An automated upper extremity motor skill assessment technique based on vision and machine learning has been developed for the convenience of the assessment. It has the advantage of being able to measure the patient’s motor function using only the RGB camera image of the mobile phone and can be used regardless of the environment. A machine learning-based classifier that extracts and learns features of patient movements using an artificial intelligence-based body tracking system was used, showing accuracy and high reliability comparable to existing studies.                                                                          

  A simple classification algorithm based on a single IMU had been developed for long-term gait for elderly healthy care. The algorithm classifies three major gait activities: leveled walk, ramp walk, and stair walk. The developed system was evaluated to have sufficiently high accuracy within a gait lab and on an outdoor daily-life walking course.