2608 papers
This paper introduces SENTRY, a secure and energy-efficient framework for WSN-IoT environments that integrates Ethereum blockchain for decentralized data integrity with a hybrid AI approach using Machine Learning and Deep Learning to detect and mitigate cyberthreats, achieving superior performance metrics compared to existing methods.
The paper introduces DiffSoil, a lightweight conditional diffusion model that generates high-quality synthetic soil fertility data across varying climate scenarios to effectively augment scarce datasets, significantly improving the accuracy of downstream crop-recommendation systems in data-scarce, climate-vulnerable regions.
This paper proposes a two-phase neural construction heuristic that combines a Transformer-based reinforcement learning model with a customized allocation algorithm to efficiently solve large-scale Multi-depot Capacitated Vehicle Routing Problems with Time Windows for airport ground scheduling, demonstrating superior performance over existing solvers on real-world hub airport data.
This paper proposes a novel neuro-symbolic framework utilizing a Deterministic Probabilistic Projection operator and advanced mathematical modeling to eliminate hallucinations and ensure legally sound, transparent judicial decision-making grounded in the Moroccan Penal Code.
This paper introduces H2Profile, a hybrid privacy-preserving framework that combines approximate homomorphic encryption and secure multiparty computation to enable targeted advertising with high utility and reduced latency while limiting confidentiality to a semi-honest, two-server model.
This paper proposes a machine learning-based approach for detecting anomalies in cybersecurity service contracts between public authorities and private providers, utilizing a case study to categorize and analyze the attributes that signify deviations from established legal practices.
This paper proposes a Levenberg-Marquardt-optimized multi-output feed-forward neural network that achieves high-accuracy day-ahead joint forecasting of electricity load and market prices by effectively capturing their nonlinear dependencies, outperforming conventional and deep-learning baselines on standard smart-grid datasets.
This paper introduces the UWRD-Person benchmark dataset and proposes RHyME-Net, a novel network leveraging relative-depth representations to achieve robust person detection in ultra-wide-angle scenes by addressing challenges like scale variation and occlusion while minimizing reliance on RGB appearance cues.
This paper proposes a DRL-based adaptive backup optimization framework for edge-cloud environments that integrates Self-Organizing Map-driven pattern learning, LSTM-Transformer-based predictive retrieval, and trust-aware management to dynamically optimize backup decisions, achieving high reliability, low latency, and efficient resource utilization.
The paper proposes MARCA, a multi-agent framework that addresses the challenges of root cause analysis in distributed systems by using a controller-executor-voter architecture to achieve high accuracy and efficiency while reducing token usage and ensuring data privacy.