Publications

@misc{Meher2023CTAM,

title = {Development of Smart Technology Exemplified Through Non-contact Heart Rate Monitoring},

author = {Jagmohan Meher and Yan-Cheng Chen and Torbjörn E M Nordling},

url = {https://ctam2023.conf.tw/},

year  = {2023},

date = {2023-11-01},

booktitle = {47th Conference on Theoretical and Applied Mechanics (CTAM 2023), Yunlin, Taiwan, Nov. 17-18, 2023},

pages = {1},

publisher = {National Formosa University, Yunlin, Taiwan},

address = {No. 64, Wenhua Road, Huwei Township, Yunlin County 63201, Taiwan},

abstract = {The rise of smart machines, driven by technologies like AI and ML, has the potential to transform various sectors, including healthcare. However, their development comes with challenges in data gathering, reliability, and adaptability. Conventional heart rate (HR) monitoring requires skin contact, which can cause discomfort and, in rare cases, infections due to the electrodes used for measuring electrocardiograms. To overcome these challenges, we develop remote photoplethysmography (rPPG) that uses computer vision to enable non-contact HR monitoring. rPPG relies heavily on data because of the wide variety in human skin tones, facial features, expressions, and external factors like changing light conditions and movement. Since there isn’t any dataset that tackled all these challenges, we designed an experiment to capture both facial videos and physiological signals, with systematic variations in lighting, motion, and camera angles, aiming to create a more effective training set for rPPG models. Precise synchronization of facial videos with ECG and PPG signals is challenging, and existing open-source software fell short. Thus, we developed our own software tailored to synchronize facial video with physiological signals recorded using a Philips patient monitor. Using this dataset, we benchmarked seven rPPG methods. The accuracy of rPPG depends on the video quality. We used VIIDEO (Video Intrinsic Integrity and Distortion Evaluation Oracle) to quantify the quality of the recorded video. We manually reduced the video quality, by adding noise and then used it to predict the HR. There remain hurdles before rPPG can be used in all clinical settings. However, through systematic validation against trusted heart rate monitors, transparent presentation of intermediate data processes, and rigorous testing across varied conditions, we are paving the way for rPPG's acceptance. Our challenges are hallmarks of development of smart technology.},

howpublished = {47th Conference on Theoretical and Applied Mechanics (CTAM 2023), Yunlin, Taiwan, Nov. 17-18, 2023},

keywords = {Non-contact HR Monitoring; rPPG Methods; Reliability in Healthcare Technology; Smart Machines; Cognitive Computing; Data Collection Challenges},

pubstate = {published},

tppubtype = {misc}

}