Pattern recognition of single and combined motions from the shoulder complex

Much research has been done towards developing control systems for artificial hands, elbows, and wrists based on the myoelectric signal (MES). While great effort has gone into developing pattern recognition based control systems for these devices, very little attention has been devoted to the shoulder. This is in part because the majority of amputees are either below elbow or mid-humeral, and true shoulder disarticulations are rare. However, as the level of limb loss increases so does the need for functional replacement. This study investigates pattern recognition concepts for independent control of an artificial shoulder.