DocumentCode :
2744242
Title :
Towards ubiquitous mobile-computing-based artificial leg control
Author :
Hernandez, Robert ; Kane, Jason ; Fan Zhang ; Xiaorong Zhang ; He Huang
Author_Institution :
Naval Undersea Warfare Center, Newport, RI, USA
fYear :
2015
fDate :
13-16 April 2015
Firstpage :
821
Lastpage :
827
Abstract :
This paper presents a rapid prototype approach for the development of a real-time capable neural-machine-interface (NMI) for control of artificial legs based on mobile processor technology (Intel Atom™ Z530 Processor.) By effectively exploiting the architectural features of a mobile embedded CPU, we implemented a decision-making algorithm, based on neuromuscular-mechanical fusion and gait phase-dependent support vector machines (SVM) classification to meet the demanding performance constraints. To demonstrate the feasibility of a real-time mobile computing based NMI, real-time experiments were performed on an able bodied subject with window increments of 50ms. The experiments showed that the mobile computing based NMI provided fast and accurate classifications of four major human locomotion tasks (level-ground walking, stair ascent, stair descent, and standing) and a 46X speedup over an equivalent MATLAB implementation. The testing yielded accuracies of 96.31% with low power consumption. An offline analysis showed the accuracy could be increased to 98.87% with minor modifications to the application.
Keywords :
artificial limbs; legged locomotion; medical computing; mobile computing; neuromuscular stimulation; support vector machines; SVM classification; artificial leg control; decision-making algorithm; gait phase-dependent support vector machine; human locomotion task; mobile embedded CPU; mobile processor technology; mobile-computing; neural-machine-interface; neuromuscular-mechanical fusion; rapid prototype approach; ubiquitous computing; Accuracy; Data acquisition; MATLAB; Mobile communication; Real-time systems; Support vector machines; leg control; mobile CPU; neural machine interface; support vector machines;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Systems Conference (SysCon), 2015 9th Annual IEEE International
Conference_Location :
Vancouver, BC
Type :
conf
DOI :
10.1109/SYSCON.2015.7116852
Filename :
7116852
Link To Document :
بازگشت