Anomalous subject and device identification based on rolling baseline

A system comprising computer-readable instructions stored in non-transitory storage media and at least one microprocessor coupled to said non-transitory storage media for executing said computer-readable instructions, said at least one microprocessor configured to:

• (a) analyze data obtained from one or more sensors, said data related to one or more devices at a site;
• (b) establish a rolling baseline for said data by assigning each packet of said data to a cluster of packets amongst a plurality of clusters of packets of said data;
• (c) score, based on its distance from a centroid of said rolling baseline, each packet of said data;
• and
• (d) identify based on said distance an anomalous device amongst said one or more devices;
• wherein said one or more sensors comprise one or more of a video sensor, an audio sensor, a cellular network sensor, a blue-tooth sensor, a radio frequency identification (RFID) sensor, a Zigbee sensor and a thermal sensor.

A computer-implemented method executing computer program instructions stored in a non-transitory storage medium and comprising the steps of:

• (a) providing at a site, one or more sensors comprising a video sensor, an audio sensor, a cellular network sensor, a blue-tooth sensor, a radio frequency identification (RFID) sensor, a Zigbee sensor and a thermal sensor;
• (b) analyzing data obtained from said one or more sensors, said data related to one or more subjects at said site;
• (c) establishing a rolling baseline for said data by assigning each packet of said data to a cluster of packets amongst a plurality of clusters of packets of said data;
• (d) scoring, based on its distance from a centroid of said rolling baseline, each packet of said data;
• and
• (e) identifying based on said distance an anomalous subject amongst said one or more subjects.