1692 papers
This case study in Bangladesh demonstrates that substituting natural coarse aggregate with 50–75% electric arc furnace (EAF) slag significantly enhances concrete's compressive strength and durability while reducing water absorption, offering a sustainable solution for infrastructure development.
This paper demonstrates an interpretable, low-power compute-in-memory implementation of Kolmogorov-Arnold networks using commercial triple-level-cell V-NAND flash memory, which achieves high prediction accuracy for multimodal gas sensing while significantly reducing energy consumption and memory requirements compared to traditional multilayer perceptrons.
This paper presents a vision-guided robotic system that integrates a six-degree-of-freedom collaborative robot, YOLO-based machine vision, and force-controlled milling to automatically identify and remove stitches from end-of-life footwear, achieving sub-millimeter positioning accuracy to facilitate efficient material recovery and component reuse.
This study systematically investigates how specimen thickness, loading rate, and aggregate gradation influence the flexural performance of asphalt mixtures in un-notched semi-circular bending tests, revealing that specimen thickness significantly affects measured properties and necessitating the standardization of testing parameters for reliable performance comparisons.
This study proposes a dual-stream deep learning model integrated into a digital-twin platform to enable multi-timescale landslide prediction and risk-informed decision-making, effectively bridging the gap between short-term emergency response and long-term engineering planning.
This paper proposes a novel Nano-Distributed Imaging System (NDIS) for the Internet of Bio-Nano Things that utilizes functionalized nanodevices and a compressed sensing-based reconstruction framework to achieve high-resolution, camera-free in-body tumor localization and biochemical activity mapping, demonstrating superior spatial observability and accuracy under realistic physiological conditions.
This paper introduces a generative model that reconstructs high-speed videos of boiling dynamics from acoustic emissions and static visual cues, effectively creating a non-invasive "virtual window" to visualize bubble behavior in optically inaccessible thermal systems where traditional imaging fails.
This study demonstrates that a Vision Transformer-based model forecasting root-zone soil moisture in physical units achieves superior subseasonal skill over Europe compared to operational baselines, yet highlights that predicting rapid flash drought onsets remains a fundamental challenge across all current systems.
This paper demonstrates that a Reinforcement Learning-based Twin Delayed Deep Deterministic Policy Gradient (RL-TD3) optimized PID controller outperforms conventional and hybrid optimization methods, such as Coati Optimization and Grey Wolf-Cuckoo Search, in enhancing load frequency control stability and disturbance rejection within renewable-based islanded microgrids.
This study demonstrates that replacing sandstone with BOF steel slag in asphalt mixtures, particularly when combined with PMB binders, significantly enhances interfacial adhesion and overall mechanical performance, including rutting, cracking, and moisture resistance, under both unaged and long-term aged conditions.