Loading...
88 results
Search Results
Now showing 1 - 10 of 88
- The use of technology in the diagnosis and treatment of epilepsy: Trends and open issuesPublication . Fernandes, J.; Gaspar, Pedro Dinis; Menino, Eva; Caldeira, J.M.L.P.; Soares, V.N.G.J.Epilepsy is one of the most common neurological diseases in the world, affecting millions of people. The impact of this disease goes beyond seizures. It has repercussions on the individual’s health and quality of life (i.e., neurological, psychological, and physical consequences) and social inclusion. This article presents a review of the literature and discusses the technological and scientific advances in the diagnosis and treatment of epilepsy. It begins by introducing the related concepts, then analyzes the different technological approaches, exposing their strengths and limitations, and concludes by identifying challenges and open problems for future research.
- The development of a prototype solution for collecting information on cycling and hiking trail usersPublication . Miguel, Joaquim; Mendonça, Pedro; Quelhas, Agnelo; Caldeira, J.M.L.P.; Soares, Vasco N.G.J.Hiking and cycling have gained popularity as ways of promoting well-being and physical activity. This has not gone unnoticed by Portuguese authorities, who have invested in infrastructure to support these activities and to boost sustainable and nature-based tourism. However, the lack of reliable data on the use of these infrastructures prevents us from recording a endance rates and the most frequent types of users. This information is important for the authorities responsible for managing, maintaining, promoting and using these infrastructures. In this sense, this study builds on a previous study by the same authors which identified computer vision as a suitable technology to identify and count different types of users of cycling and hiking routes. The performance tests carried out led to the conclusion that the YOLOv3-Tiny convolutional neural network has great potential for solving this problem. Based on this result, this paper describes the proposal and implementation of a prototype demonstrator. It is based on a Raspberry Pi 4 platform with YOLOv3-Tiny, which is responsible for detecting and classifying user types. An application available on users’ smartphones implements the concept of opportunistic networks, allowing information to be collected over time, in scenarios where there is no end-to-end connectivity. This aggregated information can then be consulted on an online platform. The prototype was subjected to validation and functional tests and proved to be a viable low-cost solution.
- Protótipo de solução de deteção e dispersão de aves para proteção de colheitasPublication . Lourenço, Leonardo G.P.S.; Micaelo, Eduardo B.; Gaspar, Pedro Dinis; Caldeira, J.M.L.P.; Soares, Vasco N.G.J.Os animais são uma das pragas que constituem uma ameaça para a produtividade das culturas destinadas ao consumo humano. As perdas de colheitas causadas por aves representam um desafio sério e dispendioso para os agricultores. O trabalho apresentado neste artigo parte de um estudo prévio dos mesmos autores que concluiu sobre a ineficiência das técnicas dissuasoras comumente utilizadas para dispersão de aves nas colheitas. Assim, num contexto de agricultura inteligente, propõe o uso de drones, inteligência artificial, sensores e IoT, para tentar resolver este problema. Apresenta uma proposta de arquitetura e descreve o processo de implementação de um protótipo, incluindo os seus componentes de hardware e software. Descreve um conjunto de testes realizados para validação do conceito e identifica pontos de trabalho em aberto.
- The development of a prototype solution for detecting wear and tear in pedestrian crossingsPublication . Rosa, Gonçalo J.M.; Afonso, João M.S.; Gaspar, Pedro Dinis; Soares, Vasco N.G.J.; Caldeira, J.M.L.P.Crosswalks play a fundamental role in road safety. However, over time, many suffer wear and tear that makes them difficult to see. This project presents a solution based on the use of computer vision techniques for identifying and classifying the level of wear on crosswalks. The proposed system uses a convolutional neural network (CNN) to analyze images of crosswalks, determining their wear status. The design includes a prototype system mounted on a vehicle, equipped with cameras and processing units to collect and analyze data in real time as the vehicle traverses traffic routes. The collected data are then transmitted to a web application for further analysis and reporting. The prototype was validated through extensive tests in a real urban environment, comparing its assessments with manual inspections conducted by experts. Results from these tests showed that the system could accurately classify crosswalk wear with a high degree of accuracy, demonstrating its potential for aiding maintenance authorities in efficiently prioritizing interventions.
- A self-sustainable opportunistic solution for emergency detection in ageing people living in rural areasPublication . Jesús-Azabal, Manuel; Berrocal-Olmeda, Javier; Soares, V.N.G.J.; García-Alonso, José; Galán-Jiménez, JaimeThere are contexts where communication with TCP/IP protocol is not possible due to the lack of infrastructure or a reliable and continuous data transmission. In this cases, alternatives such as Opportunistic Networks (OPPNets) are valid. Such challenging conditions are common in rural areas and are a significant obstacle for the deployment of eHealth technologies for older adults. Considering this context, the present work introduces Interest-based System for Communication in Isolated Areas (ISCA), an OPPNet architecture for remote monitoring and emergency detection in ageing people who live alone. For this, the energetic requirements are considered, providing efficient and sustainable operation. The proposal makes use of a routing algorithm based on interests which enables asynchronous communication among entities. ISCA is evaluated over a realistic scenario and compared with similar state-of-the-art solutions. Experimental results show that ISCA notably improves the delivery probability with an enhancement of 52.25% in comparison to the second best alternative and provides a suitable average latency. Moreover, it also achieves better performance in terms of overhead and hops number compared to the other studied protocols.
- Desenho e implementação de protótipo para deteção de contentores de resíduos em cidades inteligentesPublication . Valente, Miguel; Silva, Hélio; Caldeira, J.M.L.P.; Soares, V.N.G.J.; Gaspar, Pedro DinisEste trabalho apresenta o desenho e implementação de um protótipo funcional para avaliar e validar a utilização de técnicas de visão computacional, na identificação de contentores de resíduos no contexto de uma cidade inteli- gente. Este protótipo recorre à utilização de uma rede neuronal convolucional YOLO e de um microcomputador Jetson Nano da Nvidia. Comparativamente ao método atual de identificação de contentores de resíduos por radiofrequência, esta abordagem é mais ágil e diminui os recursos necessários para implementa- ção, contribuindo para poupar nos gastos logísticos e de implementação da gestão inteligente de resíduos.
- Aplicação para detetar e corrigir a postura em exercícios físicosPublication . Gonçalves, João; Palhares, João; Soares, V.N.G.J.; Neves, Paulo AlexandreNo ritmo acelerado da vida moderna a prática regular de exercício físico emerge como fonte de vitalidade e bem-estar. No entanto nem sempre é possível a deslocação ao ginásio e/ou pagar a um treinador pessoal. A opção por exercícios sem equipamentos usando o peso do corpo é apelativa pelos benefícios e baixo custo, mas podem surgir lesões pela sua má execução, nomeadamente devido a postura incorreta. Este trabalho apresenta uma abordagem para permitir, utilizando técnicas de visão computacional, detectar que exercício o praticante está a executar e analisar a postura, sem necessidade de intervenção de uma terceira pessoa. Os principais contributos deste artigo são: 1) Desenvolvimento de um dataset robusto para deteção de 3 exercícios de ginástica diferentes, 2) Avaliação do desempenho do modelo YOLOv8, bem como alguns dos seus diferentes níveis, usando o dataset desenvolvido; 3) Criação de um protótipo de aplicação para detetar um exercício e corrigir a realização do mesmo por parte dos utilizadores. O principal objetivo é fornecer aos utilizadores uma forma de facilitar a realização de atividade física, em qualquer lugar, sem a necessidade de acompanhamento especial ou equipamentos externos, sendo ao mesmo tempo um adjuvante para garantir que não ocorrem lesões por má postura.
- Scheduling and drop policies for traffic differentiation on vehicular delay-tolerant networksPublication . Soares, V.N.G.J.; Farahmand, Farid; Rodrigues, JoelVehicular Delay-Tolerant Networks (VDTNs) are a promising technology for vehicular communications, creating application scenarios that enable non-real time services with diverse performance requirements. Because of scarce network resources (e.g. bandwidth and storage capacity) and node’s short contact durations, the underlying VDTN network infrastructure must be capable of prioritizing traffic. This paper investigates several scheduling and drop policies, which can be used to implement traffic differentiation. Priority Greedy, Round Robin, and Time Threshold scheduling polices are proposed. In terms of drop policy, the message with the lowest priority and the lowest remaining time-to-live is discarded first. We evaluate their efficiency and tradeoffs, through simulation. The results presented in this paper can be used as a starting point for further studies in this research field, and give helpful guidelines for future VDTN protocol design.
- Road pavement damage detection using computer vision techniques: Approaches, challenges and opportunitiesPublication . Gonçalves, Miguel; Marques, Tomás; Gaspar, Pedro Dinis; Soares, V.N.G.J.; Caldeira, J.M.L.P.Este artigo apresenta uma visão geral e os resultados de uma investigação preliminar que visa a utilização de técnicas de visão computacional para deteção de defeitos em pavimentos rodoviários, no contexto de uma cidade inteligente. Primeiro introduz os conceitos relacionados. Em seguida, faz um levantamento do estado da arte e das soluções existentes, apresentando as suas principais características, pontos fortes e limitações. São identificadas as soluções mais promissoras. Para finalizar discute desafios em aberto e direções de investigação nesta área.
- iSensA: a system for collecting and integrating sensor dataPublication . Caldeira, J.M.L.P.; Soares, V.N.G.J.; Gaspar, Pedro Dinis; Rodrigues, Joel; Fontes, Ricardo Manuel Valentim; Silva, José Luís LimaThe idea of monitoring several types of parameters in various environments has been motivating significant research works in Internet of Things (IoT). This paper presents the design and construction of iSensA, a system for integrating and collecting information from sensors. The solution implements a multi-sensor monitoring system and then expands the monitoring concept to an IoT solution, by employing multi-network access, Web services, database and web and mobile applications for user interaction. iSensA system is highly configurable, enabling several monitoring solutions with different types of sensors. Experiments have been performed on real application scenarios to validate and evaluate our proposition.