A fuzzy clustering neural network architecture for multifunction upper-limb prosthesis

• Published in: IEEE transactions on biomedical engineering Vol. 50; no. 11; pp. 1255 - 1261
• Main Authors: Karlik, B., Osman Tokhi, M., Alci, M.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.11.2003; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Biological and medical sciences; Computer architecture; Elbow; Electromyography - methods; Equipment Failure Analysis; Fuzzy control; Fuzzy Logic; Fuzzy neural networks; Humans; Joint Prosthesis; Medical sciences; Movement - physiology; Multilayer perceptrons; Muscle Contraction - physiology; Muscle, Skeletal - physiology; Muscle, Skeletal - physiopathology; Muscles; Neural networks; Neural Networks (Computer); Neural prosthesis; Pattern recognition; Pattern Recognition, Automated; Prosthesis Design; Radiotherapy. Instrumental treatment. Physiotherapy. Reeducation. Rehabilitation, orthophony, crenotherapy. Diet therapy and various other treatments (general aspects); Technology. Biomaterials. Equipments. Material. Instrumentation; Upper Extremity - physiology; Upper Extremity - physiopathology; Wrist; upper-limb prosthesis; Fuzzy clustering; myoelectric signal; neural network; Biomedical engineering; pattern recognition
• ISSN: 0018-9294; 1558-2531
• DOI: 10.1109/TBME.2003.818469

Accurate and computationally efficient means of classifying surface myoelectric signals has been the subject of considerable research effort in recent years. The aim of this paper is to classify myoelectric signals using new fuzzy clustering neural network (NN) architectures to control multifunction prostheses. This paper presents a comparative study of the classification accuracy of myoelectric signals using multilayered perceptron NN using back-propagation, conic section function NN, and new fuzzy clustering NNs (FCNNs). The myoelectric signals considered are used in classifying six upper-limb movements: elbow flexion, elbow extension, wrist pronation and wrist supination, grasp, and resting. The results suggest that FCNN can generalize better than other NN algorithms and help the user learn better and faster. This method has the potential of being very efficient in real-time applications.