用于远程和便携式激光诱导击穿光谱的半监督设备上神经网络适配
Semi-supervised on-device neural network adaptation for remote and portable laser-induced breakdown spectroscopy
摘要：
激光诱导击穿光谱（LIBS）是一种流行的快速元素分析技术，用于确定目标样品的化学成分，例如在金属的工业分析或空间探索中。最近，在LIBS数据处理中使用机器学习（ML）技术的情况有所增加。然而，用于LIBS的ML具有挑战性，因为：（i）预测模型必须是轻量级的，因为它们需要部署在高度资源受限和电池供电的便携式LIBS系统中;以及（ii）由于这些系统可以是远程的，因此模型必须能够自适应于输入分布中的任何域偏移，这可能是由于在训练数据中缺少不同类型的输入或动态环境/传感器噪声。由于远程LIBS系统中缺乏新的标记数据，这种模型的设备上重新训练不仅应该快速，而且应该是无监督的。我们介绍了一个轻量级的多层感知器（MLP）模型的LIBS，可以适应设备上，而不需要标签的新输入数据。它在数据流期间显示出89.3%的平均准确率，与不支持自适应的MLP模型相比，准确率提高了2.1%。最后，我们还描述了我们的模型在Google Pixel 2手机上的推理和再训练性能。
英文摘要：
Laser-induced breakdown spectroscopy (LIBS) is a popular, fast elemental analysis technique used to determine the chemical composition of target samples, such as in industrial analysis of metals or in space exploration. Recently, there has been a rise in the use of machine learning (ML) techniques for LIBS data processing. However, ML for LIBS is challenging as: (i) the predictive models must be lightweight since they need to be deployed in highly resource-constrained and battery-operated portable LIBS systems; and (ii) since these systems can be remote, the models must be able to self-adapt to any domain shift in input distributions which could be due to the lack of different types of inputs in training data or dynamic environmental/sensor noise. This on-device retraining of model should not only be fast but also unsupervised due to the absence of new labeled data in remote LIBS systems. We introduce a lightweight multi-layer perceptron (MLP) model for LIBS that can be adapted on-device without requiring labels for new input data. It shows 89.3% average accuracy during data streaming, and up to 2.1% better accuracy compared to an MLP model that does not support adaptation. Finally, we also characterize the inference and retraining performance of our model on Google Pixel2 phone.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
