UWB Sensor Assisted Self-Quarantined Person Health Status Monitoring using LSTM

• Published in: 2021 International Conference on Information and Communication Technology Convergence (ICTC) pp. 1750 - 1753
• Main Authors: Islam, Fabliha Bushra, Nwakanma, Cosmas Ifeanyi, Lee, Jae-Min, Kim, Dong-Seong
• Format: Conference Proceeding
• Language: English
• Published: IEEE 20.10.2021
• Subjects: COVID-19; Deep learning; Long-Term Short Memory (LSTM); Medical services; Pandemics; Privacy; Social factors; Training; Ultra Wide Band (UWB) sensor
• DOI: 10.1109/ICTC52510.2021.9620923

The severe acute respiratory syndrome virus (SARS-CoV-2), known as COVID-19, has brought untold hardship and deaths all over the world. Individuals affected by COVID-19 often experience respiratory difficulties along with fever, cough, and other symptoms. Social distancing and self-quarantine are strongly suggested by researchers to avoid the exponential spread of the disease. The ultra-wideband (UWB) sensor has recently offered remote monitoring and capturing respiratory signs by ensuring privacy. In this work, a UWB sensor is employed to observe the movement and respiration of a home-quarantined person for fourteen days. After collecting the information in realtime, a deep learning (DL) approach, the long-term short memory (LSTM) framework is further applied to detect the breathing and movement patterns. The experimental result depicts that the framework accomplished 99.93% accuracy with 2 misclassification costs. The proposed application shows promising possibilities into the Internet of medical things (IoMT), smart home health care support system (ShHeS), and practical use in COVID-19 pandemic emergency.