Another high impedance fault detection scheme devised a neural network detection system that is trained to identify high impedance fault is described in [5]. Reference [6] describes a conventional high impedance fault detection technique that uses a neural network to detect high impedance faults that rely on derivatives of the maxima and minima of the load current. The results of long term high impedance fault detection tests conducted with the collaboration of five utilities and including staged faults, naturally occurring faults, and normal system operation were published in [7]. Results of the testing of three high impedance fault detection systems are reported in [8]. In another high impedance fault detection study [9], the results of years of experience with high impedance fault detection and testing are summarized. This technique was implemented in a product which uses multiple algorithms based mainly on energy, randomness, interharmonics, etc. in layers as described in [10]