18-549 Design and Architecture: 2/19/2014 Rapid Ocular Sideline Concussion Diagnostics Team 8 Brandon Lee--Andrew Pfeifer--Thomas Phillips--Ryan Quinn 1 Status Update • Our Project consists of a head-mounted eye-set that provides automated ocular-based concussion testing and diagnosis for sideline use. o Project Status In communication with several experts, planned meetings and phone calls to gather concussion-based research and contacts General idea endorsement by Dr. Vincent Miele, with suggested addition of integrated balance testing • Proposal submitted to NFL-UA-GE Head Health Challenge II o Parts Status Prototype parts ordered on February 8th, most acquired this morning 2 Architecture Concussion-Testing Eyeset Android Tablet TFT Display Camera B App Trainer A 2 RasPi D WiFi Module 3 Player OpenCV Kernel C Diagnosis 1. Severe impact observed, player brought to sideline 2. Concussion testing A. Tests administered via TFT display B. Eye movements recorded in response to tests C. Image/Video Processing on responses D. Resultant data sent over WiFi link 3. Trainer analyzes data in tablet interface (Existing) Accelerometer Sensor / Observer 1 3 Use Cases Startup 1. Severe impact observed 2. Player moved to sideline 3. Eye-set equipped 4. Trainer activates testing via App interface 5. Test cycle begins A. Visual test on TFT display B. Eye (pupil) responses recorded 6. Image/video processing on responses to compile test results 7. Next test administered 8. Diagnosis given *Test cycle includes: 1. Dilation Test 2. Depth Test 3. Tracking Test Shutdown Application Waiting for Trainer Eyeset Begin Test Cycle* Begin Test Procedure Tests in Progress... Record Responses Display Visual Test * Present Test Results Gather/Process Test Results Send Test Results 4 Risks and Mitigation Risks Mitigation Plan Direct access to concussed patients for testing might not be available Extensive testing with un-concussed subjects; UPMC contacts may help Eye-set design may be uncomfortable, unbalanced, or clunky Design a compact housing for RasPi and sensors, possibly with counter balance Camera focus may lack sharpness and clarity to perform eye analysis on a wide variety of eye types Alternative lenses may need to be acquired; image and video processing algorithms may account for possible blurs Plan A Plan B Plan C Android App works smoothly; ergonomic eye-set performs accurate tests; individualized player diagnoses Individualized player diagnoses give way to more general tests; the eye-set and App are still well packaged and easy-to-use Less refined eye-set performs accurate, general tests that are reliably sent to an easy-to-use App interface 5