1592 papers
This study demonstrates that incorporating 2% coir or jute fibers into expansive soft soil significantly improves its engineering performance by reducing plasticity and compressibility while increasing strength through mechanisms like fiber bridging and particle interlocking, offering a sustainable alternative for soil stabilization.
This study benchmarks various machine and deep learning models for predicting high-flow events at Hardinge Bridge, Bangladesh, finding that while Random Forest outperformed neural networks in meteorology-only scenarios, incorporating current hydrological state data significantly improved prediction accuracy more than architectural complexity, though results remain a reproducible proxy benchmark rather than operational skill due to shared data lineage between predictors and targets.
This study presents a low-cost, portable, and ultrasensitive glassy carbon electrode-integrated centrifugal microfluidic CD platform capable of the label-free, dual electrochemical detection of SARS-CoV-2 spike protein and prostate-specific antigen for point-of-care applications.
This study proposes a physics-guided, explainable machine learning framework using an optimized CatBoost model to accurately predict the unconfined compressive strength of nano shale–quicklime stabilized kaolin clay while quantifying uncertainties and identifying key physical drivers like plasticity and curing interactions.
This systematic review synthesizes 40 studies on air-bearing testbeds for CubeSat and nanosatellite ADCS, highlighting the shift toward modular and open-source hardware, identifying critical gaps in sensor fusion and thruster validation, and prioritizing future advancements in high-fidelity disturbance compensation, digital twins, and AI-assisted diagnostics.
This paper examines how artificial intelligence techniques, such as deep learning and optimization algorithms, address critical challenges in smart grids—including renewable integration, demand management, and cybersecurity—to enhance energy efficiency, reliability, and sustainability through real-world applications.
This paper introduces the QFDT-XMAI framework, a five-layer architecture that integrates quantum-enhanced federated learning, graph-attention multi-agent coordination, and explainable AI to enable autonomous, auditable engineering management across distributed sites while preserving data privacy and improving convergence efficiency and decision transparency.
This paper presents a sensor-centric survey of SLAM and odometry for GPS-denied environments, organizing literature by sensing modality and maturity tier to analyze performance trade-offs, identify key trends like multi-sensor fusion and neural integration, and argue that robust localization requires complementary sensing combined with uncertainty-aware estimators while highlighting fragmented benchmarking as a major barrier to progress.
This study utilizes a transformer-based framework on nearly 20,000 US robotics patents to demonstrate that while semantic novelty alone does not predict patent persistence, forward semantic influence significantly reduces the likelihood of maintenance-fee lapse, and novelty contributes to retention only when it remains technically legible within established domains.
This study develops a machine learning framework using dimensionless parameters derived from the Buckingham theorem to accurately and efficiently predict water vapor condensation heat transfer in horizontal channels with non-condensable gases, demonstrating that the XGBoost algorithm outperforms traditional correlations and other models while maintaining high accuracy even with a reduced feature set.