SYSTEM FOR INTEGRATING MULTIPLE SENSOR DATA TO PREDICT A FALL RISK

摘要

A method of determining the likelihood of a slip or fall, the method comprising: receiving, by a detection application (112) stored in a non-transitory memory (104) and executed on a processor (106), a plurality of sensor readings from a plurality of sensors (152, 154); receiving contextual information from the plurality of sensors (152, 154), wherein the contextual information comprises at least one of location information, or environmental information; selecting a subset of a plurality of movement patterns based on a context from a plurality of movement patterns stored in a historical data store (126), wherein the context is based on the received contextual information, and wherein the plurality of movement patterns correlate with the at least one of the environmental information or the location information; comparing, by the detection application (112), the plurality of sensor readings with the subset of movement patterns selected from the historical data store (126); in response to the comparison, determining, by the detection application (112), that a slip or fall is likely based on the plurality of sensor readings matching at least one movement pattern of the subset of movement patterns.