SBIR Phase I: Epidermal Sensor for Human Performance Assessment and Monitoring

The broader impact /commercial potential of this Small Business Innovation Research (SBIR) Phase I project is the development of a wearable sensor and analytical platform capable of non-invasively monitoring human health and athletic performance. This SBIR Phase 1 project will result in a miniaturized, durable wearable sensor that can be comfortably worn in any environment athletic or otherwise.

The device will contain a novel suite of sensors capable of measuring health and performance related parameters. The analytical platform will continuously predict core body temperature, athletic performance, and optimal athletic training goals. The core body temperature prediction algorithm will provide an early warning when the core temperature approaches a dangerous level, which will mitigate the serious and growing risk of heat-related illness.

The performance and optimal training prediction algorithms will provide training suggestions to achieve maximum performance growth.

This Small Business Innovation Research (SBIR) Phase I project addresses the unmet technological and clinical need to integrate biomechanical, physiological, and thermoregulatory parameters into a single unobtrusive device and provide users with meaningful and actionable insight toward health and performance. The critical research objectives of this Phase 1 project are the development of: a comprehensive suite of sensors packaged into a durable and comfortable wearable device, a reliable and accurate core temperature prediction algorithm, performance and optimal workload prediction algorithms, and an integrated system providing clear and useful feedback to users regardless of medical or scientific knowledge.

The hardware will be incorporated into a 0.75x0.75 inch form factor, continuously measure all parameters with medical grade accuracy, and achieve a minimum battery life of 90 hours. Algorithm development will leverage high-fidelity datasets, advanced signal processing, and custom deep learning architectures involving multivariate Long Short-Term Memory and feed forward neural networks to understand the non-linear, time dependent relationships between parameters and overall human performance and safety.

These complex relationships will be distilled into an easily understandable and visually appealing user interface.

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.