Machine learning (ML) and deep learning (DL) have achieved great success in different tasks. These include computer vision, image segmentation, natural language processing, predicting classification, evaluating time series, and predicting values based on a series of variables. As artificial intelligence progresses, new techniques are being applied to areas like optical spectroscopy and its uses in specific fields, such as the agrifood industry. The performance of ML and DL techniques generally improves with the amount of data available. However, it is not always possible to obtain all the necessary data for creating a robust dataset. In the particular case of agrifood applications, dataset collection is generally constrained to specific periods. Weather conditions can also reduce the possibility to cover the entire range of classifications with the consequent generation of imbalanced datasets. To address this issue, data augmentation (DA) techniques are employed to expand the dataset by adding slightly modified copies of existing data. This leads to a dataset that includes values from laboratory tests, as well as a collection of synthetic data based on the real data. This review work will present the application of DA techniques to optical spectroscopy datasets obtained from real agrifood industry applications. The reviewed methods will describe the use of simple DA techniques, such as duplicating samples with slight changes, as well as the utilization of more complex algorithms based on deep learning generative adversarial networks (GANs), and semi-supervised generative adversarial networks (SGANs).

This study introduces an innovative, cost-effective solution for detecting air bubbles in water flow systems using an AI-assisted infrared reflection system. In industries such as chemical, mechanical, oil, and nuclear, the presence of air bubbles in fluids can compromise both product quality and process efficiency. Our research develops a system that combines infrared optical sensors with machine learning algorithms to detect and quantify bubble presence effectively. The system's design utilizes infrared emitters and photodetectors arranged around a pipe to capture detailed data on bubble characteristics, which is then analyzed using a support vector machine (SVM) model to predict bubble concentrations. Experimental results demonstrate the system's ability to accurately identify different levels of bubble presence, offering significant improvements over existing methods. Key performance metrics include a Mean Squared Error (MSE) of 0.0694, a Root Mean Squared Error (RMSE) of 0.2634, and a Coefficient of Determination (R ${}^{2}$ ) of 0.9765, indicating high accuracy and reliability. This approach not only enhances operational reliability and safety but also provides a scalable solution adaptable to various industrial settings.

Impact-based acoustic inspection provides a rapid non-destructive approach for screening metallic components by analyzing the sound radiated after a controlled mechanical excitation. However, the limited availability of labeled data from defective parts remains a major challenge for deploying deep learning classifiers in production. This paper proposes a complete pipeline that converts raw impact-response audio recordings into magnitude log-spectrogram images and trains a semi-supervised Wasserstein GAN with gradient penalty (SS-WGAN-GP) designed to operate under extreme data scarcity. The architecture couples a shared convolutional backbone with two output heads: a Wasserstein critic for unsupervised discrimination between real and generated samples, and a binary classification head for supervised quality labeling, jointly optimized through a combined loss that balances Wasserstein distance, gradient penalty, and cross-entropy. A key property of the design is that the generator acts as a source of synthetic training samples, producing progressively more realistic spectrograms as training advances. These samples, in turn, enrich the feature representations learned by the shared backbone and improve the performance of the classification head. The classification head of the trained discriminator is deployed directly as the quality classifier, without requiring external data or post hoc retraining.

The agro-food industry is currently experiencing a growing emphasis on ensuring the quality and safety of food products, as well as optimizing production processes and reducing or reusing waste products. This necessitates a thorough analytical characterization of food, along with the use of real-time detection techniques. This thesis aims to contribute to the development of devices that, by combining two different techniques—optical spectroscopy, especially in the ultraviolet, visible, and near-infrared ranges, and Machine Learning and Deep Learning methods—are capable of evaluating, validating, and addressing the challenges posed by the agro-food industry. Two lines of research are developed. The first one addresses specific problems raised by the agro-food industry in various sectors and with different raw materials, ranging from forage for animal feed, the detection of disturbances in pipelines, to the identification of potential adulterations in extra virgin olive oil that may occur in bottling plants. The second line of research focuses on one of the main challenges when working with artificial intelligence models and spectroscopic data: the lack of data. The use of Generative Adversarial Networks (GANs) is proposed to quickly, easily, and economically augment datasets, thereby improving the performance of the proposed models.