This research vision and challenges paper focuses on microprocessor design and activity-recognition data processing for medical devices in student-athlete health care. Sports are the second leading cause of mild traum...
详细信息
ISBN:
(纸本)9781509022793
This research vision and challenges paper focuses on microprocessor design and activity-recognition data processing for medical devices in student-athlete health care. Sports are the second leading cause of mild traumatic brain injury (mTBI) for people aged between 15 and 24 years. Significant work has been done in the use of sensors to determine the linear and rotational acceleration of head impacts, and their potential correlation to concussions. However, recent studies have shown that subconcussive trauma may be a better indicator of future risks, such as impaired cognitive, motor, and sensory functions, as well as loss of control of emotion and behavior. Therefore, the current reactive and hospital-centered approach where waiting until a concussion has been diagnosed before providing quality care to student athletes is insufficient. Our project will enable a transformation in student-athlete healthcare through the design and utilization of wearable impact sensors to support a preventive, proactive, and evidence-based approach for assessing and mitigating the risk of long-term brain injury. Research and develop activities will focus on a next-generation form-factor xPatch device with an encrypted 915MHz ISM band radio transceiver for secure and efficient real-time access to head impact data, while meeting requirements for transmission range vs. power consumption, receiver sensitivity, data rate, start-up time, latency, capacity, and cost. We will enhance X2 Biosystems's currently existing Injury Management System data platform through development and integration of on-chip data analytics, in addition to real-time recording and secure wireless transmission of impact data. Integration of support vector data machine and other machine learning models will enhance predictive injury analytics based on head impact data. Integration of on-chip machine learning and cloud-based impact classification algorithms will be investigated in order to enhance real-time interpretati
暂无评论