Abstract
Transformer models have significantly advanced the field of emotion recognition. However, there are still open challenges when exploring open-ended queries for Large Language Models (LLMs). Although current models offer good results, automatic emotion analysis in open texts presents significant challenges, such as contextual ambiguity, linguistic variability, and difficulty interpreting complex emotional expressions. These limitations make the direct application of generalist models difficult. Accordingly, this work compares the effectiveness of fine-tuning and prompt engineering in emotion detection in three distinct scenarios: (i) performance of fine-tuned pre-trained models and general-purpose LLMs using simple prompts; (ii) effectiveness of different emotion prompt designs with LLMs; and (iii) impact of emotion grouping techniques on these models. Experimental tests attain metrics above 70% with a fine-tuned pre-trained model for emotion recognition. Moreover, the findings highlight that LLMs require structured prompt engineering and emotion grouping to enhance their performance. These advancements improve sentiment analysis, human-computer interaction, and understanding of user behavior across various domains.

Abstract
In the field of gaming artificial intelligence, selecting the appropriate machine learning approach is essential for improving decision-making and automation. This paper examines the effectiveness of deep reinforcement learning (DRL) within interactive gaming environments, focusing on complex decision-making tasks. Utilizing the Unity engine, we conducted experiments to evaluate DRL methodologies in simulating realistic and adaptive agent behavior. A vehicle driving game is implemented, in which the goal is to reach a certain target within a small number of steps, while respecting the boundaries of the roads. Our study compares Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) in terms of learning efficiency, decision-making accuracy, and adaptability. The results demonstrate that PPO successfully learns to reach the target, achieving higher and more stable cumulative rewards. Conversely, SAC struggles to reach the target, displaying significant variability and lower performance. These findings highlight the effectiveness of PPO in this context and indicate the need for further development, adaptation, and tuning of SAC. This research contributes to developing innovative approaches in how ML can improve how player agents adapt and react to their environments, thereby enhancing realism and dynamics in gaming experiences. Additionally, this work emphasizes the utility of using games to evolve such models, preparing them for real-world applications, namely in the field of vehicles' autonomous driving and optimal route calculation.

Abstract
The increase in complexity of deep learning models demands explanations that can be obtained with methods like Grad-CAM. This method computes an importance map for the last convolutional layer relative to a specific class, which is then upsampled to match the size of the input. However, this final step assumes that there is a spatial correspondence between the last feature map and the input, which may not be the case. We hypothesize that, for models with large receptive fields, the feature spatial organization is not kept during the forward pass, which may render the explanations devoid of meaning. To test this hypothesis, common architectures were applied to a medical scenario on the public VinDr-CXR dataset, to a subset of ImageNet and to datasets derived from MNIST. The results show a significant dispersion of the spatial information, which goes against the assumption of Grad-CAM, and that explainability maps are affected by this dispersion. Furthermore, we discuss several other caveats regarding Grad-CAM, such as feature map rectification, empty maps and the impact of global average pooling or flatten layers. Altogether, this work addresses some key limitations of Grad-CAM which may go unnoticed for common users, taking one step further in the pursuit for more reliable explainability methods.

Abstract

Abstract
Business Continuity Management (BCM) is critical for organizations to mitigate disruptions and maintain operations, yet many struggle with fragmented and non-standardized self-assessment tools. Existing frameworks often lack holistic integration, focusing narrowly on isolated components like cyber resilience or risk management, which limits their ability to evaluate BCM maturity comprehensively. This research addresses this gap by proposing a structured Self-Assessment System designed to unify BCM components into an adaptable, standards-aligned methodology. Grounded in Design Science Research, the system integrates a BCM Model comprising eight components and 118 activities, each evaluated through weighted questions to quantify organizational preparedness. The methodology enables organizations to conduct rapid as-is assessments using a 0-100 scoring mechanism with visual indicators (red/yellow/green), benchmark progress over time and against peers, and align with international standards (e.g., ISO 22301, ITIL) while accommodating unique organizational constraints. Demonstrated via focus groups and semi-structured interviews with 10 organizations, the system proved effective in enhancing top management commitment, prioritizing resource allocation, and streamlining BCM implementation-particularly for SMEs with limited resources. Key contributions include a reusable self-assessment tool adaptable to any BCM framework, empirical validation of its utility in identifying weaknesses and guiding continuous improvement, and a pathway from initial assessment to advanced measurement via the Plan-Do-Check-Act cycle. By bridging the gap between theoretical standards and practical application, this research offers a scalable solution for organizations to systematically evaluate and improve BCM resilience.

Abstract
[No abstract available]