Effectiveness of Using Artificial Intelligence for Early Child Development Screening

This study presents a novel approach to recognizing emotions in infants using machine learning models. To address the lack of infant-specific datasets, custom dataset infants' faces was created by extracting images from AffectNet dataset. The then used train various models with different parameters. best-performing model evaluated on City Infant Faces proposed deep achieved an accuracy 94.63% positive, negative, and neutral facial expressions. These results provide benchmark for performance infant emotion recognition suggest potential applications developing emotion-sensitive technologies infants. fills gap literature recognition, which has largely focused adults or children highlights importance datasets evaluating parameters achieve accurate results.