A Simulated Controller Based on Fuzzy Logic for Wheelchair Control Using Head and Neck Movements Detected by Polymer Optical Fiber and Inertial Movement Unit

This work shows a simulated fuzzy logic controller used for wheelchair control based on head and neck movements detected by Polymer Optical Fiber (POF) and Inertial Movement Unit (IMU). The first controller uses as input signals from head movements detected by an Inertial Measurement Unit (IMU), and the second controller uses input neck movements detected by a Polymer Optical Fiber (POF) pressure line sensor. The accuracy attained by the classification system to detect head and neck movements was 99.52% using a Common Average Reference (CAR) filter who minimizes uncorrelated sources of signal and noise through averaging, while eliminating sources of noise common to all sites, and a Support Vector Machine (SVM) to classify body postures. The best accuracy using cross-validation was 99.16% using a k-Nearest Neighbor (kNN) algorithm. Future works are related to the implementation of the controllers, in real-time, in the wheelchair as well as the inclusion of a user’s posture monitoring system. Also, a Graphical User Interface (GUI) to guide the user will be developed.