Estimating an individual's oxygen uptake during cycling exercise with a recurrent neural network trained from easy-to-obtain inputs: A pilot study

Estimating intra- and inter-subject oxygen consumption in outdoor human gait using multiple neural network approaches

Oxygen consumption ([Formula: see text]) is an important measure for exercise test, such as walking and running, that can be measured outdoors using portable spirometers or metabolic analyzers. However, these devices are not feasible for regular use by consumers as they intervene with the user's physical integrity, and are expensive and difficult to operate. To circumvent these drawbacks, indirect estimation of [Formula: see text] using neural networks combined with motion features and heart rate measurements collected with consumer-grade sensors has been shown to yield reasonably accurate [Formula: see text] for intra-subject estimation. However, estimating [Formula: see text] with neural networks trained with data from other individuals than the user, known as inter-subject estimation, remains an open problem. In this paper, five types of neural network architectures were tested in various configurations for inter-subject [Formula: see text] estimation. To analyse predictive performance, data from 16 participants walking and running at speeds between 1.0 m/s and 3.3 m/s were used. The most promising approach was Xception network, which yielded average estimation errors as low as 2.43 ml×min-1×kg-1, suggesting that it could be used by athletes and running enthusiasts for monitoring their oxygen consumption over time to detect changes in their movement economy.

Combined Impact of Heart Rate Sensor Placements with Respiratory Rate and Minute Ventilation on Oxygen Uptake Prediction

Oxygen uptake (V˙O2) is an essential metric for evaluating cardiopulmonary health and athletic performance, which can barely be directly measured. Heart rate (HR) is a prominent physiological indicator correlated with V˙O2 and is often used for indirect V˙O2 prediction. This study investigates the impact of HR placement on V˙O2 prediction accuracy by analyzing HR data combined with the respiratory rate (RESP) and minute ventilation (V˙E) from three anatomical locations: the chest; arm; and wrist. Twenty-eight healthy adults participated in incremental and constant workload cycling tests at various intensities. Data on V˙O2, RESP, V˙E, and HR were collected and used to develop a neural network model for V˙O2 prediction. The influence of HR position on prediction accuracy was assessed via Bland-Altman plots, and model performance was evaluated by mean absolute error (MAE), coefficient of determination (R2), and mean absolute percentage error (MAPE). Our findings indicate that HR combined with RESP and V˙E (V˙O2HR+RESP+V˙E) produces the most accurate V˙O2 predictions (MAE: 165 mL/min, R2: 0.87, MAPE: 15.91%). Notably, as exercise intensity increases, the accuracy of V˙O2 prediction decreases, particularly within high-intensity exercise. The substitution of HR with different anatomical sites significantly impacts V˙O2 prediction accuracy, with wrist placement showing a more profound effect compared to arm placement. In conclusion, this study underscores the importance of considering HR placement in V˙O2 prediction models, with RESP and V˙E serving as effective compensatory factors. These findings contribute to refining indirect V˙O2 estimation methods, enhancing their predictive capabilities across different exercise intensities and anatomical placements.

Machine learning prediction of pulmonary oxygen uptake from muscle oxygen in cycling

The purpose of this study was to test whether a machine learning model can accurately predict VO2 across different exercise intensities by combining muscle oxygen (MO2) with heart rate (HR). Twenty young highly trained athletes performed the following tests: a ramp incremental exercise, three submaximal constant intensity exercises, and three severe intensity exhaustive exercises. A Machine Learning model was trained to predict VO2, with model inputs including heart rate, MO2 in the left (LM) and right legs (RM). All models demonstrated equivalent results, with the accuracy of predicting VO2 at different exercise intensities varying among different models. The LM+RM+HR model performed the best across all intensities, with low bias in predicted VO2 for all intensity exercises (0.08 ml/kg/min, 95% limits of agreement: -5.64 to 5.81), and a very strong correlation (r = 0.94, p < 0.001) with measured VO2. Furthermore, the accuracy of predicting VO2 using LM+HR or RM+HR was higher than using LM+RM, and higher than the accuracy of predicting VO2 using LM, RM, or HR alone. This study demonstrates the potential of a machine learning model combining MO2 and HR to predict VO2 with minimal bias, achieving accurate predictions of VO2 for different intensity levels of exercise.

Pro-cycling team cyclist assignment for an upcoming race

Professional bicycle racing is a popular sport that has attracted significant attention in recent years. The evolution and ubiquitous use of sensors allow cyclists to measure many metrics including power, heart rate, speed, cadence, and more in training and racing. In this paper we explore for the first time assignment of a subset of a team's cyclists to an upcoming race. We introduce RaceFit, a model that recommends, based on recent workouts and past assignments, cyclists for participation in an upcoming race. RaceFit consists of binary classifiers that are trained on pairs of a cyclist and a race, described by their relevant properties (features) such as the cyclist's demographic properties, as well as features extracted from his workout data from recent weeks; as well additional properties of the race, such as its distance, elevation gain, and more. Two main approaches are introduced in recommending on each stage in a race and aggregate from it to the race, or on the entire race. The model training is based on binary label which represent participation of cyclist in a race (or in a stage) in past events. We evaluated RaceFit rigorously on a large dataset of three pro-cycling teams' cyclists and race data achieving up to 80% precision@i. The first experiment had shown that using TP or STRAVA data performs the same. Then the best-performing parameters of the framework are using 5 weeks time window, imputation was effective, and the CatBoost classifier performed best. However, the model with any of the parameters performed always better than the baselines, in which the cyclists are assigned based on their popularity in historical data. Additionally, we present the top-ranked predictive features.

Prediction of peak oxygen consumption using cardiorespiratory parameters from warmup and submaximal stage of treadmill cardiopulmonary exercise test

This study investigates the quality of peak oxygen consumption (VO2peak) prediction based on cardiac and respiratory parameters calculated from warmup and submaximal stages of treadmill cardiopulmonary exercise test (CPET) using machine learning (ML) techniques and assesses the importance of respiratory parameters for the prediction outcome. The database consists of the following parameters: heart rate (HR), respiratory rate (RespRate), pulmonary ventilation (VE), oxygen consumption (VO2) and carbon dioxide production (VCO2) obtained from 369 treadmill CPETs. Combinations of features calculated based on the HR, VE and RespRate time-series from different stages of CPET were used to create 11 datasets for VO2peak prediction. Thirteen ML algorithms were employed, and model performances were evaluated using cross-validation with mean absolute percentage error (MAPE), R2 score, mean absolute error (MAE), and root mean squared error (RMSE) calculated after each iteration of the validation. The results demonstrated that incorporating respiratory-based features improves the prediction of VO2peak. The best results in terms of R2 score (0.47) and RMSE (5.78) were obtained for the dataset which included both cardiac- and respiratory-based features from CPET up to 85% of age-predicted HRmax, while the best results in terms of MAPE (10.5%) and MAE (4.63) were obtained for the dataset containing cardiorespiratory features from the last 30 seconds of warmup. The study showed the potential of using ML models based on cardiorespiratory features from submaximal tests for prediction of VO2peak and highlights the importance of the monitoring of respiratory signals, enabling to include respiratory parameters into the analysis. Presented approach offers a feasible alternative to direct VO2peak measurement, especially when specialized equipment is limited or unavailable.

Heart Rate Variability Based Estimation of Maximal Oxygen Uptake in Athletes Using Supervised Regression Models

Wearable Heart Rate monitors are used in sports to provide physiological insights into athletes' well-being and performance. Their unobtrusive nature and ability to provide reliable heart rate measurements facilitate the estimation of cardiorespiratory fitness of athletes, as quantified by maximum consumption of oxygen uptake. Previous studies have employed data-driven models which use heart rate information to estimate the cardiorespiratory fitness of athletes. This signifies the physiological relevance of heart rate and heart rate variability for the estimation of maximal oxygen uptake. In this work, the heart rate variability features that were extracted from both exercise and recovery segments were fed to three different Machine Learning models to estimate maximal oxygen uptake of 856 athletes performing Graded Exercise Testing. A total of 101 features from exercise and 30 features from recovery segments were given as input to three feature selection methods to avoid overfitting of the models and to obtain relevant features. This resulted in the increase of model's accuracy by 5.7% for exercise and 4.3% for recovery. Further, post-modelling analysis was performed to remove the deviant points in two cases, initially in both training and testing and then only in training set, using k-Nearest Neighbour. In the former case, the removal of deviant points led to a reduction of 19.3% and 18.0% in overall estimation error for exercise and recovery, respectively. In the latter case, which mimicked the real-world scenario, the average R value of the models was observed to be 0.72 and 0.70 for exercise and recovery, respectively. From the above experimental approach, the utility of heart rate variability to estimate maximal oxygen uptake of large population of athletes was validated. Additionally, the proposed work contributes to the utility of cardiorespiratory fitness assessment of athletes through wearable heart rate monitors.

Surrogate Modelling for Oxygen Uptake Prediction Using LSTM Neural Network

Oxygen uptake (V˙O2) is an important metric in any exercise test including walking and running. It can be measured using portable spirometers or metabolic analyzers. Those devices are, however, not suitable for constant use by consumers due to their costs, difficulty of operation and their intervening in the physical integrity of their users. Therefore, it is important to develop approaches for the indirect estimation of V˙O2-based measurements of motion parameters, heart rate data and application-specific measurements from consumer-grade sensors. Typically, these approaches are based on linear regression models or neural networks. This study investigates how motion data contribute to V˙O2 estimation accuracy during unconstrained running and walking. The results suggest that a long short term memory (LSTM) neural network can predict oxygen consumption with an accuracy of 2.49 mL/min/kg (95% limits of agreement) based only on speed, speed change, cadence and vertical oscillation measurements from an inertial navigation system combined with a Global Positioning System (INS/GPS) device developed by our group, worn on the torso. Combining motion data and heart rate data can significantly improve the V˙O2 estimation resulting in approximately 1.7-1.9 times smaller prediction errors than using only motion or heart rate data.

Smart Electrically Assisted Bicycles as Health Monitoring Systems: A Review

This paper aims to provide a review of the electrically assisted bicycles (also known as e-bikes) used for recovery of the rider's physical and physiological information, monitoring of their health state, and adjusting the "medical" assistance accordingly. E-bikes have proven to be an excellent way to do physical activity while commuting, thus improving the user's health and reducing air pollutant emissions. Such devices can also be seen as the first step to help unhealthy sedentary people to start exercising with reduced strain. Based on this analysis, the need to have e-bikes with artificial intelligence (AI) systems that recover and processe a large amount of data is discussed in depth. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines were used to complete the relevant papers' search and selection in this systematic review.

Pop Music Trend and Image Analysis Based on Big Data Technology

With people's pursuit of music art, a large number of singers began to analyze the trend of music in the future and create music works. Firstly, this study introduces the theory of music pop trend analysis, big data mining technology, and related algorithms. Then, the autoregressive integrated moving (ARIM), random forest, and long-term and short-term memory (LSTM) algorithms are used to establish the image analysis and prediction model, analyze the music data, and predict the music trend. The test results of the three models show that when the singer's songs are analyzed from three aspects: collection, download, and playback times, the LSTM model can predict well the playback times. However, the LSTM model also has some defects. For example, the model cannot accurately predict some songs with large data fluctuations. At the same time, there is no big data gap between the playback times predicted by the ARIM model image analysis and the actual playback times, showing the allowable error fluctuation range. A comprehensive analysis shows that compared with the ARIM algorithm and random forest algorithm, the LSTM algorithm can predict the music trend more accurately. The research results will help many singers create songs according to the current and future music trends and will also make traditional music creation more information-based and modern.

Temporal convolutional networks predict dynamic oxygen uptake response from wearable sensors across exercise intensities

Oxygen consumption ([Formula: see text]) provides established clinical and physiological indicators of cardiorespiratory function and exercise capacity. However, [Formula: see text] monitoring is largely limited to specialized laboratory settings, making its widespread monitoring elusive. Here we investigate temporal prediction of [Formula: see text] from wearable sensors during cycle ergometer exercise using a temporal convolutional network (TCN). Cardiorespiratory signals were acquired from a smart shirt with integrated textile sensors alongside ground-truth [Formula: see text] from a metabolic system on 22 young healthy adults. Participants performed one ramp-incremental and three pseudorandom binary sequence exercise protocols to assess a range of [Formula: see text] dynamics. A TCN model was developed using causal convolutions across an effective history length to model the time-dependent nature of [Formula: see text]. Optimal history length was determined through minimum validation loss across hyperparameter values. The best performing model encoded 218 s history length (TCN-VO2 A), with 187, 97, and 76 s yielding <3% deviation from the optimal validation loss. TCN-VO2 A showed strong prediction accuracy (mean, 95% CI) across all exercise intensities (-22 ml min^-1, [-262, 218]), spanning transitions from low-moderate (-23 ml min^-1, [-250, 204]), low-high (14 ml min^-1, [-252, 280]), ventilatory threshold-high (-49 ml min^-1, [-274, 176]), and maximal (-32 ml min^-1, [-261, 197]) exercise. Second-by-second classification of physical activity across 16,090 s of predicted [Formula: see text] was able to discern between vigorous, moderate, and light activity with high accuracy (94.1%). This system enables quantitative aerobic activity monitoring in non-laboratory settings, when combined with tidal volume and heart rate reserve calibration, across a range of exercise intensities using wearable sensors for monitoring exercise prescription adherence and personal fitness.