China 
Africa 
Explore chapters and articles related to this topic
Smart War on COVID-19 and Global Pandemics
Published in Chhabi Rani Panigrahi, Bibudhendu Pati, Mamata Rath, Rajkumar Buyya, Computational Modeling and Data Analysis in COVID-19 Research, 2021
Anil D. Pathak, Debasis Saran, Sibani Mishra, Madapathi Hitesh, Sivaiah Bathula, Kisor K. Sahu
According to recent medical research, the patients infected with COVID-19 have more rapid respiration and have a different respiratory pattern than patients with the flu or common cold. It has been reported that the Tachypnea type of respiratory patterns has been observed in COVID-19 patients (Williamson 2020). Based on breathing characteristics, Yunlu Wang et al. (2020) deployed a deep learning model for prognosis, diagnosis, and screening of patients infected with COVID-19. The author utilized Gated Recurrent Unit (GRU) neural network with bidirectional and attentional method to classify six types of respiratory patterns such as Eupnea, Tachypnea, Bradypnea, Biots, Cheyne-Stokes, and Central-Apnea. M. Iqbal et al. (2020) proposed a robust method of active surveillance for COVID-19 patient using AI-based speech-recognition techniques through a mobile application to analyze cough sounds of suspected people and classify them in three levels as: mild, moderate, and severe. Li Yan et al. (2020) developed XGBoost machine learning-based COVID-19 prognostic prediction model using three clinical features, i.e., lactic dehydrogenase (LDH), lymphocyte, and high-sensitivity C-reactive protein (hs-CRP). The model used a dataset of 2,799 patients with more than 90% accuracy, enabling early detection of COVID-19. The remote monitoring and diagnosis of COVID-19 patients are essential to reduce the risk of transmission and also reduce hospital resource requirements during a pandemic (HIMSS Research 2020).
Cardiopulmonary signal acquisition from different regions using video imaging analysis
Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2019
Ali Al-Naji, Javaan Chahl, Sang-Heon Lee
The extracted parameters of the cardiopulmonary signal in this paper can also provide key information about abnormal cardiopulmonary events, such as tachycardia, bradycardia, tachypnea, bradypnea and apnoea. Though the proposed systems based on analysis of both color and motion were attractive in principle, cost effective and safe, they still have some challenges in terms of noise artefacts reduction, multiple subject detection and long-distance detection which will need to be addressed in future work.