Abstract
Pressure ulcers are a critical issue for patients and healthcare professionals, requiring their frequent monitoring, with a consequent impact on healthcare costs. This problem has been gaining attention and approaches have been proposed, using sensor-based systems, to facilitate this monitoring and help health caregivers to achieve greater effectiveness in the treatment of this type of ulcer. In this paper, the architecture, and the prototype of a new system for pressure ulcer monitoring and prevention are presented. It considers information related to both intrinsic and extrinsic predisposing factors and it addresses the components of data acquisition, data analysis, and production of complementary support to well-informed clinical decision-making. The system includes a pressure ulcer management portal and a mobile application, that allows caregivers to manage clinical information about pressure ulcers of the patients and uses data acquired from a pressure sensor sheet under the mattress to provide useful information for monitoring the patients. Considering the situation of each patient, the system will produce indicators/alerts to healthcare professionals, simultaneously improving pressure-ulcer patient care quality and safety and minimizing the burnout in healthcare professionals. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
Falls are one of the main causes of mortality and morbidity in the elderly worldwide. This had let to the research and development of electronic fall-detection systems. We propose a complete fall-detection system, that combines a wearable device (called Nyon) and a message microservice (for email and SMS) to alert caregiver every time a fall occurs. The wearable uses a simple threshold method and has the capability of search and switch between Wi-Fi and Bluetooth, using the available communication technology when a fall occurs. The results have shown that the wearable autonomy is adequate for a daily use and the server microservices are reliable and deliver a message to the caregiver every time a fall alert occurs. Several improvements are planned to increase the autonomy and range of the wearable device. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
Efficient use of resources is a critical factor in almond crops. Technological solutions can significantly contribute to this purpose. The VeraTech project aims to explore the integration of sensors and cloud-based technologies in almond crops for efficient use of resources and reduction of environmental impact. It also makes available a set of relevant and impactful performance indicators in agricultural activity, which promote productivity gains supported by efficient use of resources. The proposed solution includes a sensor network in the almond crops, the transmission of data and its integration in the cloud, making this data available to be consumed, processed, and presented in the monitoring and alerts dashboard. In the current state of the development, several data are collected by sensors, transmitted over LoRaWAN, integrated using AWS IoT Core, and monitored and analysed through a cloud business analytics service. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
The 5th International Conference on Production Economics and Project Evaluation ICOPEV 2022 held on 29th – 30th of September 2022 in Castelo Branco, Portugal, continues the series of annual events shaping the future of Project Evaluation and Selection. Projects compete for scarce resources and choosing the best allocation of these resources is a complex and challenging task that decision makers face every day. The conference has covered a broad range of important and timely issues related to business intelligence, innovation & technology, project management, knowledge & technology trans-fer, energy issues, decision support systems, cost management, sustainability, innovation, and entrepreneurship. ICOPEV 2022 also featured keynote sessions and round tables. Our deepest appreciation goes to all that put in a lot of hard work of all who are involved in making this conference a success, including the organizing staff at Polytechnic Institute of Castelo Branco and the sponsors. In this conference participated authors from ten countries, namely Brazil, China, Chile, Colombia, Mexico, Poland, Portugal, Spain, and United Kingdom. The technical program is the result of the dedication and efforts of 56 members of the Scientific Committee as well as 37 reviewers, who have greatly contributed to the success of the ICOPEV 2022 paper review process, with an acceptance rate of 80%. The 2022 edition is the 5th conference since the inaugural event held in Guimarães, Portugal in 2011. The ICOPEV conferences follow a tradition of a high scientific quality and an informal atmosphere that fosters innovative and open discussions between academia and industry. Based on the many high-quality contributions in the technical program and interesting discussions during the conference, we are sure that this year edition in Castelo Branco was a worthy successor of the previous ICOPEV events.

Abstract
Physical models and probabilistic applications often guide the study and characterization of natural phenomena in engineering. Such is the case of the study of air change rates (ACHs) in buildings for their complex mechanisms and high variability. It is not uncommon for the referred applications to be costly and impractical in both time and computation, resulting in the use of simplified methodologies and setups. The incorporation of airtightness limits to quantify adequate ACHs in national transpositions of the Energy Performance Building Directive (EPBD) exemplifies the issue. This research presents a roadmap for developing an alternative instrument, a compliance tool built with a Machine Learning (ML) framework, that overcomes some simplification issues regarding policy implementation while fulfilling practitioners' needs and general societal use. It relies on dwellings' terrain, geometric and airtightness characteristics, and meteorological data. Results from previous work on a region with a mild heating season in southern Europe apply in training and testing the proposed tool. The tool outputs numerical information on the air change rates performance of the building envelope, and a label, accordingly. On the test set, the best regressor showed mean absolute errors (MAE) below 1.02% for all the response variables, while the best classifier presented an average accuracy of 97.32%. These results are promising for the generalization of this methodology, with potential for application at regional, national, and European Union levels. The developed tool could be a complementary asset to energy certification programmes of either public or private initiatives. (c) 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Abstract
Zero-shot learning enables the recognition of classes not seen during training through the use of semantic information comprising a visual description of the class either in textual or attribute form. Despite the advances in the performance of zero-shot learning methods, most of the works do not explicitly exploit the correlation between the visual attributes of the image and their corresponding semantic attributes for learning discriminative visual features. In this paper, we introduce an attention-based strategy for deriving features from the image regions regarding the most prominent attributes of the image class. In particular, we train a Convolutional Neural Network (CNN) for image attribute prediction and use a gradient-weighted method for deriving the attention activation maps of the most salient image attributes. These maps are then incorporated into the feature extraction process of Zero-Shot Learning (ZSL) approaches for improving the discriminability of the features produced through the implicit inclusion of semantic information. For experimental validation, the performance of state-of-the-art ZSL methods was determined using features with and without the proposed attention model. Surprisingly, we discover that the proposed strategy degrades the performance of ZSL methods in classical ZSL datasets (AWA2), but it can significantly improve performance when using face datasets. Our experiments show that these results are a consequence of the interpretability of the dataset attributes, suggesting that existing ZSL datasets attributes are, in most cases, difficult to be identifiable in the image. Source code is available at https://github.com/CristianoPatricio/SGAM.