Electroencephalogram-Based Attention Level Classification Using Convolution Attention Memory Neural Network

Abstract

Attentive learning is an important feature of the learning process. It provides a beneficial learning experience and plays a key role in generating positive learning outcomes. Most studies widely applied electroencephalogram (EEG) to measure human attention level. Although most studies use EEG handcrafted features and statistical methods to classify attention level, a more effective feature learning technique is still needed. In this paper, we aim to analyze participants' EEG signals through a deep learning model and classify those signals as showing either attentive or inattentive behaviors. To carry out this research, we initially conducted a background study on attention and its detection in EEG. After that, we design a Troxler's fading experiment and use an EEG device to collect data on participants' attentive and inattentive behaviors during the test. The collected EEG data will be analyzed using a Convolution Attention Memory Neural Network (CAMNN) model to classify participants' attention level. The proposed CAMNN model is optimized with Vector-to-Vector (Vec2Vec) modeling, where the model can be learned through deep neural networks in an end-to-end approach. The result shows that our model can achieve 92% accuracy and 0.92 F1 score which outperforms several existing neural network models such as Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Convolutional Neural Network (CNN), Deep Learning with Convolutional Neural Networks (deep ConvNets), and Compact Convolutional Network for EEG-based BCIs (EEGNet). This research can be useful for those who are interested in developing attention level monitoring or biofeedback system in areas such as educational classroom learning, medical research, and industrial operator.

A deep learning approach to detect the electroencephalogram-based cognitive task states

“…Different approaches like SVM, K-nearest neighbour (KNN), and neuro-fuzzy have been utilized for classification purposes, and the authors found the maximum accuracy with the SVM classifier of 96.70%. Toa et al [69] proposed a method to detect the attention level, i.e., whether the subject is attentive or inattentive. The proposed convolution attention memory network (CAMNN) model outperforms to the previously used method with an accuracy of 92%.…”

Identification of Students’ Confusion in Classes from EEG Signals using Convolution Neural Network

“…It was observed that the classification accuracy was 73.3% and the gamma 1 wave can be used to identify the confusion [23]. A deep learning approach can also be implemented on EEG signals to find out the attention level of a student [33]. Thus, the survey concludes that the traditional machine learning, deep learning and spiking neural network analysed and classified the EEG signals for extracting specific patterns [27,28].…”

Deep residual learning with attention mechanism for breast cancer classification

“…Recently, the deep learning-based system is suggested by a researcher on the application such as lung cancer (K.-L. , (Kumar et al, 2015), breast cancer classification (D. Wang et al, 2016), (Fung Fung Ting et al, 2019), cognitive classification (Toa et al, 2021), Alzheimer's disease (AD) (Ji et al, 2019), (Suk et al, 2014), and even pain quantification (Elsayed et al, 2020). Moreover, recent studies mention that deeply learned features can provide a more effective feature learning technique for image classification compared to handcrafted features (Toa et al, 2021), (Arevalo et al, 2016). A. Cruz-Roa et al provide automatic detection of IDC in WSI using CNN.…”