<![CDATA[The purpose of this study is to examine the Convolutional Neural Network (CNN) model for classifying the age groups of hospital visits, both children and adults. Hospitals serve as treatment facilities for a variety of ailments caused by viruses, germs, car accidents, and other factors. Children are not permitted to visit the hospital due to hurdles to patient comfort as well as hazards associated with immunity and trauma to children. As a result, a digital strategy is required to monitor the presence of youngsters in the hospital setting. The notion of computer vision and the Convolutional Neural Network (CNN) are employed in this study to attain this goal. The dataset utilized is All-Age-Faces (AAF), which includes photos of human faces ranging in age from 2 to 80 years. To categorize visitors into children or adults, two CNN architectures, ResNet and SqueezeNet, are used with fine-tuning (FT) and full retraining (FR) approaches. The accuracy of FR-ResNet was 97.22%, beating the accuracy of the previous research FT-SqueezeNet, which was 93.09%, better to 4.13%. This study confirmed that the use of CNN, namely the FR-ResNet technique, was effective in accurately categorizing the age of hospital visits. Controlling children's access to hospital areas can help reduce the danger of illness transmission.]]>
Copyrights © 2024
