As the Next Gen E-learning solutions will cover some or all objectives to bring effective utilization of e-learning solutions using AI/ML, some of them are already present in some solutions.
As:-
Moodle is shipped with the following core models,
- Students at risk of dropping out
- Upcoming activities due
- No teaching
The following table contains, AI/ ML, Data-mining Techniques in E-learning solutions for different objectives with prediction accuracy.
| E-learning Feature | ML Models and Technique | Prediction Accuracy | Criteria Evaluated using ML |
|---|---|---|---|
| User Opinion | HMM [Hidden Markov Model],SVM [Support Vector Machine] Data Mining Technique : MI [Mutual Information],IG[Infor- mation Gain],CHI | F-Measure 0.803 | The accuracy rate of user opinion predicted |
| Course Recommendation to Students | ADTree classification Algorithm, Apriori Association Rule algorithm, Simple K-Means Algorithm | Apriori Association gives the best cluster of courses | Course mapping is obtained |
| Timely system response to students | Genetic Algorithm, ML technique | – | Automated web bot gives timely reply |
| Student performance knowledge | SVM | F-Measures-0.986 | Predicts the rate of student’s knowledge |
| Student Emotions | k-NN, SVM | SVM accuracy ration- 97.15% | Accurately predicts students emotions |
| Online session assessment | Ensemble Classifier Baggins embedded with ML | 78.04% accuracy | Predict the beneficial session |
| Student ranking credits | ECOC [Error Correcting Output Code] combines Classifier | F statistics is 3.05 | Predicts college opportunity |
| Learning style and learning objects | Bayesian Estimation | Bayesian infer the increase in the visual category | Estimate learning style |
| Learner behaviors sequence | Fuzzy cluster technique | 78% matched with real-world data | Predicts learner behavior |
| Learner sequence, Learning pattern | FCM [Fuzzy Clustering Methodd], K-means clustering | FCM shows 96.89% accuracy K-Means shows 80.12 % accuracy | Classified learner Sequence |
| Student graduation results | perception ANN [Artificial Neural Network] | Predicts successful 77% unsuccessful 68% | Predicts graduation successfulness |
| AUI features courses | Felder Silverman model | Classifies learning Models | Learning Models predicted |
| Course information | ANN, LMA algorithm | R-value 9.08% | Evaluate future GPA |
| learning processing data | Conv-GRU-avgP in P-xNN | accuracy 80.04% | Predicted Learning Performance |
| Student assessment | Deep learning TensorFlow Engine | 80%-91% of accuracy | Predicts student pathway |
| Student test results | Radom Forest | 26.7% error rate | predicts student performance |
| Student engagement in the course | K-means clustering | Silhouette coefficient for two-level cluster is .7003 | Classify student groups |
