This repository contains the code for implementing Generative Adversarial Networks (GAN) as part of a research project described in a published manuscript. The aim of the project is to augment Fourier Transform Infrared (FTIR) data to improve the classification of glucose in a hydrothermal liquefaction system.
The GAN model is a powerful machine learning technique consisting of a generator network and a discriminator network. The generator is trained to generate realistic samples that can deceive the discriminator. The discriminator, on the other hand, is trained to distinguish between real and generated samples accurately.
By training the GAN on FTIR data, we aim to generate synthetic samples that closely resemble real glucose samples in a hydrothermal liquefaction system. This augmentation process can enhance the training dataset, leading to improved classification performance when using machine learning algorithms.
To use this code, please follow the instructions provided in the accompanying documentation. It includes information on data preprocessing, GAN architecture, training procedure, and evaluation methods. Additionally, we have included a link to the published manuscript for further details on the research (https://doi.org/10.1039/D3YA00236E).
We hope that this code repository and research project will contribute to advancements in classifying glucose in hydrothermal liquefaction systems using GANs and augmenting FTIR data. Feel free to explore, experiment, and adapt the code to your own projects or research endeavors. If you have any questions or suggestions, please don't hesitate to reach out.
Thank you for your interest in our work, and we look forward to any collaborations or contributions that may arise from this repository.