A5086489308- Advanced Image Processing Techniques
- Image Enhancement Techniques
- Image and Signal Denoising Methods
- Air Quality Monitoring and Forecasting
- Peanut Plant Research Studies
- Metabolomics and Mass Spectrometry Studies
- Air Quality and Health Impacts
- Atmospheric chemistry and aerosols
- Advanced Cellulose Research Studies
- Insect Pheromone Research and Control
- Additive Manufacturing Materials and Processes
- Antibiotics Pharmacokinetics and Efficacy
- Fire dynamics and safety research
- Liquid Crystal Research Advancements
- Advanced Computing and Algorithms
- Advanced Antenna and Metasurface Technologies
- Advanced Chemical Sensor Technologies
- Brain Tumor Detection and Classification
- Fire Detection and Safety Systems
- Pharmaceutical and Antibiotic Environmental Impacts
- Video Surveillance and Tracking Methods
- Plant nutrient uptake and metabolism
- Genomics and Phylogenetic Studies
- Plant Disease Resistance and Genetics
- Advanced Image Fusion Techniques
Sun Yat-sen University
2024
Southwestern University of Finance and Economics
2022-2023
Jiangnan University
2023
Shandong Jianzhu University
2023
Zhejiang Gongshang University
2022
Beihang University
2020
Shandong University
2016
Defects including inclusions and voids significantly affect the mechanical properties of additive manufacturing materials. It is necessary to precisely capture defects determine their hazardous effects on material properties. In this paper, a damage model developed describe nucleation, growth, coalescence in materials, revealing nature true stress drop. order characterize defect morphology depict evolution, an in-situ tensile test with synchrotron radiation X-ray topography (SRXT) carried...
Abstract Fire detection methods based on the Convolutional Neural Networks (CNN) have advantages of high accuracy, wide coverage and robustness, receiving significant attention from researchers. Among CNN‐based methods, ResNet has achieved better performance than other CNN frameworks in fire system, since it uses stacked residual blocks to enlarge receptive field overcome vanishing gradient problem with learning. The merits can be attributed similarity between single‐step explicit solver for...
Continuous, long-term monitoring of hazardous, noxious, explosive, and flammable gases in industrial environments using electronic nose (E-nose) systems faces the significant challenge reduced gas identification accuracy due to time-varying drift sensors. To address this issue, we propose a novel unsupervised attention-based multi-source domain shared-private feature fusion adaptation (AMDS-PFFA) framework for with compensation E-nose systems. The AMDS-PFFA model effectively leverages...
Emotion recognition plays an important role in medicine, criminal investigation, human-computer interaction and other fields. through machine learning has become a promising research direction. VGG network is kind of classic convolutional neural networks (CNN) which can be used for emotion recognition, VGG-16 one the architectures VGG. However, too many parameters it seems that doesn't perform well on FER2013 because overfitting. To solve these problems, this paper proposes CNN based variant...