A comparative study of machine learning methods for automated identification of radioisotopes using NaI gamma-ray spectra
| Autor: | Hyoung-Koo Lee, P.K. Bhowmik, Shaikat M. Galib, Ashish V. Avachat |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Artificial neural network
Real-time processing Computer science 020209 energy Radioisotope identification Gamma ray spectra 02 engineering and technology Machine learning computer.software_genre Convolutional neural network Nuclear security 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine 0202 electrical engineering electronic engineering information engineering Nuclear threat detection Gamma-ray spectroscopy business.industry Deep learning TK9001-9401 Identification (information) Nuclear Energy and Engineering Metric (mathematics) Nuclear engineering. Atomic power Alternating decision tree Artificial intelligence F1 score business computer |
| Zdroj: | Nuclear Engineering and Technology, Vol 53, Iss 12, Pp 4072-4079 (2021) |
| ISSN: | 1738-5733 |
| Popis: | This article presents a study on the state-of-the-art methods for automated radioactive material detection and identification, using gamma-ray spectra and modern machine learning methods. The recent developments inspired this in deep learning algorithms, and the proposed method provided better performance than the current state-of-the-art models. Machine learning models such as: fully connected, recurrent, convolutional, and gradient boosted decision trees, are applied under a wide variety of testing conditions, and their advantage and disadvantage are discussed. Furthermore, a hybrid model is developed by combining the fully-connected and convolutional neural network, which shows the best performance among the different machine learning models. These improvements are represented by the model's test performance metric (i.e., F1 score) of 93.33% with an improvement of 2%–12% than the state-of-the-art model at various conditions. The experimental results show that fusion of classical neural networks and modern deep learning architecture is a suitable choice for interpreting gamma spectra data where real-time and remote detection is necessary. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|