Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Publicações

Publicações por Hugo Paredes

2024

Usability Evaluation of an Application for Managing Older Adults Physical Activity Sessions in an Immersive Multiuser Virtual Environment

Autores
Qbilat, M; Netto, A; Paredes, H; Mota, T; de Carvalho, F; Mendonça, J; Nitti, V;

Publicação
2024 IEEE 12TH INTERNATIONAL CONFERENCE ON SERIOUS GAMES AND APPLICATIONS FOR HEALTH, SEGAH 2024

Abstract
This paper presents a usability evaluation of a companion application for managing older adults' physical activity sessions in an immersive multiuser virtual environment. The companion application was designed to facilitate the trainer ' s role and enhance the overall user experience in the virtual multiuser environment. Four trainers were recruited to participate in the study, they performed two tasks to prepare and manage training sessions with older adults using the companion application. Researchers used an open-ended questionnaire to interview the participants. The results revealed a high satisfaction and appreciation for the application features used to prepare and manage the training sessions. Participants found the application useful and intuitive, and they also recommended a list of future desirable features related to the application ' s feedback and help mechanisms, as well as its content. In addition to the necessity to provide mobile and tablet versions of the application. A few usability problems were detected related to information presentation and navigation. The future design of the companion application will consider all the detected usability problems and desired features.

2024

Lightweight 3D CNN for the Segmentation of Coronary Calcifications and Calcium Scoring

Autores
Santos, R; Baeza, R; Filipe, VM; Renna, F; Paredes, H; Pedrosa, J;

Publicação
2024 IEEE 22ND MEDITERRANEAN ELECTROTECHNICAL CONFERENCE, MELECON 2024

Abstract
Coronary artery calcium is a good indicator of coronary artery disease and can be used for cardiovascular risk stratification. Over the years, different deep learning approaches have been proposed to automatically segment coronary calcifications in computed tomography scans and measure their extent through calcium scores. However, most methodologies have focused on using 2D architectures which neglect most of the information present in those scans. In this work, we use a 3D convolutional neural network capable of leveraging the 3D nature of computed tomography scans and including more context in the segmentation process. In addition, the selected network is lightweight, which means that we can have 3D convolutions while having low memory requirements. Our results show that the predictions of the model, trained on the COCA dataset, are close to the ground truth for the majority of the patients in the test set obtaining a Dice score of 0.90 +/- 0.16 and a Cohen's linearly weighted kappa of 0.88 in Agatston score risk categorization. In conclusion, our approach shows promise in the tasks of segmenting coronary artery calcifications and predicting calcium scores with the objectives of optimizing clinical workflow and performing cardiovascular risk stratification.

2014

Online Gym : um ginásio virtual 3D integrando a kinect : análise comparativa de bibliotecas de suporte

Autores
Cassola, Fernando; Morgado, Leonel; Paredes, Hugo; Fonseca, Benjamim; Martins, Paulo; Carvalho, Fausto de;

Publicação

Abstract
A sincronização online de ginástica potencia novas possibilidades para melhorar o bem-estar físico e social das pessoas com restrições de deslocação. A nossa proposta passa pela criação de uma plataforma 3D - Online Gym - que permita que os utilizadores interajam e participem em sessões online de ginástica em grupo através do Microsoft Kinect. No presente artigo, com vista à concretização desta proposta, analisamos três alternativas tecnológicas para a implementação de serviços de deteção de movimentos que possam ser integrados em plataformas gráficas multiutilizador. Nos resultados, expõem-se as características de cada uma e o impacte respetivo para sua utilização na concretização desta proposta ou outras iniciativas similares.

2016

Proceedings of the 7th International Conference on Software Development and Technologies for Enhancing Accessibility and Fighting Info-Exclusion

Autores
Hugo Paredes;

Publicação

Abstract

2021

Simple VR for better living

Autores
Mota, Telma; Carvalho, Fausto de; Paredes, Hugo; Morgado, Leonel;

Publicação
InnovAction

Abstract
Physical and cognitive rehabilitation based on natural interaction and VR has been on our horizon for several years, and we have been conducting experimentation towards that goal through several exploratory research initiatives.This article addresses some aspects of the state-of-the-art of VR in healthcare and well-being, with opportunities in the domain of rehabilitation based on natural interaction and VR being analyzed and put in perspective with the SmartAL ecosystem roadmap.

2024

3D Modelling to Address Pandemic Challenges: A Project-Based Learning Methodology

Autores
Rocha, T; Ribeiro, A; Oliveira, J; Nunes, RR; Carvalho, D; Paredes, H; Martins, P;

Publicação
CoRR

Abstract

  • 33
  • 33