863 papers
This paper presents a data-driven approach using sensor networks and ensembles of randomized decision trees to accurately detect, localize, and track radioactive sources in complex environments, demonstrating superior performance over traditional methods while eliminating the need for detailed radiation transport modeling.
This paper proposes the Quality-Constrained Preference Fading (QCPF) model, which enhances discrete diffusion recommendation by replacing uniform random sampling with a quality-aware mixture distribution and a false-negative filtering mechanism to generate more informative preference degradation trajectories, thereby significantly improving Top-K recommendation performance without adding inference latency.
This paper proposes a hybrid phishing URL detection model that integrates Graph Neural Networks with Random Forest to achieve superior accuracy and reduced false positives compared to traditional machine learning and alternative GNN approaches.
This paper proposes a multi-agent architecture leveraging LLM-driven autonomous agents to enable self-directed software quality assurance by automating test generation, execution, self-healing, and defect triage while continuously learning from historical outcomes to address the limitations of traditional scripted testing.
This paper proposes a Hybrid Explainable Deep Learning Framework (HEDLF) that integrates CNN, BiLSTM, and attention mechanisms with multi-sensor fusion and SHAP-based explainability to achieve high-accuracy predictive maintenance and physical interpretability for industrial IoT systems, as validated by superior performance on NASA C-MAPSS and IEEE PRONOSTIA benchmarks.
This systematic review of 22 studies published between 2010 and 2026 concludes that while learnable Gabor and wavelet filters offer interpretable and parameter-efficient improvements for mammographic breast cancer classification, a significant evidence gap remains regarding their joint integration for multiclass radiological and pathological staging.
This paper proposes a distilled edge intelligence framework that combines a two-phase knowledge distillation strategy with a confidence-aware edge-cloud collaborative inference mechanism to achieve high-accuracy bolt defect detection on resource-constrained communication tower devices while significantly reducing cloud upload ratios and latency.
This study proposes and validates a hierarchical deep learning framework that combines YOLOv8 detection with DenseNet121 classification to achieve robust pineapple disease detection, typification, and spatial visualization under challenging real-field tropical conditions, demonstrating superior accuracy and confidence in blind-field tests compared to single-stage approaches.
This paper proposes a computational framework that formalizes the metaphor of "thinking outside the box" by defining conceptual boundaries as geometric regions in a latent semantic space, thereby enabling the measurement of creative deviation through a topic-normalized geometric distance metric.
This paper introduces SBC-AND, a curated dataset of 442 Portuguese scientific publication records designed to address the underrepresentation of non-English languages in Author Name Disambiguation research and serve as a challenging benchmark for evaluating multilingual disambiguation models.