US 12,394,293 B2
Life safety device with machine learning based analytics
Ryan Nathanial Sandler, Santee, CA (US)
Assigned to The ADT Security Corporation, Boca Raton, FL (US)
Filed by The ADT Security Corporation, Boca Raton, FL (US)
Filed on Mar. 8, 2024, as Appl. No. 18/600,274.
Application 18/600,274 is a continuation of application No. 17/845,743, filed on Jun. 21, 2022, granted, now 11,961,381.
Prior Publication US 2024/0212469 A1, Jun. 27, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G08B 17/117 (2006.01); G08B 29/18 (2006.01)
CPC G08B 17/117 (2013.01) [G08B 29/186 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A detector, comprising:
at least one sensor configured to detect airborne particulates at a premises;
at least one processor in communication with the at least one sensor;
at least one memory storing instructions that, when executed by the at least one processor, cause the at least one processor to:
determine at least one characteristic associated with the airborne particulates, the at least one characteristic associated with the airborne particulates comprising a composition of the airborne particulates;
compare the at least one characteristic associated with the airborne particulates to data associated with predefined characteristics of reference particulates;
detect, based at least on a result of the comparison, a presence of an alarm condition; and
determine, in response to the presence of the alarm condition being detected, at least one characteristic of the alarm condition based at least on the at least one characteristic associated with the airborne particulates and the result of the comparison, the at least one characteristic of the alarm condition comprising an identity of a substance that is a source of the airborne particulates; and
indicate an egress point or an ingress point based on the at least one characteristic of the alarm condition.