ANN-based mapping of febrile subjects in mass thermogram screening: facts and myths

Abstract

Severe Acute Respiratory Syndrome (SARS) is a highly infectious disease caused by a coronavirus. Screening to detect potential SARS-infected subjects with elevated body temperature plays an important role in preventing the spread of SARS. Thermography is being used with ANN/AI to analyse the data collected from the designated SARS hospital in Singapore, and conclusive results are drawn. The current work evaluates the correlations (and classifications) between facial skin temperatures, including eye range and forehead, to aural temperature using a neural network (NN) approach, namely training backpropagation (BP) and Kohonen self-organizing map (SOM), to confirm the suitability of thermal imagers for human temperature screening. Both BP and SOM can form an opinion about the type of network that is better able to complement thermogram technology in fever diagnosis. This can produce better parameters for reducing the size of the NN classifier, while maintaining good classification accuracy. We observe that BP performs better than SOM NN. Confusion matrix (CM), an alternative display instrument, is able to process a high volume of input data and show the clustered output rapidly and accurately. The current research application will remain an interesting and useful reference for both local and overseas manufacturers of thermal scanners, users and various government and private establishments. As the elevation of body temperature is a common presenting symptom for many illnesses, including infectious diseases such as SARS, thermal imagers are useful and essential tools for mass screening of body temperature. This is true not only for SARS but also during other public health crises where widespread transmission of infection such as the danger of avian flu pandemic is a concern, in particular at places like hospitals and cross-border checkpoints.