INTERACTIVE LEARNING THROUGH TECHNOLOGY: A MACHINE LEARNING-BASED TRAFFIC SIGN RECOGNITION SYSTEM FOR YOUNG LEARNERS

Vocabulary should be presented to young learners in context with the help of real objects that surround them. Helping them get aware of the recognition of traffic signs could reduce accidents. The current study developed a traffic sign recognition system based on Machine Learning through which the ability of young learners to recognize traffic signs would improve, along with their vocabulary acquisition. The developed system, based on the ADDIE model, was piloted and tested in the Interactive Learning Environment among kindergarten and primary school students. Children can scan and name signs of traffic using mobile devices instantly, having some hands-on experience. The results have shown significant development regarding knowledge of road safety, along with the acquisition of traffic vocabulary and long-term retention that considerably outperformed the state of the art. Parents' feedback strengthened the practicality, interactivity, and usability of the system within young learners' education. This research thus provides evidence for machine learning's role in transforming early education and providing an incredibly effective tool for teaching some of life's most important skills. The development that will be done in the future should be geared towards generalizing the system, adding auditory features of pronunciation, and other sections of vocabulary.