The foot strike pattern performed during running is an important variable for runners, performance practitioners, and industry specialists. Versatile, wearable sensors may provide foot strike information while encouraging the collection of diverse information during ecological running. The purpose of the current study was to predict foot strike angle and classify foot strike pattern from Loadsol^TM wearable pressure insoles using three machine learning techniques (multiple linear regression―MR, conditional inference tree―TREE, and random forest―FRST). Model performance was assessed using three-dimensional kinematics as a ground-truth measure. The prediction-model accuracy was similar for the regression, inference tree, and random forest models (RMSE: MR = 5.16°, TREE = 4.85°, FRST = 3.65°; MAPE: MR = 0.32°, TREE = 0.45°, FRST = 0.33°), though the regression and random forest models boasted lower maximum precision (13.75° and 14.3°, respectively) than the inference tree (19.02°). The classification performance was above 90% for all models (MR = 90.4%, TREE = 93.9%, and FRST = 94.1%). There was an increased tendency to misclassify mid foot strike patterns in all models, which may be improved with the inclusion of more mid foot steps during model training. Ultimately, wearable pressure insoles in combination with simple machine learning techniques can be used to predict and classify a runner’s foot strike with sufficient accuracy.

The instant of turn switch (TS) in alpine skiing has been assessed with a variety of sensors and TS concepts. Despite many published methodologies, it is unclear which is best or how comparable they are. This study aimed to facilitate the process of choosing a TS method by evaluating the accuracy and precision of the methodologies previously used in literature and to assess the influence of the sensor type. Optoelectronic motion capture, inertial measurement units, pressure insoles, portable force plates, and electromyography signals were recorded during indoor treadmill skiing. All TS methodologies were replicated as stated in their respective publications. The method proposed by Supej assessed with optoelectronic motion capture was used as a comparison reference. TS time differences between the reference and each methodology were used to assess accuracy and precision. All the methods analyzed showed an accuracy within 0.25 s, and ten of them within 0.05 s. The precision ranged from ~0.10 s to ~0.60 s. The TS methodologies with the best performance (accuracy and precision) were Klous Video, Spörri PI (pressure insoles), Martinez CTD (connected boot), and Yamagiwa IMU (inertial measurement unit). In the future, the specific TS methodology should be chosen with respect to sensor selection, performance, and intended purpose.

A simple and accurate method of determining foot strike angle (FSA) during running can simplify data collections and validations of wearable sensors. The purpose of this study was to determine the validity of two simplified methods for estimating FSA and foot angle (throughout the ground contact) from three-dimensional kinematics. Markers were placed on the heel and head of the second metatarsal (HEEL-TOE) or on the lateral side of the head of the fifth metatarsal (HEEL-MET₅). When compared to the reference foot segment, the HEEL-TOE method performed similarly with a minimal mean difference (0.28° [0.19°,0.36°], p < 0.001), a high Pearson’s r (r = 0.994; p < 0.001), and low bias (−0.20°±1.05°). Alternatively, the HEEL-MET₅ method underestimated FSA: mean difference = 4.28° [4.07°,4.91°] (p < 0.001), Pearson’s r = 0.968 (p < 0.001), and bias = −4.58°±2.61°. Throughout the contact phase, significant SPM cluster regions were identified, indicating that the HEEL-MET₅ method underestimated the angle of the foot for all foot strike patterns in the first 23–34% of the stance (p < 0.025). This study supports the idea that the HEEL-TOE method can be used as a simplified method for determining FSA from 3D kinematics. Researchers should proceed with caution when employing the HEEL-MET₅ method, as it is likely underestimating FSA due to foot inversion in the early stance phase.

Exercise intensity and perceived autonomy are important factors for the affective response toward exercise and adherence. Dual‐mode theory suggests an inverted‐J response curve of affect with increased exercise intensity, but little is known about how different running programs affect the affective response and subsequent incidental affect in daily life. This ambulatory assessment study examines the short‐ to long‐term effects of two 8‐week running interventions (affect‐based vs. polarized‐prescribed) on subjective vitality and perceived fatigue in young female novices. Participants engaged in 3 × 30 minute running sessions weekly in their natural environments and completed electronic diaries three times daily. Autoregressive multilevel models indicate small effects of training intensity on immediate affective subjective vitality (ß = ‐2.37; p = .03; f ² = 0.02) but negligible non‐significant effects on fatigue (ß = 0.26; p = 0.12; f ² = 0.002). Novices experienced increased vitality throughout the day when their running was evaluated positively (ß = 0.23; p = .03; f ² = 0.04), with effects lasting over two days before returning to baseline (ß = ‐0.26; p < .001; f ² = 0.004). However, no significant long‐term effects were observed over 8 weeks in vitality or fatigue. Results indicate between‐ and within‐person variations, but limited sample power does not allow differentiating between programs. This study supports the dual‐mode theory and highlights the importance of distinguishing affective response from incidental affect.