ECSS Paris 2023: CP-AP22
INTRODUCTION: Advance footwear technology (AFT), particularly carbon fiber plates (CBP), has been linked to improvements in running economy and performance of athletes. Increased longitudinal bending stiffness and enhanced energy return are proposed mechanisms. However, most studies have assessed AFT as a single technological system, limiting understanding of the independent effects of plate. This study aims to compare the physiological response between a carbon-plated shoe (AFT) and a high-quality running conventional shoe without CBP (CONV). METHODS: Repeated measures crossover design was employed. Runners completed two experimental trials under identical laboratory conditions wearing either AFT or CONV, in randomized order. Participants performed a standardized incremental treadmill protocol to assess submaximal physiological response. Oxygen consumption (VO₂) was continuously measured using a metabolic cart, while capillary blood lactate (LA) was obtained at predefined exercise intensities and post-exercise. Participants were classified as Responders or Non-responders based on individual physiological changes between footwear conditions. Statistical analyses included repeated-measures ANOVA with footwear and functional group as factors. RESULTS: Regarding LA, levels were significantly higher with CONV (M = 5.12, SE = 0.343) compared to AFT (M = 4.19, SE = 0.227; p < .001). A significant interaction between functional group and footwear was observed; post hoc analysis revealed that Responders exhibited higher LA concentrations with CONV (M = 6.12, SE = 0.528) than with AFT (M = 4.77, SE = 0.349; p < .001), whereas no significant differences were found for non-responders (p > .05). Furthermore, Responders using CONV showed significantly higher LA levels compared to Non-responders (M = 4.11, SE = 0.438; p = .024). In terms of oxygen consumption, while no main effect was observed for footwear type (p > .05), a significant interaction was detected. Responders demonstrated higher VO₂ with CONV (M = 44.1, SE = 0.878) compared to AFT (M = 42.5, SE = 1.025; p = .009); conversely, non-responders showed higher VO₂ with AFT (M = 46.2, SE = 0.810) than with CONV (M = 44.9, SE = 0.694; p = .014). CONCLUSION: Contrary to literature, aggregate results showed no significant VO₂ differences between shoe conditions. However, lower lactate levels with AFT suggest metabolic benefits not captured by global oxygen uptake. Crucially, the data reveals high heterogeneity; AFT benefits are not universal but dependent on the runner’s functional profile. While 'Responders' gain metabolic advantages, 'Non-responders' experience increased oxygen cost, indicating AFT can hinder performance in some athletes. In conclusion, AFT efficacy is individual-specific. Adoption should be personalized through functional assessments to ensure metabolic gains and avoid performance decrements.
Read CV JAVIER Gámez-PayáECSS Paris 2023: CP-AP22
INTRODUCTION: Traditional table tennis training relies heavily on coaches' subjective experience, making it difficult to provide precise quantitative data. With the advancement of wearable sensors and AI, Edge AI offers new possibilities for real-time motion analysis. This study develops a TinyML-integrated intelligent racket capable of low-latency stroke recognition and VR visualization feedback without cloud dependency. METHODS: The hardware core utilizes an ARM Cortex-M7-based STM32F767 microcontroller paired with a high-performance ICM-20948 9-axis inertial measurement unit (IMU), precisely embedded within the racket handle. The system performs acquisition of acceleration and angular velocity signals for six core stroke techniques, including forehand/backhand drives, chops, and pushes. During the data processing phase, the raw sensor data were randomly partitioned into an 80% training set and a 20% testing set to evaluate the performance of four distinct deep learning architectures. Ultimately, an optimized and quantized Convolutional Neural Network (CNN) model was selected for deployment on the MCU. To ensure seamless feedback, classification results are transmitted instantaneously to a VR environment via an nRF24L01P wireless module. RESULTS: The study recruited four professional athletes and four amateur players for empirical testing. Initial statistics revealed that in a test of 20 strokes per person, the raw recognition rates were 83.75% for professionals and 85.58% for amateurs. To establish a more robust baseline, the research filtered high-standard stroke trajectories to perform deep model optimization. The refined CNN model demonstrated exceptional performance; the recognition accuracy for each individual stroke type exceeded 96%, while the overall average accuracy reached 98.2%. These results prove that the embedded AI racket possesses a rigorous and accurate classification standard. For general players, the system can effectively identify postural deviations and provide guidance through the VR interface, facilitating precise movement correction and autonomous skill acquisition. CONCLUSION: Compared to vision-based systems that rely on cameras, this sensor-based approach offers significant advantages, including immunity to ambient lighting conditions, enhanced privacy, and significantly lower computational overhead. Achieving such high accuracy confirms the robustness and feasibility of implementing TinyML on resource-constrained embedded devices. While the current results are promising, future research will focus on enhancing the model's generalization capabilities to accommodate users of different body types and strength levels, while expanding the database to include complex, multi-stage maneuvers. In conclusion, this study successfully integrates AI recognition with VR feedback, providing a high-efficiency, portable, and cost-effective cutting-edge solution for the future of personalized and digitally-augmented athletic education.
Read CV Yung-Hoh SheuECSS Paris 2023: CP-AP22