Del-Pozo-Bueno Daniel, Kepaptsoglou Demie, Ramasse Quentin M, Peiró Francesca, Estradé Sònia
LENS-MIND, Departament d'Enginyeria Electrònica i Biomèdica, Universitat de Barcelona, 1-11 Martí i Franquès, 08028 Barcelona, Spain.
Institute of Nanoscience and Nanotechnology (IN2UB), Universitat de Barcelona, 1-11 Martí i Franquès, 08028 Barcelona, Spain.
Microsc Microanal. 2024 Apr 29;30(2):278-293. doi: 10.1093/mam/ozae014.
Recent advances in machine learning (ML) have highlighted a novel challenge concerning the quality and quantity of data required to effectively train algorithms in supervised ML procedures. This article introduces a data augmentation (DA) strategy for electron energy loss spectroscopy (EELS) data, employing generative adversarial networks (GANs). We present an innovative approach, called the data augmentation generative adversarial network (DAG), which facilitates data generation from a very limited number of spectra, around 100. Throughout this study, we explore the optimal configuration for GANs to produce realistic spectra. Notably, our DAG generates realistic spectra, and the spectra produced by the generator are successfully used in real-world applications to train classifiers based on artificial neural networks (ANNs) and support vector machines (SVMs) that have been successful in classifying experimental EEL spectra.
机器学习（ML）的最新进展凸显了一个新的挑战，即有效训练监督式机器学习程序中的算法所需数据的质量和数量问题。本文介绍了一种用于电子能量损失谱（EELS）数据的数据增强（DA）策略，该策略采用生成对抗网络（GAN）。我们提出了一种创新方法，称为数据增强生成对抗网络（DAG），它能够从非常有限数量（约100个）的光谱中生成数据。在本研究中，我们探索了生成对抗网络的最佳配置以生成逼真的光谱。值得注意的是，我们的DAG生成了逼真的光谱，并且生成器生成的光谱已成功应用于实际应用中，用于训练基于人工神经网络（ANN）和支持向量机（SVM）的分类器，这些分类器在对实验性电子能量损失谱进行分类方面取得了成功。
