System and method of robust and highly generalized faulty sensor data detection

A system, comprising:

• memory;
• and
• processor circuitry forming at least one processor communicatively coupled to the memory and being arranged to operate by:
• receiving sensor data from a group of sensors used to contribute to monitoring of an object or situation for a common end goal;
• determining temporal dependencies of sensor data from the same sensor, and repeated for multiple sensors of the group of sensors, and spatial dependencies among senor data from different sensors from the group of sensors;
• generating, by at least one processor, indicators that indicate whether sensor data associated with individual sensors of the group of sensors is faulty comprising inputting a version of the spatial and temporal dependencies into a convolutional neural network (CNN);
• and
• training the CNN with both a faulty sensor data classifier neural network and a domain adaptive neural network (DA-NN) to increase generalization of the CNN to cross-domains with the same group of sensors but with different environments from domain to domain affecting the same group of sensors.

At least one non-transitory computer-readable medium comprising instructions thereon that when executed by at least one computing device, cause the computing device to operate by:

• receiving sensor data from a group of sensors used to contribute to monitoring of an object or situation for a common end goal;
• determining temporal dependencies of sensor data from the same sensor, and repeated for multiple sensors of the group of sensors, and spatial dependencies among senor data from different sensors from the group of sensors;
• generating indicators that indicate whether sensor data associated with individual sensors of the group of sensors is faulty sensor data comprising inputting a version of the spatial and temporal dependencies into a convolutional neural network (CNN);
• and
• restoring the faulty sensor data to non-faulty sensor data comprising formatting the indicators and the sensor data used to determine dependencies associated with the indicators into separate indicator embeddings and sensor data embeddings, combining the indicator embeddings and sensor data embeddings to form combined data, and using the combined data to form a three dimensional vector with features that indicate faulty sensor data to input into a multi-attention transformer neural network that has a spatial encoder and a temporal encoder.