An Iterative Method for Classifying Stroke Subjects’ Motor Imagery EEG Data in the BCI-FES Rehabilitation Training System

Abstract Interpretation of brain activity responses using Motor Imagery (MI) paradigms is vital for medical diagnosis and monitoring. Assessed by machine learning techniques, identification of imagined actions is hindered by substantial intra and inter subject variability. Here, we develop an architecture of Convolutional Neural Networks (CNN) with enhanced interpretation of the spatial brain neural patterns that mainly contribute to the classification of MI tasks. Two methods of 2D-feature extraction from EEG data are contrasted: Power Spectral Density and Continuous Wavelet Transform. For preserving the spatial interpretation of extracting EEG patterns, we project the multi-channel data using a topographic interpolation. Besides, we include a spatial dropping algorithm to remove the learned weights that reflect the localities not engaged with the elicited brain response. Obtained results in a bi-task MI database show that the thresholding strategy in combination with Continuous Wavelet Transform improves the accuracy and enhances the interpretability of CNN architecture, showing that the highest contribution clusters over the sensorimotor cortex with differentiated behavior between μ and β rhythms.

Download Full-text

Pengaruh Latar Belakang Warna pada Objek Gambar terhadap Hasil Ekstraksi Sinyal EEG

IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) ◽

10.22146/ijeis.22893 ◽

2017 ◽

Vol 7 (2) ◽

pp. 161 ◽

Cited By ~ 1

Author(s):

Catur Atmaji ◽

Zandy Yudha Perwira

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Training System ◽

Training Data ◽

Spectrum Estimation ◽

Quality Classification ◽

Eeg Data ◽

Two Systems ◽

Artificial Neural ◽

Color Background

In this study, observation on the differences in features quality of EEG records as a result of training on subjects has been made. The features of EEG records were extracted using two different methods, the root mean square which is acquired from the range between 0.5 and 5 seconds and the average of power spectrum estimation from the frequency range between 20 and 40Hz. All of the data consists of a 4-channel recording and produce good quality classification on artificial neural network, with each of which generates training data accuracy over 90%. However, different results are occured when the trained system is tested on other test data. The test results show that the two systems which are trained using training data with object with color background produce higher accuracy than the other two systems which are trained using training data with object without background color, 63.98% and 60.22% compared to 59.68% and 56.45% accuracy respectively. From the use of the features on the artificial neural network classification system, it can be concluded that the training system using EEG data records derived from the visualization of object with color background produces better features than the visualization of object without color background.

Download Full-text

Clinical Effect of Virtual Reality Technology on Rehabilitation Training of Sports Injury

Journal of Healthcare Engineering ◽

10.1155/2021/1361851 ◽

2021 ◽

Vol 2021 ◽

pp. 1-7

Author(s):

Jing Chen

Keyword(s):

Virtual Reality ◽

Upper Limb ◽

Sports Injury ◽

Training System ◽

Average Score ◽

Virtual Reality Technology ◽

Upper Limb Rehabilitation ◽

Rehabilitation Training ◽

Rehabilitation System ◽

Limb Rehabilitation

In order to make most patients recover most of their limb functions after rehabilitation training, virtual reality technology is an emerging human-computer interaction technology, which uses the computer and the corresponding application software to build the virtual reality environment. Completing the training tasks in the virtual environment attracts the patients to conduct repeated training in the game and task-based training mode and gradually realizes the rehabilitation training goals. For the rehabilitation population with certain exercise ability, the kinematics of human upper limbs is mainly analyzed, and the virtual reality system based on HTC VIVE is developed. The feasibility and work efficiency of the upper limb rehabilitation training system were verified by experiments. Adult volunteers who are healthy and need rehabilitation training to participate in the experiment were recruited, and experimental data were recorded. The virtual reality upper limb rehabilitation system was a questionnaire. By extracting the motion data, the system application effect is analyzed and evaluated by the simulation diagram. Follow-up results of rehabilitation training showed that the average score of healthy subjects was more than 4 points and 3.8 points per question. Therefore, it is feasible to perform upper limb rehabilitation training using the HTC VIVE virtual reality rehabilitation system.

Download Full-text