New Directions in Radioisotope Spectrum Identi?cation

Recent studies have found the performance of commercial handheld detectors with automatic RIID software to be less than acceptable [14, 15]. Previously, we have explored approaches rooted in speech processing such as cepstral features and information-theoretic measures [18]. Scienti?c advances are often made when researchers identify mathematical or physical commonalities between di?erent ?elds and are able to apply mature techniques or algorithms developed in one ?eld to another ?eld which shares some of the same challenges. The authors of this paper have identi?ed similarities between the unsolved problems faced in gamma-spectroscopy for automated radioisotope identi?cation and the challenges of the much larger body of research in speech processing. Our research has led to a probabilistic framework for describing and solving radioisotope identi?cation problems. Many heuristic approaches to classi?cation in current use, including for radioisotope classi?cation, make implicit probabilistic assumptions which are not clear to the users and, if stated explicitly, might not be considered desirable. Our framework leads to a classi?cation approach with demonstrable improvements using standard feature sets on proof-of-concept simulated and ?eld-collected data.