Assessment of bike handling during cycling individual time trials with a novel analytical technique adapted from motorcycle racing.

A methodology to study bike handling of cyclists during individual time trials (ITT) is presented. Lateral and longitudinal accelerations were estimated from GPS data of professional cyclists (n = 53) racing in two ITT of different length and technical content. Acceleration points were plotted on a plot (g-g diagram) and they were enclosed in an ellipse. A correlation analysis was conducted between the area of the ellipse and the final ITT ranking. It was hypothesised that a larger area was associated with a better performance. An analytical model for the bike-cyclist system dynamics was used to conduct a parametric analysis on the influence of riding position on the shape of the g-g diagram. A moderate (n = 27, r = -0.40, p = 0.038) and a very large (n = 26, r = -0.83, p < 0.0001) association were found between the area of the enclosing ellipse and the final ranking in the two ITT. Interestingly, this association was larger in the shorter race with higher technical content. The analytical model suggested that maximal decelerations are highly influenced by the cycling position, road slope and speed. This investigation, for the first time, explores a novel methodology that can provide insights into bike handling, a large unexplored area of cycling performance.

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

Measurement of oxygen uptake during exercise ([Formula: see text]) is currently non-accessible to most individuals without expensive and invasive equipment. The goal of this pilot study was to estimate cycling [Formula: see text] from easy-to-obtain inputs, such as heart rate, mechanical power output, cadence and respiratory frequency. To this end, a recurrent neural network was trained from laboratory cycling data to predict [Formula: see text] values. Data were collected on 7 amateur cyclists during a graded exercise test, two arbitrary protocols (Prot-1 and -2) and an "all-out" Wingate test. In Trial-1, a neural network was trained with data from a graded exercise test, Prot-1 and Wingate, before being tested against Prot-2. In Trial-2, a neural network was trained using data from the graded exercise test, Prot-1 and 2, before being tested against the Wingate test. Two analytical models (Models 1 and 2) were used to compare the predictive performance of the neural network. Predictive performance of the neural network was high during both Trial-1 (MAE = 229(35) mlO2min-1, r = 0.94) and Trial-2 (MAE = 304(150) mlO2min-1, r = 0.89). As expected, the predictive ability of Models 1 and 2 deteriorated from Trial-1 to Trial-2. Results suggest that recurrent neural networks have the potential to predict the individual [Formula: see text] response from easy-to-obtain inputs across a wide range of cycling intensities.

Expert-level classification of ventilatory thresholds from cardiopulmonary exercising test data with recurrent neural networks.

First and second ventilatory thresholds (VT1 and VT2) represent the boundaries of the moderate-heavy and heavy-severe exercise intensity. Currently, VTs are primarily detected visually from cardiopulmonary exercise test (CPET) data, beginning with an initial data screening followed by data processing and statistical analysis. Automated VT detection is a challenging task owing to the high signal to noise ratio typical of CPET data. Recurrent neural networks describe a machine learning form of Artificial Intelligence that can be used to uncover complex non-linear relationships between input and output variables. Here we proposed detection of VTs using a single neural network classifier, trained with a database of 228 laboratory CPET data. We tested the neural network performance against the judgement of 7 couples of board-certified exercise-physiologists on 25 CPET tests. The neural network achieved expert-level performances across the tasks (mean absolute error was 9.5% (r = 0.79) and 4.2% (r = 0.94) for VT1 and VT2, respectively). Estimation errors are compatible with the typical error of the current gold standard visual methodology. The neural network demonstrated VT detecting and exercise intensity level classifying at a high competence level. Neural networks could potentially be embedded in CPET hardware/software to extend the reach of exercise physiologists beyond their laboratories.

Comparison of two warning concepts of an intelligent Curve Warning system for motorcyclists in a simulator study.

Curve crashes are a particular matter of concern regarding motorcycle riding safety. For this reason, an intelligent Curve Warning system has been designed that gives the riders support when negotiating a curve. The system has been tested in a simulator study carried out with 20 test riders. The subjects performed three rides: one without the system (baseline) and two experimental rides using a version of the Curve Warning system, one providing the warnings by a force feedback throttle and one by a haptic glove. The effects of the two system versions were evaluated both in terms of the simulated riding performance and the subjective assessment by the riders. A descriptive analysis of the riders' reactions to the warnings shows that the warnings provided by both system versions provoke an earlier and stronger adaptation of the motorcycle dynamics to the curve than when the riders do not use the system. Riding with the Curve Warning system with the haptic glove furthermore leads to a reduction of critical curve events. The riders' subjective workload level was not affected by the system use, whereas the Curve Warning system with the force feedback throttle required an increased attention. The comparison of the riders' opinions about the system reveals a preference of the Curve Warning system with the haptic glove. The better acceptance of this system version suggests a higher potential in the enhancement of riding safety.