ABSTRACT
The most severe physical impairment in children is caused by cerebral palsy, a frequent disorder that impairs movement. Early diagnosis and early intervention increase the likelihood of a full recovery but is also crucial better therapy in general. Children with cerebral palsy are prone to being misjudged when assessed with Habitual Physical Activity (HPA) levels, a trait in common with children with mobility challenges. Motion sensors based on accelerometers are now the benchmark for accurately measuring physical activity in children and adolescents. This chapter uses classical machine learning algorithms to predict cerebral palsy from visual impairment and evaluates them individually as well as comparing them.
