US 11,727,091 B2
Method and system for training machine learning models on sensor nodes
Karanpreet Singh, Aspinwall, PA (US); and Rajen Bhatt, McDonald, PA (US)
Assigned to Qeexo, Co., San Jose, CA (US)
Filed by QEEXO, CO., San Jose, CA (US)
Filed on Sep. 8, 2021, as Appl. No. 17/469,439.
Claims priority of provisional application 63/077,338, filed on Sep. 11, 2020.
Prior Publication US 2022/0083823 A1, Mar. 17, 2022
Int. Cl. G06F 18/2433 (2023.01); G08B 21/18 (2006.01); G06F 18/2413 (2023.01)
CPC G06F 18/2433 (2023.01) [G06F 18/2413 (2023.01); G08B 21/182 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method of automatically training a sensor node to detect anomalies in an environment, the method comprising:
receiving at the sensor node an indication to initiate training by the sensor node to detect anomalies in the environment based on sensor data generated by a sensor that resides on such sensor node and is operable to detect sensor signals from the environment;
after training is initiated, the sensor node automatically training a model that resides on the sensor to detect anomalies in the environment, wherein such training is based on the sensor data; and
after the model is trained, executing by the sensor node the model to detect anomalies in the environment.