Abstract
This paper proposes an Artificial Intelligence (AI) driven solution, Chatto, designed for emotional support among older adults. It integrates emotion recognition, Natural Language Processing (NLP), and human-computer interaction (HCI) to facilitate meaningful interactions and aid in self-emotion regulation while providing caregivers with tools to monitor and support the elder's emotional state remotely. The proposal includes an infrastructure to personalize the system through a human labeling approach and retraining of the deep learning models. The findings revealed the solution's impact on the emotional well-being of the elderly and identified potential improvements in emotion detection, conversational features, and user interface. These improvements were based on feedback from feasibility and usability tests conducted with caregivers and older adults subject to the influence of demographic variables, such as age, cultural background, and technological literacy.

Abstract
We live in an era where robotics and IoT represent a significant transition towards a unified and automated world. Nonetheless, this convergence faces challenges, including system compatibility and device interoperability. The lack of flexibility of conventional robotic architectures amplifies these obstacles, highlighting the urgency for solutions. Furthermore, the complexity of adopting new technologies can be overwhelming. To address these challenges, this article features a Robot Operating System (ROS2)-centered middleware, referred to as Gateway since it applies the concept of a gateway, designed to ease the robot integration. Focusing on the payload module and fostering several types of external communication, it enhances modularity and interoperability. Developers can select payloads and communication modes through a console, which the middleware subsequently configures, guaranteeing flexibility. The goal is to highlight this middleware's potential to overcome robotics limitations, allowing a flexible integration of robots. This work contributes to the Internet of Robotic Things (IoRT) matter, underscoring the importance of modular payload engineering and interoperable communication in robotics and IoT.

Abstract
Traditionally, there are two main market designs for user connected smart objects and smart appliances: cloud dependent and/or local centralized servers but both approaches bring concerns to the enduser side. The cloud-based approach raises concerns related with (apart from technical configuration and setup) security and privacy as user data may be exchanged with the cloud. Even in solutions that keep user data in the user side raises doubts and uncertainty to the final-user. On the other hand, the solutions based on local server may mitigate the security and privacy concerns but usually require end-user technical configuration and setup besides the fact that the local server becomes a single point of failure. Our aim is to address these concerns by the adoption of a peerto-peer, self-contained and interoperable approach to ensure truly plug-and-play, to keep user data in the user side and to allow seamlessly interoperability among end-users' devices hence towards real Smart Environments. In this first paper we evaluate, for the first time, the oneM2M world wide IoT standard over peer-to-peer networking and the preliminary results are very promising, allowing us to move forward addressing other requirements such as IP provisioning, security and privacy, efficient peer discovery, etc.

Abstract
Forest fires in Portugal are a recurring tragedy, especially during the summer, leaving a devastating trail affecting the environment and local communities. In addition to the loss of vast forest areas, these disasters harm wildlife, pollute the air, and compromise soil and water quality, contributing to environmental degradation and increasing the risk of soil erosion and landslides. Furthermore, fires have significant economic impacts, affecting communities that depend on the forest for subsistence, tourism, and agricultural activities. To address this issue, an innovativeWeb Service has been developed that uses artificial intelligence algorithms to calculate real-time fire risk. This service integrates up-todate weather data with historical fire patterns, providing an accurate and timely assessment of fire potential in specific areas. The machine learning model behind the service was trained with historical fire data from mainland Portugal between 2017 and 2023, allowing for a more accurate and predictive analysis of fire risk. The Web Service facilitates proactive emergency prevention and decision-making response by integrating realtime weather information with historical fire data. Authorities can use the information provided by the service to implement preventive policies to help elderly people.

Abstract
Explainable Artificial Intelligence (XAI) aims to enhance the interpretability of Artificial Intelligence (AI) systems for humans. The goal is to ensure that algorithmic decisions and underlying data are understandable to non-technical stakeholders. Advanced Machine Learning (ML) models, such as deep neural networks, enable AI systems to process vast data and extract intricate patterns, akin to the human brain, but this complicates XAI development. Complex ML models require substantial data for training, exacerbating the challenge. Consequently, this paper proposes a novel approach to improve XAI for complex ML models, particularly those with large data needs. Using K-Means clustering, the paper proposes to identify relevant data instances to create similarity clusters. This filtering process focuses XAI on essential information, even with complex models, reducing the data set to find patterns and explanations, so that, using the same approach, only the best explanations are filtered efficiently. The paper proposes to implement and test this model with a case study on ML for PV generation forecasting in buildings. Results show that the proposed approach is able to generate explanations that are very similar to those generated when using the entire available data, in only a portion of the execution time, leveraging from the identification of a small number of representative data points. This approach, therefore, enhances the efficiency of XAI by achieving promising results with a smaller dataset. It also facilitates the development of more understandable and fastly provided solutions, which is essential for real-world XAI users such as electric mobility users that need PV forecasting explanations as support for their vehicles charging management.

Abstract
With the serious danger to nature and humanity that forest fires are, taken into consideration, this work aims to develop an artificial intelligence model capable of accurately predicting the forest fire risk in a certain region based on four different factors: temperature, wind speed, rain and humidity. Thus, three models were created using three different approaches: Artificial Neural Networks (ANN), Random Forest (RF), and K-Nearest Neighbor (KNN), and making use of an Algerian forest fire dataset. The ANN and RF both achieved high accuracy results of 97%, while the KNN achieved a slightly lower average of 91%.