Automatic and Real-Time Identification of Radionuclides in Gamma-Ray Spectra: A New Method Based on Convolutional Neural Network Trained With Synthetic Data Set

Daniel, G.; Ceraudo, Francesco; Limousin, O.; Maier, Daniel; Meuris, A.

doi:10.1109/tns.2020.2969703

Cited by 50 publications

(30 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additional research is needed in the area of interpretability of spectral models, for example, understanding convolutional kernels as with ref. [13], or generating saliency maps which relate the most significant input features in determining a given network output. dimension of the features by summarizing a group of features with a single value.…”

Section: Discussionmentioning

confidence: 99%

“…The first applications of neural networks for source identification were examined between the early 1990s and 2000s [2,[7][8][9][10], with networks that mapped input spectra to the relative amount of known background and sources contained within the spectrum. More recently, modern approaches to perform identification using neural networks have been developed [3,[11][12][13][14][15], using methods similar to those seen since the deep learning boom of the early 2010s (e.g., ref. [16]).…”

Section: Artificial Neural Networkmentioning

confidence: 99%

“…Recent research in the area (e.g., refs. [12][13][14]) has emphasized methodologies that are more applicable to nuclear safety and security, however, due to a lack of a characterization of these methods under operationally-relevant conditions, compared to a known benchmark method, the utility of these methods remains unclear. Additionally, the use of neural networks for spectral anomaly detection has not been previously studied, and this work begins by briefly introducing networks that can be used to accomplish this.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

“…Specifically, one or more convolutional layers are used to produce convolutional feature maps, and these feature maps are flattened into a 1-dimensional vector, as done in refs. [12,13], which is then transformed using dense layers. This work makes use of a network with one convolutional layer followed by a max pooling layer and two dense layers, shown in Figure 2.…”

Section: Source Identificationmentioning

confidence: 99%

“…t+1 to be used in performing inference on new spectra (i.e., computing h [12,13]. A 2-dimensional feature map resulting from convolutional operations is flattened into a single feature vector of length 1024, and this is reduced down to the output size of 18 (17 sources, 1 background channel).…”

Section: Source Identificationmentioning

confidence: 99%

See 4 more Smart Citations

Neural Network Approaches for Mobile Spectroscopic Gamma-Ray Source Detection

Bilton

Joshi

Bandstra

et al. 2021

JNE

View full text Add to dashboard Cite

Artificial neural networks (ANNs) for performing spectroscopic gamma-ray source identification have been previously introduced, primarily for applications in controlled laboratory settings. To understand the utility of these methods in scenarios and environments more relevant to nuclear safety and security, this work examines the use of ANNs for mobile detection, which involves highly variable gamma-ray background, low signal-to-noise ratio measurements, and low false alarm rates. Simulated data from a 2” × 4” × 16” NaI(Tl) detector are used in this work for demonstrating these concepts, and the minimum detectable activity (MDA) is used as a performance metric in assessing model performance.In addition to examining simultaneous detection and identification, binary spectral anomaly detection using autoencoders is introduced in this work, and benchmarked using detection methods based on Non-negative Matrix Factorization (NMF) and Principal Component Analysis (PCA). On average, the autoencoder provides a 12% and 23% improvement over NMF- and PCA-based detection methods, respectively. Additionally, source identification using ANNs is extended to leverage temporal dynamics by means of recurrent neural networks, and these time-dependent models outperform their time-independent counterparts by 17% for the analysis examined here. The paper concludes with a discussion on tradeoffs between the ANN-based approaches and the benchmark methods examined here.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Artificial Neural Networkmentioning

confidence: 99%

Section: Artificial Neural Networkmentioning

confidence: 99%

Section: Source Identificationmentioning

confidence: 99%

Section: Source Identificationmentioning

confidence: 99%

See 3 more Smart Citations

Neural Network Approaches for Mobile Spectroscopic Gamma-Ray Source Detection

Bilton

Joshi

Bandstra

et al. 2021

JNE

View full text Add to dashboard Cite

show abstract

Prediction of Linear Energy Transfer Based on Geant4 Simulation and Neural Networks

Zhang

Chen

Liu

et al. 2023

Advcd Theory and Sims

View full text Add to dashboard Cite

Most of the traditional studies based on single event effects (SEEs) favor the analysis of electrical mechanisms of semiconductor devices. Professional simulation software in microelectronics requires researchers to have a solid knowledge of microelectronics theory, and the modeling threshold of the software is relatively high, the simulation speed is slow, and accurate simulation of inter‐particle and particle–material interactions is lacking. SEEs are related to linear energy transfer (LET), in this paper, a method is proposed to obtain LET datas to predict SEEs of particles incident on silicon materials by using the Geant4 Monte Carlo toolkit in combination with a dense convolutional network to accurately and rapidly estimate the energy deposition characteristics of the particles. The proposed network structure has a high prediction accuracy with a mean square error （MSE） of only 1.77 × 10−4. Compared with Geant4, which takes 1 min to compute a set of data, the proposed network structure takes only 0.0817 s. The method explores the feasibility of using Geant4 to model semiconductor devices combined with deep learning algorithms, providing a new research perspective for the prediction of microelectronic devices and making it possible to explore the influence of integrated circuits by SEEs.

show abstract

A machine learning oracle for parameter estimation

Koepke,

Gregg,

Frey

2023

Statistical Analysis

View full text Add to dashboard Cite

Competing procedures, involving data smoothing, weighting, imputation, outlier removal, etc., may be available to prepare data for parametric model estimation. Often, however, little is known about the best choice of preparatory procedure for the planned estimation and the observed data. A machine learning‐based decision rule, an “oracle,” can be constructed in such cases to decide the best procedure from a set of available preparatory procedures. The oracle learns the decision regions associated with based on training data synthesized solely from the given data using model parameters with high posterior probability. An estimator in combination with an oracle to guide data preparation is called an oracle estimator. Oracle estimator performance is studied in two estimation problems: slope estimation in simple linear regression (SLR) and changepoint estimation in continuous two‐linear‐segments regression (CTLSR). In both examples, the regression response is given to be increasing, and the oracle must decide whether to isotonically smooth the response data preparatory to fitting the regression model. A measure of performance called headroom is proposed to assess the oracle's potential for reducing estimation error. Experiments with SLR and CTLSR find for important ranges of problem configurations that the headroom is high, the oracle's empirical performance is near the headroom, and the oracle estimator offers clear benefit.

show abstract

Automatic and Real-Time Identification of Radionuclides in Gamma-Ray Spectra: A New Method Based on Convolutional Neural Network Trained With Synthetic Data Set

Cited by 50 publications

References 19 publications

Neural Network Approaches for Mobile Spectroscopic Gamma-Ray Source Detection

Neural Network Approaches for Mobile Spectroscopic Gamma-Ray Source Detection

Prediction of Linear Energy Transfer Based on Geant4 Simulation and Neural Networks

A machine learning oracle for parameter estimation

Contact Info

Product

Resources

About