Accelerometry-based Energy Expenditure Estimation During Activities of Daily Living: A Comparison Among Different Accelerometer Compositions

2025-02-14

AI Summary

Accurate estimation of physical activity energy expenditure (PAEE) using accelerometry remains challenged by uncertainty regarding optimal sensor placement. Method: This study systematically compared PAEE estimation accuracy across five anatomical locations—pelvis (center of mass, COM), bilateral thighs, and bilateral wrists—using synchronized ground-truth data from the COSMED K5 metabolic cart. Linear regression and CNN-LSTM models were trained on acceleration signals acquired under standardized conditions. Contribution/Results: For the first time under a unified experimental design, we quantitatively evaluated single-site (pelvis), three-sensor (pelvis + bilateral thighs), and bilateral-wrist configurations. The three-accelerometer setup achieved the highest accuracy (CNN-LSTM R² = 0.53), significantly outperforming the wrist-only configuration (R² ≈ 0, p < 0.05). No significant difference was observed between pelvis-only and the three-sensor setup (p = 0.278), confirming the COM region’s strong representativeness for whole-body energy expenditure. These findings provide empirical guidance for optimizing wearable sensor deployment in PAEE monitoring.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Search and Optimization: Algorithm Configuration

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Physical activity energy expenditure (PAEE) can be measured from breath-by-breath respiratory data, which can serve as a reference. Alternatively, PAEE can be predicted from the body movements, which can be measured and estimated with accelerometers. The body center of mass (COM) acceleration reflects the movements of the whole body and thus serves as a good predictor for PAEE. However, the wrist has also become a popular location due to recent advancements in wrist-worn devices. Therefore, in this work, using the respiratory data measured by COSMED K5 as the reference, we evaluated and compared the performances of COM-based settings and wrist-based settings. The COM-based settings include two different accelerometer compositions, using only the pelvis accelerometer (pelvis-acc) and the pelvis accelerometer with two accelerometers from two thighs (3-acc). The wrist-based settings include using only the left wrist accelerometer (l-wrist-acc) and only the right wrist accelerometer (r-wrist-acc). We implemented two existing PAEE estimation methods on our collected dataset, where 9 participants performed activities of daily living while wearing 5 accelerometers (i.e., pelvis, two thighs, and two wrists). These two methods include a linear regression (LR) model and a CNN-LSTM model. Both models yielded the best results with the COM-based 3-acc setting (LR: $R^2$ = 0.41, CNN-LSTM: $R^2$ = 0.53). No significant difference was found between the 3-acc and pelvis-acc settings (p-value = 0.278). For both models, neither the l-wrist-acc nor the r-wrist-acc settings demonstrated predictive power on PAEE with $R^2$ values close to 0, significantly outperformed by the two COM-based settings (p-values $<$ 0.05). No significant difference was found between the two wrists (p-value = 0.329).

Problem

• Compare accelerometer compositions for energy expenditure
• Evaluate wrist vs. body center for activity tracking
• Assess accuracy of predictive models for PAEE

Innovation

• Accelerometer compositions for PAEE estimation
• Comparison of COM and wrist settings
• LR and CNN-LSTM models evaluation