2608 papers
This paper presents a source-attributed ontology and knowledge graph framework that systematically digitizes and validates the contested procedural rules of Chinese mantic arts (Qimen Dunjia and Meihua Yishu) by establishing a provenance-driven verification system to preserve the auditable documentary layer of this intangible heritage.
This paper presents a pre-registered audit revealing that while mechanism-balanced adaptation is less harmful than average-risk adaptation for frozen time-series foundation models under informative missingness, all learned adaptation objectives perform significantly worse than simply leaving the models unadapted, rendering comparisons between adaptation strategies uninterpretable without an explicit no-adaptation anchor.
This paper proposes VahanSWARM, a blockchain-driven swarm learning framework that enables secure, decentralized, and privacy-preserving demand forecasting for intelligent vehicle supply chains by allowing stakeholders to collaboratively train models without sharing raw data while ensuring auditability through SHA-256 hashing.
This paper introduces SatForensics, a Transformer-based multi-modal framework that integrates satellite telemetry, RF interference, and GPS reflectometry to achieve high-accuracy cyber-attack detection and attribution while maintaining a tamper-evident chain of custody for Low-Earth-Orbit satellite networks.
This study evaluates semi-supervised and vendor-adversarial learning strategies for 3D missing-tooth localization in multi-vendor CBCT scans, finding that while vendor-adversarial training achieved the best locked test performance, semi-supervised approaches did not demonstrate significant superiority over pure supervision.
This study demonstrates that a Random Forest model outperforms Logistic Regression in predicting 30-day unplanned hospital readmissions while maintaining clinical utility through comprehensive explainability analyses that identify key risk factors like prior admissions and length of stay.
This paper proposes a novel hybrid meta-heuristic framework combining Genetic Algorithm-based feature selection with Future Search Optimization to accurately predict COVID-19 mortality rates in the Netherlands, demonstrating superior performance compared to other algorithms like Moth-Flame Optimization, Whale Optimization, and Artificial Neural Networks.
This paper proposes SHIELD-RDH, a novel framework for reversible data hiding in encrypted images that integrates lossless compression for high capacity, role-based access control, and a cryptographically secure, self-embedded authentication mechanism to ensure image integrity and tamper localization without requiring per-pixel location maps.
This paper proposes an information-supported granularity (ISG) framework that dynamically adapts semantic classification resolution to fluctuating wireless bandwidth by deriving theoretical limits via information theory and implementing a real-time, parameter-free deep learning system that ensures reliable edge perception through graceful degradation.
This paper proposes a replay-safe decision provenance framework for mutable geospatial contexts that uses version-bound receipts and geometric change frontiers to ensure decision integrity while achieving significant computational savings through selective replay.