Abstract
The increasing global burden of lung diseases necessitates the development of improved diagnostic tools. According to the WHO, hundreds of millions of individuals worldwide are currently affected by various forms of lung disease. The rapid advancement of artificial neural networks has revolutionized lung disease diagnosis, enabling the development of highly effective detection and classification systems. This article presents dual channel neural networks in image feature extraction based on classical CNN and vision transformers for multi-label lung disease diagnosis. Two separate subnetworks are employed to capture both global and local feature representations, thereby facilitating the extraction of more informative and discriminative image features. The global network analyzes all-organ regions, while the local network simultaneously focuses on multiple single-organ regions. We then apply a novel feature fusion operation, leveraging a multi-head attention mechanism to weight global features according to the significance of localized features. Through this multi-channel approach, the framework is designed to identify complicated and subtle features within images, which often go unnoticed by the human eye. Evaluation on the ChestX-ray14 benchmark dataset demonstrates that our hybrid model consistently outperforms established state-of-the-art architectures, including ResNet-50, DenseNet-121, and CheXNet, by achieving significantly higher AUC scores across multiple thoracic disease classification tasks. By incorporating test-time augmentation, the model achieved an average accuracy of 95.7% and a specificity of 99%. The experimental findings indicated that our model attained an average testing AUC of 87%. In addition, our method tackles a more practical clinical problem, and preliminary results suggest its feasibility and effectiveness. It could assist clinicians in making timely decisions about lung diseases.

Abstract
A Learning management system (LMS) is considered appropriate for company training. It is increasingly used in companies or organizations as a tool to manage their online training. The company or organization should consider the implementation of an LMS that provides ease in training content selection to achieve the best use and satisfaction of its employees in the learning process. From this perspective, the present study aims to investigate the implementation of a personalized LMS to facilitate the formative content selection tailored to employees’ roles. A Survey research methodology was used to achieve this objective. Based on the literature and survey results, we propose an approach to reach the personalization of content selection.

Abstract
Entity linking is an important task in medical natural language processing (NLP) for converting unstructured text into structured data for clinical analysis and semantic interoperability. However, in lower-resource languages, this task is challenging due to the limited availability of domain-specific resources. This paper explores a translation-based cross-lingual entity linking approach using GPT models, GPT-3.5 and GPT-4o, for zero-shot machine translation and entity linking with in-context learning. We evaluate our approach using a Portuguese-English parallel dataset of radiology abstracts. Our results show that chunk-level machine translation outperforms sentence-level translation. Moreover, our translationbased approach to cross-lingual entity linking of UMLS concepts outperformed the multilingual encoder method baseline. However, the in-context learning entity linking approach did not outperform a translation-based approach with a dictionary-based entity linking method.

Abstract
Artificial Intelligence (AI) is now ubiquitous in daily life, significantly impacting society by supporting decision-making. However, in many application areas, understanding the rationale behind AI decisions is crucial, highlighting the need for explainable AI (XAI). AI algorithms often lack transparency, making it hard to understand their inner workings. This work presents an overview of XAI solutions for decision support in mobility context. It addresses the complexity of explaining decision support models by offering explanations in various formats tailored to different user profiles. By integrating language models, XAI models may generate texts with varying technical detail levels, aiding ethical AI deployment and bridging the gap between complex models and human interpretability. This work explores the need for flexible explanation formats, supporting varied user profiles with graphical, textual, and tabular explanations. By integrating natural language processing models personalized explanations that are accurate, understandable, and accessible to a diverse audience can be generated. This study ultimately aims to support the task of making XAI robust and user-friendly, boosting its widespread use and application.

Abstract
As machine learning technologies are increasingly adopted, the demand for responsible AI practices to ensure transparency and accountability grows. To better understand the decision-making processes of machine learning models, GASTeN was developed to generate realistic yet ambiguous synthetic data near a classifier's decision boundary. However, the results were inconsistent, with few images in the low-confidence region and noise. Therefore, we propose a new GASTeN version with a modified architecture and a novel loss function. This new loss function incorporates a multi-objective measure with a Gaussian loss centered on the classifier probability, targeting the decision boundary. Our study found that while the original GASTeN architecture yields the highest Frechet Inception Distance (FID) scores, the updated version achieves lower Average Confusion Distance (ACD) values and consistent performance across low-confidence regions. Both architectures produce realistic and ambiguous images, but the updated one is more reliable, with no instances of GAN mode collapse. Additionally, the introduction of the Gaussian loss enhanced this architecture by allowing for adjustable tolerance in image generation around the decision boundary.

Abstract
Handheld controllers are standard in immersive virtual reality (iVR), but the rise of natural hand-based interactions exposes the limitations of hand gestures, especially for point-and-click tasks with graphical user interfaces (GUI). This shows the need to explore alternative hands-free selection methods. Unlike most studies focusing on the selection task itself, this work evaluates the impact of such methods on multiple dimensions when selections occur alongside another primary task. The tested methods were: head gaze + dwell, leaning, and voice; eye gaze + dwell, leaning, blinking, and voice; and voice-only. Controllers served as the baseline. Methods were further analyzed by pointing and confirming mechanisms. Four dimensions were analyzed: (1) iVR experience, (2) user satisfaction, (3) usability, and (4) efficiency and effectiveness. With 72 participants, results show hands-free methods provide comparable experiences to controllers, suggesting selection methods have a lower impact on the user experience when users focus on a primary task.