Deep Learning‐Assisted Sensitive 3C‐SiC Sensor for Long‐Term Monitoring of Physical Respiration

• DOI: 10.1002/adsr.202300159
• Publication Date: 2024-04-05T07:48:25Z
• Authors: Thi Lap Tran; Duy Van Nguyen; Hung Nguyen; Thi Phuoc Van Nguyen; Pingan Song; Ravinesh C Deo; Clint Moloney; Viet Dung Dao; Nam‐Trung Nguyen; Toan Dinh
• Keywords: Respiratory diseases; Biomedical and clinical sciences; convolutional neuron network (CNN); Science; Q; Deep Learning-Assisted Sensitive 3C-SiC Sensor; thermal flow sensor; 610; Deep learning; 600; cubic silicon carbide (3C‐SiC); 0104 chemical sciences; T1-995; long‐term monitoring; respiration rate; Data structures and algorithms; 0210 nano-technology; Biomedical engineering; Technology (General)

Abstract In human life, respiration serves as a crucial physiological signal. Continuous real‐time monitoring can provide valuable insights for the early detection and management of several respiratory diseases. High‐sensitivity, noninvasive, comfortable, long‐term stable devices are highly desirable. spite this, existing sensors cannot continuous due to erosion from moisture, fluctuations in body temperature, many other environmental factors. This research developed wearable thermal‐based sensor made cubic silicon carbide (3C‐SiC) using microfabrication process. The results showed that result Joule heating effect robustness 3C‐SiC material, offered high sensitivity with negative temperature coefficient resistance approximately 5,200ppmK ‐1 , an excellent response stability monitoring. Furthermore, by incorporating deep learning model, this fabricated develop advanced capabilities distinguish between four distinct breath patterns: slow, normal, fast, breathing, impressive classification accuracy rate ≈ 99.7%. represent significant step developing personal healthcare systems.