2787 papers
This paper introduces PDE-shaped finite-relaxation neural media that achieve resolution-stable spatial binding by learning continuous conductivity, absorption, and coupling fields, demonstrating superior generalization across resolutions compared to local-kernel and CoordConv baselines while providing a controlled framework for analyzing inspectable finite-relaxation mechanisms.
This study presents the development, external validation, and open-source release of a scalable, Clinical BERT-based NLP framework that successfully extracts structured data from multi-cancer pathology reports, demonstrating strong internal performance and clinically meaningful, albeit reduced, generalizability across external institutions.
This paper proposes STE-BiMamba, a lightweight and efficient bidirectional Mamba-based network that integrates multi-scale temporal extraction and three-view statistical pooling to achieve state-of-the-art motor imagery EEG decoding accuracy with significantly reduced computational complexity compared to Transformer models.
This study utilizes a post-hoc proxy analysis of over 20,000 machine learning conference submissions to demonstrate that author metadata, idea abstractions, and LLM-imputed capability descriptions contain partially non-redundant signals associated with peer review outcomes, while highlighting the limitations of inferring capability without longitudinal data and raising concerns regarding fairness and resource inequality in research evaluation.
This paper proposes a real-time urban vehicle tracking framework that integrates YOLOv8 detection, an adaptive Kalman Filter, and a Random Forest predictor within a wireless sensor network to achieve high-accuracy, identity-stable tracking under dynamic traffic conditions with low latency.
This study presents a systematic review of AI-driven facemask detection architectures, identifying YOLOv5-based models as the most effective solution for embedding into hospital infrastructure to simultaneously advance digitalization, resilience, and human-centricity in healthcare ecosystems.
This paper demonstrates that while high-accuracy machine learning intrusion detectors exhibit weak cross-domain transferability due to distinct temporal signatures for botnet and multi-vector attacks, applying a multi-method explainable AI framework successfully identifies a robust, consensus set of temporal features that transforms black-box models into auditable and transferable evidence for trustworthy intrusion detection.
This study demonstrates that a novel four-layer machine learning framework, validated against 3.3 million real-world public sector transactions and official audit reports, significantly outperforms traditional Monetary Unit Sampling by reducing audit detection risk from over 38% to 2.01% while cutting processing time by 98.7%.
This paper proposes AMADRL-ZTA, a distributed Zero Trust architecture leveraging adaptive multi-agent deep reinforcement learning to significantly enhance threat detection, reduce response times, and improve policy adaptability for securing global financial ecosystems against sophisticated cyber attacks.
This paper proposes a mathematical framework for early DDoS detection that utilizes a stability functional and distortion operator to measure the distance of network traffic from a theoretical stability domain, offering a more interpretable and robust alternative to traditional threshold-based monitoring methods.