A5100645703- Stability and Control of Uncertain Systems
- Fault Detection and Control Systems
- Neural Networks Stability and Synchronization
- Distributed Control Multi-Agent Systems
- Machine Fault Diagnosis Techniques
- Seismic Imaging and Inversion Techniques
- Adaptive Control of Nonlinear Systems
- Underwater Acoustics Research
- Advanced Sensor and Control Systems
- Network Time Synchronization Technologies
- Gear and Bearing Dynamics Analysis
- Human Pose and Action Recognition
- 3D Shape Modeling and Analysis
- Petri Nets in System Modeling
- Power Systems and Renewable Energy
- Topic Modeling
- Ocean Waves and Remote Sensing
- Oceanographic and Atmospheric Processes
- 3D Surveying and Cultural Heritage
- Graph theory and applications
- Microgrid Control and Optimization
- Advanced Algorithms and Applications
- Hydrocarbon exploration and reservoir analysis
- Privacy-Preserving Technologies in Data
- Vibration and Dynamic Analysis
Shanghai Jiao Tong University
2007-2025
Zhengzhou University of Light Industry
2007-2025
Shanghai Artificial Intelligence Laboratory
2023-2025
China Southern Power Grid (China)
2021-2025
Beijing Academy of Artificial Intelligence
2024-2025
Shenyang University of Technology
2025
China National Petroleum Corporation (China)
2006-2024
Shandong Jiaotong University
2017-2024
Inner Mongolia Electric Power (China)
2024
Tianjin University
2024
Recently, large language models (LLMs) have showcased remarkable capabilities in natural understanding. While demonstrating proficiency everyday conversations and question-answering (QA) situations, these frequently struggle domains that require precision, such as medical applications, due to their lack of domain-specific knowledge. In this article, we describe the procedure for building a powerful, open-source model specifically designed medicine termed PMC-LLaMA.
Tomato leaf diseases have a significant impact on tomato cultivation modernization. Object detection is an important technique for disease prevention since it may collect reliable information. occur in variety of environments, which can lead to intraclass variability and interclass similarity the disease. plants are commonly planted soil. When occurs near leaf's edge, soil backdrop image tends interfere with infected region. These problems make challenging. In this paper, we propose precise...
Blind face restoration usually synthesizes degraded low-quality data with a pre-defined degradation model for training, while more complex cases could happen in the real world. This gap between assumed and actual hurts performance where artifacts are often observed output. However, it is expensive infeasible to include every type of cover real-world training data. To tackle this robustness issue, we propose Diffusion-based Robust Degradation Remover (DR2) first transform image coarse but...
The textile and clothing industry generates much pollution consumes a large amount of resources. Improper uses disposal products make the problems more severe. Fast fashion shorten valid lifecycle generate waste than regular products. Considering features products, system rent-based closed-loop supply chain is developed to improve sustainability processes (fashion design manufacturing, laundry, logistics disposal), operations management issues (inventory management, logistics, human-clothing...
Dance and music are two highly correlated artistic forms. Synthesizing dance motions has attracted much attention recently. Most previous works conduct music-to-dance synthesis via directly to human skeleton keypoints mapping. Meanwhile, choreographers design from in a two-stage manner: they firstly devise multiple choreographic units (CAUs), each with series of motions, then arrange the CAU sequence according rhythm, melody emotion music. Inspired by these, we systematically study such...
The fault detection (FD) problem for systems with both model uncertainty and external disturbance is investigated in this article. First, the mathematical models of disturbance, additive faults, multiplicative faults are established left right coprime factorization. Then, an observer-based FD scheme proposed thresholds derived open-loop closed-loop manners. necessary conditions on obtained detectability analyses carried out aid gap metric technique. Finally, effectiveness method illustrated...
This paper investigates the issue of event-triggered asynchronous dissipative control for Markov jump systems with unknown probabilities and packet losses. A hidden model is used to describe problem. Bernoulli an scheme are adopted address loss reduce transmission rate sampled signals, respectively. Furthermore, there exists probability information controller. Then, Lyapunov functions constructed obtain sufficient conditions stochastic stability performance closed-loop system. Moreover, a...
Node attribute, a type of crucial information for graph analysis, may be partially or completely missing certain nodes in real world applications. Restoring the attributes is expected to benefit downstream learning. Few attempts have been made on node attribute completion, but novel framework called Structure-attribute Transformer (SAT) was recently proposed by using decoupled scheme leverage structures and attributes. SAT ignores differences contributing learning schedule finding practical...
Caching popular contents at user devices and sharing the cached content among users is one promising solution to alleviate heavy base station burden in mobile social networks. In this letter, we investigate relationships physical coupling users, and, then, choose important (IU) as a helper cache target other can get from IUs devices. particular, because tend pay more attention they interested in, recommendation system with caching placement proposed maximize offloading probability for We...
Given the importance of cerebellum in pathophysiology schizophrenia, cerebellar vermis has been proposed as a new rTMS stimulation site for negative symptoms. In this study, 64 patients from 7 psychiatric hospitals were randomized into study (n=32) or control group. Intermittent theta burst (iTBS) (or sham stimulation) to midline was administered 5 times/week 2 weeks. Psychotic symptoms assessed with Positive and Negative Symptoms Scale (PANSS) at baseline, end treatment, 2, 6, 12, 24 weeks...
Offshore substations are important sustainable power infrastructures subjected to strong vibrations induced by complex environmental excitations such as wind, waves, and currents. To protect the structures expensive facilities, lightweight vibration control devices highly desirable in offshore substations. With a high-performance energy dissipation device, inerter, conventional Tuned Mass Damper (TMD) is upgraded for control. The optimal parametric design performance evaluation of single-...