A cyber-physical system for senior collapse detection

Consumer-oriented social data fusion: controlled learning in social environments, social advertising and more

Lynne Grewe, Steven Magaa-ZookCSUEB, [email protected] cyber-physical system for senior collapse detection

Seniors FallingOver 1/3rd of seniors above 65 fall each yearLead to serious injury and even deathFalls account for 25% of all hospital admissions, and 40% of all nursing home admissions 40% of those admitted do not return to independent living; 25% die within a year.Fast medical attention can make a differenceMany falls do not result in injuries, yet a large percentage of non-injured fallers (47%) cannot get up without assistance.

Cost of Falling?2005, CDC study Cost for Falls leading to fatality

Goalcreate a smart home system to predict and detect the falling of senior/geriatric participants in home environments More seniors living at home autonomously

SCD: Senior Collapse Detection Overview

SCD: uses Kinect SensorInexpensive, commercial, well tested, good API support

Modalityexample2D 3D Audio

Feature ExtractionPerform Skeleton TrackingIdeal fall indicators often involve joint locations and range of motionGood Resolution 21 joints

Skeleton Tracking Has NoiseDegrading performance with occlusionGeneral TwitchingAlso degrades as more occlusion from being on floor