João Ramos

The evolution of Smart Grids enabled the deployment of intelligent and decentralized energy management solutions at the residential level. This work presents a comprehensive Smart Home architecture that integrates real-time energy monitoring, appliance-level consumption analysis, and environmental data acquisition using smart metering technologies and distributed IoT sensors. All collected data are structured into a scalable infrastructure that supports advanced Artificial Intelligence (AI) methods, including Large Language Models (LLMs) and machine learning, enabling predictive analysis, personalized energy recommendations, and natural language interaction. Proposed architecture is experimentally validated through a case study on a domestic refrigerator. Two series of tests were conducted. In the first phase, extreme usage scenarios were evaluated: one with intensive usage and another with highly restricted usage. In the second phase, normal usage scenarios were tested without AI feedback and with AI recommendations following them whenever possible. Under the extreme scenarios, AI-assisted interaction resulted in a reduction in daily energy consumption of about 81.4%. In the normal usage scenarios, AI assistance resulted in a reduction of around 13.6%. These results confirm that integrating AI-driven behavioral optimization within Smart Home environments significantly improves energy efficiency, reduces electrical stress, and promotes more sustainable energy usage.

The rise of robotics and the Internet of Things (IoT) could potentially represent a significant shift towards a more integrated and automated future, where the physical and digital domains may merge. However, the integration of these technologies presents certain challenges, including compatibility issues with existing systems and the need for greater interoperability between different devices. It would seem that the rigidity of traditional robotic designs may inadvertently make these difficulties worse, which in turn highlights the potential benefits of modular solutions. Furthermore, the mastery of new technologies may introduce additional complexity due to the varying approaches taken by robot manufacturers. In order to address these issues, this research proposes a Robot Operating System (ROS2)-based middleware, called the “ROS2-based gateway”, which aims to simplify the integration of robots in different environments. By focusing on the payload layer and enabling external communication, this middleware has the potential to enhance modularity and interoperability, thus accelerating the integration process. It offers users the option of selecting payloads and communication methods via a shell interface, which the middleware then configures, ensuring adaptability. The solution proposed in this article, based on the gateway concept, offers users and programmers the flexibility to specify which payloads they want to activate depending on the task at hand and the high-level protocols they wish to use to interact with the activated payloads. This approach allows for the optimisation of hardware resources (only the necessary payloads are activated), as well as enabling the programmer/user to utilise high-level communication protocols (such as RESTful, Kafka, etc.) to interact with the activated payloads, rather than low-level programming.

As the global population is expected to exceed 9.7 billion by 2050, improving the efficiency of food production systems is crucial to achieving food security. This article discusses the issues of growing populations, rising food consumption, and the need for technological revolution in the agricultural sector. Leveraging robotic technology, particularly in environments like orchards and greenhouses, holds promise in enhancing production efficiency. This work proposes a solution harnessing artificial intelligence and computer vision to mitigate labeling errors in image datasets often used for supervised learning models, offering a user-friendly interface for modifying class labels. The proposed system simplifies the annotation process through a simple architecture comprising front-end, back-end, and file storage modules, ensuring accuracy and adaptability, specifically tailored for individuals with agricultural expertise, yet lacking experience in AI or Computer Science.

The escalating threat of wildfires in Mediterranean Europe, particularly in Portugal, highlights the urgent need for innovative fire prediction and forest surveillance approaches. This paper introduces ForestML, a real-time architecture leveraging Unmanned Aerial Vehicles (UAVs) equipped with multispectral cameras and machine learning algorithms to forecast and analyze forests from an aerial perspective. This promising ForestML, which comprises Ground Station, Backstation, and Web Server components, facilitates real-time wildfire risk assessment and prediction, enabling timely decision-making to mitigate fire-related risks.

The demand for online services is increasing. Services that would require a long time to understand, use and master are becoming as transparent as possible to the users, that tend to focus only on the final goals. Combined with the advantages of the unmanned vehicles (UV), from the unmanned factor to the reduced size and costs, we found an opportunity to bring to users a wide variety of services supported by UV, through the Internet of Unmanned Vehicles (IoUV). Current solutions were analyzed and we discussed scalability and genericity as the principal concerns. Then, we proposed a solution that combines several services and UVs, available from anywhere at any time, from a cloud platform. The solution considers a cloud distributed architecture, composed by users, services, vehicles and a platform, interconnected through the Internet. Each vehicle provides to the platform an abstract and generic interface for the essential commands. Therefore, this modular design makes easier the creation of new services and the reuse of the different vehicles. To confirm the feasibility of the solution we implemented a prototype considering a cloud-hosted platform and the integration of custom-built small-sized cars, a custom-built quadcopter, and a commercial Vertical Take-Off and Landing (VTOL) aircraft. To validate the prototype and the vehicles’ remote control, we created several services accessible via a web browser and controlled through a computer keyboard. We tested the solution in a local network, remote networks and mobile networks (i.e., 3G and Long-Term Evolution (LTE)) and proved the benefits of decentralizing the communications into multiple point-to-point links for the remote control. Consequently, the solution can provide scalable UV-based services, with low technical effort, for anyone at anytime and anywhere.

Data and services are available anywhere at any time thanks to the Internet and mobile devices. Nowadays, there are new ways of representing data through trendy technologies such as augmented reality (AR), which extends our perception of reality through the addition of a virtual layer on top of real-time images. The great potential of unmanned aerial vehicles (UAVs) for carrying out routine and professional tasks has encouraged their use in the creation of several services, such as package delivery or industrial maintenance. Unfortunately, drone piloting is difficult to learn and requires specific training. Since regular training is performed with virtual simulations, we decided to propose a multiplatform cloud-hosted solution based in Web AR for drone training and usability testing. This solution defines a configurable trajectory through virtual elements represented over barcode markers placed on a real environment. The main goal is to provide an inclusive and accessible training solution which could be used by anyone who wants to learn how to pilot or test research related to UAV control. For this paper, we reviewed drones, AR, and human–drone interaction (HDI) to propose an architecture and implement a prototype, which was built using a Raspberry Pi 3, a camera, and barcode markers. The validation was conducted using several test scenarios. The results show that a real-time AR experience for drone pilot training and usability testing is achievable through web technologies. Some of the advantages of this approach, compared to traditional methods, are its high availability by using the web and other ubiquitous devices; the minimization of technophobia related to crashes; and the development of cost-effective alternatives to train pilots and make the testing phase easier for drone researchers and developers through trendy technologies.