Abstract
Primary healthcare (PHC) is a fundamental pillar in a health system, and its role has only been enhanced in the COVID-19 pandemic. The emergence of COVID-19 required health systems and, in particular, PHCs to develop a constant capacity to adapt and resist adversity. Therefore, it was considered important to identify innovative measures and thus the experience of a family health unit (USF) in Portugal - USF Arte Nova (USFAN) was reported. After carrying out a systematic review of the literature and interviews with the Presidents of the Clinical and Health Councils of five Health Centre Groupings, the measures identified were gathered and compared to the ones carried out by USFAN. Subsequently, the study identified the measures considered to be truly original executed by the health unit. Between the measures presented, the use of an access prioritization score was highlighted, as were daily briefing regarding the management of resources and equipment, qualification of the use of personal protective equipment, the project that aimed to optimize the use of paper; the use of a drive-through method to update the National Vaccination Program; and the daily training and sharing of information about COVID-19. In light of the current pandemic, innovative practices and tools have been created and carried out by the healthcare professionals in response to the growing needs of the population. This shows the resilience of these professionals and constitutes an opportunity to share and implement these tools in other health-care facilities highlighting the continuing chance of improving.

Abstract

Abstract

Abstract
E-commerce has become an essential aspect of modern life, providing consumers worldwide with convenience and accessibility. However, the high volume of short and noisy product descriptions in text streams of massive e-commerce platforms translates into an increased number of clusters, presenting challenges for standard model-based stream clustering algorithms. This is the case of a dataset extracted from the Brazilian NF-e Project containing electronic invoice product descriptions, including many product clusters. While LDA-based clustering methods have shown to be crucial, they have been mainly evaluated on datasets with few clusters. We propose the Topic Model with Contextual Outlier Handling (TMCOH) method to overcome this limitation. This method combines the Dirichlet Process, specific word representation, and contextual outlier detection techniques to recycle identified outliers aiming to integrate them into appropriate clusters later on. The experimental results for our case study demonstrate the effectiveness of TMCOH when compared to state-of-the-art methods and its potential for application to text clustering in large datasets.

Abstract
Digital transformation plays a significant role in modernizing and improving the efficiency of ports around the world. However, digitalization also brings a set of challenges that ports must face. They have to respond to several unique challenges because of the complexity of their operations and the varying demands of stakeholders. This study seeks to identify and summarize the challenges of digital transformation processes in ports. For this purpose, the World Ports Sustainability Program database was used. The findings revealed 74 digitalization initiatives carried out by ports, which makes it possible to recognize 7 dimensions and 32 sub-dimensions of challenges to the digital transformation process. Among the identified dimensions are port infrastructure, the interconnection between various systems, the port organization model, regulation, security and privacy, market evolution, and the establishment of partnerships to implement these projects. The results of this study are relevant to mitigate the risks of the digitalization process in ports and respond to market needs that demand greater transparency and visibility of their operations.

Abstract
In a photovoltaic power plant (PVPP), the DC-AC converter (inverter) is one of the components most prone to faults. Even though they are key equipment in such installations, their fault detection techniques are not as much explored as PV module-related issues, for instance. In that sense, this paper is motivated to find novel tools for detection focused on the inverter, employing machine learning (ML) algorithms trained using a hybrid dataset. The hybrid dataset is composed of real and synthetic data for fault-free and faulty conditions. A dataset is built based on fault-free data from the PVPP and faulty data generated by a digital twin (DT). The combination DT and ML is employed using a Clarke/space vector representation of the inverter electrical variables, thus resulting in a novel feature engineering method to extract the most relevant features that can properly represent the operating condition of the PVPP. The solution that was developed can classify multiple operation conditions of the inverter with high accuracy.