Camera control with EMG signals using Principal Component Analysis and support vector machines

The main goal of Human Computer Interface (HCI) is to improve the interactions between users and computers by making computers more usable and receptive to the user's needs. Accordingly, surveillance is one of the major areas where human computer interface is critical. Surveillance cameras are usually controlled with joysticks. For this reason, it is almost impossible to be controlled by an amputee with no finger functionality. In this paper, the Fast Fourier Transform (FFT) analysis was applied to raw EMG data and then features are extracted with Principal Component Analysis (PCA) and Simple Principal Component Analysis (SPCA). In the proposed system, in order to make a decision whether the wrist is moving right, left, up, down or neutral, multi-class Support Vector Machine is employed. Additionally to Electromyography (EMG) signals, standard datasets that involves Electroencephalography (EEG) signals is also tested with multi-class SVM to verify the system robustness. Finally, classified EMG decisions are received by the camera as movement comments. Successful operation of camera employing EMG signals has been accomplished with 81% accuracy with SPCA.

[1]  Xiaoying Tai,et al.  Long-term relevance feedback using simple PCA and linear transformation , 2002, Proceedings. 13th International Workshop on Database and Expert Systems Applications.

[2]  Kazuyo Tanaka,et al.  A myoelectric interface for robotic hand control using support vector machine , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[4]  C. D. De Luca.  Physiology and Mathematics of Myoelectric Signals , 1979, IEEE Transactions on Biomedical Engineering.

[5]  Andrzej P. Dobrowolski,et al.  Spectral Analysis of Motor Unit Action Potentials , 2007, IEEE Transactions on Biomedical Engineering.

[6]  H. Piroska,et al.  Specific Movement Detection in EEG Signal Using Time-Frequency Analysis , 2008, 2008 First International Conference on Complexity and Intelligence of the Artificial and Natural Complex Systems. Medical Applications of the Complex Systems. Biomedical Computing.

[7]  Minoru Fukumi,et al.  Wrist Motion Pattern Recognition System by EMG Signals , 2005, KES.

[8]  Carlo J. De Luca,et al.  Physiology and Mathematics of Myoelectric Signals , 1979 .

[9]  Yasue Mitsukura,et al.  Hybrid EMG Recognition System by MDA and PCA , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[10]  Ferat Sahin,et al.  A study of recent classification algorithms and a novel approach for EEG data classification , 2010, 2010 IEEE International Conference on Systems, Man and Cybernetics.

[11]  Marti A. Hearst.  Trends & Controversies: Support Vector Machines , 1998, IEEE Intell. Syst..

[12]  Marti A. Hearst.  Intelligent Connections: Battling with GA-Joe. , 1998 .

[13]  Fabien Lotte,et al.  The Use of Fuzzy Inference Systems for Classification in EEG-based Brain-Computer Interfaces , 2006 .

[14]  Andreas Daffertshofer,et al.  PCA in studying coordination and variability: a tutorial. , 2004, Clinical biomechanics.

[15]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

[16]  Rafael A. Calvo,et al.  Fast Dimensionality Reduction and Simple PCA , 1998, Intell. Data Anal..

[17]  Guanglin Li,et al.  Principal Components Analysis Preprocessing for Improved Classification Accuracies in Pattern-Recognition-Based Myoelectric Control , 2009, IEEE Transactions on Biomedical Engineering.

[18]  Anatole Lécuyer,et al.  Classifying EEG for brain computer interfaces using Gaussian processes , 2008, Pattern Recognit. Lett..

[19]  Sabri Koçer,et al.  Classification of EMG Signals Using PCA and FFT , 2005, Journal of Medical Systems.