The rapid advancement in information and communication technology has made e‐learning an alternative learning method for many learners. In the last few years, a huge number of learners around the world have registered in massive open online courses (MOOCs) provided by various online learning platforms. However, MOOC platforms have a vital task for the online course provider to provide enhanced students' learning experiences and satisfaction. In this work, we developed a brain–computer interface for gathering data and detecting a learner's mental situation by observing MOOC videos and electroencephalogram (EEG) devices based on John Sweller's Cognitive Load Theory. The acquired EEG signals are preprocessed with two different normalization methods to scale signals. To validate the introduced framework, the system adopted three machine learning algorithms (random forest using non‐Markovian model, support vector machine, and k‐nearest neighbors) to develop a model with preprocessed training data and test the classifiers to validate their ensemble classifiers' performance. Finally, experimental analysis showed that the random forest classifier with the non‐Markovian approach achieved more than the other two techniques in the form of overall accuracy (99.15%) and F‐measures (99.21%).

中文翻译：

---

脑计算机接口，用于使用非马尔科夫排队模型评估电子学习中的心理努力

信息和通信技术的飞速发展使电子学习成为许多学习者的另一种学习方法。在过去的几年中，世界各地的大量学习者已经注册了由各种在线学习平台提供的大规模开放式在线课程（MOOC）。但是，MOOC平台对于在线课程提供者来说至关重要的任务是提供增强的学生学习体验和满意度。在这项工作中，我们开发了一个脑机接口，用于通过基于约翰·斯威勒的认知负荷理论观察MOOC视频和脑电图（EEG）设备来收集数据并检测学习者的心理状况。使用两种不同的归一化方法对获取的EEG信号进行预处理，以缩放信号。为了验证引入的框架，该系统采用了三种机器学习算法（使用非马尔可夫模型的随机森林，支持向量机和k最近邻）来开发具有预处理训练数据的模型，并测试分类器以验证其整体分类器的性能。最后，实验分析表明，采用非马尔可夫方法的随机森林分类器在总体准确性（99.15％）和F度量（99.21％）方面比其他两种技术取得了更多的成就。