A5031593368- Underwater Vehicles and Communication Systems
- Robotic Path Planning Algorithms
- Maritime Navigation and Safety
- Reinforcement Learning in Robotics
- Advanced Image and Video Retrieval Techniques
- Robotics and Sensor-Based Localization
- Advanced Vision and Imaging
- Per- and polyfluoroalkyl substances research
- Remote Sensing and Land Use
- Advanced Technologies in Various Fields
- Air Quality Monitoring and Forecasting
- Birth, Development, and Health
- Face and Expression Recognition
- Optical measurement and interference techniques
- Gestational Diabetes Research and Management
- Urban Heat Island Mitigation
- Multimodal Machine Learning Applications
- Network Security and Intrusion Detection
- Distributed Control Multi-Agent Systems
- Machine Learning in Healthcare
- Land Use and Ecosystem Services
- Hydrology and Sediment Transport Processes
- Handwritten Text Recognition Techniques
- Face recognition and analysis
- Vehicle emissions and performance
Shanghai Jiao Tong University
2022-2025
Tianjin University
2019-2025
Inner Mongolia University
2025
Ruijin Hospital
2025
Beijing University of Technology
2021-2024
XinHua Hospital
2022-2024
Shijiazhuang University
2024
Nanchang Hangkong University
2024
Zhejiang University
2022-2024
Qingdao University of Technology
2024
The Unmanned Aerial Vehicles (UAVs) are competent to perform a variety of applications, possessing great potential and promise. Deep Neural Network (DNN) technology has enabled the UAV-assisted paradigm, accelerated construction smart cities, propelled development Internet Things (IoT). UAVs play an increasingly important role in various such as surveillance, environmental monitoring, emergency rescue, supplies delivery, for which robust path planning technique is foundation prerequisite....
The path planning of the autonomous underwater vehicle (AUV) has shown great potential in various Internet Underwater Things (IoUT) applications. Although considerable efforts had been made, prior studies are confronted with some limitations. For one thing, existing work only uses ocean current simulation model without introducing real information, having not supported by data. another, traditional algorithms have strong environment dependence and lack flexibility: once changes, they need to...
Emerging epidemiological evidence has linked per- and polyfluoroalkyl substances (PFAS) exposure could be to the disturbance of gestational glucolipid metabolism, but toxicological mechanism is unclear, especially when at a low level. This study examined metabolic changes in pregnant rats treated with relatively dose perfluorooctanesulfonic acid (PFOS) through oral gavage during pregnancy [gestational day (GD): 1–18]. We explored molecular mechanisms underlying perturbation. Oral glucose...
Deep learning is well known as a method to extract hierarchical representations of data. In this paper novel unsupervised deep based methodology, named Local Binary Pattern Network (LBPNet), proposed efficiently and compare high-level over-complete features in multilayer hierarchy. The LBPNet retains the same topology Convolutional Neural (CNN) - one most studied architectures whereas trainable kernels are replaced by off-the-shelf computer vision descriptor (i.e., LBP). This enables achieve...
In 3-D attitude angle estimation, monocular vision-based methods are often utilized for the advantages of short-time and high efficiency. However, limitations these lie in complexity algorithm specificity scene, which needs to match characteristics cooperation object scene. this article, we propose a fully connected detection network (FADN), combines neural traditional algorithms estimation. FADN provides whole process from input single frame image industrial video stream output...
As one of the commonly used vehicles for underwater detection, robots are facing a series problems. The real environment is large-scale, complex, real-time and dynamic, many unknown obstacles may exist in environment. Under such complex conditions lack prior knowledge, existing path planning methods difficult to plan, therefore they cannot effectively meet actual demands. In response these problems, three-dimensional marine including multiple established with ocean current data this paper,...
The Autonomous Underwater Glider (AUG) is a kind of prevailing underwater intelligent internet vehicle and occupies dominant position in industrial applications, which path planning an essential problem. Due to the complexity variability ocean, accurate environment modeling flexible algorithms are pivotal challenges. traditional models mainly utilize mathematical functions, not complete reliable. Most existing depend on lack flexibility. To overcome these challenges, we propose system for...
In the decade, artificial intelligence has achieved great popularity and applications in medicine healthcare. Various AI-based algorithms have shown astonishing performance. However, various data-driven smart healthcare algorithms, problem of incomplete dataset remains a huge challenge. this paper, we propose data completeness enhancement algorithm based on generative AI (i.e., GenAI-DAA) to solve problems in-sufficient for model training, imbalance, biases training samples. We first...
Autonomous underwater vehicle (AUV) shows great potential in the Internet of Underwater Things (IoUT) system, which path planning algorithm plays a fundamental role. However, complex environment brings greater challenges to AUV planning, especially ocean current, has profound impact on time and energy consumption. This article focuses current condition proposes an method based proximal policy optimization (UP4O). In this novel method, deep reinforcement network is constructed serve as...
Rapid urbanization is causing ecological and environmental issues to worsen. The stability of the ecosystem function farming–pastoral ecotone (FPE) in Inner Mongolia essential ensuring sustained growth nearby cities, acting as a vital safeguard China’s northern regions. This study used “production–living–ecological” spaces (PLES) spatial dynamics, rate change index, standard deviation ellipse examine temporal evolution PLES FPE Mongolia. constructed conflict index model based on theory...
Abstract Aims Intensive systolic blood pressure (BP) control is associated with a lower risk of cardiovascular disease (CVD) but an increased worsening renal function (WRF). This study aimed to investigate whether intensive BP should be continued after WRF. Methods We performed post hoc analysis SPRINT (Systolic Blood Pressure Intervention Trial). WRF was defined as eGFR decline ≥30% during follow-up from baseline. The associations between WRF, efficacy and safety outcomes, treatment were...
The Tactile Internet (TI) allows operators to have an immersive experience in a remote environment. During this process, users generate large amount of demonstration data containing tactile information. It is important reasonably use user-generated improve the intelligence applications without infringing on user privacy. In order only datasets for learning expensive environment interaction, conservative policy estimation offline reinforcement introduced paper ensure convergence algorithms....
Remote sensing image (RSI) scene classification plays an active role in many application areas. Due to the excellent performance of convolutional neural networks (CNNs), which have widely applied RSI recent years. However, most existing methods improve accuracy by improving model parameters or fusing features CNNs. This will make whole very complicated and unable extract multiscale at a more granular level. letter proposes novel lightweight depthwise network (MSDWNet) with efficient spatial...
With the rapid advancement of modern society, autonomous systems have been broadly applied in people's daily lives. Under guidance this trend, vehicles gradually become popular. However, due to some adverse factors (such as insufficient computing force and limited communication bandwidth) edge scenarios lack decision-making ability, safety is not enough. It a good solution use deep reinforcement learning (DRL) algorithm, which combines (DL) (RL), provide fast convergence speed an appropriate...
Two-phase closed thermosyphons (TPCTs) are effective devices for transferring heat and could be used to reduce the internal of coal piles, inhibiting spontaneous combustion. Nanofluids have recently been investigated as working media improving thermal efficiency TPCTs by exploiting high conductivity nanoparticles. In this study, transfer performance a TPCT containing CuO–H2O nanofluids various nanoparticle concentrations was experimentally through simulations pile at different operating...