Towards Smarter E-Learning: Real-Time Analytics and Machine Learning for Personalized Education

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(1)

Published: Jan. 2, 2025

E-Learning platforms change fast, and real-time behavioural analytics with machine learning provides the most powerful means to enhance learner outcomes. The datasets undergo preprocessing techniques like Z-score outlier detection, Min-Max scaling for feature normalization, Ridge-RFE (Ridge regression Recursive Feature Elimination) selection in order improve accuracy reliability of predictions. Applying Gradient Boosting Machine, classification up a 94% level respect model about predictions on outcomes was achievable. Thus, applying this, feedback systems may offer timely recommendations or directions class that propel students toward better understanding how raise participation success percentages. However, this approach has some potential benefits but there are still various challenges such as managing data imbalance models generalize dynamic environment. Though hybrid methods mitigate problem, pipelines behaviour incorporation call significant computer-intensive resources infrastructure. This integration very high paybacks. It makes possible more responsive individual needs almost met manners, thus giving instantaneous feedback, content suggestions, interventions. Finally, convergence ML culminates adaptive environments which student engagement, retention, quality academic results.

Language: Английский

---

Innovative Computational Intelligence Frameworks for Complex Problem Solving and Optimization

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(1)

Published: Jan. 9, 2025

The rapid advancement of computational intelligence (CI) techniques has enabled the development highly efficient frameworks for solving complex optimization problems across various domains, including engineering, healthcare, and industrial systems. This paper presents innovative that integrate advanced algorithms such as Quantum-Inspired Evolutionary Algorithms (QIEA), Hybrid Metaheuristics, Deep Learning-based models. These aim to address challenges by improving convergence rates, solution accuracy, efficiency. In context a framework was successfully used predict optimal treatment plans cancer patients, achieving 92% accuracy rate in classification tasks. proposed demonstrate potential addressing broad spectrum problems, from resource allocation smart grids dynamic scheduling manufacturing integration cutting-edge CI methods offers promising future optimizing performance real-world wide range industries.

Language: Английский

---

Depression Sentiment Analysis using Machine Learning Techniques:A Review

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(1)

Published: Feb. 20, 2025

Depression is one of the habitual psychological well-being diseases and a significant number depressed individuals end their lives. People suffering from depression don’t ask for help doctors due to hesitation or unawareness about that causes delay in diagnosis treatment. A lot people share opinions emotions on social networking sites. Several studies site posts related rely upon Facebook, Twitter, Blogs, other networks because they recording behavioral attributes which are person’s thinking, socialization, communication, etc. Datasets various sites useful sentiment analysis. Various machine learning deep techniques like Naïve Bayes, maximum entropy, Support Vector Machine (SVM), Decision Tree classifiers neural networks, recurrent have been used detection. This paper presents review analysis performed media platforms detection The datasets utilized also discussed. comparative existing work area provided get clear understanding used. Finally, challenges future can be done field discussed

Language: Английский

---

Students Performance prediction by EDA analysis and Hybrid Deep Learning Algorithms

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(2)

Published: April 9, 2025

Education is a pillar of any individual to attain success in their life. Knowledge evaluate students’ performance which resulted with low accuracy and many algorithms not able manage imbalanced dataset. This research utilized the ML algorithms, EDA development learning makes everyone become educated person. Many universities colleges lend graduate course study for various disciplines, students choose courses based on interest. At same time researches consider normal factors like, personal academic features, experimented machine models analysis Hybrid prediction. Exploratory data performed identify correlation between features support evaluation student’s Based evidence from this paper aims provide deep learning-based hybrid approach that consists Deep Neural Network -Random Forest (DNN-RF), -Light GBM (DNN-Light GBM) students' prediction capable handling wide range datasets small enormous improve accuracy. The results shows achieved an 99.56%, precision 97.82%, recall 98.13%, f1 score 98.95% DNN-Light attained 90.76%, 85.13%, 84.94%, 87.93%. while comparing RF, Light GBM, DNN-RF utmost effective algorithm forecasting student performance.

Language: Английский

---

Environmental Assessment For Mapping Land Degradation and Lands Changes Using Remotely Sensed Data with Geospatial Analysis

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(1)

Published: Feb. 26, 2025

Lands degradation is one of the problems that facing humanity throughout world as well abandonment farming on their lands by farmers, in addition to fragmentation most orchards and agricultural fields conversion into residential areas, has a negative impact Economic, Environmental Social (Reduced Agricultural Productivity, Economic Loss, Soil Degradation, productivity. Water Scarcity, Biodiversity Rural-Urban Migration, Food Security, Conflict Instability). However, Karbala Province, Iraq, Agriculture are this dilemma since 2003. Therefore, order start solving problem and, it important detect all changes study area then put recommendations for overcoming dilemma. The aim monitor LCLU reasons behind that. For that, Authors employed pixel based classification techniques (Maximum Likelihood Method) four Landsat satellite (9 ,7 ETM+, TM5, TM4) images acquired at intervals (1990, 2000, 2010, 2023). first step research applied pre-processing stages (radiometric geometric corrections) correct images, secondly, processing stage (layer stacking, sub-setting) corrected classified using supervise six regions. results show desertification markedly intensified city last three decades. In 2023, water volume, decreased 14.21%, both Urban dark soil increased 3.05%, 8.63% respectively, give indicator about what happen area, evidences land processes was seen, mostly due Human activities such urban expansion unsustainable use practices. confusion matrix evaluate results. overall accuracy kappa statistic were above 90% 0.90 respectively.

Language: Английский

---

AI-Driven Predictive Maintenance for Smart Manufacturing Systems Using Digital Twin Technology

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(1)

Published: March 2, 2025

The rapid advancements in Industry 4.0 and smart manufacturing systems have necessitated the integration of Artificial Intelligence (AI) Digital Twin Technology (DTT) to enhance operational efficiency predictive maintenance strategies. This study proposes an AI-driven framework that leverages enable real-time monitoring, fault diagnosis, failure prediction industrial environments. integrates machine learning (ML) models, deep techniques, edge computing analyze sensor data, detect anomalies, optimize schedules. A reinforcement learning-based decision model is employed dynamically adjust strategies, reducing downtime extending equipment lifespan. Additionally, physics-informed AI models are incorporated into digital twin architecture simulate behaviours predict potential failures with high accuracy. proposed system validated through a case plant, demonstrating 35% improvement accuracy, 40% reduction unplanned downtimes, 25% optimization costs compared traditional approaches. findings indicate DTT significantly enhances reliability cyber-physical (CPMS), paving way for more autonomous intelligent operations.

Language: Английский

---

Heart Failure Prediction: A Comparative Study of SHAP, LIME, and ICE in Machine Learning Models

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2024, Volume and Issue: 10(4)

Published: Dec. 29, 2024

Heart disease remains a critical public health issue, prompting the need for effective predictive modeling. This study evaluates performance of LightGBM, SVM, Random Forest, and Logistic Regression models on heart dataset. achieved highest accuracy 86.89%, demonstrating strong in classification with balanced precision recall. LightGBM Forest also performed competitively, accuracies 85.33% 85.25%, respectively. Notably, had recall (96.97%) but lower (80%). SVM showed at 93.94% lowest (83.61%). The findings underscore importance model interpretability, facilitated by SHAP, LIME, ICE, which enhance understanding decisions healthcare applications, ultimately supporting improved clinical outcomes.

Language: Английский

---