Data on transport usage is important in a wide range of areas. These data are often obtained manually through costly and inaccurate interviews. In the last decade, several researchers explored the use of smartphone sensors for the automatic detection of transport modes. However, such works have focused on developing centralized machine learning mechanisms. This centralized approach requires user data to be transferred to a central server and, therefore, does not satisfy a transport mode detection mechanism’s practical response time and privacy needs. This research presents the Federated System for Transport Mode Detection (FedTM). The main contribution of FedTM is exploring Federated Learning on transport mode detection using smartphone sensors. In FedTM, both the training and inference process is moved to the client side (smartphones), reducing response time and increasing privacy. The FedTM was designed using a Neural Network for the classification task and obtained an average accuracy of 80.6% in three transport classes (cars, buses and motorcycles). Other contributions of this work are: (i) The use of data collected only on the curves of the route. Such reduction in data collection is important, given that the system is decentralized and the training and inference phases take place on smartphones with less computational capacity. (ii) FedTM and centralized classifiers are compared with regard to execution time and detection performance. Such a comparison is important for measuring the pros and cons of using Federated Learning in the transport mode detection task.
Drones, or unmanned aerial vehicles, can be used as air base stations (UAV-BSs) for telecommunications. They prove useful in situations where the network is overloaded or unavailable due to natural disasters or maintenance work. UAV-BSs grant access to user/IoTs sensors on the ground, but their electromagnetic signals may suffer losses because of their dynamic capacity to provide access at different altitudes. These losses lead to transmission impairments, such as attenuation, fading, and distortion. To overcome these issues and improve signal quality, the UAV-BS position must be optimized. However, finding the optimal placement is a challenge, and a wide range of strategies employing different approaches have been adopted. In this study, we proposed a 3D positioning strategy for UAV-BSs that serves the maximum number of users with the smallest number of UAV-BSs. Results showed that the proposed heuristic could find the best position and altitude for the UAV-BSs, provide network access for mobile user/IoTs (Internet of things) sensors, maximize the number of devices connected to the UAV-BSs, and guarantee a minimum throughput for users. The proposed heuristic not only performs well in terms of coverage and performance, but is also more energy-efficient than other algorithms found in the literature.
In every business, equipment requires repair services. Over time, equipment wears out; however, with well-conducted and guided maintenance, this degradation can be controlled, and failed equipment can be restored to operational status. Preventive maintenance allows this concept to be applied, given the great advantages for large companies in reusing equipment and machinery, always putting the worker’s health and safety first. Rail transport has several pieces of equipment that can be reused if they are in a regular and well-defined maintenance cycle. In this sense, this article sought to create a method using real data for identifying cracks in wagons. Through the use of computer vision algorithms to prepare the data, along with several machine learning classification algorithms to locate cracks in train cars, the classification used properly annotated images and obtained great results, with a best case 98.10% hit-rate when wagons had a crack problem.
COVID-19 disease has become an unprecedented public health crisis. Although a relatively small percentage of people require intensive care, due to the high degree of contagion of the disease, the public system quickly collapses. Due to the highly complex nature of this disease and variation in its behavior depending on the characteristics of each geographic region, in this work, we analyze data from the Amazon region in Brazil (Pará). We applied several machine learning models to forecast the contagious curve to up 10 days. The Linear SVM and Multilayer Perceptron presented the best overall performances. Until the discovery of a vaccine, every effort is needed to understand and anticipate this disease.
Introdução: As forças auxiliares responsáveis pela segurança pública, compostas pela Polícia Militar (PM), Corpo de Bombeiros (CB) e Polícia Civil (PC), têm um papel essencial na proteção da sociedade e na manutenção da ordem pública. Dadas as necessidades físicas de suas atribuições, o Teste de Aptidão Física (TAF) é uma ferramenta de seleção dos candidatos aos cargos dessas instituições, sendo um componente fundamental para evitar intercorrências nos concursos de ingresso. Objetivo: Apresentar os testes utilizados nos TAFs de concursos públicos para ingresso nas carreiras de PM, CB e PC da Região Norte do Brasil. Método: Foi realizada uma pesquisa documental que analisou 110 editais dos concursos públicos para PM, CB e PC realizados entre 2013 e 2023 nos estados da Região Norte do Brasil. Resultados: Os resultados indicaram que todos os 110 editais analisados incluíram testes de corrida (100%) e abdominais (100%); 100 incluíram testes de flexão de cotovelos com mãos apoiadas no solo e corpo em decúbito ventral (90,9%); 85 incluíram testes de flexão de cotovelo na barra fixa (77,2%); 72 incluíram testes de deslocamento na água (natação) (66%); 9 incluíram testes de saltos (8,1%); 9 incluíram testes de sentar e alcançar (8,1%); 4 incluíram testes de equilíbrio (3,6%); e 1 incluiu o teste Shuttle Run Test (0,9%). Conclusões: Os testes utilizados são caracterizados por baixo custo, facilidade de aplicação em larga escala e adaptabilidade a diferentes espaços. As necessidades de adaptação geram grande heterogeneidade nas formas de aplicação dos testes.