 3.7 pp (up to 13 pp) and achieving competitive performance with up to 60% fewer training subjects than STDAs. As the first systematic study of PPDA in sensor-based HAR, these results highlight the advantages of pursuing physical plausibility in data augmentation and the potential of physics simulation for generating synthetic Inertial Measurement Unit data for training deep learning HAR models. This cost-effective and scalable approach therefore helps address the annotation scarcity challenge in HAR.

Problem

• Addressing scarcity of labeled IMU data for activity recognition
• Ensuring physical plausibility in wearable sensor data augmentation
• Reducing training data requirements through physics simulation techniques

Innovation

• Physics simulation for realistic data augmentation
• Incorporating body movement and sensor variabilities
• Reducing training data needs with plausible augmentations