Runbei Cheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Runbei Cheng has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Jeroen H. M. Bergmann
Biomedical Engineering Centre, Department of Technology and Innovation, University of Southern Denmark, 5230 Odense, Denmark
2 shared publications - Abhishek Dasgupta
Oxford Research Software Engineering Group, Doctoral Training Centre Oxford University of Oxford
1 shared publication - Challenger Mishra
University of Cambridge
1 shared publication - Rahul Sharma
Institut de Mathématiques, École Polytechnique Fédérale de Lausanne, EPFL SB MATH LCVMM
1 shared publication - Vikranth Harthikote Nagaraja
Affiliation Centre for Human Movement and Rehabilitation Research, University of Salford, Salford, United Kingdom
1 shared publication
Latest Publications
- 13 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 7 (3) , 1-4
A Case for an Oral Cavity-Based Respiratory Rate Sensor System
Respiratory rate has been identified as a promising metric for field-based sports monitoring. While respiratory metrics such as minute ventilation (VE) are commonly used in lab-based metabolic tests, they have yet to be implemented in contact sports which encounter physical impact. This study proposes that breathing can be captured on-field via acoustic sensors embedded inside existing sports gears. Two suitable locations for such a system have been identified, either as a smart mouthguard or an instrumented headgear. The signal-to-noise ratio (SNR) at these placements and their potential for respiratory rate estimation will be compared in this study. Four participants were recruited, and respiratory data were captured in both indoor and outdoor settings. A fast-Fourier transform (FFT) based frequency domain analysis was used to estimate the respiratory rate and determine the breathing rate accuracy. A Wilcoxon signed-rank test was carried out to compare the datasets from the two sensor placements. It was found that the SNR of the oral placement is significantly better than the head placement for both indoor and outdoor settings (indoor: $P = 5.73 \times 10^{-7}, z = 5$ ; outdoor: $P = 2.12 \times 10^{-7}, z = 5.19$ ). It was also found that the oral placement had a significantly smaller error compared to the head location when predicting respiratory rate (indoor: $P = 1.72 \times 10^{-6}, z = -4.78$ ; outdoor: $P = 1.06 \times 10^{-7}, z = 5.32$ ). In addition, a convolutional neural network (CNN) based classifier was trained to clean up any non-respiratory sounds from recorded audio, which subsequently achieved a 90% test accuracy. This shows is a promising result for demonstrating the viability of a fully automated oral-based respiratory rate monitoring system.
- 13 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 7 (3) , 1-4
A Case for an Oral Cavity-Based Respiratory Rate Sensor System
Respiratory rate has been identified as a promising metric for field-based sports monitoring. While respiratory metrics such as minute ventilation (VE) are commonly used in lab-based metabolic tests, they have yet to be implemented in contact sports which encounter physical impact. This study proposes that breathing can be captured on-field via acoustic sensors embedded inside existing sports gears. Two suitable locations for such a system have been identified, either as a smart mouthguard or an instrumented headgear. The signal-to-noise ratio (SNR) at these placements and their potential for respiratory rate estimation will be compared in this study. Four participants were recruited, and respiratory data were captured in both indoor and outdoor settings. A fast-Fourier transform (FFT) based frequency domain analysis was used to estimate the respiratory rate and determine the breathing rate accuracy. A Wilcoxon signed-rank test was carried out to compare the datasets from the two sensor placements. It was found that the SNR of the oral placement is significantly better than the head placement for both indoor and outdoor settings (indoor: $P = 5.73 \times 10^{-7}, z = 5$ ; outdoor: $P = 2.12 \times 10^{-7}, z = 5.19$ ). It was also found that the oral placement had a significantly smaller error compared to the head location when predicting respiratory rate (indoor: $P = 1.72 \times 10^{-6}, z = -4.78$ ; outdoor: $P = 1.06 \times 10^{-7}, z = 5.32$ ). In addition, a convolutional neural network (CNN) based classifier was trained to clean up any non-respiratory sounds from recorded audio, which subsequently achieved a 90% test accuracy. This shows is a promising result for demonstrating the viability of a fully automated oral-based respiratory rate monitoring system.
- 16 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 22 (19) , 18684-18697
Machine Learning for Musculoskeletal Modeling of Upper Extremity
We propose a novel machine learning (ML)-driven methodology to estimate biomechanical variables of interest traditionally obtained from upper-extremity musculoskeletal (MSK) modeling. MSK models facilitate personalized modeling, perform “what-if” analyses, and potentially enhance clinical decision-making. In certain settings, MSK models are driven by inertial motion capture (IMC) data. IMC systems are portable, user-friendly, and relatively affordable as well as provide additional biomechanical information. However, MSK models can be computationally expensive, often require extensive data, and can be prohibitively slow in making real-time predictions. Our ML method—involving a rigorous hyperparameters search—predicts kinematic and kinetic biomechanical information associated with human upper-extremity movements solely using IMC input data, thereby bypassing MSK models. The scaled cadaver-based MSK model was based on the Dutch Shoulder Model and the spine model implemented in the AnyBody Managed Model Repository. We employ neural networks (NNs), which are trained on IMC data obtained from five nondisabled subjects in subject-exposed (SE) settings (at least a trial from all subjects is used in training) and subject-naive (SN) settings (no information from test subjects is used in training). We compare the predictions of our ML model with that of an MSK model and find an excellent agreement in SE settings (average Pearson’s ${r}={0.96}$ , $\text {normalized RMSE (NRMSE)} ={0.23}$ ) and strong correspondence in SN settings (average ${r}={0.89}$ , $\text {NRMSE} ={0.45}$ ). The linear model performed poorly for SN settings, which motivated a more complex ML model. Our findings suggest that an ML-based approach is highly viable for estimating upper-extremity biomechanical information solely from IMC data.
- 16 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 22 (19) , 18684-18697
Machine Learning for Musculoskeletal Modeling of Upper Extremity
We propose a novel machine learning (ML)-driven methodology to estimate biomechanical variables of interest traditionally obtained from upper-extremity musculoskeletal (MSK) modeling. MSK models facilitate personalized modeling, perform “what-if” analyses, and potentially enhance clinical decision-making. In certain settings, MSK models are driven by inertial motion capture (IMC) data. IMC systems are portable, user-friendly, and relatively affordable as well as provide additional biomechanical information. However, MSK models can be computationally expensive, often require extensive data, and can be prohibitively slow in making real-time predictions. Our ML method—involving a rigorous hyperparameters search—predicts kinematic and kinetic biomechanical information associated with human upper-extremity movements solely using IMC input data, thereby bypassing MSK models. The scaled cadaver-based MSK model was based on the Dutch Shoulder Model and the spine model implemented in the AnyBody Managed Model Repository. We employ neural networks (NNs), which are trained on IMC data obtained from five nondisabled subjects in subject-exposed (SE) settings (at least a trial from all subjects is used in training) and subject-naive (SN) settings (no information from test subjects is used in training). We compare the predictions of our ML model with that of an MSK model and find an excellent agreement in SE settings (average Pearson’s ${r}={0.96}$ , $\text {normalized RMSE (NRMSE)} ={0.23}$ ) and strong correspondence in SN settings (average ${r}={0.89}$ , $\text {NRMSE} ={0.45}$ ). The linear model performed poorly for SN settings, which motivated a more complex ML model. Our findings suggest that an ML-based approach is highly viable for estimating upper-extremity biomechanical information solely from IMC data.
- Open Access
- 31 March 2022
- Published by IOP Publishing in Physiological Measurement
- Vol. 43 (3) , 03TR01
Impact and workload are dominating on-field data monitoring techniques to track health and well-being of team-sports athletes
Objective. Participation in sports has become an essential part of healthy living in today’s world. However, injuries can often occur during sports participation. With advancements in sensor technology and data analytics, many sports have turned to technology-aided, data-driven, on-field monitoring techniques to help prevent injuries and plan better player management. Approach. This review searched three databases, Web of Science, IEEE, and PubMed, for peer-reviewed articles on on-field data monitoring techniques that are aimed at improving the health and well-being of team-sports athletes. Main results . It was found that most on-field data monitoring methods can be categorized as either player workload tracking or physical impact monitoring. Many studies covered during this review attempted to establish correlations between captured physical and physiological data, as well as injury risk. In these studies, workloads are frequently tracked to optimize training and prevent overtraining in addition to overuse injuries, while impacts are most often tracked to detect and investigate traumatic injuries. Significance . This review found that current sports monitoring practices often suffer from a lack of standard metrics and definitions. Furthermore, existing data-analysis models are created on data that are limited in both size and diversity. These issues need to be addressed to create ecologically valid approaches in the future.
- 31 March 2022
- Published by IOP Publishing in Physiological Measurement
- Vol. 43 (3) , 03TR01
Open AccessImpact and workload are dominating on-field data monitoring techniques to track health and well-being of team-sports athletes
Objective. Participation in sports has become an essential part of healthy living in today’s world. However, injuries can often occur during sports participation. With advancements in sensor technology and data analytics, many sports have turned to technology-aided, data-driven, on-field monitoring techniques to help prevent injuries and plan better player management. Approach. This review searched three databases, Web of Science, IEEE, and PubMed, for peer-reviewed articles on on-field data monitoring techniques that are aimed at improving the health and well-being of team-sports athletes. Main results . It was found that most on-field data monitoring methods can be categorized as either player workload tracking or physical impact monitoring. Many studies covered during this review attempted to establish correlations between captured physical and physiological data, as well as injury risk. In these studies, workloads are frequently tracked to optimize training and prevent overtraining in addition to overuse injuries, while impacts are most often tracked to detect and investigate traumatic injuries. Significance . This review found that current sports monitoring practices often suffer from a lack of standard metrics and definitions. Furthermore, existing data-analysis models are created on data that are limited in both size and diversity. These issues need to be addressed to create ecologically valid approaches in the future.