Wearable sensors are increasingly used to monitor and quantify physical activity types and levels in a real-life environment. In this project we studied the activity classification in manual wheelchair users using wearable sensors. Twenty-seven subjects performed a series of representative activities of daily living in a semi-structured setting with a wheelchair propulsion monitoring device (WPMD) attached to their upper limb and their wheelchair. The WPMD included a wheel rotation datalogger that collected wheelchair movements and an eWatch that collected tri-axial acceleration on the wrist. Features were extracted from the sensors and fed into four machine learning algorithms to classify the activities into three and four categories. The results indicated that these algorithms were able to classify these activities into three categories including self propulsion, external pushing, and sedentary activity with an accuracy of 89.4-91.9%.

We have developed an intelligent single switch scanning interface and wheelchair navigation assistance system, called ISSWN, to improve driving safety, comfort, and efficiency for individuals who rely on single switch scanning as a control method. ISSWN combines a standard powered wheelchair with a laser rangefinder, a single switch scanning interface and a computer. It provides the user with context sensitive and task specific scanning options that reduce driving effort, based on an interpretation of sensor data together with user input. Trials performed by 9 able-bodied participants showed that the system significantly improved driving safety and efficiency in a navigation task.