The aims of the study were to describe the physiological profile of a 65-km (4000-m cumulative elevation gain) running mountain ultra-marathon (MUM) and to identify predictors of MUM performance. Twenty-three amateur trail-runners performed anthropometric evaluations and an uphill graded exercise test (GXT) for VO ventilatory thresholds (VTs), power outputs (PMax, PVTs) and heart rate response (HRmax, HR@VTs). Heart rate (HR) was monitored during the race and intensity was expressed as: Zone I (VT2) for exercise load calculation (training impulse, TRIMP). Mean race intensity was 77.1%±4.4% of HRmax distributed as: 85.7%±19.4% Zone I, 13.9%±18.6% Zone II, 0.4%±0.9% Zone III. Exercise load was 766±110 TRIMP units. Race time (11.8±1.6h) was negatively correlated with VO (r = -0.66, P <0.001) and PMax (r = -0.73, P <0.001), resulting these variables determinant in predicting MUM performance, whereas exercise thresholds did not improve performance prediction. Laboratory variables explained only 59% of race time variance, underlining the multi-factorial character of MUM performance. Our results support the idea that VT1 represents a boundary of tolerable intensity in this kind of events, where exercise load is extremely high. This information can be helpful in identifying optimal pacing strategies to complete such extremely demanding MUMs.

No abstract

No abstract

No abstract

We propose an objective stress assessment method based on the extraction of features from physiological time series and their classification using Support Vector Machine and K-Nearest Neighbors algorithms. For this purpose, we used an open dataset consisting of multiparametric physiological signals (electrocardiogram, electromyogram, galvanic skin response and breath signal) obtained during the execution of a driving route within the city of Boston with restful, highway and city driving periods indicative of three different stress states. To predict the driver stress level, 21 features were extracted from 122 chunks of raw signals and were subsequently managed by classification algorithms. Our analysis showed a prediction accuracy of 98.4% when all features were used, decreasing when signals from specific physiological systems were not considered. Our results highlighted that multidomain data acquisition by wearable sensors combined with appropriate classification models may represent a promising strategy to detect drivers' stress status in an unobtrusive and objective way that can in perspective be applicable in several other fields such as in the clinics.