Generative artificial intelligence is increasingly embedded in higher education learning practices, yet its contribution to academic performance remains contested. This study developed an explainable machine-learning framework for predicting students’ post-semester GPA from Generative AI usage patterns and learning-related characteristics. Using a structured dataset of 50,000 student records, the study modelled academic performance with predictors including pre-semester GPA, weekly GenAI usage hours, primary use case, prompt-engineering skill, tool diversity, traditional study hours, perceived AI dependency, institutional policy, exam anxiety, year of study, and major category. To prevent outcome leakage, non-relevant outcome variables and student identifiers were excluded before training. Ridge Regression, Decision Tree Regression, and Extra Trees Regression were compared using R², RMSE, and MAE. The results showed that Ridge Regression achieved the strongest predictive performance, indicating that academic outcomes were largely explainable through stable relationships among prior achievement, GenAI-related behaviours, and study characteristics. Feature-importance analysis revealed that prior GPA, primary GenAI use case, and prompt-engineering skill were among the most informative predictors. The study contributes to GenAI-aware learning analytics by demonstrating how explainable modelling can support evidence-based academic monitoring.
This study proposes a novel approach by employing SteganoGAN, a steganographic framework based on Generative Adversarial Networks (GANs). The impact of image categories with different semantic contents (art, building, and nature) on system performance was examined in detail using the SteganoGAN architecture. A hybrid dataset composed of BossBase and USC-SIPI images was utilized to conduct the experiments. The influence of image quality, categorized by visual content, on performance was systematically analyzed. In particular, changes in skewness and kurtosis values, as well as the widely used image quality metrics PSNR and SSIM, were investigated. Experimental results demonstrated that nature images provided superior performance, achieving an SSIM value of 99.59 and exhibiting the lowest skewness deviation from the original cover images.
Industrial spray drying is a complex nonlinear process characterized by strong interactions among thermal, mechanical, environmental, and temporal variables, making accurate prediction and operational optimization challenging. This study proposes a hybrid machine learning–evolutionary optimization framework for predictive modeling and intelligent operational optimization in industrial spray drying systems. The framework integrates Random Forest Regression (RFR) for nonlinear process prediction with a Genetic Algorithm (GA) for adaptive exploration of optimal operating conditions under industrial constraints. The RFR model achieved strong predictive performance, with a coefficient of determination of R² = 0.9144 and stable generalization performance (cross-validation R² = 0.8427 ± 0.2027), demonstrating robustness under dynamic industrial variability. Feature importance analysis revealed gas flow and temporal dynamics as the dominant process drivers, enhancing interpretability and supporting operational decision-making. The GA-based optimization identified operating configurations that improved process efficiency by approximately 5.91% compared to baseline conditions while maintaining operational feasibility. The results demonstrate that integrating ensemble learning with evolutionary optimization provides both high predictive accuracy and actionable optimization capability for complex industrial systems. Furthermore, the proposed surrogate-assisted framework reduces computational dependency on physical experimentation by enabling rapid evaluation of candidate operating conditions through data-driven intelligence. The study contributes a deployable data-driven optimization architecture for intelligent and energy-efficient manufacturing operations within Industry 4.0 environments.
Digital grocery shopping has shifted consumer patterns toward multi- item purchasing. While bundle recommendation systems address this, existing models relying on product ID co-occurrence fail to capture the mixed shopping intentions inherent in consumer baskets. To address these limitations, we propose Intent-aware Bundle Recommendation (IABR), a framework shifting from structural matching to semantic intent reasoning. IABR utilizes Large Language Models to decompose baskets into coherent sub-packages. Subsequently, we fine- tuned Gemma-3-4B using Parameter-Efficient Fine-Tuning to generate narrative intent descriptions regarding short-term shopping missions and long-term sustainable user lifestyles. These intents are encoded via Sentence Transformers for semantic retrieval. Extensive testing on the Instacart dataset demonstrates IABR’s significance against baselines like BGCN. Our IABR method achieved a Recall@20 of 28.15% while improving diversity scores by 12% (p < 0.05). This validates that generative semantic modeling enables accurate next- bundle predictions, effectively balancing precision with thematic variation and personalization.
