US 11,860,712 B1
Sensor fault prediction and resolution
Zachary A. Silverstein, Georgetown, TX (US); Jacob Ryan Jepperson, St. Paul, MN (US); Jeremy R. Fox, Georgetown, TX (US); and Spencer Thomas Reynolds, Austin, TX (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Aug. 24, 2022, as Appl. No. 17/821,954.
Int. Cl. G06F 11/07 (2006.01); G16Y 40/40 (2020.01)
CPC G06F 11/0709 (2013.01) [G06F 11/0793 (2013.01); G16Y 40/40 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
identifying a set of sensors in an Internet of Things (IoT) system including a first sensor, wherein the IoT system is configured to perform at least one action, the IoT system includes one or more IoT devices including a first IoT device, each sensor of the set of sensors is correlated to one IoT device of the one or more IoT devices, and each sensor sends an output data feed to the IoT system including a first data feed for the first sensor;
predicting, by a generative adversarial network (GAN), an expected output of the first sensor;
determining that a difference between the expected output and an actual output of the first sensor exceeds a first threshold; and
replacing, in response to the difference exceeding the first threshold, the first data feed with a first generated data feed.