ECSS Paris 2023: OP-AP21
INTRODUCTION: Research into the benefits of different advance footwear technologies (AFT) spikes on middle/long distance track performance is lacking. This study aimed to examine the influence of different spikes technologies on running economy (RE) and middle-distance performance measures in trained runners. METHODS: Sixteen male trained runners completed four different visits on a 400 m outdoor track, running in three different spikes conditions. We compared a traditional EVA midsole spike (Control) with a modern midsole foam (PEBA) spike and a spike with a PEBA midsole and a carbon-fiber plate (PEBA+Plate). During the first three visits, participants performed 6x200 m at self-perceived 800 m race pace wearing each condition twice in a mirrored order (a-b-c-c-b-a) separated by 8 min rest between trials. Subsequently, they performed a 3,000 m time trial using one of the three shoe condition, in each visit. During visit 4, participants completed 6x4 min efforts at 18 km/h in each condition to assess RE (W/kg). RESULTS: The main effect for spike condition was significant for the runs at self-perceived 800 m pace (p<0.001; η2 =0.438), the 3,000 m time trial (p=0.013; η2 =0.342) and RE (p<0.001; η2 =0.694). At 800 m race pace, PEBA+Plate (6.63±0.36 m/s; p<0.001) resulted in 2.8% faster 200 m runs compared to Control (6.45±0.36 m/s), while PEBA (6.53±0.45 m/s) and Control were similar. The 3,000 m speed improved in the PEBA (5.79±0.23 m/s; p=0.034; 1.0%) and PEBA+Plate conditions (5.87±0.37 m/s; p=0.032; 2.4%) compared to Control (5.73±0.29 m/s). RE improved significantly in the PEBA (20.25±1.79 W/kg; p<0.001; 5.1%) and PEBA+Plate conditions (20.47±1.43 W/kg; p<0.001; 4.0%) compared to Control (21.30±1.59 W/kg), without significant differences between the PEBA and PEBA+Plate conditions. CONCLUSION: Our results suggest that AFT spikes with modern foams enhance running performance across middle- and long-distance events. However, at mid-distance speeds the PEBA+Plate technology performed better than Control, while modern foam alone (PEBA) did not significantly improve performance. This may be because when running at higher speeds, the optimal longitudinal bending stiffness of the shoe might be higher (1). However, for running at 18 km/h, RE improved similarly in both AFT spikes (PEBA and PEBA+Plate) compared to traditional EVA spikes. At sub-maximal speeds, differences may be mainly due to differences in midsole foam rather than in longitudinal bending stiffness (2). References 1. Rodrigo-Carranza, V., et al., (2022). European Journal of Sport Science, 22(10), 1508-1521. https://doi.org/10.1080/17461391.2021.1955014 2. Rodrigo‐Carranza, V., et al., (2023). Scandinavian Journal of Medicine & Science in Sports. https://doi.org/10.1111/sms.14526
Read CV Víctor Rodrigo CarranzaECSS Paris 2023: OP-AP21
INTRODUCTION: Athletic activity recognition is the procedure of recognizing individual or group-specific activities utilizing mobile and wearable sensors. In previous research, human activity recognition is done by applying traditional machine learning models to recognize individual activities, however, this approach can result in data security and privacy issues. To address these issues, we investigate the use of privacy-preserving federated learning models to recognize users activities without sharing data [1]. METHODS: We design a privacy-preserving federated learning method that can recognize athletic activities by sharing training parameters not data. Our privacy-preserving federated learning model contains three steps: training the local model, sharing parameters with the global model, aggregating weights with other clients, getting back the global model, and retraining again by using the updated local model. We performed multiple rounds until we achieved maximum accuracy. Comparing the performance of each client in a federated learning approach and traditional approach. Also, implementing multiple deep learning algorithms and comparing their performance as well. RESULTS: The privacy-preserved federated learning approach using the LSTM model, achieved an 88.38 % average accuracy for 15 different clients, and the traditional approach 92.7%. In the case of the RNN model average testing accuracy is 88.69% and for the traditional approach testing accuracy is about 93.4%. CONCLUSION: Federated learning can provide a reasonable alternative to traditional approaches for activity recognition using mobile sensor data. The federated learning approach presented in this work can protect users’ privacy whilst maintaining acceptable accuracy. 1. Sozinov, K., Vlassov, V., & Girdzijauskas, S. (2018, December). Human activity recognition using federated learning. In 2018 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Ubiquitous Computing & Communications, Big Data & Cloud Computing, Social Computing & Networking, Sustainable Computing & Communications (ISPA/IUCC/BDCloud/SocialCom/SustainCom) (pp. 1103-1111). IEEE. 2. Shoaib, M., Scholten, H., & Havinga, P. J. (2013, December). Towards physical activity recognition using smartphone sensors. In 2013 IEEE 10th international conference on ubiquitous intelligence and computing and 2013 IEEE 10th international conference on autonomic and trusted computing (pp. 80-87). IEEE. 3. Sardar, A. W., Ullah, F., Bacha, J., Khan, J., Ali, F., & Lee, S. (2022). Mobile sensors based platform of Human Physical Activities Recognition for COVID-19 spread minimization. Computers in Biology and Medicine, 146, 105662. 4. Chai, Y., Liu, H., Zhu, H., Pan, Y., Zhou, A., Liu, H., ... & Qian, Y. (2024). A profile similarity-based personalized federated learning method for wearable sensor-based human activity recognition. Information & Management, 103922. 5. https://www.cis.fordham.edu/wisdm/index.php
Read CV ABDUL WASAY SARDARECSS Paris 2023: OP-AP21
INTRODUCTION: The ability to rapidly generate muscle force (produce power) is a critical determinant of athletic performance. Recent technological progress provides opportunities for limb-specific assessment of neuromuscular parameters during training or competition, which can reveal inter-limb asymmetries (ILAs) that may limit functional capacity. Yet, due to difficulties with on-ice data collection, hockey athletes are an understudied population compared to other sporting groups. The purpose of this study was to explore the implementation of skate-secured 3-D accelerometers to assess on-ice performance, and to investigate the relationship between on- and off-ice performance metrics. We hypothesized that relationships would exist between on- and off-ice metrics, including ILAs, and that lower-limb ILA would be inversely related to skating performance. METHODS: Seventeen participants (15.0 ± 1.2 years; seven females) completed two performance-based tasks to assess lower-limb function: a 30-m forward sprint (on-ice), and a vertical countermovement jump (CMJ) (off-ice). On-ice metrics of interest included mean stride power and total sprint time. The vertical CMJ was performed on a dual force plate system, and metrics of interest included peak jump height, relative peak force and power, relative braking rate of force development, and impulse (braking and propulsive). Mean stride power, as well as CMJ impulse (braking and propulsive), force, and rate of force development were used to assess ILA. Linear regressions were performed to determine relationships between on- and off-ice variables. RESULTS: An inverse relationship was found for mean stride power and skating sprint time (R2 = 0.30; p = 0.02). Positive relationships were detected between peak CMJ height and both mean stride power (R2 = 0.37; p = 0.01) and skating sprint time (R2 = 0.75; p < 0.01), as well as between peak CMJ relative power and both mean stride power (R2 = 0.30; p = 0.02) and skating sprint time (R2 = 0.71; p < 0.01). Regarding asymmetries, there was a positive relationship between ILAs for CMJ rate of force development and mean stride power (R2 = 0.31; p = 0.02); however, no other relationships between off-ice and on-ice ILA measures were significant (p ≥ 0.32). Additionally, no on- or off-ice measure of ILA related to skating sprint time (p ≥ 0.09). CONCLUSION: In summary, skate-secured 3-D accelerometers allow assessment of limb-specific on-ice parameters that are important for skating performance. Although a relationship between on- and off-ice performance was identified, the presence of on- or off-ice ILAs may not be important for short-term power production.
Read CV Bryce TwibleECSS Paris 2023: OP-AP21