Sequential probability ratio test for long-term radiation monitoring

Abstract

Among the possible decision-making algorithms for sequentially-acquired radiation sensor data is the Sequential Probability Ratio Test (SPRT). The suitability of the SPRT for long-term monitoring applications is discussed, and the decision-making performance of the SPRT is compared to that of the commonly used single-interval test (SIT). The analysis spans a wide range of signal and background count rates so that results are applicable to sensors of all sizes operating in different ambient conditions, with a spectrum of alarm thresholds. It is demonstrated that, for these simulated long-term monitoring scenarios, decisions to issue an alarm when the measured count rate equals the threshold count rate are made 3-5 times faster using the SPRT than with the SIT. The ability of the SPRT to provide an "all-clear" indication and the need for SPRT truncation strategies to limit decision times when the measured count rate falls between background and the specified threshold are also discussed. Under an early termination scenario, it is shown that a truncated SPRT retains a higher probability of detection.