Accuracy to detection timing for assisting repetitive facilitation exercise system using MRCP and SVM

Abstract

This paper presents a feasibility study of a brain–machine interface system to assist repetitive facilitation exercise. Repetitive facilitation exercise is an effective rehabilitation method for patients with hemiplegia. In repetitive facilitation exercise, a therapist stimulates the paralyzed part of the patient while motor commands run along the nerve pathway. However, successful repetitive facilitation exercise is difficult to achieve and even a skilled practitioner cannot detect when a motor command occurs in patient’s brain. We proposed a brain–machine interface system for automatically detecting motor commands and stimulating the paralyzed part of a patient. To determine motor commands from patient electroencephalogram (EEG) data, we measured the movement-related cortical potential (MRCP) and constructed a support vector machine system. In this paper, we validated the prediction timing of the system at the highest accuracy by the system using EEG and MRCP. In the experiments, we measured the EEG when the participant bent their elbow when prompted to do so. We analyzed the EEG data using a cross-validation method. We found that the average accuracy was 72.9% and the highest at the prediction timing 280 ms. We conclude that 280 ms is the most suitable to predict the judgment that a patient intends to exercise or not.

Identification of an early diagnostic biomarker of lung adenocarcinoma based on co-expression similarity and construction of a diagnostic model

“…Actually, as the SVM performs better in the binary classification, we combined stage I and stage II as the early benign group, while stage III and stage IV as the advanced malignant group. To distinguish patients belonging to benign and malignant groups using risk-related genes as features, we utilized the supervised classifier support vector machine (SVM) to train a diagnostic model [ 22 ]. Default parameters were used to initialize the model, including the RBF nonlinear kernel function, gamma of 0 and so on.…”

Brain activation measurement for motion gain decision of surgical endoscope manipulation

“…Although fNIRS was inferior to EEG in terms of temporal resolution, it was sufficient to measure the brain activity during the surgical tasks because we focussed on the changes in brain activation over a relatively long time period. If we develop a system that operates according to the participant's movement in real time, the system would not operate without EEG 36 . However, in this study, we use fNIRS because the brain activity was analysed offline.…”

“…If we develop a system that operates according to the participant's movement in real time, the system would not operate without EEG. 36 However, in this study, we use fNIRS because the brain activity was analysed offline. Furthermore, because the brain activity was measured during repetitive tasks, it did not change significantly over time.…”