Abstract
Over recent decades, precision agriculture has revolutionized farming by optimizing crop yields and reducing resource use through targeted applications. Existing portable spray quality assessors lack precision, especially in detecting overlapping droplets on water-sensitive paper. This proposal aims to develop a smartphone application that uses the integrated camera to assess spray quality. Two approaches were implemented for segmentation and evaluation of both the water-sensitive paper and the individual droplets: classical computer vision techniques and a pre-trained YOLOv8 deep learning model. Due to the labor-intensive nature of annotating real datasets, a synthetic dataset was created for model training through sim-to-real transfer. Results show YOLOv8 achieves commendable metrics and efficient processing times but struggles with low image resolution and small droplet sizes, scoring an average Intersection over Union of 97.76% for water-sensitive spray segmentation and 60.77% for droplet segmentation. Classical computer vision techniques demonstrate high precision but lower recall with a precision of 36.64% for water-sensitive paper and 90.85% for droplets. This study highlights the potential of advanced computer vision and deep learning in enhancing spray quality assessors, emphasizing the need for ongoing refinement to improve precision agriculture tools. © 2024 by SCITEPRESS-Science and Technology Publications, Lda.

Abstract
Traditionally, proportional-integral (PI) control has ensured the successful application of automatic generation control (AGC). Two design features of AGC-PI are the following: (1) it is merely a reactive system which does not take full advantage of existing knowledge about the system and (2) the control signal sent to all units is divided proportionally to their participation in the AGC. These two features ensure simplicity and, thus, reliability for the regular functioning of the power system. However, when the power system is recovering from a loss of generation, such features can become shortcomings. This paper proposes a model predictive control (MPC) to improve performance of AGC in such a scenario. The contrast with the traditional approach is as follows: instead of using merely two system measures which are also the control objectives (frequency and interconnection flow), the proposed controller relies on an internal model that takes advantage of further known variables of the power system, especifically the ramping capabilities of participating units. While still respecting the participation factors, it is shown that the proposed model allows to exhaust earlier the availability of faster units, such as some demand response, as the one to be provided by hydrogen electrolysers, and thus reestablishes the frequency and interconnection flows in a faster way than typical AGC-PI.

Abstract
Resilience is an important theoretical construct that helps to conceptualise the ways individuals and organisations attempt to countervail the effects of poverty and austerity. As a response to prolonged crises, such as the global economic crisis and the COVID-19 pandemic, this chapter focuses on tracing the psychological, behavioural, sociological and spatial perspectives of resilience, advancing our current understanding of resilience theory within the marketing and consumption context of crises and austerity. The chapter reviews recent research exploring the importance of resilience and, more specifically, the notion of persistent resilience in response to long-term stressors, such as unemployment, triggered by the austerity measures imposed by European governments following the global economic crisis as well as the COVID-19 pandemic. In advancing previous research in this area, we offer a broader perspective by underlining the impetus for businesses and communities to employ a range of resilience strategies while also highlighting the importance for individuals to develop a sustainable set of resilience capacities to help creatively navigate the market and flexibly adapt to the long-term effects of intense and long-standing crises © 2024 selection and editorial matter, Caroline Moraes, Morven G. McEachern and Deirdre O’Loughlin; individual chapters, the contributors. All rights reserved.

Abstract
The main objective of this study is to detect signs of under-invoicing by applying Benford's law to the Portuguese restaurant sector during the COVID-19 pandemic, in the context of government support policies. Between 2020 and 2021, the State adopted several measures to provide additional support to companies that have seen a significant decrease in their activity, namely, a reduction of at least 25% in turnover. A literature review was carried out focusing on the impact of the COVID-19 pandemic on the companies under analysis, the support measures adopted by the State and, finally, a survey of the theoretical component relating to the application of Benford's law in accounting. The data were collected from the Iberian Balance Sheet Analysis System database for 2019, 2020, and 2021. After analysing the data, significant deviations are observed in several digits, practically for all the compliance tests, both in the analysis of the first digit test and in the analysis of the first two digits test. The results therefore show signs of under-invoicing in 2020 by the analysed companies, which suffered, on average, a 79% reduction in turnover.

Abstract
Autism Spectrum Disorder (ASD) affects individuals in diverse ways, making personalized therapeutic approaches crucial. In this context, we propose a personalized mobile application designed for music-based therapy tailored to people with ASD. This adaptive piano app can be customized to suit the individual abilities of each user. The paper is structured as follows: The introduction provides context on autism and the importance of personalized therapy. The background section reviews related studies on music-based therapy. The methodology section introduces Professor Piano, our adaptive and adaptable music therapy application. The results and discussion section explores the challenges encountered during development and presents the findings from a heuristic evaluation conducted by experts. Finally, the conclusion summarizes the main insights and implications of the study.

Abstract
The manual monitoring of refilling stations in industrial environments can lead to inefficiencies and errors, which can impact the overall performance of the production line. In this paper, we present an unsupervised detection pipeline for identifying refilling stations in industrial environments. The proposed pipeline uses a combination of image processing, pattern recognition, and deep learning techniques to detect refilling stations in visual data. We evaluate our method on a set of industrial images, and the findings demonstrate that the pipeline is reliable at detecting refilling stations. Furthermore, the proposed pipeline can automate the monitoring of refilling stations, eliminating the need for manual monitoring and thus improving industrial operations' efficiency and responsiveness. This method is a versatile solution that can be applied to different industrial contexts without the need for labeled data or prior knowledge about the location of refilling stations.