Search for: All records

Abstract The increasing demand for concrete in construction presents challenges such as pollution, high energy consumption, and complex structural requirements. Three‐dimensional printing (3DP) offers a promising solution by eliminating formwork, reducing waste, and enabling intricate geometries. Predicting the strength of 3D‐printed fiber‐reinforced concrete (3DP‐FRC) remains challenging due to the nonlinear nature of neural networks and uncertainty in optimizing key parameters. In this study, we developed machine learning models using five metaheuristic algorithms—arithmetic optimization algorithm, African Vulture Optimization Algorithm, flow direction algorithm, generalized normal distribution optimization, and Mountain Gazelle Optimizer—to optimize the weights and biases in a feed‐forward backpropagation network. Among all the algorithms, MGO demonstrated the best performance. To address data limitations, a data augmentation method combining Kernel density estimation and Wasserstein generative adversarial networks is employed. Sensitivity analysis using SHapley Additive exPlanations (SHAP) identifies the most influential input parameters. The proposed MGO‐ANN model enhances predictive accuracy, reducing the need for extensive laboratory testing. Additionally, a user‐friendly graphical user interface is developed to facilitate practical applications in estimating 3DP‐FRC flexural strength. 

Distributional drift detection is important in medical applications as it helps ensure the accuracy and reliability of models by identifying changes in the underlying data distribution that could affect the prediction results of machine learning models. However, current methods have limitations in detecting drift, for example, the inclusion of abnormal datasets can lead to unfair comparisons. This paper presents an accurate and sensitive approach to detect distributional drift in CT-scan medical images by leveraging data-sketching and fine-tuning techniques. We developed a robust baseline library model for real-time anomaly detection, allowing for efficient comparison of incoming images and identification of anomalies. Additionally, we fine-tuned a pre-trained Vision Transformer model to extract relevant features, using mammography as a case study, significantly enhancing model accuracy to 99.11%. Combining with data-sketches and fine-tuning, our feature extraction evaluation demonstrated that cosine similarity scores between similar datasets provide greater improvements, from around 50% increased to 99.1%. Finally, the sensitivity evaluation shows that our solutions are highly sensitive to even 1% salt-and-pepper and speckle noise, and it is not sensitive to lighting noise (e.g., lighting conditions have no impact on data drift). The proposed methods offer a scalable and reliable solution for maintaining the accuracy of diagnostic models in dynamic clinical environments.