Microcontroller based neural network for landmine detection using magnetic gradient data

Landmines are affecting the live and livelihood of millions of people around the world. In this paper, we have developed a new method for detection of landmines using Hopfield neural network as applied to gradiometer magnetic data. The Hopfield Neural Network is used to optimize the magnetic moment of dipole source representing the landmine at regular locations. For each location, Hopfield neural network reaches its stable energy state. The location of the landmine corresponds to the location yielding the minimum Hopfield energy. Output results include position in two dimensions, horizontal location and depth of the landmine. Furthermore, the proposed algorithm was implemented on a microcontroller, to be suitable for real time detection. Theoretical and actual field examples prove the effectiveness of using the microcontroller based Hopfield neural network as an objective tool for detection of landmines.