833 papers
This study introduces and validates a four-layer machine learning framework that significantly reduces audit detection risk and processing time compared to traditional methods by leveraging unsupervised and supervised models on 3.3 million real-world transactions from a Mongolian energy utility, while also uncovering a novel "aggregation masking effect" in Benford's Law anomalies.
This study proposes an explainable AI framework that integrates association rule mining with tri-dimensional sensory profiling to analyze Thai restaurant transaction data, thereby uncovering culturally grounded dish pairing patterns and enabling the generation of interpretable, authentic meal recommendations.
This research proposes a lightweight neural network approach for phishing URL detection using the PhiUSIIL dataset, demonstrating that optimizing hyperparameters and applying data scaling significantly enhances classification accuracy while maintaining low computational complexity.
This study proposes an auditable generative workflow for Miao and Dong timber heritage scenes that integrates morphological priors, photogrammetric conditioning, and provenance logging to ensure reviewable semantic and structural evidence without claiming survey-grade reconstruction.
This paper proposes a Random Forest-based machine learning framework, enhanced with SMOTE-Tomek class balancing, to effectively detect healthcare provider fraud and mitigate financial risks by outperforming traditional models like Decision Trees, Logistic Regression, SVM, and Naive Bayes in accuracy and key performance metrics.
The paper proposes MSAL-YOLO, an enhanced YOLOv8 detector that integrates a Spatial–Channel Mixed Convolution module, a Multi-Branch Enhanced Coordinate Attention mechanism, and a Region-Adaptive Wise-IoU loss to effectively address the challenges of detecting small and densely distributed objects in UAV aerial imagery, achieving significant performance improvements on the VisDrone2019 and DOTAv1 datasets.
This study validates the TRAUMA method, a supervised machine learning-based record linkage approach using LightGBM, demonstrating its superior ability to recover true matches with high precision and specificity compared to the traditional CIDACS-RL tool in Brazilian health databases.
This paper introduces Diamojism, a novel photomosaic rendering architecture that enhances large-format emoji mosaics by integrating semantic theme scoring and iterative palette correction into a diamond tile grid system, thereby improving thematic relevance and color accuracy without relying on generative models.
This paper proposes a novel (n, n) threshold visual secret sharing scheme that utilizes color QR codes as meaningful shares to securely encrypt and losslessly recover privacy images by leveraging color redundancy and XOR operations.
This paper presents an empirical study demonstrating that problem difficulty in code generation benchmarks is a stable, transferable metric driven by specification features (like examples and prompt length) on HumanEval and solution complexity on MBPP, offering critical insights for improving benchmarking, autograding, and educational tool design as aggregate model scores saturate.