HMM-based decision fusion in wireless sensor networks with noncoherent multiple access

We develop a novel decision fusion (DF) approach which exploits time-correlation of the unknown binary source under observation through a wireless sensor network (WSN) reporting local decisions to a fusion center (FC) over interfering Rayleigh fading channels. The system is modeled via a hidden Markov model (HMM): both learning and detection phases are developed. The learning phase is blind, i.e. it requires only a set of observations without knowledge of the corresponding source states. Remarkably, the approach allows the FC to take decisions without knowledge of the local sensor performance. Numerical results confirm the effectiveness of the proposed approach.