2731 papers
This study presents an explainable machine learning framework using an XGBoost model to predict early-stage construction duration based on limited project information, demonstrating that while the model achieves strong predictive performance with project cost as the primary driver, its results require careful interpretation due to sensitivity to data partitioning.
This paper introduces Photonic Quantum-Enhanced Knowledge Distillation (PQKD), a hybrid framework that leverages the intrinsic stochasticity of photonic quantum processors to generate conditioning signals for a parameter-efficient student network, achieving competitive accuracy under aggressive compression across standard benchmarks while utilizing shot-noise scaling and feature smoothing to manage finite sampling limitations.
This paper proposes a certified selection method for ARINC-653 partition window counts that identifies near-optimal supply granularity with significantly reduced computational cost compared to exhaustive search, leveraging the observation that many window counts yield nearly identical performance values.
This paper proposes the PACPT-LB framework, a hybrid machine learning approach that proactively predicts handover failures, radio link failures, and ping-pong events in 5G mmWave networks by leveraging a large-scale simulated dataset and optimized model combinations to achieve superior accuracy across diverse mobility conditions.
This study presents and validates a context-aware AI-assisted screening system that significantly improves the efficiency and accuracy of detecting image duplication in biomedical publications by integrating visual similarity with contextual risk adjudication to reduce false positives while maintaining high sensitivity.
This paper proposes a Visibility-Aware Texture Consensus method with local structural constraints to improve 3D Gaussian Splatting reconstruction in texture-degraded scenes, demonstrating statistically significant robustness gains under controlled protocols while acknowledging limitations in real-world state-of-the-art performance.
This paper introduces BEACON, an open-source multilingual mobile agent that integrates real-time fire perimeter data, weather-based risk scoring, and polygon-avoidant routing to provide personalized, language-adaptive wildfire evacuation guidance for limited English proficiency communities.
This paper presents a comparative academic evaluation of Veeam Backup & Replication and Cohesity DataProtect, demonstrating that while both platforms offer distinct approaches to immutability and ransomware detection for VMware environments, they are most effective when integrated into a comprehensive defense-in-depth strategy.
This study demonstrates that applying an inverse-frequency re-weighting approach to MARBERT significantly outperforms baseline models in classifying underrepresented emoji pragmatic functions within Arabic digital discourse, effectively addressing severe label imbalance to advance computational pragmatics in Arabic NLP.
This paper demonstrates that migrating a blockchain prototype to the post-quantum ML-DSA-44 signature scheme revealed that critical implementation flaws in application validation, data representation, and concurrency logic had a far greater impact on system correctness and performance than the signature algorithm transition itself.