Local optimal sensor deployment for random field reconstruction

Deploying the sensor nodes at the best locations for random field reconstruction via sensor network is a fundamental task. We propose two criteria to evaluate the performance of random field reconstruction. The local optimal solutions for the random field reconstruction under both criteria are also proposed. We show that the local optimal sensor deployments under the proposed criteria are both uniformly distributed for the one dimensional random field which is stationary and isotropic. Several simulations show the performance of our proposed method.