Device, method and computer program for determining sleep event using radar

A method for determination of a sleep event using a radar, comprising:

• transmitting a radar signal toward a subject;
• receiving the radar signal reflected from the subject;
• deriving an average breathing signal of the subject based on the radar signal;
• deriving a breathing feature session by detecting a duration in which the radar signal strays from the average breathing signal for a predetermined threshold time period or more;
• deriving a peak of the radar signal within the detected breathing feature session;
• generating breathing feature information based on the derived peak, the average breathing signal, and a predetermined threshold condition;
• deriving event occurrence prediction information for a plurality of sleep items based on the breathing feature information;
• and
• determining whether a sleep event has occurred in the subject based on the event occurrence prediction information.

A non-transitory computer-readable storage medium that stores a sequence of instructions for determination of a sleep event using a radar,

• wherein the sequence of instructions, when executed by a computing device, causes a computing device to:
• transmit a radar signal toward a subject;
• receive the radar signal reflected from the subject;
• derive an average breathing signal of the subject based on the radar signal;
• derive a breathing feature session by detecting a duration in which the radar signal strays from the average breathing signal for a predetermined threshold time period or more;
• derive a peak of the radar signal within the detected breathing feature session:
• generate breathing feature information of the subject based on the derived peak, the average breathing signal, and a predetermined threshold condition;
• derive event occurrence prediction information for a plurality of sleep items based on the breathing feature information;
• and
• determine whether a sleep event has occurred in the subject based on the event occurrence prediction information.