This chapter investigates the perceived erosion of critical academic skills among 745 university students due to dependency on AI tools. The survey measured six key constructs: AI Dependency (AID), Cognitive Offloading (CO), Motivational Decline (MD), Academic Skills Erosion (ASE), Academic Integrity Awareness (AIA), and External Pressures (EP), using a five-point Likert scale. Path Analysis was employed to examine the interrelationships among these constructs. The results revealed a strong positive relationship between AID and both CO and MD, which indicated that the increased reliance on AI leads to reduced cognitive engagement and diminished academic motivation. Additionally, CO and MD were positively associated with ASE, which means that students who offload cognitive tasks and experience MD are more likely to exhibit deteriorating academic skills. While AIA had a weak negative relationship with AID, EP showed a moderate positive association and highlighted the role of academic stress in driving AI reliance.
1 July 2025 in International Journal of Computational Intelligence Systems
Prefabricated construction offers significant advantages in efficiency, resource savings, and environmental sustainability, yet its scheduling remains challenging due to complex resource constraints and task interdependencies. This study proposes a dual-objective optimization model to minimize project duration and resource fluctuation in prefabricated construction projects. To solve this model effectively, an Improved Whale Optimization Algorithm (IWOA) is developed, addressing the limitations of the standard WOA such as premature convergence and poor local search ability. The proposed IWOA incorporates Tent chaotic mapping for population diversification, a nonlinear convergence factor to balance exploration and exploitation, and a hybrid search mechanism that integrates crossover operations and multiple neighborhood strategies. A real-world case study demonstrates the algorithm’s superiority over conventional approaches in both solution accuracy and stability. The results show that the optimized schedule significantly improves resource allocation efficiency and reduces construction time, offering a promising approach for intelligent scheduling in resource-constrained prefabricated building projects.
1 August 2023 in Journal of Physics: Conference Series
YOLO V5 algorithm is the current target detection algorithm, but the accuracy of target boundary regression is relatively low, and it cannot be used in scenarios with high requirement of prediction frame intersection ratio. Therefore, this paper proposes an improved YOLO V5 algorithm with high accuracy of target frame and fast convergence of model. The algorithm can avoid the loss of shallow semantic information, deepen the pyramid depth and increase the detection layer by using cross-hierarchy method and multiple feature fusion. By reducing network computation and parameter number, network lightweight processing is realized, and real-time performance loss caused by model complexity is avoided.
Road accidents contribute significantly to annual fatalities. Various agencies engaged in road safety management are consistently striving for quality improvement to predict and mitigate accidents through the aid of information technology. As machine learning emerged, its data analysis, visualization, and prediction capabilities have proven to help policymakers. The main objective of this study is to develop a machine-learning model for predicting road accidents in Urdaneta City, Philippines. The dataset used consists of three years (2021–2023) of road accident records from the Emergency Medical Services (EMS). Various preprocessing methods are employed, and a grid search technique is implemented to identify optimal features for the model. Random Forest, XGBoost, AdaBoost, Decision Tree, and LGBM algorithms are developed to predict and visualize road accident occurrences. Upon development, it was found that XGBoost performs well among other models, acquiring a total Rsquared of 0.9996 in training and 0.9898 during testing. To validate the findings of the study, the model's interpretability was assessed using a William Plot. The SHAP and LIME methodologies offer valuable insights into how various variables affect the model's forecast of the monthly number of road accidents. The Permutation Feature Importance approach provides insight into the specific impact of each feature on the model's predictions, emphasizing the significant influence of time on accident frequency, particularly during peak hours or late-night accidents. The Box Plot offers valuable insights, with the median (Q2) indicated by a line showing a value of around 10. Leveraging this model can significantly reduce the likelihood of accidents in real-time, resulting in a safer and more intelligent transportation ecosystem.