|
|
|
| A Two-Stage Support Vector Machine Algorithm Based on Meta Learning and Stacking Generalization |
| ZHU Min, LI Xue-Ling, LI Xiao-Lai, GE Yun-Jian |
| Robot Sensor and Human-Machine Interaction Laboratory,Institute of Intelligent Machines,Chinese Academy of Sciences,Hefei 230031 |
|
|
|
|
Abstract A Two-Stage Support Vector Machine Algorithm (TSSVM) is proposed to improve the recognition accuracy of the surface electromyography (SEMG). The proposed algorithm is integrated with parallel method of meta-learning and the stacking idea of ensemble learning. In this algorithm, the basic classifiers are paralleled and distributed on the first stage and the outputs of the first-stage Support Vector Machine (SVM) are input into the second-stage SVM to integrate multi-source features and output the classification result. And then the proposed algorithm is used on test data set of the SEMG from human upper limb. The signals of SEMGs from individual muscles are respectively input into the first-stage SVMs. And the output of the first-stage SVMs is input into the second-stage SVM combiner to integrate and recognize the electromyographic signal features of individual muscle. Results show that TSSVM is superior to single SVM in classification accuracy. Moreover, TSSVM outperforms other state-of-art ensemble classifiers, such as random forest and rotation forest in classification accuracy, time cost and robustness.
|
|
Received: 26 October 2011
|
|
|
|
|
|
[1] Naito J,Obinata G,Nakayama A,et al.Development of a Wearable Robot for Assisting Carpentry Workers.International Journal of Advanced Robotic Systems,2007,4(4): 431-436
[2] Fleischer C,Wege A,Kondak K,et al.Application of EMG Signals for Controlling Exoskeleton Robots.Biomedical Engineering/Biomedizinische Technik,2006,51(5/6): 314-319
[3] Khadivi A,Nazarpour K,Zadeh H S.SEMG Classification for Upper-Limb Prosthesis Control Using Higher Order Statistics // Proc of the IEEE International Conference on Acoustics,Speech and Signal Processing.Philadelphia,USA,2005: 385-388
[4] Joyce C Z,Wang J,McKeown M J.A Windowed Eigenspectrum Method for Multivariate sEMG Classification during Reaching Movements.IEEE Signal Processing Letters,2008,15: 293-296
[5] Khokhar Z O,Xiao Z G,Menon C.Surface EMG Pattern Recognition for Real-Time Control of a Wrist Exoskeleton.Biomedical Engineering Online,2010,9: 41
[6] Schapire R E.The Strength of Weak Learnability.Machine Learning,1990,5(2): 197-227
[7] Valentini G,Masulli R.Ensembles of Learning Machines [EB/OL].[2011-10-01].http://machine-learning.martinsewell.com/ensembles/ValentiniMasulli2002.pdf
[8] Breiman L.Bagging Predictors.Machine Learning,1996,24(2): 123-140
[9] Li Xueling,Zhu Min,Li Xiaolai,et al.Protein-Protein Binding Affinity Prediction Based on an SVR Ensemble // Proc of the 8th International Conference on Intelligent Computing Technology.Huangshan,China,2012,I: 145-151
[10] Breiman L.Random Forests.Machine Learning,2001,45(1): 5-32
[11] Rodriguez J J,Kuncheva L I.Rotation Forest: A New Classifier Ensemble Method.IEEE Trans on Pattern Analysis and Machine Intelligence,2006,28(10): 1619-1630
[12] Wolpert D H.Stacked Generalization.Neural Networks,1992,5(2): 241-259
[13] Vilalta R,Drissi Y.A Perspective View and Survey of Meta-Learning.Artificial Intelligence Review,2002,18(2): 77-95
[14] Li Xueling,Zhu Min,Li Xiaolai,et al.Protein-Protein Interaction Affinity Prediction Based on Interface Descriptors and Machine Learning // Proc of the 8th International Conference on Intelligent Computing Technology.Huangshan,China,2012,II: 205-212 |
|
|
|
2012, Vol. 25 
