Abstract
The Czech Republic is home to the Hranice Abyss, the world's deepest natural underwater cave, a site extensively explored by a dedicated team of divers from a speleology group. Over the years, numerous studies have been conducted to unravel the cave's mysteries, delving into fields such as biology, hydrogeology, and geology. Mapping a cave of such vast dimensions and staggering depth poses formidable challenges, making the task hazardous, demanding, and timeintensive for a limited team of divers. In July 2022, the UNEXUP project was invited to explore and map the cave with its robot (UX1-neo), which contains many acoustic and optical sensors, used for navigation, localization, and mapping. Its unique control and dynamics allow the robot to successfully navigate through caves and flooded mines. This paper delves into the specifics of the six days of mission dives, offering insights into the mapping process, and presenting some of the results obtained from the entire cave.

Abstract
Raw materials are essential for Europe’s industrial base, as they are used to produce vital goods and technologies. The European Comission’s assessment identifies lithium and tin as critical and strategic raw materials due to rising demand. A PhD thesis aims to create a 3D geological model of the Argemela District in Central Portugal to provide vital information about the genesis of the hydrothermal tin and lithium mineralizations founded in the region. The study places emphasis on the very-low-frequency (VLF) electromagnetic method as a tool to provide information about the mineralization, lithologic contacts, and structural features that can be related to the mineralizations. Argemela district has two main areas, the Argemela Tin and Lithium Mine and the Argemela Hill Top. VLF data was collected and analyzed, showing that low resistivity may be associated with mineralization in the Argemela Mine, while high resistivity may be linked to the Argemela microgranite in the Argemela Hill Top. This geophysical method is effective in non-invasively mapping subsurface features, assisting in the development of a comprehensive 3D geological model and enhancing resource evaluation.

Abstract
Chest X-Ray (CXR), plays a vital role in diagnosing lung and heart conditions, but the high demand for CXR examinations poses challenges for radiologists. Automatic support systems can ease this burden by assisting radiologists in the image analysis process. While Deep Learning models have shown promise in this task, concerns persist regarding their complexity and decision-making opacity. To address this, various visual explanation techniques have been developed to elucidate the model reasoning, some of which have received significant attention in literature and are widely used such as GradCAM. However, it is unclear how different explanations methods perform and how to quantitatively measure their performance, as well as how that performance may be dependent on the model architecture used and the dataset characteristics. In this work, two widely used deep classification networks - DenseNet121 and ResNet50 - are trained for multi-pathology classification on CXR and visual explanations are then generated using GradCAM, GradCAM++, EigenGrad-CAM, Saliency maps, LRP and DeepLift. These explanations methods are then compared with radiologist annotations using previously proposed explainability evaluations metrics - intersection over union and hit rate. Furthermore, a novel method to convey visual explanations in the form of radiological written reports is proposed, allowing for a clinically-oriented explainability evaluation metric - zones score. It is shown that Grad-CAM++ and Saliency methods offer the most accurate explanations and that the effectiveness of visual explanations is found to vary based on the model and corresponding input size. Additionally, the explainability performance across different CXR datasets is evaluated, highlighting that the explanation quality depends on the dataset's characteristics and annotations.

Abstract
Olive trees play a crucial role in the global agricultural landscape, serving as a primary source of olive oil production. However, olive trees are susceptible to several diseases, which can significantly impact yield and quality. This study addresses the challenge of improving the diagnosis of diseases in olive trees, specifically focusing on aculus olearius and Olive Peacock Spot diseases. Using a novel hybrid approach that combines deep learning and machine learning methodologies, the authors aimed to optimize disease classification accuracy by analyzing images of olive leaves. The presented methodology integrates Local Binary Patterns (LBP) and an adapted ResNet50 model for feature extraction, followed by classification through optimized machine learning models, including Stochastic Gradient Descent (SGD), Support Vector Machine (SVM), and Random Forest (RF). The results demonstrated that the hybrid model achieved a groundbreaking accuracy of 99.11%, outperforming existing models. This advancement underscores the potential of integrated technological approaches in agricultural disease management and sets a new benchmark for the early and accurate detection of foliar diseases.

Abstract

Abstract
Retail transactions represent sales of consumer goods, or final goods, by consumer companies. This sector faces security challenges due to the hustle and bustle of sales, affecting employees' workload. In this context, it is essential to estimate the number of customers who will appear in the store daily so that companies can dynamically adjust employee schedules, aligning workforce capacity with expected demand. This can be achieved by forecasting transactions using past observations and forecasting algorithms. This study aims to compare the ARIMA time series algorithm with several Machine Learning algorithms to predict the number of daily transactions in different store patterns, considering data variability. The study identifies four typical store patterns based on these criteria using daily transaction data between 2019 and 2023 from all retail stores of the leading company in Portugal. Due to data variability and the results obtained, the algorithm that presents the most minor errors in predicting daily transactions is selected for each store. This study's ultimate goal is to fill the gap in forecasting daily customer transactions and present a suitable forecasting model to mitigate risks associated with transactions in retail stores.