Assessing the attention levels of students by using a novel attention aware system based on brainwave signals

摘要: Rapid progress in information and communication technologies ( ICTs) has fueled the popularity of e-learning. However, an e-learning environment is limited that online instructors cannot monitor immediately whether students remain focus during autonomous learning. Therefore, this study tries to develop a novel attention aware system AAS) capable recognizing students' levels accurately based on electroencephalography EEG) signals, thus having high potential be applied providing timely alert for conveying low-attention level feedback environment. To construct AAS, responses their corresponding EEG signals are gathered continuous performance test CPT), ie, assessment test. Next, AAS constructed by using training testing data Neuro Sky brainwave detector support vector machine SVM), well-known learning model. Additionally, discrete wavelet transform DWT), collected decomposed into five primary bands (ie, alpha, beta, gamma, theta, delta). Each band contains statistical parameters (including approximate entropy, total variation, energy, skewness, standard deviation), generating 25 features associated with constructing AAS. An attempt genetic algorithm GA) also made enhance prediction proposed terms identifying levels. According GA, seven most influential selected from considered features; optimized. Analytical results indicate can recognize individual student's state as either or low level, average accuracy rate reaches 89.52%. Moreover, integrated video lecture tagging examine detect periods while about electrical safety workplace via lecture. Four experiments designed assess high- processes. identify generated when engaging activity Meanwhile, some degree even engage random disturbances. Furthermore, strong negative correlations found between posttest score progressive score) identified Results demonstrate effective, assisting evaluating performance. [ABSTRACT FROM AUTHOR]