1663 papers
This study demonstrates that an Ag/Ti heterobilayer passivation stack enables bonding-driven self-optimization of Cu–Cu interfaces, transforming static protective layers into energetically favorable, adhesive interfacial zones that ensure robust wafer-scale bonding integrity and reliability for 3D integration.
This paper reviews the application of artificial intelligence across six critical areas of modern power systems, proposing an engineering-oriented methodology for its implementation and concluding that AI delivers maximum value as a physics-aware, human-supervised decision-support tool while highlighting key barriers such as data readiness, cybersecurity, and regulatory acceptance.
This study proposes a comprehensive system integrating Building Information Modeling (BIM) with big data and ensemble machine learning techniques to significantly enhance the accuracy of building lifecycle cost predictions, reducing mean squared error from 160,000 to 54,280 and achieving a coefficient of determination of 0.93 based on an analysis of over 3,500 years of data from 120 buildings.
This diagnostic study reveals that the effectiveness of saliency-guided multimodal brain image fusion is highly modality-dependent and inconsistent across evaluation metrics, challenging the generalizability of current methods and highlighting the risks of relying on narrow or single-metric validation for clinical applications.
This paper presents a comprehensive review and numerical investigation of thermomechanical simulations for friction stir welding of aluminum-polymer joints, synthesizing two decades of literature to analyze modeling strategies, process parameters, and optimization pathways for lightweight hybrid components.
This paper proposes a novel quantum-classical mechatronic framework that integrates diamond Nitrogen-Vacancy center magnetometers with an Adaptive Unscented Kalman Filter and Robust Sliding Mode Controller to achieve high-precision, drift-free attitude estimation and trajectory tracking for autonomous UAVs in GPS-denied and jammed environments, demonstrating significantly superior performance over classical MEMS-based systems.
This paper proposes a physical-layer security framework for diffusion-based molecular communication in IoBNT that derives a closed-form secrecy capacity under advection–diffusion–reaction conditions and demonstrates that machine learning models, particularly Gradient Boosting and lightweight LSTM, significantly outperform conventional methods in detecting simultaneous eavesdropping and molecule injection attacks.
This study evaluates GPT-4o's ability to assist in the design and simulation of low-dropout regulators with inductive LC filters, finding that while the model effectively accelerates topology generation and stability analysis, it requires rigorous human verification to correct errors in component sizing, netlist syntax, and complex magnetic load configurations.
This paper presents an Artificial Intelligence-based optimization framework that integrates machine learning with advanced optimization techniques to identify optimal combustion parameters for hydrogen engines, thereby significantly improving brake thermal efficiency and reducing nitrogen oxide emissions.
This paper proposes and validates a hybrid control framework that enhances quadcopter trajectory tracking in dynamic environments by integrating a traditional PID controller with real-time reference modulation via Artificial or Deep Neural Networks, demonstrating that the PID+DNN approach outperforms PID+ANN in convergence smoothness and control efficiency.