Systems and methods for patient fall detection

A method of determining whether a user has fallen by processing signals indicative of movement by the user, the method comprising:

• receiving, with a processing device from a sensor, signals responsive to a linear acceleration of said user with respect to a roll axis, a pitch axis, and a yaw axis, said roll axis corresponding to a longitudinal axis extending along a length of said user's body, said pitch axis corresponding to said user's hips, and said yaw axis corresponding to a horizontal plane in which said user is located, wherein said sensor is configured to be worn by said user and comprises an accelerometer, a gyroscope, and a first wireless transceiver, and wherein said processing device comprises a processor and a second wireless transceiver configured to communicate with the first wireless transceiver of said sensor;
• receiving, with said processing device from said sensor, signals responsive to an angular velocity of said user with respect to said roll axis, said pitch axis, and said yaw axis;
• and
• processing said received signals responsive to said linear acceleration and said angular velocity of said user with said processor of said processing device by:
• forming a sensor data vector comprising a plurality of data elements, each of the plurality of data elements responsive to one of said linear acceleration or said angular velocity with respect to one of said roll axis, said pitch axis, and said yaw axis;
• normalizing said plurality of data elements to form a normalized sensor data vector;
• generating a feature vector from said normalized sensor data vector, said feature vector comprising a plurality of features indicative of a fall, wherein each of the plurality of features are generated based on one or more of the plurality of data elements from said normalized sensor data vector;
• deriving an activation value based on an application of a weight vector to said feature vector, wherein said weight vector comprises a plurality of weights, each of the plurality of weights associated with one of the plurality of features of said feature vector;
• and
• determining whether the fall has occurred based on the derived activation value.

A method of determining whether a user has fallen, the method comprising:

• receiving, with a processing device, a first set of signals responsive to an acceleration of the user from a sensor configured to be worn by said user, said sensor comprising an accelerometer and a gyroscope, said processing device comprising a processor;
• receiving, with said processing device, a second set of signals responsive to an angular velocity of said user from said sensor;
• and
• generating a feature vector comprising a plurality of features indicative of a fall, wherein each of the plurality of features are generated based on at least one of:
• one or more of the first set of signals;
• and
• one or more of the second set of signals;
• deriving an activation value based on an application of a weight vector to said feature vector, said weight vector comprising a plurality of weights, each of the plurality of weights associated with one of the plurality of features of said feature vector;
• and
• determining whether the fall has occurred based on the derived activation value.

A system configured to determine whether a user has fallen, the system comprising:

• a sensor including an accelerometer and a gyroscope, said sensor configured to transmit a first set of signals responsive to an acceleration of the user and a second set of signals responsive to an angular velocity of said user;
• a processing device comprising a processor, said processing device configured to:
• receive said first and second sets of signals from said sensor;
• generate a feature vector comprising a plurality of features indicative of a fall, wherein each of the plurality of features are generated based on at least one of:
• one or more of the first set of signals;
• and
• one or more of the second set of signals;
• derive an activation value based on an application of a weight vector to said feature vector, said weight vector comprising a plurality of weights, each of the plurality of weights associated with one of the plurality of features of said feature vector;
• and
• determine whether the fall has occurred based on the derived activation value.