Untitled

Funder

Organizational Unit

Publications

Publication . Jonker, Richard A.A.; Poudel, Roshan; Fajarda, Olga; Matos, Sérgio; Oliveira, José Luís; Lopes, Rui Pedro

Over the last two years, the COVID-19 pandemic has affected hundreds of millions of people around the world. As in many crises, people turn to social media platforms, like Twitter, to communicate and share information. Twitter datasets have been used over the years in many research studies to extract valuable information. Therefore, several large COVID- 19 Twitter datasets have been released over the last two years. However, none of these datasets contains only Portuguese Tweets, despite the Portuguese Language being reported as one of the top five languages used on Twitter. In this paper, we present the first large-scale Portuguese COVID-19 Twitter dataset. The dataset contains over 19 million Tweets spanning 2020 and 2021, allowing the entire pandemic to be analyzed. We also conducted a sentiment analysis on the dataset and correlated the various spikes in Tweet count and sentiment scores to various news articles and government announcements in Portugal and Brazil. The dataset is available at: https://github.com/bioinformaticsua/ Portuguese-Covid19-Dataset

2022Conference paper

Open access

DyPrune: dynamic pruning rates for neural networks

Publication . Jonker, Richard A.A.; Poudel, Roshan; Fajarda, Olga; Oliveira, José Luís; Lopes, Rui Pedro; Matos, Sérgio

Neural networks have achieved remarkable success in various applications such as image classification, speech recognition, and natural language processing. However, the growing size of neural networks poses significant challenges in terms of memory usage, computational cost, and deployment on resource-constrained devices. Pruning is a popular technique to reduce the complexity of neural networks by removing unnecessary connections, neurons, or filters. In this paper, we present novel pruning algorithms that can reduce the number of parameters in neural networks by up to 98% without sacrificing accuracy. This is done by scaling the pruning rate of the models to the size of the model and scheduling the pruning to execute throughout the training of the model. Code related to this work is openly available.

2023Conference paper

Restricted access

Digital Twin for Regional Water Consumption Simulation and Forecasting

Publication . Galvão, Matheus Rigoni; Rici, Pedro; Lopes, Rui Pedro

Water scarcity is a global concern due to population growth, climate change, and industrialization. Accurate water consumption simulation and forecasting are essential for understanding consumption patterns and predicting future demand. The control and visualization of how different aspects such as precipitation, season, and population affect water consumption can be a way for public agencies to plan actions that minimize waste and assist in the correct use of water. Technology, and especially Machine Learning and Digital Twin, can be used as tools for this. In light of this, this project aims to develop a system for simulating and forecasting water consumption in the Bragan¸ca region using a Digital Twin. In order to accomplish this, a comprehensive analysis is conducted to determine the necessary requirements for designing the system. This analysis encompasses the evaluation of hardware, software, data, machine learning models, web interface, as well as security and performance requirements. Furthermore, the architecture of this system and how it will be configured is analyzed, proposing a system with Training Data Sources, Training Process, Updated Data Sources, Digital Twin, Web Interface and Monitoring System. The system described in this article is under development and it is hoped to achieve as a result the full design of the Digital Twin and User Interface systems.

2024Conference paper

Restricted access