Real-time, Adaptive Radiological Anomaly Detection and Isotope Identification Using Non-negative Matrix Factorization

2025-07-14

AI Summary

In mobile radiation detection, dynamic environmental changes cause mismatches with pre-trained background models, leading to increased false alarms or reduced sensitivity. To address this, we propose a real-time adaptive radioactive anomaly detection and isotope identification method. Our core contribution is a periodically updated non-negative matrix factorization (NMF) background model that abandons the strong assumption of static environments, enabling online background spectrum modeling and adaptive evolution. The method integrates real-time spectral data stream-driven NMF optimization with a robust anomaly discrimination mechanism, achieving both low false-alarm rates and enhanced weak-source detection sensitivity. Extensive evaluation on multiple simulated scenarios and real-world mobile detection datasets demonstrates detection performance comparable to or superior to state-of-the-art methods, significantly improving robustness and practical utility in complex, dynamically varying environments.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

Spectroscopic anomaly detection and isotope identification algorithms are integral components in nuclear nonproliferation applications such as search operations. The task is especially challenging in the case of mobile detector systems due to the fact that the observed gamma-ray background changes more than for a static detector system, and a pretrained background model can easily find itself out of domain. The result is that algorithms may exceed their intended false alarm rate, or sacrifice detection sensitivity in order to maintain the desired false alarm rate. Non-negative matrix factorization (NMF) has been shown to be a powerful tool for spectral anomaly detection and identification, but, like many similar algorithms that rely on data-driven background models, in its conventional implementation it is unable to update in real time to account for environmental changes that affect the background spectroscopic signature. We have developed a novel NMF-based algorithm that periodically updates its background model to accommodate changing environmental conditions. The Adaptive NMF algorithm involves fewer assumptions about its environment, making it more generalizable than existing NMF-based methods while maintaining or exceeding detection performance on simulated and real-world datasets.

Problem

• Detect radiological anomalies adaptively in real-time
• Identify isotopes despite changing gamma-ray backgrounds
• Update background models dynamically for mobile detectors

Innovation

• Adaptive NMF updates background model in real-time
• Reduces false alarm rate and maintains sensitivity
• Generalizable across changing environmental conditions