Abstract

Abstract
Precision spraying in agriculture is crucial for optimizing the application of pesticides while minimizing environmental impact. Despite significant advancements in control models for spraying systems, predictive control algorithms were not used. This paper addresses this gap by proposing a real-time control framework that integrates predictive control strategies to ensure consistent pressure output in a trailer sprayer. Based on information from various sensors, the framework anticipates and adapts to dynamic environmental conditions, enhancing accuracy and sustainability in spraying practices. A methodology is developed to define a proportional valve model. Based on this valve model, the predictive control model optimizes valve movements to minimize errors between predicted and reference pressures, thereby improving spraying efficiency. This study demonstrates the viability of predictive control in improving precision spraying systems applicable to autonomous robots, encouraging future advances in agricultural spraying technologies.

Abstract
Smart home devices are becoming more popular over the years. A diverse range of appliances is being created, and Ambient Intelligence is growing in homes. However, there are various producers of these gadgets, different kinds of protocols, and diverse environments. The lack of interoperability reduces comfort of the user and turns into a barrier to smart home adoption. Matter is growing by constructing an open-source application layer protocol that can be compatible with all smart home ecosystems. In this article, a Matter overview is provided (namely, of the Commissioning stage), and a Matter Accessory using ESP32-S3 is developed referring to the manufacturer's SDKs and is inserted into an existent household ecosystem. Its behavior on the network is briefly analyzed, and interactions with the device are carried out. The simplicity of these tasks demonstrates accessibility for developers to create products, especially when it comes to firmware. Additionally, device commissioning and control are straightforward for the consumer. This capacity of gadget incorporation into diverse ecosystems using Matter is already on the market and might result in higher device production and enhanced smart home adoption.

Abstract
Object detection is a crucial task in autonomous driving, where domain shift between the training and the test set is one of the main reasons behind the poor performance of a detector when deployed. Some erroneous priors may be learned from the training set, therefore a model must be invariant to conditions that might promote such priors. To tackle this problem, we propose an adversarial learning framework consisting of an encoder, an object-detector, and a condition-classifier. The encoder is trained to deceive the condition-classifier and aid the object-detector as much as possible throughout the learning stage, in order to obtain highly discriminative features. Experiments showed that this framework is not very competitive regarding the trade-off between precision and recall, but it does improve the ability of the model to detect smaller objects and some object classes.

Abstract
The efficient last-mile delivery of goods involves complex challenges in optimizing driver sectors and routes. This problem tends to be large-scale and involves several criteria to meet simultaneously, such as creating compact sectors, balancing the workload among drivers, minimizing the number of undelivered packages and reducing the dissimilarity of sectors on different days. This work proposes a Decision Support System (DSS) that allows decision-makers to select improved allocation strategies to define sectors. The main contribution is an interactive DSS tool that addresses a many-objective (more than 3 objectives) sectorization problem with integrated routing. It establishes a global allocation strategy and uses it as a benchmark for the created daily allocations and routes. A Preference-Inspired Co-Evolutionary Algorithm with Goal vectors using Mating Restriction (PICEA-g-mr) is employed to solve the many-objective optimization problem. The DSS also includes a visualization tool to aid decision-makers in selecting the most suitable allocation strategy. The approach was tested in a medium-sized Metropolitan Area and evaluated using resource evaluation metrics and visualization methods. The proposed DSS deals effectively and efficiently with the sectorization problem in the context of last-mile delivery by producing a set of viable and good-quality allocations, empowering decision-makers in selecting better allocation strategies. Focused on enhancing service efficiency and driver satisfaction, the DSS serves as a valuable tool to improve overall service quality.

Abstract
The teaching and learning process in higher education needs continuous cultivation of pedagogical expertise, encompassing subject mastery and pedagogical methodologies. This article explores the transformation of higher education institutions (HEIs) into hybrid campuses and the importance of pedagogical innovation, highlighting the need for training in hybrid/e-learning environments, and emphasizing the potential of mobile technologies. Furthermore, it presents a case study on two professional development courses offered to faculty members, working in the field of Engineering in Portugal, aiming to reconfigure their professionality. The research adopts an ethnographic methodology, integrating quantitative methods and utilizing a variety of data collection tools, including field notes and self-reflection sheets, to analyze the teachers' reconfiguration of their professional practices. The main findings of the study reveal that the majority of faculty members reported significant gains in transforming traditional courses to digital formats, mastering various online platforms and tools, and developing skills in online communication.