Gang Hu
YOU?
Author Swipe
View article: Investment Risk Analysis of Municipal Railway Construction Projects Based on Improved SNA Methodology
Investment Risk Analysis of Municipal Railway Construction Projects Based on Improved SNA Methodology Open
By analyzing all types of risks in the investment process of a municipal railroad construction project, 16 investment risk factors are extracted, and a network of investment risk factors and a comprehensive impact matrix of the project are…
View article: The exosomal protein biomarkers auxiliary in diagnosis of interstitial lung disease
The exosomal protein biomarkers auxiliary in diagnosis of interstitial lung disease Open
View article: On structural loads and responses of monopile offshore wind turbines under typhoons: Numerical case study of Super Typhoon Chan-hom
On structural loads and responses of monopile offshore wind turbines under typhoons: Numerical case study of Super Typhoon Chan-hom Open
View article: Recovery Lanthanum by Monolithic Conjugated Porous Polymers from Seawater with High Selectivity
Recovery Lanthanum by Monolithic Conjugated Porous Polymers from Seawater with High Selectivity Open
View article: The Effect of Loading Condition on the Thermal Decomposition Characteristics of Rdx
The Effect of Loading Condition on the Thermal Decomposition Characteristics of Rdx Open
View article: Towards high-fidelity urban wind profiles for the built environment: a Neural Field approach to fuse multi-source observational data
Towards high-fidelity urban wind profiles for the built environment: a Neural Field approach to fuse multi-source observational data Open
View article: Development of 100 kN m deadweight torque standard machine at NIM
Development of 100 kN m deadweight torque standard machine at NIM Open
View article: Intelligent control of structural vibrations based on deep reinforcement learning
Intelligent control of structural vibrations based on deep reinforcement learning Open
View article: Thermal properties regulation of primary explosive based on adhesives’ composition effect
Thermal properties regulation of primary explosive based on adhesives’ composition effect Open
With the upgrading and development of weapons, primary explosive charge methods based on extrusion/printing technology had become important direction for the support capacity improvement for in service and novel equipment. Binders as the k…
View article: Study on the Settlement and Deformation Characteristics of Surrounding Rock of Loess Tunnel
Study on the Settlement and Deformation Characteristics of Surrounding Rock of Loess Tunnel Open
There is a water culvert with masonry structure in the mountain of Hanguguan Tunnel. Soil deformation caused by tunnel excavation leads to channel cracking. On the one hand, channel water infiltration leads to loess tunnel collapse, which …
View article: Health Behaviors and Social Determinants of Health in Children from Under-resourced Communities: Does Weight Status Play a Role?
Health Behaviors and Social Determinants of Health in Children from Under-resourced Communities: Does Weight Status Play a Role? Open
Background: Social determinants of health (SDOHs) may affect children’s health and health behaviors. This study aimed to understand the relationship between health behaviors and SDOHs in a child population from under-resourced communities …
View article: A modeling method for the Earth's interior structure based on the principles of 2n geometry and the resulting Earth's tectonic model
A modeling method for the Earth's interior structure based on the principles of 2n geometry and the resulting Earth's tectonic model Open
A non-seismic wave detection method based on 2n geometry principle is proposed to deduce the vertical structure of the earth. By using this method, a new earth structure model can be derived by pure theory, avoiding the traditional earth m…
View article: Markowitz Meets Bellman: Knowledge-distilled Reinforcement Learning for Portfolio Management
Markowitz Meets Bellman: Knowledge-distilled Reinforcement Learning for Portfolio Management Open
Investment portfolios, central to finance, balance potential returns and risks. This paper introduces a hybrid approach combining Markowitz's portfolio theory with reinforcement learning, utilizing knowledge distillation for training agent…
View article: No Language is an Island: Unifying Chinese and English in Financial Large Language Models, Instruction Data, and Benchmarks
No Language is an Island: Unifying Chinese and English in Financial Large Language Models, Instruction Data, and Benchmarks Open
While the progression of Large Language Models (LLMs) has notably propelled financial analysis, their application has largely been confined to singular language realms, leaving untapped the potential of bilingual Chinese-English capacity. …
View article: A novel vector potential random flow generation method for synthesizing divergence-free homogeneous isotropic turbulence with arbitrary spectra
A novel vector potential random flow generation method for synthesizing divergence-free homogeneous isotropic turbulence with arbitrary spectra Open
A novel method, known as the vector potential random flow generation (VPRFG) method, is introduced for synthesizing divergence-free homogeneous isotropic turbulence with arbitrary spectra. First, the proposed approach employs the random-fl…
View article: Bidirectional prediction between wake velocity and surface pressure using deep learning techniques
Bidirectional prediction between wake velocity and surface pressure using deep learning techniques Open
The surface pressure and flow field of rectangular cylinders are of great importance in aerodynamic analyses of the cylinders. In general, it is easy to obtain one side of the information, either the surface pressure or the flow field, in …
View article: Aerodynamic force reduction of rectangular cylinder using deep reinforcement learning-controlled multiple jets
Aerodynamic force reduction of rectangular cylinder using deep reinforcement learning-controlled multiple jets Open
The drag and lift forces of rectangular cylinders with four aspect ratios (AR) are mitigated at a Reynolds number of 1000 using deep reinforcement learning (DRL) controlled multiple jet actuators at four corners of the cylinders in this st…
View article: Urban wind field prediction based on sparse sensors and physics‐informed graph‐assisted auto‐encoder
Urban wind field prediction based on sparse sensors and physics‐informed graph‐assisted auto‐encoder Open
The urban flow wind field is a critical element for downstream research, such as mitigation of urban wind disasters, assessment of urban wind environment, and urban drone route planning. However, it is impractical to arrange a large number…
View article: Effects of Tree Morphology on Aerodynamics of Fractal Trees in Extreme-Gust Wind
Effects of Tree Morphology on Aerodynamics of Fractal Trees in Extreme-Gust Wind Open
View article: Effects of Tree Geometry on the Aerodynamics of Sympodial Trees with Analysis of Extreme Gust Wind
Effects of Tree Geometry on the Aerodynamics of Sympodial Trees with Analysis of Extreme Gust Wind Open
View article: An Aerodynamic Database of Synchronized Surface Pressure and Flow Field for Rectangular Cylinders
An Aerodynamic Database of Synchronized Surface Pressure and Flow Field for Rectangular Cylinders Open
View article: Research on Confidence Analysis Method of Lightning Strike Accidents on Distribution Lines
Research on Confidence Analysis Method of Lightning Strike Accidents on Distribution Lines Open
Currently, lightning is the main cause of power system faults. Due to insufficient equipment and technology, low insulation level, the distribution network being the main part of power outages, and the complex causes of distribution networ…
View article: Advancing Algorithmic Trading: A Multi-Technique Enhancement of Deep Q-Network Models
Advancing Algorithmic Trading: A Multi-Technique Enhancement of Deep Q-Network Models Open
This study enhances a Deep Q-Network (DQN) trading model by incorporating advanced techniques like Prioritized Experience Replay, Regularized Q-Learning, Noisy Networks, Dueling, and Double DQN. Extensive tests on assets like BTC/USD and A…
View article: Front Cover
Front Cover Open
A method based on deep learning was proposed to enhance the defocused resolution and signal‐to‐noise ratio of optical‐resolution photoacoustic microscopy. A fully dense U‐Net was trained with randomly distributed sources of different shape…
View article: Surrogate model-based deep reinforcement learning for experimental study of active flow control of circular cylinder
Surrogate model-based deep reinforcement learning for experimental study of active flow control of circular cylinder Open
The flow around a circular cylinder is a classical problem in fluid mechanics, and the reduction of drag and lift has been a long-standing research focus in flow control. In this study, we apply deep reinforcement learning (DRL) to intelli…
View article: An optimal sensor placement scheme for wind flow and pressure field monitoring
An optimal sensor placement scheme for wind flow and pressure field monitoring Open
View article: Aerodynamic Characterization of a Fan Array Wind Generator
Aerodynamic Characterization of a Fan Array Wind Generator Open
Experimental assessment of safe and precise flight control algorithms for unmanned aerial vehicles (UAVs) under gusty wind conditions requires the capability to generate a large range of velocity profiles. In this study, we employ a small …
View article: Dynamic Feature-based Deep Reinforcement Learning for Flow Control of Circular Cylinder with Sparse Surface Pressure Sensing
Dynamic Feature-based Deep Reinforcement Learning for Flow Control of Circular Cylinder with Sparse Surface Pressure Sensing Open
This study proposes a self-learning algorithm for closed-loop cylinder wake control targeting lower drag and lower lift fluctuations with the additional challenge of sparse sensor information, taking deep reinforcement learning as the star…
View article: Lightweight Classification Network for Pulmonary Tuberculosis Based on CT Images
Lightweight Classification Network for Pulmonary Tuberculosis Based on CT Images Open
With the continuous development of medical informatics and digital diagnosis, the classification of tuberculosis cases from computed tomography (CT) images of the lung based on deep learning is an important guiding aid in clinical diagnosi…
View article: A Direct Extrusion‐Shear Deformation (SD) Composite Process for Significantly Improving the Metallurgical Bonding and Textures Regulations and Grain Refinements Mechanical Properties of Hot-Extruded Az31 / Aa6063 Composite Tubes
A Direct Extrusion‐Shear Deformation (SD) Composite Process for Significantly Improving the Metallurgical Bonding and Textures Regulations and Grain Refinements Mechanical Properties of Hot-Extruded Az31 / Aa6063 Composite Tubes Open