Research On Learning State Analysis System Based On Distributed EEG Signal

With the continuous improvement of education level,people pay more and more attention to the management of the learning process.The teacher-centered education method is gradually replaced by the student-centered education concept.Mastering the individualized learning characteristics of students and teaching students according to their aptitude are the key directions of school education reform.With the rapid development of information technology,it is possible to intelligently analyze the learning status of students in the teaching environment.That is,the computer analyzes the current learning status by acquiring students 'visual,auditory,or physiological signals,etc.,so that teachers can obtain comprehensive and timely access Each student's learning status information.In many ways,the analysis of students' learning status through EEG signals is an advanced and objective new method.At present,the collection of EEG signals is still in the form of one-to-one,which is not suitable for multi-person collaborative learning scenarios.Therefore,this paper proposes a distributed EEG signal collection scheme that can collect EEG signals of multiple people at the same time and summarize them wirelessly;in data collection,the previous brain-computer interface devices are usually 32-pole or 64-pole devices,which is complicated The acquisition equipment interferes greatly with student learning,and the obtained data cannot truly reflect the learning state of the student;in the feature extraction,the EEG device selected by this system can extract brain wave energy.If the brain wave energy can be used to analyze the student learning state,Will greatly reduce the complexity of the system.In order to reduce the interference of the acquisition equipment on the analysis of the student's learning status and the complexity of the system,this paper uses the data collected by the single channel of the forehead and the multi-channel collected data and the brain wave energy as the eigenvalues in the DEAP data set to accurately analyze the emotion model Comparison of degrees,established the feasibility of using the forehead singlechannel data collection and the use of brain wave energy as a feature value.Through analyzing and studying the learning state,it is found that the learning state is closely related to interest,pleasure,and concentration,so it is improved on the basis of the existing sentiment analysis model,and a three-dimensional learning state evaluation model is established.Using analytic hierarchy process to determine the importance of the three for students to form an efficient learning effect,the definition of participation(learning status)is given.Afterwards,machine learning and deep learning algorithms are used to classify the collected data according to the learning state model through feature selection and parameter optimization,and the student's learning state is combined by the three aspects of pleasure,interest,and concentration.Analysis and research.Studies have shown that applying forehead monopolar EEG signals can effectively identify the learning status of learners participating in group learning from three dimensions of interest,pleasure and concentration.