A5100932454- Industrial Vision Systems and Defect Detection
- Face and Expression Recognition
- Intracranial Aneurysms: Treatment and Complications
- Cerebrovascular and Carotid Artery Diseases
- Generative Adversarial Networks and Image Synthesis
- Machine Learning and Data Classification
- Visual Attention and Saliency Detection
- Color Science and Applications
- Surface Roughness and Optical Measurements
- Energy Load and Power Forecasting
- Gene expression and cancer classification
- Advanced Computational Techniques and Applications
- Intracerebral and Subarachnoid Hemorrhage Research
- Machine Learning and ELM
- Radiomics and Machine Learning in Medical Imaging
- Text and Document Classification Technologies
- Aquatic Ecosystems and Phytoplankton Dynamics
- Stock Market Forecasting Methods
- Silicone and Siloxane Chemistry
- Advanced Neural Network Applications
- Antimicrobial agents and applications
- Personality Traits and Psychology
- Digital Communication and Language
- Robotic Path Planning Algorithms
- Antiplatelet Therapy and Cardiovascular Diseases
Zhujiang Hospital
2023-2025
Southern Medical University
2023-2025
Changchun University of Technology
2024-2025
Institute of Art
2024
Shandong First Medical University
2024
Xi'an Polytechnic University
2016-2023
Xi'an University of Architecture and Technology
2023
South China University of Technology
2019
Health Commission of Jilin Province
2007
In inspection of fabric surface quality in production line, small defects have to be detected a large background. this paper, new method is put forward detect defect by target-driven features. First all, feature analyzed; and then, area number are used as tasks, which drive enhance saliency defective regions form maps; finally, using threshold segmentation, fusion, filtering, gained from the maps. Experiments show that detection algorithm, compared with classic can achieve accurate...
In recent years, deep-learning detection algorithms based on automatic feature extraction have become the focus of defect detection. However, limited by industrial field conditions, insufficient number images in collected dataset restricts effect deep learning. this paper, an algorithm strip steel classification using improved GAN and EfficientNet was proposed. First, label deconvolution network is constructed, where image labels were deconvolved layer to obtain conditional masks that...
In order to improve the objectivity of fabric pilling evaluation, a saliency deep convolutional network method for evaluation is proposed. First all, instrument used generate samples as nonstandard dataset that added standard dataset. The expanded through data augmentation increase number and diversity data. Then, preprocessing model constructed achieve image by fusing local global map. Finally, improvements ResNet 34 are made. layer improved small target features enhancement. residual...
Abstract Multivariate time series have more complex and high‐dimensional characteristics, which makes it difficult to analyze predict the data accurately. In this paper, a new multivariate prediction method is proposed. This generative adversarial networks (GAN) based on Fourier transform bi‐directional gated recurrent unit (Bi‐GRU). First, utilized extend features, helps GAN better learn distributional features of original data. Second, in order guide model fully distribution data, Bi‐GRU...
In this paper, an objective and reliable evaluation method of fabric pilling using a bottom-up visual attention model with higher accuracy is presented. Through analyzing mechanism characteristic, new designed to detect information, by which the contrast between background texture enhanced in saliency map constructed. And then, Otsu algorithm adapted segment interesting region from map, area mean foreground target thought as segmented threshold separate region. On basis, extracting features...
Abstract The accuracy of straightness monitoring scraper conveyor seriously restricts the development unmanned mining technology in underground coal mines. Fiber Bragg Grating sensors have characteristics passive intrinsic safety and broad application prospects mine technology. In this paper, motion between two adjacent scrapers were fully analyzed, mathematical expressions illustrated, furthermore, we designed manufactured a 3D vector sensor using FBG sensors. calibration testing...
<title>Abstract</title> Flow-diverter devices (FDs) are effective in treating intracranial aneurysms (IAs) but carry substantial periprocedural risks, particularly ischemic complications. This study aimed to determine if elevated Systemic Immune-Inflammation Index (SII) can independently predict these risks and assess the impact of age dual antiplatelet therapy on this association. We conducted a retrospective analysis patients treated with FDs between February 2016 August 2023, using blood...
The research of biomedical data is crucial for disease diagnosis, health management, and medicine development. However, are usually characterized by high dimensionality class imbalance, which increase computational cost affect the classification performance minority class, making accurate difficult. In this paper, we propose a method based on feature selection resampling. First, use minimal-redundancy maximal-relevance (mRMR) to select features, reduce dimension, cost, improve generalization...
Repetitive transcranial magnetic stimulation (rTMS) is a common non-invasive treatment for medication-resistant major depressive disorder (MDD). It utilizes continuous and adjustable to modulate neural circuits implicated in the pathogenesis of depression. Nevertheless, constructing universal effective predictive factor forecasting outcomes remains challenging. To address this, we first collect neuroimaging data five depression scales from 26 MDD patients before after rTMS treatment. Then...
The abstract cover the following points in order analyzing and resolving epidemics today’s social from a medical perspective, which is based on perspectives of palliative care, medicine, epidemiology, focuses changes human health orientation adaptability during process development,I have focused occurrence depression young children mechanisms potential risks factors coronary heart disease hypertension elderly population through field investigations. Combining relevant data clinical practice...
We participate this challenge by developing a hierarchical framework.We build the model from two fully convolutional networks:(1) simple Unet to normalize input iamges, (2) segmentaion network which is an attention based on Deeplab model.Two models are connected in tandem and trained end-to-end.To ensure better results, we use preprocess method proposed nnUnet our experiments.
In order to reduce the dependence of dynamic motion primitive model's trajectory planning on data sets and improve its generalization ability small sets, we propose an improved Mixture Motors Primitives (MoMP) algorithm. MoMP uses a new model achieve same direction as taught learned by using less teaching information components build original base. Additionally, gating unit develop optimal weighting strategy learn primitives form trajectory. Using MATLAB software combined with Robotics...