Semi-supervised on-device neural network adaptation for remote and portable laser-induced breakdown spectroscopy
This addresses the problem of domain shift and limited resources in portable LIBS systems for industrial and space exploration applications, though it is incremental as it builds on existing MLP methods with added adaptation capabilities.
The paper tackles the challenge of deploying lightweight machine learning models for laser-induced breakdown spectroscopy (LIBS) in resource-constrained, remote systems by introducing a semi-supervised on-device adaptation method, achieving 89.3% average accuracy during data streaming and up to 2.1% better accuracy than non-adaptive models.
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.