Exploiting accelerometers to improve movement classification for prosthetics

Recent studies have explored the integration of additional input modalities to improve myoelectric control of prostheses. Arm dynamics in particular are an interesting option, as these can be measured easily by means of accelerometers. In this work, the benefit of accelerometer signals is demonstrated on a large scale movement classification task, consisting of 40 hand and wrist movements obtained from 20 subjects. The results demonstrate that the accelerometer modality is indeed highly informative and even outperforms surface electromyography in terms of classification accuracy. The highest accuracy, however, is obtained when both modalities are integrated in a multi-modal classifier.

[1]  Manfredo Atzori,et al.  Building the Ninapro database: A resource for the biorobotics community , 2012, 2012 4th IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob).

[2]  Sebastian Nowozin,et al.  On feature combination for multiclass object classification , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[3]  Kongqiao Wang,et al.  A Framework for Hand Gesture Recognition Based on Accelerometer and EMG Sensors , 2011, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[4]  Johannes Wagner,et al.  Bi-channel sensor fusion for automatic sign language recognition , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[5]  David P. Allen,et al.  A frequency domain Hampel filter for blind rejection of sinusoidal interference from electromyograms , 2009, Journal of Neuroscience Methods.

[6]  Andreas Keil,et al.  Relation of Accelerometer and EMG Recordings for the Measurement of Upper , 1999 .

[7]  Marie-Françoise Lucas,et al.  Multi-channel surface EMG classification using support vector machines and signal-based wavelet optimization , 2008, Biomed. Signal Process. Control..

[8]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[9]  Kevin B. Englehart,et al.  A robust, real-time control scheme for multifunction myoelectric control , 2003, IEEE Transactions on Biomedical Engineering.

[10]  J. Rafiee,et al.  Wavelet basis functions in biomedical signal processing , 2011, Expert Syst. Appl..

[11]  Bruce C. Wheeler,et al.  EMG feature evaluation for movement control of upper extremity prostheses , 1995 .

[12]  Jing Peng,et al.  SVM vs regularized least squares classification , 2004, ICPR 2004.

[13]  Barbara Caputo,et al.  Multi Kernel Learning with Online-Batch Optimization , 2012, J. Mach. Learn. Res..

[14]  C. Castellini,et al.  Using Ultrasound Images of the Forearm to Predict Finger Positions , 2012, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[15]  D Howard,et al.  Dimensional change in muscle as a control signal for powered upper limb prostheses: a pilot study. , 1999, Medical engineering & physics.

[16]  Ilja Kuzborskij,et al.  On the challenge of classifying 52 hand movements from surface electromyography , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[17]  C. K. van der Sluis,et al.  Learning to control opening and closing a myoelectric hand. , 2010, Archives of physical medicine and rehabilitation.

[18]  Siping Chen,et al.  Control of Powered Prosthetic Hand Using Multidimensional Ultrasound Signals: A Pilot Study , 2011, HCI.

[19]  Øyvind Stavdahl,et al.  A multi-modal approach for hand motion classification using surface EMG and accelerometers , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.