Adaptive machine learning algorithm employed statistical signal processing for classification of ECG signal and myoelect
- PDF / 1,566,864 Bytes
- 18 Pages / 439.37 x 666.142 pts Page_size
- 2 Downloads / 188 Views
Adaptive machine learning algorithm employed statistical signal processing for classification of ECG signal and myoelectric signal Pandia Rajan Jeyaraj1
· Edward Rajan Samuel Nadar1
Received: 17 September 2019 / Revised: 8 February 2020 / Accepted: 12 February 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In this research paper we present designing and evaluating the electrocardiography (ECG) and Myoelectric signal (EMG) pattern recognition methods based on the adaptive machine learning. For this theoretical model to describe how the Boundary Misclassification Risk (BMR) changes along parameters including, the adaptive learning times, the adaptive learning frequencies, the generalization ability of the predictive model, and the ratio of samples without supervised information during the adaptive learning were proposed. The models are built up based on the formulated adaptive learning process of the myoelectric signal recognition, and the classification from the measured electrocardiogram (ECG) pattern. The theoretical model can be regarded as the extensions of current statistical learning theory and domain adaption theory. In the experiment, the maximum error rate (MER), and the average error rate (AER) of the RCS is employed as the approximation of the BMR. During the experiment, MER and AER change tendency matches the theoretical BMR change tendency. For different learning time interval AER is presented, from the result tendency match with the experimental and theoretical evaluated value is confirmed. Hence, the proposed theoretical model can be used for ECG and EMG pattern matching. Keywords Machine learning techniques · Statistical signal processing · Classification · Pattern recognition · Feature extraction
1 Introduction Myoelectric control based on pattern recognition (PR) has been widely used to improve the perception and the functionality of the expert prosthetic hand (Cao et al. 2016). However, the pattern recognition based myoelectric control suffers from long-term performance
B
Pandia Rajan Jeyaraj [email protected] Edward Rajan Samuel Nadar [email protected]
1
Department of Electrical and Electronics Engineering, Mepco Schlenk Engineering College, Sivakasi, India
123
Multidimensional Systems and Signal Processing
degradation, because of confounding factors such as temperature and humidity changes, skin impedance variation, muscular fatigue, electrode shifting and limb position changes (Jie et al. 2018). The long-term performance degradation hinders the PR-based myoelectric control in its clinical application and the commercialization (Kobayashi 2013). From the aspect of machine learning, the Electromyography (EMG) features that changes over time lead to the concept drift, which refers to the change of the relation between the input data and the target variable. In order to track the concept drift and reduce the performance degradation of myoelectric control, the adaptive learning methods are widely adopted in the PR-based myoelectric control
Data Loading...
