Value-fusion versus decision-fusion for fault-tolerance in collaborative target detection in sensor networks

Abstract – Collaborative signal processing algorithms in sensor networks must be robust to device failures because one expects a large number of failures due to the harsh con-ditions in which they are usually deployed. In this paper, we study two distinct approaches, value-fusion and decision-fusion, for achieving fault-tolerance in collaborative target detection algorithms. In value-fusion, sensor devices first exchange their measured values to arrive at a fault-tolerant consensus on the measurement. Then each device makes an independent decision as to whether or not a target is present based on the consensus measurement. In contrast, in decision-fusion, each device first makes an independent decision as to whether or not a target is present and then the devices exchange their decisions to arrive at a fault-tolerant consensus decision. In this paper, we compare the performance of value and decision fusion using two mea-sures: probability of correct detection and probability of false alarm. The results show that if fault-tolerance is not required, then value-fusion is better than decision-fusion and whereas if fault-tolerance is essential, then decision-fusion is better than value-fusion