Fault-Tolerant Classification in Multisensor Networks Using Coding Theory

A fault-tolerant distributed classification system employing the fault-tolerant fusion rule approach was proposed in [1]. Code matrix design is essential for the design of such systems. Two efficient code matrix design algorithms are proposed in this paper. The relative merits of both algorithms are also studied. Performance evaluation of the DCFECC (distributed classification fusion using error correcting codes) approach with faults due to hardware/software damage or drained batteries in sensors are provided. These results have shown significant improvement of fault-tolerance capability as compared with conventional parallel fusion networks. A generalization of the above approach that may handle channel transition errors is also provided.