对比60种辐射脉冲识别算法，发现深度学习更优。
Pulse Shape Discrimination Algorithms: Survey and Benchmark
- 按统计与先验知识分两类，涵盖时频域和神经网络方法。
- 深度模型在FOM、F1等指标上普遍优于传统方法，尤其MLP和混合模型。
- 开源工具包+数据集，助力可复现研究，适合辐射探测领域学者。
本文全面综述并基准测试了辐射探测中的脉冲形状识别（PSD）算法，将近六十种方法分为统计（时域、频域、基于神经网络）和先验知识（机器学习、深度学习）两大类。我们在两个标准化数据集上实现并评估所有算法：来自241Am-9Be源的无标签数据集和来自238Pu-9Be源的时间飞行标注数据集，采用图灵优势（FOM）、F1分数、ROC-AUC及方法间相关性等指标。分析表明，深度学习模型，尤其是多层感知机（MLP）和结合统计特征与神经回归的混合方法，通常优于传统方法。我们讨论了模型架构适用性、FOM指标局限性、替代评估指标及不同能量阈值下的表现。附带本工作发布了一个开源工具箱（Python和MATLAB版），以及数据集，以促进可复现性并推动PSD研究发展。
原文摘要 · Abstract (English)
This review presents a comprehensive survey and benchmark of pulse shape discrimination (PSD) algorithms for radiation detection, classifying nearly sixty methods into statistical (time-domain, frequency-domain, neural network-based) and prior-knowledge (machine learning, deep learning) paradigms. We implement and evaluate all algorithms on two standardized datasets: an unlabeled set from a 241Am-9Be source and a time-of-flight labeled set from a 238Pu-9Be source, using metrics including Figure of Merit (FOM), F1-score, ROC-AUC, and inter-method correlations. Our analysis reveals that deep learning models, particularly Multi-Layer Perceptrons (MLPs) and hybrid approaches combining statistical features with neural regression, often outperform traditional methods. We discuss architectural suitabilities, the limitations of FOM, alternative evaluation metrics, and performance across energy thresholds. Accompanying this work, we release an open-source toolbox in Python and MATLAB, along with the datasets, to promote reproducibility and advance PSD research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。