Silva, GabrielBatista, PatríciaRodrigues, Pedro Miguel2023-07-102023-07-102022-11-150892-1997http://hdl.handle.net/10400.14/41625COVID-19 is a disease caused by the new coronavirus SARS-COV-2 which can lead to severe respiratory infections. Since its first detection it caused more than six million worldwide deaths. COVID-19 diagnosis non-invasive and low-cost methods with faster and accurate results are still needed for a fast disease control. In this research, 3 different signal analyses have been applied (per broadband, per sub-bands and per broadband & sub-bands) to Cough, Breathing & Speech signals of Coswara dataset to extract non-linear patterns (Energy, Entropies, Correlation Dimension, Detrended Fluctuation Analysis, Lyapunov Exponent & Fractal Dimensions) for feeding a XGBoost classifier to discriminate COVID-19 activity on its different stages. Classification accuracies ranged between 83.33% and 98.46% have been achieved, surpassing the state-of-art methods in some comparisons. It should be empathized the 98.46% of accuracy reached on pair Healthy Controls vs all COVID-19 stages. The results shows that the method may be adequate for COVID-19 diagnosis screening assistance.engBreathingClassificationCoughCOVID-19Non-linear patternsSpeech signalsjournal article10.1016/j.jvoice.2022.11.00885143292554PMC966373836464573001494077600001