BioAIM: Bio-inspired Autonomous Infrastructure Monitoring

The Bio-inspired Autonomous Infrastructure Monitoring (BioAIM) system detects anomalous behavior during the deployment and maintenance of a wireless communication network formed autonomously by unmanned airborne nodes. A node may experience anomalous or unexpected behavior in the presence of hardware/software faults/failures, or external influence (e.g. natural weather phenomena, enemy threats). This system autonomously detects, reasons with (e.g. differentiates an anomaly from natural interference), and alerts a human operator of anomalies at runtime via a communication network formed by the Bio-inspired Artificial Intelligence Reconfiguration (BioAIR) system. In particular, BioAIM learns and builds a prediction model which describes how data from relevant sensors should change when a behavior executes under normal circumstances. Surprises occur when there are discrepancies between what is predicted and what is observed. BioAIM identifies a dynamic set of states from the prediction model and learns a structured model similar to a Markov Chain in order to quantify the magnitude of a surprise or divergence from the norm using a special similarity metric. While in operation BioAIM monitors the sensor data by testing the applicable models for each valid behavior at regular time intervals, and informs the operator when a similarity metric deviates from the acceptable threshold.