A New Mixed Clustering-Based Method to Analyze the Gait of Children with Cerebral Palsy

Cerebral palsy is a group of persistent central movement and posturaldevelopmental disorders, and restricted activity syndromes. This syndrome iscaused by non-progressive brain damage to the developing fetus or infants. Cerebralpalsy assessment can determine whether the brain is behind or abnormal. If itexists, early intervention and rehabilitation can be carried out as soon as possibleto restore brain function to the greatest extent. The direct external manifestation ofcerebral palsy is abnormal gait. Accurately determining the muscle strengthrelatedreasons that cause this abnormal gait is the primary problem for treatment.In this paper, clustering methods were used to compare and analyze the differencesbetween the abnormal and normal gait parameters of children with andwithout cerebral palsy. Since the collected data contains overlapping data thatmay be mutated, while the centroids are also different, the expected result is stratified.To solve this problem, a mixed clustering method is proposed that combinesthe advantages of K-means and hierarchical clustering, meaning that eachset of data shows a similar trend to specific parameters. Experiment results showthat this method can detect cerebral palsy through the difference between theabnormal gait of children with cerebral palsy and that of normal children.