Motion Function Clinic System Of Cerebral Palsy Based On ANN

A medical expert system (MES) attempts to simulate the thoughts and the clinic processes of medical experts when making medical diagnose based on the principles and methodologies developed in the fields of artificial intelligence (AI) and expert system, and it can help doctors solve complicate medical problems and as an important assistant tool of diagnosis, therapy and prognosis. Medical expert system is a application of AI in the field of medicine. It is close connection between knowledge engineering and medical science. It is also a crossing of medicine and computer technique, network technique,communications technique and database technique and so on. it has become a significant component of modern medical science.Cerebral palsy (CP) is a kind of syndrome caused by an injury to the brain before,during, or shortly after birth. Children with CP have a lot of Parallel obstacles. At present, the incidence of cerebral palsy in children is 1.4-1.5‰, and main symptoms of cerebral palsy is motion dysfunction. To children with cerebral palsy, assessment of efficacy lacks of uniformity, mainly relying on the experience of the experts, This resulted that fuzzy is increased in the diagnosis and treatment, helpness to the rehabilitation of children.In the paper, children CP is deeply analyzed. building body model, human motion information is detected by motion attitude detection system. Then overall system architecture of CP motion function clinic system is established based on ANN. Reseaching mechanisms and methods to achieve. Analyisis of the clinics focus on the function of the system needs and main function modules Implementation and Neural network design for the system and the diagnosis process . Motion attitude dataes are achieved by motion detection hardware system. by neural network training, it can achieve nonlinear mapping from signs data to signs evaluation. So evaluates motion function to CP children. The result is good by simulation.The paper analyzes detaily body motion methods and builds motion attitude models and three degrees of freedom of human limb. It deduces detaily angel formulaes. Based on buiding body model, reseaching human body motion simulation technology. And implementation of CP children body motion function clinic system based on ANN. By using CP children motion dataes training neural network, it can achieve nonlinear mapping from signs data to signs evaluation. The module of this system in simulated example adopts a three-layer BP net structure. On algorithm, this paper used the gradient iteration method, constantly correct the weight value. After iteration 10 thousand times, the precision of study (the total error of this system) is E=0.001.