I-Corps: Adaptable Speed-Endurance Training Algorithm to Manage Aerobic and Anaerobic Capacity Development

I-Corps项目更广泛的影响/商业潜力是整合新颖和成熟的可穿戴生理传感器、机器学习和适应性运动训练算法，以优化性能，最大限度地降低受伤或过度训练的风险。职业和大学球队面临着严重的问题，由于受伤，过度劳累（横纹肌溶解）和劳累性中暑（EHI）。通过适当的管理和培训，近一半的问题是可以避免的。在优秀运动员中，达到训练过度或训练不足的平衡仍然是困难和难以捉摸的。精英和专业运动员，以及他们的教练、运动科学家和精英团队训练师需要对训练和表现进行最精确的评估和管理，失败的代价要大得多。在这一人群中取得成功后，这项创新可能会适用于精度不那么重要，效率和动力更受重视的健身和健康应用。对于慢性疾病管理应用来说，精确、生理监测、即时反馈和运动进展变得至关重要。I-Corps项目旨在使用定制的传感器阵列、适应性速度耐力训练算法和集成的机器学习，实现对运动训练的生理反应的实时持续监测，从而为精英和专业运动员创造最佳的个性化运动训练计划，以达到最佳表现，并最大限度地减少伤害。目前，运动员管理这种情况的主要方式缺乏对生理数据与工作量的整合和个性化，以防止在运动期间过度训练。迄今为止，很少有标准化和渐进式的非稳态训练计划，可以根据特定的个人调整计划。通过使用实时新颖的、成熟的生理传感器和机器学习，训练算法能够根据个人的特定生理反应调整锻炼。为此项目开发的一种新型传感器在初步测试中证明是有效的。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this I-Corps project is to integrate novel and established wearable physiological sensors, machine learning and an adaptable exercise-training algorithm to optimize performance and minimize risk of injury or overtraining. Professional and collegiate teams face significant problems due to injuries, overexertion (rhabdomyolysis) and exertional heat illness (EHI). Nearly half of these issues are avoidable via proper management and training. In elite athletes, achieving the balance of over or undertraining remains difficult and elusive. Elite and professional athletes, and their coaches, sports scientists, and elite team trainers require the most precise assessment and management of training and performance and the cost of failure is much greater. With success in this population, this innovation can potentially be adaptable to fitness and wellness applications where precision is less important, and efficiency and motivation is more highly valued. For chronic disease management applications, precision, physiological monitoring, instant feedback, and exercise progression become vitally important.This I-Corps project seeks to enable real-time and continuous monitoring of physiological responses to exercise training using a custom sensor array, adaptable speed-endurance training algorithm and integrated machine learning to create an optimal, individualized exercise-training program for peak performance and minimize injury in elite and professional athletes. Currently, the primary way in which athletes manage this lacks integration and individualization of physiological data to workload in order to prevent overtraining during the exercise session. To date, there have been few standardized and progressive non-steady state training programs that can adjust a program to a specific individual. Using real-time novel and established physiological sensors with machine learning, the training algorithm has the capability to adapt a workout to an individual's specific physiological responses. A novel sensor developed for this project has proven effective in preliminary testing.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.