Using Ensemble Learning Algorithms to Predict Student Failure and Enabling Customized Educational Paths

Smirani, Lassaad K.; Yamani, Hanaa Abdulraheem; Menzli, Leila Jamel; Boulahia, Jihane A.

doi:10.1155/2022/3805235

Cited by 19 publications

(13 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The benefits of ensemble learning encourage previous research to apply it in the context of solving the educational problems we are currently facing. The previous research related to the use of this algorithm includes: predicting students who are at risk of academic failure in distance learning [16], predicting student failure and activating customized educational paths [15], and predicting student academic performance [35], to estimate the effect of individual treatment on student success [36]. However, previous research has not explored SVM kernels as base learners in the application of ensemble learning-stacking.…”

Section: The Ensemble Learningmentioning

confidence: 99%

“…Therefore, several researchers develop these methods to increase the performance of the system or model being built. Several previous studies that have developed existing methods include: modifying KNN to improve the performance of the prediction model [9], combining Fuzzy-C-means and K-means to group learners [14], applying ensemble learning to predict student failure [15], and predicting the academic failure risk of students [16], etc.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detecting Students’ Behavior on the E-Learning System Using SVM Kernels - Based Ensemble Learning Algorithm

2023

IJIES

View full text Add to dashboard Cite

The corona pandemic has changed learning methods from face-to-face to online. However, the application of online learning creates difficulties for teachers in monitoring student behavior because of the reduced direct interaction. This problem causes the learning process to be less optimal. Moreover, students may fail to achieve learning objectives. This research addresses this problem by building a model to detect student behavior in this online learning. It focuses on finding an optimal model by exploring the ensemble learning-stacking method based on a combination of SVM kernels (Linear, Polynomial, RBF, Sigmoid). After the model was built, it was evaluated using two performance measurement techniques, namely: cross-validation and percentage split, and several performance measures, namely: AUC, Accuracy, F1, Precision, and Recall. The evaluation results show the superiority of the models applying ensemble learning over those without it. In terms of accuracy, the highest result in the cross-validation technique is 98.4%, achieved by three models employing stacking. Those three are with base learners combination of linear-polynomial-sigmoid kernel (LinPolSig_Stack), a combination of linear-RBF-sigmoid kernel (LinRBFSig_Stack), and a combination of all kernels-linear, polynomial, RBF, sigmoid (AllKernels_Stack). In the percentage split technique, the highest performance is 97.4%, achieved by two models implementing ensemble learning-stacking with base-learners combination of RBF-sigmoid kernel (RBFSig_Stack) and combination of linearpolynomial-sigmoid kernel (LinPolSig_Stack). Finally, the highest performance of these models is equivalent to the minimum error in detecting student behavior. Detection errors were only three students in the three models in the cross-validation technique and only six in the two models in the percentage split technique.

show abstract

Section: The Ensemble Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Detecting Students’ Behavior on the E-Learning System Using SVM Kernels - Based Ensemble Learning Algorithm

2023

IJIES

View full text Add to dashboard Cite

show abstract

“…In our approach to detecting suspicious audio messages, we also use ensemble learning techniques to improve the performance of our system. [20] [21] In this diagram, the training dataset is used to train multiple base models. These base models can be of different types, such as decision trees, neural networks, or support vector machines.…”

Section: 23mentioning

confidence: 99%

Real-Time Deployment of Machine Learning-Based Audio Analysis Systems for Suspicious Message Detection

Hussain

2023

Preprint

View full text Add to dashboard Cite

In recent years, the proliferation of digital communication has made it easier for individuals to transmit audio messages in a variety of contexts. While this has facilitated many positive aspects of communication, it has also created new challenges for detecting suspicious activity that may pose a threat to security or privacy[1]. In response to these challenges, researchers have proposed various approaches to detect suspicious audio messages using machine learning techniques. This paper presents a novel approach to detecting suspicious audio messages that combine acoustic features and statistical models. We use machine learning algorithms to identify anomalies in audio messages that may indicate suspicious activity. The system analyzes various characteristics of the audio messages, including speech patterns, voice quality, background noise, and other acoustic features. We evaluate our approach on a dataset of real-world audio messages[2] and achieve promising results in terms of accuracy and efficiency. Our system can be used in a variety of applications, such as law enforcement, national security, and corporate communication monitoring. Our work contributes to the development of effective and reliable tools for detecting suspicious audio messages in today's digital age. By leveraging machine learning and acoustic analysis, our approach offers a valuable tool for ensuring security and privacy in audio communication.

show abstract

“…It helps researchers to improve the educational process and learning outcomes of students (Xu et al, 2021). Ensemble learning techniques have been used to enhance the predicting model of them (Badal & Sungkur, 2022;Karalar et al, 2021;Nachouki & Abou Naaj, 2022;Smirani et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Predictive Model for Clustering Learning Outcomes Affected by COVID-19 Using Ensemble Learning Techniques

Nuankaew¹,

Nuankaew²

2023

INT J EDUC METHODOL

View full text Add to dashboard Cite

<p style="text-align: justify;">The influence of COVID-19 has caused a sudden change in learning patterns. Therefore, this research studied the learning achievement modified by online learning patterns affected by COVID-19 at Rajabhat Maha Sarakham University. This research has three objectives. The first objective is to study the cluster of learning outcomes affected by COVID-19 at Rajabhat Maha Sarakham University. The second objective is to develop a predictive model using machine learning and data mining technique for clustering learning outcomes affected by COVID-19. The third objective is to evaluate the predictive model for clustering learning outcomes affected by COVID-19 at Rajabhat Maha Sarakham University. Data collection comprised 139 students from two courses selected by purposive sampling from the Faculty of Information Technology at the Rajabhat Maha Sarakham University during the academic year 2020-2021. Research tools include student educational information, machine learning model development, and data mining-based model performance testing. The research findings revealed the strengths of using educational data mining techniques for developing student relationships, which can effectively manage quality teaching and learning in online patterns. The model developed in the research has a high level of accuracy. Accordingly, the application of machine learning technology obviously supports and promotes learner quality development.</p>

show abstract

Using Ensemble Learning Algorithms to Predict Student Failure and Enabling Customized Educational Paths

Cited by 19 publications

References 57 publications

Detecting Students’ Behavior on the E-Learning System Using SVM Kernels - Based Ensemble Learning Algorithm

Detecting Students’ Behavior on the E-Learning System Using SVM Kernels - Based Ensemble Learning Algorithm

Real-Time Deployment of Machine Learning-Based Audio Analysis Systems for Suspicious Message Detection

Predictive Model for Clustering Learning Outcomes Affected by COVID-19 Using Ensemble Learning Techniques

Contact Info

Product

Resources

About