AI system classifies seven radioactive isotopes with varied accuracy
AI-Enhanced Radiation Classification in ROS
Robotics
Summary
Classifying different radioactive materials can be important for safety and research. This paper presents computer programs that use artificial intelligence to help identify seven types of radioactive isotopes from detector data. The system showed 95% accuracy on test data but was less accurate when used on a robot in the field, correctly identifying 71% of samples. The authors also created a way to turn images of radiation data into usable numbers for their system.
What this means in practice
- •For robotic system integrators: Add isotope classification capability to radiation-sensing robots using ROS-based AI nodes.
- •For radiation safety teams: Use AI-enhanced software to quickly identify radioactive sources during field surveys with mobile detectors.
Authors
Youngseo Lee, Cesar Alan Contreras, Tianshu Ruan, Manolis Chiou, Rustam Stolkin
Abstract
This study presents the development of two Robot Operating System (ROS) nodes with a primary focus on differentiating seven radioactive isotopes. The first node, referred to as the model training node, uses a Gradient Boosting classifier to identify and classify these isotopes. The classifier achieved a reported overall accuracy of 95\% on the held-out test dataset. The second node, known as the prediction node, provides classification results when users input data in CSV format. For the practical demonstration, the C12137 radiation detector module was mounted on the Jackal UGV, and an operator approached different radiation sources to collect data. To support future dataset expansion, we also developed a method for converting gamma-spectrum graph images into CSV files. In a separate robotic evaluation across three source locations, 30 of 42 trials were correctly classified (71.43\%). Am-241, Co-60, Cs-137, Na-22, and Ti-44 were correctly classified in all six trials each, whereas Ba-133 and Eu-152 were incorrectly classified in all six trials each. These results show lower accuracy in robotic trials than in the held-out test set.