Machine learning (ML) and deep learning (DL) algorithms work well where future estimations and predictions are required. Particularly, in educational institutions, ML and DL algorithms can help instructors in predicting the learning performance of learners. Furthermore, the prediction of the learning performance of learners can assist instructors and intelligent learning systems (ILSs) in taking preemptive measures (i.e., early engagement or early intervention measures) so that the learning performance of weak learners could be increased thus reducing learners’ failures and dropout rates. In this study, we propose an intelligent learning system (ILS) powered by the mobile learning (M-learning) model that predicts learners’ performance and classify them into various performance groups. Subsequently, adaptive feedback and support are provided to those learners who struggle in their studies. Four M-learning models were created for different learners considering their learning features (study behavior) and their weight values. The M-learning model was based on the artificial neural network (ANN) algorithm with the aim to predict learners’ performance and classify them into five performance groups, whereas the random forest (RF) algorithm was used to determine each feature’s importance in the creation of the M-learning model. In the last stage of this study, we performed an early intervention/engagement experiment on those learners who showed weak performance in their study. End-user computing satisfaction (EUCS) model questionnaire was adopted to measure the attitude of learners towards using an ILS. As compared to traditional machine learning algorithms, ANN achieved the highest prediction accuracy for all four learning models, i.e., model 1 = 90.77%, model 2 = 87.69%, model 3 = 83.85%, and model 4 = 80.00%. Moreover, the five most important features that significantly affect the students’ final performance were MP3 = 0.34, MP1 = 0.26, MP2 = 0.24, NTAQ = 0.05, and AST = 0.018.

中文翻译：

---

利用深度学习技术的力量创建智能、上下文感知和自适应 M-Learning 模型

机器学习 (ML) 和深度学习 (DL) 算法适用于需要未来估计和预测的情况。特别是在教育机构中，ML 和 DL 算法可以帮助教师预测学习者的学习表现。此外，对学习者学习成绩的预测可以帮助教师和智能学习系统（ILS）采取先发制人的措施（即早期参与或早期干预措施），从而提高弱学习者的学习成绩，从而减少学习者的失败和辍学率。在这项研究中，我们提出了一种由移动学习 (M-learning) 模型提供支持的智能学习系统 (ILS)，该系统可以预测学习者的表现并将其分为不同的表现组。随后，为那些在学习中遇到困难的学习者提供适应性反馈和支持。考虑到他们的学习特征（学习行为）和他们的权重值，我们为不同的学习者创建了四种 M 学习模型。M-learning 模型基于人工神经网络 (ANN) 算法，旨在预测学习者的表现并将其分为五个表现组，而随机森林 (RF) 算法则用于确定每个特征在创建过程中的重要性M学习模型。在本研究的最后阶段，我们对那些在研究中表现不佳的学习者进行了早期干预/参与实验。采用最终用户计算满意度（EUCS）模型问卷来衡量学习者对使用 ILS 的态度。与传统的机器学习算法相比，ANN 对所有四种学习模型都实现了最高的预测精度，即模型 1 = 90.77%、模型 2 = 87.69%、模型 3 = 83.85% 和模型 4 = 80.00%。此外，显着影响学生最终表现的五个最重要的特征是 MP3 = 0.34、MP1 = 0.26、MP2 = 0.24、NTAQ = 0.05 和 AST = 0.018。