Short-term gamma background anticipation using learning Gaussian processes

The use of machine intelligence for gamma-ray background radiation anticipation is discussed and the test results on experimentally obtained spectra are presented. In this paper, a Gaussian process is adopted for learning recent measurements and subsequently anticipating the next ones in a short ahead in time horizon. Anticipated values are compared to respective incoming measurements and a decision is made whether an alarm should be raised. The proposed algorithm is tested on a set of real experimental gamma-ray measurements taken with a low resolution detector.