Systems and methods for compressing sensor data using clustering and shape matching in edge nodes of distributed computing networks

Abstract

A system and method for compressing sensor data at an edge node of a distributed computing network. The method includes training the edge node to with a plurality of known signal templates. Each known signal template corresponding to a corresponding one of a plurality of events observable by the sensor. A raw data signal is collected by a sensor of the edge node. The raw data signal is classified to one of the known signal templates based on a degree of similarity between the raw data signal and the known signal template. A compression scheme is selected based on the classification of the raw data signal. The raw data signal is compressed in accordance with the compression scheme.

1 . A method of analyzing analog responses of a passive infrared (PIR) sensor at an edge node of a distributed network, comprising:
 collecting an analog data signal as an analog portion of a response from the PIR sensor detecting movement with respect to the sensor;   processing the analog data signal with dynamic time warping to compare the analog data signal to a plurality of known signal templates based on a degree of similarity between the analog data signal and each of the plurality of known signal templates, each of the plurality of known signal template comprising a data set describing a type of movement detected with respect to the PIR sensor;   identifying a matching one of the plurality of known signal templates that most closely resembles the analog data signal using a pattern recognition algorithm;   determining the type of movement detected based on the matching one of the known signal templates; and   transmitting an indication of the type of movement, the indication of the type of movement being a compressed representation of the analog data signal.