Abstract
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.
Highlights
The development of human–machine Interfaces (HMI) has been on the rise due to the incorporation of physiological signals as inputs to the control algorithms
To perform different experiments to validate the operation of the designed HMI system, a graphical interface was developed that allows the operator to visualize the EOG signals of both channels, the movement of a virtual robot that emulates the movements generated by the interaction of the gaze, a graph showing the position in Cartesian coordinates of the data generated by the fuzzy classifier, and a visual feedback of the object to be taken by means of the image acquired by an external camera placed on the end effector
The purpose was to demonstrate that a system that adapts to the user allows a learning curve that requires fewer repetitions and less time to perform a defined task, with the advantage of reducing the training time of a user to become an expert
Summary
The development of human–machine Interfaces (HMI) has been on the rise due to the incorporation of physiological signals as inputs to the control algorithms. Robots are collaborative and interact with humans to improve their quality of life, which has allowed the development of intuitive interfaces for human–robot collaboration, in tasks, such as assistance and robotic rehabilitation. Shared control has HMI Using Neural Network Modeling originated in research fields, such as human–robot co-adaptation, where the two agents can benefit by each other’s skills or must adapt to the other’s behavior, to achieve the execution of effective cooperative tasks. It was considered that the human and individual characteristics affect the execution of the task that the HMI perform; these parameters are highly variable, and it is required to analyze and reduce the effects on the efficiency of the system. The proposed HMI will be implemented in the future to assist people with severe disabilities, where a manipulator robot will be adapted to a wheelchair, so that the user can control the movements of the robot by means of orientation of the gaze with the ability of taking objects and increasing their autonomy
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
