Systems and methods for classification of radiation energy spectra

GB2638590APending Publication Date: 2025-08-27RAPISCAN HOLDINGS INC
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
GB2025002964
Authority / Receiving Office
GB · GB
Patent Type
Applications
Current Assignee / Owner
Priority Date
2022-09-01
Filing Date
2023-08-01
Publication Date
2025-08-27

AI Technical Summary

Technical Problem

Radiation-based inspection systems face high nuisance alarms due to naturally occurring radiation materials (NORM), which are costly to manage with high-resolution detectors and algorithms, especially at high throughputs, necessitating a method to reduce false alarms using low-cost detectors and machine learning analysis.

Method used

A radiation portal monitor system with low-resolution detectors and a machine learning framework that generates a database of training spectra for NORM materials, normalizes and energy-scales detected spectra, fits them to training spectra, and identifies NORM based on residuals and threshold values, using techniques like Spectrum Dose Index and Optimal Linear Associative Memory neural networks.

Benefits of technology

Effectively reduces nuisance alarms by accurately classifying radiation spectra into NORM or 'other' categories, improving throughput and reducing false alarms while using cost-effective detectors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000000_0000_ABST
    Figure 00000000_0000_ABST
Patent Text Reader

Abstract

A method of determining if a radiation spectra comprises radiation corresponding to naturally occurring radiation material sources (NORM), the method including: gathering the radiation spectra; normalizing the gathered spectra by using one or more predefined normalization techniques; energy scaling the normalized spectra by using one or more energy scaling techniques; and determining materials corresponding to each energy reading in the scaled energy spectra for categorizing the determined materials into one or more predefined categories by using one or more classification algorithms.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Advanced pattern recognition systems for spectral analysis

    US20070211248A1

  • Gamma-ray spectrum classification

    US20200116879A1

  • Nuclear radiation monitoring apparatus and method

    US20200309972A1