1616 papers
This paper introduces BPqu, a deep learning algorithm for edge-AI devices that enables zero-latency, real-time breath phase quantification and prediction for running, aiming to provide immediate, non-distracting guidance to reduce respiratory distress and enhance runner well-being.
This study proposes a network-physical coupling framework for distributed energy microgrids in disaster-prone island communities that integrates multi-source data, HOMER Pro optimization, and agent-based simulations to enhance resilience, operational efficiency, and rapid emergency recovery.
This paper proposes an Energy Management System for microgrids that utilizes the Pelican Optimization Algorithm combined with demand-side load shifting to achieve optimal generation scheduling and minimum operating costs, outperforming benchmark algorithms across four scenarios involving hybrid renewable sources and battery storage.
This study demonstrates that incorporating 20% reclaimed asphalt pavement (RAP) and 2% waste engine oil (WEO) into bituminous concrete creates a sustainable, cost-effective flexible pavement mixture that achieves performance comparable to conventional mixes while reducing construction costs by 14.22% and minimizing reliance on virgin materials.
This paper proposes a Skeleton-Guided Multi-OBB Decomposition (SG-MOBD) method that leverages RGB-D segmentation and skeleton-based watershed partitioning to generate tight bounding boxes for unknown obstacles, significantly reducing false alarms and computational latency in online robotic collision detection compared to traditional convex bounding volumes.
This study demonstrates that blending natural goat hair fibers with crumb rubber from waste tires creates a high-performance asphalt binder that significantly reduces carbon emissions and energy consumption while improving mechanical durability, offering a sustainable solution for Iran's road infrastructure.
This study combines centrifuge model tests, PIV analysis, and 3D lower-bound finite-element limit analysis to reveal that the stability and failure mechanisms of shallow-buried tunnel faces in sand-over-clay composite ground are significantly governed by the soil-layer interface position and the internal friction angle of the upper sand layer, ultimately establishing a linear relationship between the critical cover-to-diameter ratio and the friction angle to guide support pressure design.
This paper proposes a microscopic model utilizing an enhanced Alternating Direction Method of Multipliers (ADMM) algorithm to investigate and improve the interfacial friction properties of concrete between building layers under cyclic coupling effects, demonstrating superior performance in resisting stress damage and enhancing structural stability compared to conventional methods.
This study investigates how increasing fines content (up to 35%) enhances the reliquefaction resistance of silty sand and alters its consolidation-reconsolidation behavior, revealing that resistance surpasses initial liquefaction thresholds when fines content reaches 25% and the proposed anisotropic coefficient ratio drops below 1.
This study presents an evidence-constrained machine-learning framework enhanced by an LLM-assisted agent that utilizes Gradient Boosted Regression Trees for accurate CFST capacity prediction and implements a validation-gated online updating mechanism to ensure reliable, interpretable, and adaptive structural assessment.