A5100370772- Manufacturing Process and Optimization
- Digital Transformation in Industry
- Additive Manufacturing and 3D Printing Technologies
- Flexible and Reconfigurable Manufacturing Systems
- Advanced Manufacturing and Logistics Optimization
- Advanced Neural Network Applications
- BIM and Construction Integration
- Microgrid Control and Optimization
- Robot Manipulation and Learning
- Scheduling and Optimization Algorithms
- Assembly Line Balancing Optimization
- Industrial Vision Systems and Defect Detection
- Advanced Vision and Imaging
- Solar and Space Plasma Dynamics
- Machine Learning and Data Classification
- IoT and Edge/Fog Computing
- Smart Grid Energy Management
- 3D Shape Modeling and Analysis
- Frequency Control in Power Systems
- Domain Adaptation and Few-Shot Learning
- Image Processing and 3D Reconstruction
- Topic Modeling
- Face recognition and analysis
- Generative Adversarial Networks and Image Synthesis
- Advanced Sensor and Energy Harvesting Materials
Second Affiliated Hospital of Zhejiang University
2025
Lanzhou University
2022-2025
North China Electric Power University
2025
State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources
2025
Simon Fraser University
2023-2025
Wuhan University of Technology
2015-2024
Wuhan College
2024
Hunan University
2020-2024
Nanjing Medical University
2024
Northwestern Polytechnical University
2024
Importance Large language models (LLMs) may facilitate the labor-intensive process of systematic reviews. However, exact methods and reliability remain uncertain. Objective To explore feasibility using LLMs to assess risk bias (ROB) in randomized clinical trials (RCTs). Design, Setting, Participants A survey study was conducted between August 10, 2023, October 30, 2023. Thirty RCTs were selected from published Main Outcomes Measures structured prompt developed guide ChatGPT (LLM 1) Claude 2)...
Remanufacturing has gained increasing attention due to its economic, environmental and societal benefits as well contribution the sustainability of natural resources. Disassembly is first usually most difficult process in remanufacturing a product. sequence planning, which aims find optimal disassembly sequence, required improve efficiency reduce cost. There have been many investigations this field several planning methods developed. This article reviews main existing from perspectives mode,...
Increasing attention is being paid to remanufacturing due environmental protection and resource saving. Disassembly, as an essential step of remanufacturing, always manually finished which time-consuming while robotic disassembly can improve efficiency. Before the execution disassembly, generating optimal sequence plays a vital role in improving In this paper, minimise total time, enhanced discrete Bees algorithm (EDBA) proposed solve planning (RDSP) problem. Firstly, modified feasible...
The emergence of digital twin enables real-time interaction and integration between the physical world information world. Digital twin-based manufacturing systems, as a typical representative smart manufacturing, have set advantages beyond traditional ones, such verifying predicting system performance based on operation virtual one. This paper presents five-dimensional modeling approach for which can not only realize mapping twins, but also some capabilities dependencies twins be derived. A...
Disassembly, which plays an essential role in remanufacturing, is the first step to extend service life of end-of-life (EOL) products. Traditional disassembly always accomplished by either humans or robots. Manual a time-consuming process, and high labour intensity will also pose threat human health, while robotic difficult flexibly handle complex parts. Continuous manual work leads accumulation fatigue, decreases efficiency work. In this paper, sequence planning considering fatigue for...
Large language models (LLMs) have the potential to enhance evidence synthesis efficiency and accuracy. This study assessed LLM-only LLM-assisted methods in data extraction risk of bias assessment for 107 trials on complementary medicine. Moonshot-v1-128k Claude-3.5-sonnet achieved high accuracy (≥95%), with performing better (≥97%). significantly reduced processing time (14.7 5.9 min vs. 86.9 10.4 conventional methods). These findings highlight LLMs' when integrated human expertise.
This study aimed to assess the feasibility and safety of robotic-assisted navigation system for percutaneous transthoracic needle biopsy (PTNB), compare it with conventional freehand technique, evaluate its generalizability across operators varying experience levels. After excluding 5 patients in whom PTNB could not be performed due technical problems, a total 50 200 who puncture were included. Using propensity score matching (PSM) match two groups simulate randomized controlled scenario....
The digital twin-based manufacturing system is a typical representative of smart and has number advantages beyond the state art. However, when needs to be reconfigured meet new requirements production, manual reconfiguration time-consuming high labor cost because complexity imperfection related models. This problem will even worse if there are industrial robots with characteristics complex functions inflexible programming in system. paper presents five-dimensional fusion model twin virtual...
Abstract We prove that by showing for any set C not of PA-degree and A , there exists an infinite subset G or such ⊕ is also PA-degree.
The predominant paradigm for using machine learning models on a device is to train model in the cloud and perform inference trained device. However, with increasing number of smart devices improved hardware, there interest performing training Given this surge interest, comprehensive survey field from device-agnostic perspective sets stage both understanding state-of-the-art identifying open challenges future avenues research. on-device an expansive connections large related topics AI...
Gait analysis, as a common inspection method for human gait, can provide series of kinematics, dynamics and other parameters through instrumental measurement. In recent years, gait analysis has been gradually applied to the diagnosis diseases, evaluation orthopedic surgery rehabilitation progress, especially, phase abnormality be used clinical diagnostic indicator Alzheimer Disease Parkinson Disease, which usually show varying degrees abnormality. This research proposed an inertial sensor...
Defect detection is an important part of the manufacturing process mechanical products. In order to detect appearance defects quickly and accurately, a method defect for metal base TO-can packaged laser diode (metal TO-base) based on improved You Only Look Once (YOLO) algorithm named YOLO-SO proposed in this study. Firstly, convolutional block attention mechanism (CBAM) module was added layer backbone network. Then, random-paste-mosaic (RPM) small object data augmentation basis Mosaic...
Disassembly is an inevitable process of recycling end-of-life products and robotic disassembly sequence planning could improve efficiency. However, the missing condition component uncertain it not be pre-known before execution process. The optimal solution should dynamically generated according to recognized during In this article, digital twin utilized solve dynamic under condition. First, framework proposed method studied established. Afterwards, deep <italic...
Purpose To develop and validate a deep learning radiomics (DLR) model that uses X-ray images to predict the classification of osteoporotic vertebral fractures (OVFs). Material methods The study encompassed cohort 942 patients, involving examinations 1076 vertebrae through X-ray, CT, MRI across three distinct hospitals. OVFs were categorized as class 0, 1, or 2 based on Assessment System Thoracolumbar Osteoporotic Fracture. dataset was divided randomly into four subsets: training set...
With the general trend of increasing Convolutional Neural Network (CNN) model sizes, compression and acceleration techniques have become critical for deployment these models on edge devices. In this paper, we provide a comprehensive survey Pruning, major strategy that removes non-critical or redundant neurons from CNN model. The covers overarching motivation pruning, different strategies criteria, their advantages drawbacks, along with compilation pruning techniques. We conclude discussion...