Automated Detection of Real-World Falls: Modeled From People With Multiple Sclerosis.

Falls are a major health problem with one in three people over the age of 65 falling each year, oftentimes causing hip fractures, disability, reduced mobility, hospitalization and death. A major limitation in fall detection algorithm development is an absence of real-world falls data. Fall detection algorithms are typically trained on simulated fall data that contain a well-balanced number of examples of falls and activities of daily living. However, real-world falls occur infrequently, making them difficult to capture and causing severe data imbalance. People with multiple sclerosis (MS) fall frequently, and their risk of falling increases with disease progression. Because of their high fall incidence, people with MS provide an ideal model for studying falls. This paper describes the development of a context-aware fall detection system based on inertial sensors and time of flight sensors that is robust to imbalance, which is trained and evaluated on real-world falls in people with MS. The algorithm uses an auto-encoder that detects fall candidates using reconstruction error of accelerometer signals followed by a hyper-ensemble of balanced random forests trained using both acceleration and movement features. On a clinical dataset obtained from 25 people with MS monitored over eight weeks during free-living conditions, 54 falls were observed and our system achieved a sensitivity of 92.14%, and false-positive rate of 0.65 false alarms per day.

Context-aware fall detection using inertial sensors and time-of-flight transceivers.

Automatic detection of falls is important for enabling people who are older to safely live independently longer within their homes. Current automated fall detection systems are typically designed using inertial sensors positioned on the body that generate an alert if there is an abrupt change in motion. These inertial sensors provide no information about the context of the person being monitored and are prone to false positives that can limit their ongoing usage. We describe a fall-detection system consisting of a wearable inertial measurement unit (IMU) and an RF time-of-flight (ToF) transceiver that ranges with other ToF beacons positioned throughout a home. The ToF ranging enables the system to track the position of the person as they move around a home. We describe and show results from three machine learning algorithms that integrate context-related position information with IMU based fall detection to enable a deeper understanding of where falls are occurring and also to improve the specificity of fall detection. The beacons used to localize the falls were able to accurately track to within 0.39 meters of specific waypoints in a simulated home environment. Each of the three algorithms was evaluated with and without the context-based false alarm detection on simulated falls done by 3 volunteer subjects in a simulated home. False positive rates were reduced by 50% when including context.