Methodology Proposal of EMG Hand Movement Classification Based on Cross Recurrence Plots

Efficient strategies for finger movement classification using surface electromyogram signals

One of the famous research areas in biomedical engineering and pattern recognition is finger movement classification. For hand and finger gesture recognition, the most widely used signals are the surface electromyogram (sEMG) signals. With the help of sEMG signals, four proposed techniques of finger movement classification are presented in this work. The first technique proposed is a dynamic graph construction and graph entropy-based classification of sEMG signals. The second technique proposed encompasses the ideas of dimensionality reduction utilizing local tangent space alignment (LTSA) and local linear co-ordination (LLC) with evolutionary algorithms (EA), Bayesian belief networks (BBN), extreme learning machines (ELM), and a hybrid model called EA-BBN-ELM was developed for the classification of sEMG signals. The third technique proposed utilizes the ideas of differential entropy (DE), higher-order fuzzy cognitive maps (HFCM), empirical wavelet transformation (EWT), and another hybrid model with DE-FCM-EWT and machine learning classifiers was developed for the classification of sEMG signals. The fourth technique proposed uses the ideas of local mean decomposition (LMD) and fuzzy C-means clustering along with a combined kernel least squares support vector machine (LS-SVM) classifier. The best classification accuracy results (of 98.5%) were obtained using the LMD-fuzzy C-means clustering technique classified with a combined kernel LS-SVM model. The second-best classification accuracy (of 98.21%) was obtained using the DE-FCM-EWT hybrid model with SVM classifier. The third best classification accuracy (of 97.57%) was obtained using the LTSA-based EA-BBN-ELM model.

Studying the functional connectivity of the primary motor cortex with the binarized cross recurrence plot: The influence of Parkinson's disease

Two new recurrence plot methods (the binary recurrence plot and binary cross recurrence plot) were introduced here to study the long-term dynamic of the primary motor cortex and its interaction with the primary somatosensory cortex, the anterior motor thalamus of the basal ganglia motor loop and the precuneous nucleus of the default mode network. These recurrence plot methods: 1. identify short-term transient interactions; 2. identify long-lasting delayed interactions that are common in complex systems; 3. work with non-stationary blood oxygen level dependent (BOLD) data; 4. may study the relationship of centers with non-linear functional interactions; 5 may compare different experimental groups performing different tasks. These methods were applied to BOLD time-series obtained in 20 control subjects and 20 Parkinson´s patients during the execution of motor activity and body posture tasks (task-block design). The binary recurrence plot showed the task-block BOLD response normally observed in the primary motor cortex with functional magnetic resonance imaging methods, but also shorter and longer BOLD-fluctuations than the task-block and which provided information about the long-term dynamic of this center. The binary cross recurrence plot showed short-lasting and long-lasting functional interactions between the primary motor cortex and the primary somatosensory cortex, anterior motor thalamus and precuneous nucleus, interactions which changed with the resting and motor tasks. Most of the interactions found in healthy controls were disrupted in Parkinson's patients, and may be at the basis of some of the motor disorders and side-effects of dopaminergic drugs commonly observed in these patients.