Abstract
Lung cancer stands as the most prevalent and deadliest type of cancer, with adenocarcinoma being the most common subtype. Computed Tomography (CT) is widely used for detecting tumours and their phenotype characteristics, for an early and accurate diagnosis that impacts patient outcomes. Machine learning algorithms have already shown the potential to recognize patterns in CT scans to classify the cancer subtype. In this work, two distinct pipelines were employed to perform binary classification between adenocarcinoma and non-adenocarcinoma. Firstly, radiomic features were classified by Random Forest and eXtreme Gradient Boosting classifiers. Next, a deep learning approach, based on a Residual Neural Network and a Transformer-based architecture, was utilised. Both 2D and 3D CT data were initially explored, with the Lung-PET-CT-Dx dataset being employed for training and the NSCLC-Radiomics and NSCLC-Radiogenomics datasets used for external evaluation. Overall, the 3D models outperformed the 2D ones, with the best result being achieved by the Hybrid Vision Transformer, with an AUC of 0.869 and a balanced accuracy of 0.816 on the internal test set. However, a lack of generalization capability was observed across all models, with the performances decreasing on the external test sets, a limitation that should be studied and addressed in future work.

Abstract
Virtual Reality allows users to experience realistic environments in an immersive and controlled manner, particularly beneficial for contexts where the real scenario is not easily or safely accessible. The choice between 360° content and 3D models impacts outcomes such as perceived quality and computational cost, but can also affect user attention. This study explores how attention manifests in VR using a 3D model or a 360° image rendered from said model during visuospatial tasks. User tests revealed no significant difference in workload or cybersickness between these types of content, while sense of presence was reportedly higher in the 3D environment. © 2025 IEEE.

Abstract
In this paper we introduce and develop the concept of interval-weighted networks (IWN), a novel approach in Social Network Analysis, where the edge weights are represented by closed intervals composed with precise information, comprehending intrinsic variability. We extend IWN for both Newman's modularity and modularity gain and the Louvain algorithm, considering a tabular representation of networks by contingency tables. We apply our methodology to two real-world IWN. The first is a commuter network in mainland Portugal, between the twenty three NUTS 3 Regions (IWCN). The second focuses on annual merchandise trade between 28 European countries, from 2003 to 2015 (IWTN). The optimal partition of geographic locations (regions or countries) is developed and compared using two new different approaches, designated as Classic Louvain and Hybrid Louvain , which allow taking into account the variability observed in the original network, thereby minimizing the loss of information present in the raw data. Our findings suggest the division of the twenty three Portuguese regions in three main communities for the IWCN and between two to three country communities for the IWTN. However, we find different geographical partitions according to the community detection methodology used. This analysis can be useful in many real-world applications, since it takes into account that the weights may vary within the ranges, rather than being constant.

Abstract
Portable X-Ray Fluorescence (XRF) has become increasingly popular where traditional laboratory methods are either impractical, time consuming, and/or too costly. While the Limit of Detection (LOD) is generally poorer for XRF compared to laboratory-based methods, recent advances have improved XRF LODs and increased its potential for field-based studies. Portable XRF can be used to screen food products for toxic elements such as lead (Pb), cadmium (Cd), mercury (Hg), arsenic (As), manganese, (Mn), zinc (Zn), and strontium (Sr). In this study, 23 seafood samples were analyzed using portable XRF in a home setting. After XRF measurements were completed in each home, the same samples were transferred to the laboratory for re-analysis using microwave-assisted digestion and Inductively Coupled Plasma Tandem Mass Spectrometry (ICP-MS/MS). Four elements (Mn, Sr, As, and Zn) were quantifiable by XRF in most samples, and those results were compared to those obtained by ICP-MS/MS. Agreement was judged reasonable for Mn, Sr, and As, but not for Zn. Discrepancies could be due to (1) the limited time available to prepare field samples for XRF, (2) the heterogeneous nature of real samples analyzed by XRF, and (3) the small beam spot size (similar to 1 mm) of the XRF analyzer. Portable XRF is a cost-effective screening tool for public health investigations involving exposure to toxic metals. It is important for practitioners untrained in XRF spectrometry to (1) recognize the limitations of portable instrumentation, (2) include validation data for each specific analyte(s) measured, and (3) ensure personnel have some training in sample preparation techniques for field-based XRF analyses.

Abstract
Worldwide, forests have been harassed by fire in recent years. Either by human intervention or other reasons, the history of the burned area is increasing considerably, harming fauna and flora. It is essential to detect an early ignition for fire-fighting authorities can act quickly, decreasing the impact of forest damage impacts. The proposed system aims to improve nature monitoring and improve the existing surveillance systems through satellite image recognition. The soil recognition via satellite images can determine the sensor modules' best position and provide crucial input information for artificial intelligence-based systems. For this, satellite images from the Sentinel-2 program are used to generate forest density maps as updated as possible. Four classification algorithms make the Tree Cover Density (TCD) map, consisting of the Gaussian Mixture Model (GMM), Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbors (K-NN), which identify zones by training known regions. The results demonstrate a comparison between the algorithms through their performance in recognizing the forest, grass, pavement, and water areas by Sentinel-2 images.

Abstract
Artificial intelligence (AI) is playing a growing role today in several areas, especially in health, where understanding AI models and their predictions is extremely important for health professionals. In this context, Explainable AI (XAI) plays a crucial role in seeking to provide understandable explanations for these models. This article analyzes two different XAI approaches applied to analyzing gastric endoscopy images. The first, more conventional approach uses Grad CAM, while the second, even less explored but with great potential, is based on “similarity-based explanations”. This example-based XAI technique aims to provide representative examples to support the decisions of AI models. In this study, we compare these two techniques applied to two different models: one based on the VGG16 architecture and the other based on ResNet50, designed to classify images from the KVASIR-capsule database. The results reveal that Grad-CAM provided intuitive explanations only for the VGG16 model, while the “similarity-based explanations” technique provided consistent explanations for both models. We conclude that exploring other XAI techniques can be a significant asset in improving the understanding of the various AI models. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.