26 documents found, page 1 of 3
The impact of Covid-19 on the tourism activity in Portugal and Greece: a compar...
Fernandes, Joel; Albuquerque, Eduardo B.; Silva, Amândio F. C. da; Sousa, Gisela P. de; Anjo, Manuel M.; Brito, Miguel A.; Cardoso, Miguel P.The objective of this study was to analyze the impact of Covid-19 on the tourism sector of Portugal and Greece. Both countries have similar tourism demand and supply characteristics and the industry is very important for their economies. In the methodology, we reviewed the literature of the topic and analyzed several statistical data for the period of 2018 to 2021. The main results confirm that in both countrie...
Machine learning on insurance premium prediction
Jesus, Rodrigo M.; Brito, Miguel A.; Duarte, Duarte N.The insurance field is going through a phase of great transformation due to the growth of new technologies and techniques that are causing a change in the way data is handled and analyzed. The main perpetrator of this phenomenon is the introduction of Machine Learning (ML) in financial decision-making due to their efficiency and productivity. However, there is a new intervenient in the room, which will automate...
Agnostic performance testing framework
Esteves, Rui P.; Brito, Miguel A.The vast majority of software developed must have the capacity to support thousands of simultaneous users. To ensure that this is the case, systems must be tested to their limits to ensure possible points of failure at an early stage of development, avoiding wasting time and money on tuning and fixing those problems. Failure points in application performance can cause users to be unable to perform key transacti...
Active learning in the detection of anomalies in cryptocurrency transactions
Cunha, Leandro L.; Brito, Miguel A.; Oliveira, Domingos Filipe; Martins, Ana P.The cryptocurrency market has grown significantly, and this quick growth has given rise to scams. It is necessary to put fraud detection mechanisms in place. The challenge of inadequate labeling is addressed in this work, which is a barrier to the training of high-performance supervised classifiers. It aims to lessen the necessity for laborious and time-consuming manual labeling. Some unlabeled data points have...
Business Intelligence over and above Apache Superset
Soares, Guilherme H.; Brito, Miguel A.This study looks for an alternative to the platforms that are most frequently utilized in business intelligence developments. In order to do this, a literature review on each subject typically addressed during the development of a BI platform was performed. Since it was determined that Apache Superset would be the appropriate platform, experiments are currently being developed to evaluate the platform's viability.
Development of an interoperability platform for information systems in the ehea...
Pereira, José D.; Brito, Miguel A.; Machado, Ricardo J.EHealth has emerged as a new field at the intersection of medical informatics, public health and business, referring to healthcare services and information provided or enhanced through information technologies. Today, it is very focused on improving the interoperability between Electronic Health Records (EHRs), Electronic Medical Records (EMRs), and between them and the applications installed on patients' devic...
Anomaly detection in cryptocurrency transactions with active learning
Cunha, Leandro L.; Brito, Miguel A.Cryptocurrencies have gained tremendous popularity in recent years, with the rise of Bitcoin and other altcoins. However, this surge in popularity has also attracted fraudulent activities, such as scams, phishing, and money laundering. Particularly, machine learning (ML) algorithms have the potential to detect these fraudulent patterns. However, since in the fraud detection (FD) domain labels are scarce and mos...
Fraud detection and anti-money laundering applying machine learning techniques ...
Martins, Ana P.; Brito, Miguel A.Cryptocurrencies have advantages such as lower costs, efficiency, and security, but are vulnerable to fraud due to a lack of controls and anonymity. Criminals use virtual currencies for quick, anonymous transactions. Robust measures are needed to prevent illegal activities like money laundering. Machine learning (ML) and graph analysis can help detect fraud in the cryptocurrency market, despite criminals mimick...
Continuous inspection of software quality in an automotive project
Ferreira, Ana Margarida Oliveira; Brito, Miguel A.; Lima, JoséDue to the amount of software that is produced every day in the automotive industry, improve software quality became a necessity, especially in areas where safety is a critical point, such as autonomous driving. Following on from this, continuous inspection of software is important, timely and central, to guarantee software quality and avoid the worst scenarios related to the automotive industry, particularly w...
Development of a self-diagnostic system integrated into a cyber-physical system
Oliveira, Domingos F.; Gomes, João P.; Pereira, Ricardo B.; Brito, Miguel A.; Machado, Ricardo J.CONTROLAR provides Bosch with an intelligent functional testing machine used to test the correct functioning of the car radios produced. During this process, the radios are submitted to several tests, raising the problem of how the machine detects errors in several radios consecutively, making it impossible to know if the device has a problem since it has no module to see if it works correctly. This article ari...