An ensemble of hmms for cognitive fault detection in distributed sensor networks

Abstract. Distributed sensor networks working in harsh environmental conditions can suffer from permanent or transient faults affecting the em-bedded electronics or the sensors. Fault Diagnosis Systems (FDSs) have been widely studied in the literature to detect, isolate, identify, and pos-sibly accommodate faults. Recently introduced cognitive FDSs, which represents a novel generation of FDSs, are characterized by the capabil-ity to exploit temporal and spatial dependency in acquired datastreams to improve the fault diagnosis and by the ability to operate without re-quiring a priori information about the data-generating process or the possible faults. This paper suggests a novel approach for fault detection in cognitive FDSs based on an ensemble of Hidden Markov Models. A wide experimental campaign on both synthetic and real-world data com-ing from a rock-collapse forecasting system shows the advantages of the proposed solution.