DATA STUDY OF SAFE ENTRY STATION (SES) TO ENSURE FIT FOR DUTY
Journal of International Research in Medical and Pharmaceutical Sciences,
We have developed an AI based pipeline to estimate body temperature, respiration rate, SOP (Standard Operating Procedure) violation and heart rate. Moreover we have also developed a plan under the management framework, which includes the collection of datasets from Indonesian university, various corporate events, and hospitals in different geographical areas. The dataset collected from different sources are tested and validated to assess the capabilities of the existing models that we have developed over period and further helps to improve the accuracy level. Our screening platform for infectious disease symptom is a quick, noninvasive, no-contact solution that can detect the first-look indication of symptoms. All it takes is a simple walk-through, followed by standing in front of the camera following SOP guidelines. In a few seconds, our AI powered technology identifies if the subject fit for duty or not. We have used datasets from various events, hospitals, labs to shape and validate our model and have also implemented multi-layer model-based 3D Convolutional Networks to detect heart rate, respiration rate and body temperature. We obtained 98.37%, 98.38% and 85% accuracy for temperature, respiration rate and heart rate respectively. These accuracy values are obtained on our testing dataset obtained from multiple events, hospitals and labs.
- Data study
- safe entry system
How to Cite
Ferrari C, Berlincioni L, Bertini M, Del Bimbo A. Inner eye canthus localization for human body temperature screening. In 2020 25th International Conference on Pattern Recognition (ICPR). IEEE. 2021;8833-8840.
Špetlík R, Franc V, Matas J. Visual heart rate estimation with convolutional neural network. In Proceedings of the british machine vision conference, Newcastle, UK. 2018;3-6.
Niu X, Shan S, Han H, Chen X. Rhythmnet: End-to-end heart rate estimation from face via spatial-temporal representation. IEEE Transactions on Image Processing. 2019);29: 2409-2423.
Chen L, Liu N, Hu M, Zhai G. RGB-thermal imaging system collaborated with marker tracking for remote breathing rate measurement. In 2019 IEEE Visual Communications and Image Processing (VCIP). IEEE. 2019;1-4.
Chen L, Hu M, Liu N, Zhai G, Yang SX. Collaborative use of RGB and thermal imaging for remote breathing rate measurement under realistic conditions. Infrared Physics & Technology. 2020;111:103504.
Kumar AK, Ritam M, Han L, Guo S, Chandra R. Deep learning for predicting respiratory rate from biosignals. Computers in Biology and Medicine. 2022;144:105338.
Husom EJBG, Bernabé P, Sen S. Deep learning to predict power output from respiratory inductive plethysmography data. Applied AI Letters. 2022;3(2):e65.
Abstract View: 417 times
PDF Download: 5 times