View in EDS

A retention-based method for explosive classification using broadband lightsource X-ray absorption spectroscopy (BL-XAS).

Saved in:
Bibliographic Details
Title: A retention-based method for explosive classification using broadband lightsource X-ray absorption spectroscopy (BL-XAS).
Authors: Fang, Zheng1,2 (AUTHOR) fangzheng@xmu.edu.cn, Gao, Yuao1 (AUTHOR), Cai, Yuheng1 (AUTHOR), Liang, Wei1,3 (AUTHOR) wliang@xmu.edu.cn
Source: Measurement (02632241). Mar2026, Vol. 265, pN.PAG-N.PAG. 1p.
Subjects: Explosives analysis, Deep learning, Spectrometry, Nondestructive testing, X-ray absorption spectra, Real-time computing, Classification
Abstract: The escalating threat of terrorist attacks demands rapid and non-destructive explosives detection technologies for security checks. Recognizing the limitations of current approaches, namely Raman and infrared spectroscopy, whose testing depth rarely exceeds 5 mm. Mass spectrometry and chromatography also demand tight environmental control and expert operators. To address these drawbacks, we developed a portable broadband lightsource X-ray absorption spectroscopy (BL-XAS) system integrated with a novel deep-learning classifier. The hardware combines a 128-channel CdTe photon-counting detector with a tungsten-target X-ray source. We propose the Parallelized Retention Encoder PR-Encoder that places gated multi-scale retention and multi-layer perceptron modules on parallel computation paths to reduce per-layer latency and accelerate inference. Trained on 2000 spectra from 10 explosive materials, the PR-Encoder was evaluated against two baseline models. Transformer baselines achieved 88.5% classification accuracy with a per-spectrum inference latency of 13.1 ms, while Retention encoders reached 90.1% accuracy with 12.5 ms latency. In contrast, the PR-Encoder attained the highest performance — 93.4% accuracy under ten-fold cross-validation, with an average inference latency of approximately 10.1 ms per spectrum, demonstrating superior accuracy and computational efficiency. Integrating portable BL-XAS instrumentation with retention-based deep learning provides a real-time and non-destructive solution for explosive security screening. [Display omitted] • Portable BL-XAS with 128-channel CdTe detector enables rapid broadband spectra acquisition for explosives. • Parallelized Retention Encoder (PR-Encoder) combines gated multi-scale retention and MLP in parallel paths to speed inference. • PR-Encoder achieves 93.4% classification accuracy on ten explosives, outperforming Transformer and Retention baselines. • Parallel design reduces per-spectrum inference latency to 10.1 ms, yielding ∼ 20% speedups over baselines. • System offers a real-time, non-destructive field solution with superior penetration compared to optical spectroscopy. [ABSTRACT FROM AUTHOR]
Copyright of Measurement (02632241) is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:The escalating threat of terrorist attacks demands rapid and non-destructive explosives detection technologies for security checks. Recognizing the limitations of current approaches, namely Raman and infrared spectroscopy, whose testing depth rarely exceeds 5 mm. Mass spectrometry and chromatography also demand tight environmental control and expert operators. To address these drawbacks, we developed a portable broadband lightsource X-ray absorption spectroscopy (BL-XAS) system integrated with a novel deep-learning classifier. The hardware combines a 128-channel CdTe photon-counting detector with a tungsten-target X-ray source. We propose the Parallelized Retention Encoder PR-Encoder that places gated multi-scale retention and multi-layer perceptron modules on parallel computation paths to reduce per-layer latency and accelerate inference. Trained on 2000 spectra from 10 explosive materials, the PR-Encoder was evaluated against two baseline models. Transformer baselines achieved 88.5% classification accuracy with a per-spectrum inference latency of 13.1 ms, while Retention encoders reached 90.1% accuracy with 12.5 ms latency. In contrast, the PR-Encoder attained the highest performance — 93.4% accuracy under ten-fold cross-validation, with an average inference latency of approximately 10.1 ms per spectrum, demonstrating superior accuracy and computational efficiency. Integrating portable BL-XAS instrumentation with retention-based deep learning provides a real-time and non-destructive solution for explosive security screening. [Display omitted] • Portable BL-XAS with 128-channel CdTe detector enables rapid broadband spectra acquisition for explosives. • Parallelized Retention Encoder (PR-Encoder) combines gated multi-scale retention and MLP in parallel paths to speed inference. • PR-Encoder achieves 93.4% classification accuracy on ten explosives, outperforming Transformer and Retention baselines. • Parallel design reduces per-spectrum inference latency to 10.1 ms, yielding ∼ 20% speedups over baselines. • System offers a real-time, non-destructive field solution with superior penetration compared to optical spectroscopy. [ABSTRACT FROM AUTHOR]
ISSN:02632241
DOI:10.1016/j.measurement.2026.120479