Environment and Disaster Assessment Research Division, Korea Atomic Energy Research Institute.
Department of Nuclear & Quantum Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea.
Appl Radiat Isot. 2021 Apr;170:109593. doi: 10.1016/j.apradiso.2021.109593. Epub 2021 Jan 17.
Liquid scintillation counters are common instruments used in the measurement of pure beta-emitting radionuclides, and while they represent a conventional radiometric technique, they are still competitive for their potential to measure multiple radionuclides simultaneously. In this work, we propose an algorithm based on an artificial neural network (ANN) for the simultaneous analysis of the beta-ray spectra of H and C in dual beta-labeled samples using a liquid scintillation counter. We achieved percentage deviations below 5.0% using the proposed algorithm in 16 out of 18 cases, with RMSDs below 1.5% in 17 out of 18 cases. The trained ANN also produced activity ratios with high accuracy even while having to deal with highly fluctuating spectra. Results demonstrate that the rapid predictions with a short measurement time from our proposed ANN method are compatible with the calculated ones from previous studies that were obtained with long measurement times.
液体闪烁计数器是用于测量纯β发射放射性核素的常用仪器，虽然它们代表了一种常规的放射性测量技术，但它们仍然具有同时测量多种放射性核素的潜力，因此具有竞争力。在这项工作中，我们提出了一种基于人工神经网络（ANN）的算法，用于使用液体闪烁计数器同时分析双β标记样品中 H 和 C 的β射线能谱。在 18 种情况下中的 16 种情况下，我们使用提出的算法实现了低于 5.0%的百分比偏差，在 18 种情况下中的 17 种情况下，RMSD 低于 1.5%。经过训练的 ANN 即使在处理高度波动的光谱时，也能产生高精度的活性比。结果表明，我们提出的 ANN 方法具有快速预测能力，测量时间短，与之前使用长测量时间获得的研究中计算得到的结果相兼容。
