A5009116003- Remote-Sensing Image Classification
- Distributed and Parallel Computing Systems
- Cloud Computing and Resource Management
- Remote Sensing and Land Use
- Advanced Image Fusion Techniques
- Parallel Computing and Optimization Techniques
- Scientific Computing and Data Management
- Remote Sensing in Agriculture
- Advanced Image and Video Retrieval Techniques
- IoT and Edge/Fog Computing
- Advanced Data Storage Technologies
- Remote Sensing and LiDAR Applications
- Geochemistry and Geologic Mapping
- Data Management and Algorithms
- Land Use and Ecosystem Services
- Automated Road and Building Extraction
- Landslides and related hazards
- Advanced Computational Techniques and Applications
- Image and Signal Denoising Methods
- Flood Risk Assessment and Management
- Oil Spill Detection and Mitigation
- Advanced Image Processing Techniques
- Geographic Information Systems Studies
- Impact of Light on Environment and Health
- Sparse and Compressive Sensing Techniques
China University of Geosciences
2016-2025
Chinese Academy of Sciences
2012-2025
Commercial Aircraft Corporation of China (China)
2021-2025
Qingdao University
2021-2025
China University of Geosciences (Beijing)
2014-2024
Beijing Institute of Big Data Research
2023-2024
Xi’an Jiaotong-Liverpool University
2021-2024
Hubei University of Technology
2024
Xidian University
2021-2024
Anhui Medical University
2024
When mounted on the skin, modern sensors, circuits, radios, and power supply systems have potential to provide clinical-quality health monitoring capabilities for continuous use, beyond confines of traditional hospital or laboratory facilities. The most well-developed component technologies are, however, broadly available only in hard, planar formats. As a result, existing options system design are unable effectively accommodate integration with soft, textured, curvilinear, time-dynamic...
Cloud computing emerges as a new paradigm which aims to provide reliable, customized and QoS guaranteed dynamic environments for end-users. This paper reviews recent advances of computing, identifies the concepts characters scientific Clouds, finally presents an example data centers
With the advent of Cloud computing, large-scale virtualized compute and data centers are becoming common in computing industry. These distributed systems leverage commodity server hardware mass quantity, similar theory to many fastest Supercomputers existence today. However these can consume a cities worth power just run idle, require equally massive cooling keep servers within normal operating temperatures. This produces CO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML"...
The notion of Cloud computing has not only reshaped the field distributed systems but also fundamentally changed how businesses utilize today. While provides many advanced features, it still some shortcomings such as relatively high operating cost for both public and private Clouds. area Green is becoming increasingly important in a world with limited energy resources an ever-rising demand more computational power. In this paper new framework presented that efficient green enhancements...
Abstract El Niño-Southern Oscillation (ENSO), which is one of the main drivers Earth’s inter-annual climate variability, often causes a wide range anomalies, and advance prediction ENSO always an important challenging scientific issue. Since unified complete theory has yet to be established, people use related indicators, such as Niño 3.4 index southern oscillation (SOI), predict development trends through appropriate numerical simulation models. However, because phenomenon highly complex...
With the ability to exploit internal structure of data, graph-based models have received a lot attention and achieved great success in multiview subspace clustering for multimedia data. Most existing methods individually construct an affinity graph each single view fuse result obtained from graph. However, common representation shared by different views complementary diversity across these are not efficiently exploited. In addition, noise outliers often mixed original which adversely...
Over the last few years, we have seen a plethora of Internet Things (IoT) solutions, products and services, making their way into industry's market-place. All such solution will capture large amount data pertaining to environment, as well users. The objective IoT is learn more serve better system Some these solutions may store locally on devices ('things'), others in Cloud. real value collecting comes through processing aggregation large-scale where new knowledge can be extracted. However,...
Cloud computing that provides elastic and storage resource on demand has become increasingly important due to the emergence of "big data". resources are a natural fit for processing big data streams as they allow application run at scale which is required handling its complexities (data volume, variety velocity). With no longer under users' direct control, security in cloud becoming one most concerns adoption resources. In order improve reliability availability, storing multiple replicas...
Remote sensing image scene classification has been widely applied and attracted increasing attention. Recently, convolutional neural networks (CNNs) have achieved remarkable results in classification. However, images complex semantic relationships between multiscale ground objects, the traditional stacked network structure lacks ability to effectively extract key features, resulting limited feature representation capabilities. By simulating way that humans understand perceive images,...
Although demonstrating great success, previous multi-view unsupervised feature selection (MV-UFS) methods often construct a view-specific similarity graph and characterize the local structure of data within each single view. In such way, cross-view information could be ignored. addition, they usually assume that different views are projected from latent space while diversity cannot fully captured. this work, we resent MV-UFS model via preserved consensus learning, referred to as CvLP-DCL...
Graph based multi-view clustering has been paid great attention by exploring the neighborhood relationship among data points from multiple views. Though achieving success in various applications, we observe that most of previous methods learn a consensus graph building certain representation models, which at least bears following drawbacks. First, their performance highly depends on capability model. Second, solving these resultant optimization models usually results high computational...
In recent years unmanned aerial vehicles (UAVs) have emerged as a popular and cost-effective technology to capture high spatial temporal resolution remote sensing (RS) images for wide range of precision agriculture applications, which can help reduce costs environmental impacts by providing detailed agricultural information optimize field practices. Furthermore, deep learning (DL) has been successfully applied in applications such weed detection, crop pest disease etc. an intelligent tool....
Road information from high-resolution remote-sensing images is widely used in various fields, and deep-learning-based methods have effectively shown high road-extraction performance. However, for the detection of roads sealed with tarmac, or covered by trees images, some challenges still limit accuracy extraction: 1) large intraclass differences between unclear interclass urban objects, especially buildings; 2) occluded trees, shadows, buildings are difficult to extract; 3) lack...
Deep convolutional neural networks have become an indispensable method in remote sensing image scene classification because of their powerful feature extraction capabilities. However, the ability models to extract multiscale features and global on surface objects complex scenes is currently insufficient. We propose a framework based context spatial attention (GCSA) densely connected features, called GCSANet. The mixup operation used enhance mixed data images, discrete sample space rendered...