W2W: A Simulated Exploration of IMU Placement Across the Human Body for Designing Smarter Wearable

2025-07-07

AI Summary

Current wearable inertial measurement unit (IMU) deployments rely on empirical conventions, lacking systematic evaluation and optimization. Method: We propose W2W, a simulation-driven framework featuring a high-fidelity, 512-point human surface model that synthesizes task-specific IMU signals. It enables fine-grained, cross-task utility quantification—e.g., for pose estimation and activity recognition—by integrating motion-capture-driven signal modeling with multimodal real-world data validation. Contribution/Results: W2W is the first to identify task-consistent high-value sensing regions, challenging the fixed-layout paradigm of commercial devices. Experiments demonstrate strong rank correlation (r > 0.92) between simulated and empirical performance, and uncover several non-canonical placements—overlooked by conventional approaches—that yield superior accuracy. W2W establishes the first open-source, reproducible, simulation-based paradigm for task-adaptive and scalable IMU placement design.

Technology Category

Cognitive Modeling & Cognitive Systems: Simulating Human BehaviorPlanning, Routing, and Scheduling: Activity and Plan RecognitionIntelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systemsSystems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deploymentsWeb Mining and Content Analysis: Web data generation and simulation

Abstract

Inertial measurement units (IMUs) are central to wearable systems for activity recognition and pose estimation, but sensor placement remains largely guided by heuristics and convention. In this work, we introduce Where to Wear (W2W), a simulation-based framework for systematic exploration of IMU placement utility across the body. Using labeled motion capture data, W2W generates realistic synthetic IMU signals at 512 anatomically distributed surface patches, enabling high-resolution, task-specific evaluation of sensor performance. We validate reliability of W2W by comparing spatial performance rankings from synthetic data with real IMU recordings in two multimodal datasets, confirming strong agreement in activity-wise trends. Further analysis reveals consistent spatial trends across activity types and uncovers overlooked high-utility regions that are rarely used in commercial systems. These findings challenge long-standing placement norms and highlight opportunities for more efficient, task-adaptive sensor configurations. Overall, our results demonstrate that simulation with W2W can serve as a powerful design tool for optimizing sensor placement, enabling scalable, data-driven strategies that are impractical to obtain through physical experimentation alone.

Problem

• Systematic exploration of optimal IMU placement for wearables
• Evaluating sensor performance across 512 body surface patches
• Challenging conventional norms with data-driven placement strategies

Innovation

• Simulation-based framework for IMU placement
• Generates synthetic IMU signals anatomically
• Validates performance with real data comparison