Fever Detection with Infrared Thermography: Enhancing Accuracy through Machine Learning Techniques

Parsa Razmara, Tina Khezresmaeilzadeh, B. Keith Jenkins

Keywords: COVID-19, Infrared Sensors, Temperature Measurement, Infrared Thermography, Machine Learning, Regression analysis, Deep Learning

TL;DR: Integrating machine learning with infrared thermography, this paper enhances non-contact temperature measurement accuracy for fever detection. Heuristic feature engineering and regression models improve predictive accuracy for early COVID detection.

Abstract: The COVID-19 pandemic has underscored the necessity for advanced diagnostic tools in global health systems. Infrared Thermography (IRT) has proven to be a crucial non-contact method for measuring body temperature, vital for identifying febrile conditions associated with infectious diseases like COVID-19. Traditional non-contact infrared thermometers (NCITs) often exhibit significant variability in readings. To address this, we integrated machine learning algorithms with IRT to enhance the accuracy and reliability of temperature measurements. Our study systematically evaluated various regression models using heuristic feature engineering techniques, focusing on features' physiological relevance and statistical significance. The Convolutional Neural Network (CNN) model, utilizing these techniques, achieved the lowest RMSE of 0.2223, demonstrating superior performance compared to results reported in previous literature. Among non-neural network models, the Binning method achieved the best performance with an RMSE of 0.2296. Our findings highlight the potential of combining advanced feature engineering with machine learning to improve diagnostic tools' effectiveness, with implications extending to other non-contact or remote sensing biomedical applications. This paper offers a comprehensive analysis of these methodologies, providing a foundation for future research in the field of non-invasive medical diagnostics.

Track: 3. AI for combating long COVID

Registration Id: RTN6RRBYJCF

Submission Number: 105