A5103109893- Multimedia Communication and Technology
- Electric Power System Optimization
- Energy Load and Power Forecasting
- Recommender Systems and Techniques
- Image Enhancement Techniques
- Advanced Neural Network Applications
- Power System Reliability and Maintenance
- Infrastructure Maintenance and Monitoring
- Remote Sensing and Land Use
- Adaptive optics and wavefront sensing
- Quantum Computing Algorithms and Architecture
- Cryospheric studies and observations
- Methane Hydrates and Related Phenomena
- Medical Imaging and Analysis
- CO2 Sequestration and Geologic Interactions
- Hemoglobinopathies and Related Disorders
- Diabetes Treatment and Management
- Image and Signal Denoising Methods
- Image and Video Quality Assessment
- Complex Network Analysis Techniques
- Bone health and osteoporosis research
- Water Quality Monitoring and Analysis
- Water Quality Monitoring Technologies
- Seismic Waves and Analysis
- Benford’s Law and Fraud Detection
Pfizer (United States)
2023
The University of Sydney
2012-2022
Wuhan University
2012-2021
Nanjing University of Science and Technology
2016
Nanjing Institute of Technology
2016
Data61
2012-2013
IHE Delft Institute for Water Education
2007
Online fault detection of insulators is a necessary requirement for the development smart grid, which directly affects safety and reliability power system operations. Breakage an important factor causing insulator abnormalities, large number image samples are often required training to complete defect identification with help AI deep learning. In this paper, we propose convolutional neural network ensemble implemented using small samples, data augmentation transfer learning breakage...
Insulators are one of the widely used important devices in power systems, and proposing an accurate effective online monitoring method for insulator defects is urgent need intelligent informative systems. We propose a multiscale residual neural network surface breakage recognition. The proposed convolution filter uses three different size kernels filtering, performs feature maps fusion, which can enrich spatial correlation channel maps. investigated effects learning rates on model...
Web-based catch-up TV has revolutionised watching habits as it provides users the opportunity to watch programs at their preferred time and place, using a variety of devices. With increasing offer content, there is an emergent need for personalised recommendation solutions, which help select interest. In this work, we study patterns Australian nation-wide service provider develop suite approaches scenario. We evaluate these new large-scale dataset gathered by portal deployed provider. The...
Automatic detection for remote sensing targets is a profound challenging problem in the field of image analysis.This paper presents novel fast model based on kernel sparse coding with spatial bag visual words (KSC-SBOW) optical images.Before implementation sliding window detection, saliency prediction introduced to predict suspected which can extremely depress influence backgrounds and rationally decrease computational cost.Following determination processing by SIFT features extraction from...
This paper introduces a data fusion processing method based on remote-sensed image and the algorithm of support vector machine, analyzes an experiment water quality monitoring Taihu Lake. builds SVM model to map remote sensing into dispersed classifications lake's spots, then, it distinguishes whole condition combining with this model. By comparing results, shows that results identifications Lake match practical conditions well by using such method, provides convenient effective technical...