โก Quick Summary
This study introduces a time-efficient continuous ramp protocol for estimating walking energy expenditure using wearable devices. By integrating a data-driven approach, the protocol significantly enhances data diversity, leading to improved model performance in energy expenditure estimation.
๐ Key Details
- ๐ Dataset: 14 subjects for initial protocol comparison, 13 additional subjects for smartwatch evaluation
- ๐งฉ Features used: Energy expenditure measured via indirect calorimetry and IMUs
- โ๏ธ Technology: Deep learning models trained on datasets from both continuous and discrete protocols
- ๐ Performance: Mean error of 13.1% for discrete and 10.7% for continuous protocols
๐ Key Takeaways
- ๐ถโโ๏ธ Continuous ramp protocol allows for gradual speed increases, enhancing data collection efficiency.
- ๐ก No significant differences in energy expenditure were found between the two protocols after compensating for respiratory delays.
- ๐ค Deep learning models trained on continuous datasets outperformed traditional smartwatch estimates.
- ๐ Kinematic differences were noted at speeds above 1.5 m/s, but did not affect estimation accuracy.
- ๐ Broader applications of this protocol extend beyond walking to other forms of locomotion.
- โณ Time efficiency is crucial for constructing diverse datasets needed for deep learning.
- ๐ Potential to replace traditional indirect calorimetry methods, which require extensive lab work.
๐ Background
Estimating walking energy expenditure accurately is essential for various applications, including health monitoring and fitness tracking. Traditional methods often rely on indirect calorimetry, which can be time-consuming and inefficient. Recent advancements in wearable technology and data-driven models present an opportunity to streamline this process, making it more accessible and practical for everyday use.
๐๏ธ Study
The study involved 14 subjects who walked on a treadmill while wearing four inertial measurement units (IMUs) to measure energy expenditure through indirect calorimetry. The researchers compared a continuous ramp protocol, where subjects gradually increased their walking speed over 10 minutes, with a conventional discrete step protocol, which involved maintaining five constant speeds for six minutes each.
๐ Results
The results indicated that after adjusting for respiratory delays, there were no significant differences in energy expenditure between the two protocols. Both deep learning models trained on the discrete and continuous datasets demonstrated comparable performance, with mean errors of 13.1% and 10.7%, respectively. Notably, the continuous ramp protocol provided a more diverse dataset, leading to improved accuracy across a broader speed range.
๐ Impact and Implications
The findings from this study have significant implications for the future of energy expenditure estimation. By adopting the continuous ramp protocol, researchers and practitioners can gather richer datasets more efficiently, paving the way for enhanced model performance. This approach not only benefits walking speed estimation but can also be adapted for various exercise intensities, potentially transforming how we monitor physical activity and energy expenditure in real-time.
๐ฎ Conclusion
This study highlights the importance of innovative protocols in advancing our understanding of energy expenditure during walking. The continuous ramp protocol stands out as a promising method that can improve data collection efficiency and model accuracy. As we continue to explore the integration of technology in health monitoring, this research encourages further investigation into similar methodologies across different forms of locomotion.
๐ฌ Your comments
What are your thoughts on this new approach to estimating walking energy expenditure? We would love to hear your insights! ๐ฌ Join the conversation in the comments below or connect with us on social media:
A time-efficient continuous ramp protocol for data-driven walking energy expenditure estimation across multiple speeds.
Abstract
BACKGROUND: Recent research has sought to use data-driven models to estimate walking energy expenditure across multiple speeds via wearable devices. Many studies employ a discrete step protocol-repeatedly walking at a constant speed for several minutes-because indirect calorimetry depends on time-delayed respiratory responses. However, this approach becomes time-inefficient when constructing sufficiently diverse datasets for deep learning, which requires large amounts of distinctive data. To address this issue, we integrated a data-driven approach with a previously proposed continuous protocol wherein walking speeds are gradually increased within a single trial. The purpose of this study is to compare the effectiveness of such a continuous dataset for energy expenditure estimation against a conventional discrete approach.
METHODS: Fourteen subjects walked on a treadmill wearing four IMUs, while energy expenditure was measured using an indirect calorimetry. In the continuous ramp protocol, subjects walked for 10ย mins at speeds linearly increasing from 1.0 to 1.75ย m/s. The discrete step protocol involved five speeds within the same range, each maintained for 6 mins. In the continuous ramp protocol, energy expenditure was mapped to each speed after compensating for respiratory delay, whereas in the discrete step protocol, we used averaged breath-by-breath measurements of the final 3ย minutes. We compared the kinematics, kinetics, and energy expenditure between the two protocols. Subsequently, 13 additional subjects were recruited to compare a commercial smartwatch with linear and deep learning models trained on datasets from each protocol.
RESULTS: After compensating for respiratory delays, no differences in energy expenditure were observed between the two protocols, although kinematic differences appeared at speeds above 1.5ย m/s. These differences did not impair estimation accuracy: deep learning models trained on the discrete and continuous datasets showed comparable performance (13.1% vs. 10.7% mean error, respectively), both significantly outperforming the smartwatch. Furthermore, when trained on the more diverse data from the continuous ramp protocol, a deep learning model achieved uniformly low error across a broad speed range with only a single IMU.
CONCLUSION: The continuous ramp protocol can generate a valid walking motion-energy expenditure dataset in a time-efficient manner, improving model performance by providing richer data diversity. This approach is not limited to walking speed but can be applied to other continuously changing exercise intensities across various forms of locomotion, thus promoting efforts to replace indirect calorimetry, traditionally requires extensive laboratory experiments.
Author: [‘Hyunho J’, ‘Sukyung P’]
Journal: J Neuroeng Rehabil
Citation: Hyunho J and Sukyung P. A time-efficient continuous ramp protocol for data-driven walking energy expenditure estimation across multiple speeds. A time-efficient continuous ramp protocol for data-driven walking energy expenditure estimation across multiple speeds. 2025; 22:206. doi: 10.1186/s12984-025-01707-8