Although different physiological signals, such as electrooculography (EOG) have been widely used in the control of assistance systems for people with disabilities, customizing the signal classification system remains a challenge. In most interfaces, the user must adapt to the classification parameters, although ideally the systems must adapt to the user parameters. Therefore, in this work the use of a multilayer neural network (MNN) to model the EOG signal as a mathematical function is presented, which is optimized using genetic algorithms, in order to obtain the maximum and minimum amplitude threshold of the EOG signal of each person to calibrate the designed interface. The problem of the variation of the voltage threshold of the physiological signals is addressed by means of an intelligent calibration performed every 3 min; if an assistance system is not calibrated, it loses functionality. Artificial intelligence techniques, such as machine learning and fuzzy logic are used for classification of the EOG signal, but they need calibration parameters that are obtained through databases generated through prior user training, depending on the effectiveness of the algorithm, the learning curve, and the response time of the system. In this work, by optimizing the parameters of the EOG signal, the classification is customized and the domain time of the system is reduced without the need for a database and the training time of the user is minimized, significantly reducing the time of the learning curve. The results are implemented in an HMI for the generation of points in a Cartesian space (X, Y , Z) in order to control a manipulator robot that follows a desired trajectory by means of the movement of the user's eyeball.
The work carried out in this paper consists of the classification of the physiological signal generated by eye movement called Electrooculography (EOG). The human eye performs simultaneous movements, when focusing on an object, generating a potential change in origin between the retinal epithelium and the cornea and modeling the eyeball as a dipole with a positive and negative hemisphere. Supervised learning algorithms were implemented to classify five eye movements; left, right, down, up and blink. Wavelet Transform was used to obtain information in the frequency domain characterizing the EOG signal with a bandwidth of 0.5 to 50 Hz; training results were obtained with the implementation of K-Nearest Neighbor (KNN) 69.4%, a Support Vector Machine (SVM) of 76.9% and Decision Tree (DT) 60.5%, checking the accuracy through the Jaccard index and other metrics such as the confusion matrix and ROC (Receiver Operating Characteristic) curve. As a result, the best classifier for this application was the SVM with Jaccard Index.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.