A5042058386- Advanced Algorithms and Applications
- Smart Agriculture and AI
- Advanced Sensor and Control Systems
- Simulation and Modeling Applications
- Advanced Graph Theory Research
- Advanced Computational Techniques and Applications
- IoT and Edge/Fog Computing
- Industrial Technology and Control Systems
- Robotic Path Planning Algorithms
- Advanced Neural Network Applications
- Graph theory and applications
- Adaptive Control of Nonlinear Systems
- Electromagnetic Launch and Propulsion Technology
- Advanced Research in Science and Engineering
- Domain Adaptation and Few-Shot Learning
- Target Tracking and Data Fusion in Sensor Networks
- Advanced Measurement and Detection Methods
- Manufacturing Process and Optimization
- Generative Adversarial Networks and Image Synthesis
- Embedded Systems and FPGA Design
- Water Quality Monitoring Technologies
- Interconnection Networks and Systems
- Industrial Vision Systems and Defect Detection
- Higher Education and Teaching Methods
- Remote Sensing and Land Use
Chinese Academy of Sciences
2015-2025
Aerospace Information Research Institute
2025
State Key Laboratory of Remote Sensing Science
2025
University of Chinese Academy of Sciences
2025
Beijing Aerospace Flight Control Center
2023-2024
Shaanxi Normal University
2024
Zhongkai University of Agriculture and Engineering
2012-2024
Guzhou Transportation Planning Survey & Design Academe (China)
2024
Harbin Institute of Technology
2024
Chongqing Technology and Business University
2005-2024
In recent years, smart factory in the context of Industry 4.0 and industrial Internet Things (IIoT) has become a hot topic for both academia industry. IIoT system, there is an increasing requirement exchange data with different delay flows among devices. However, are few studies on this topic. To overcome limitations traditional methods address problem, we seriously consider incorporation global centralized software defined network (SDN) edge computing (EC) EC. We propose adaptive...
At present, smart manufacturing computing framework has faced many challenges such as the lack of an effective fusing historical heritages and resource scheduling strategy to guarantee low-latency requirement. In this paper, we propose a hybrid design intelligent fulfill real-time requirement in with edge support. First, four-layer system environment is provided support artificial intelligence task operation network perspective. Then, two-phase algorithm for resources layer designed based on...
In the traditional agricultural wireless sensor networks (WSNs), there is a large amount of redundant data and high latency on critical events (CEs) for collection systems, which increases time energy consumption. order to overcome these problems, an effective edge computing (EC) enabled approach CE in smart agriculture proposed. First, key features types (KFDTs) are extracted from historical dataset keep main information CEs. Next, KFDTs selected as type software-defined network (SDWSN)....
At present, precision agriculture and smart are the hot topics, which based on efficient data collection by using wireless sensor networks (WSNs). However, agricultural WSNs still facing many challenges such as multitasks, quality, latency. In this paper, we propose an solution for multiple tasks exploiting edge computing-enabled in agriculture. First, a novel framework is presented merging WSN computing. Second, process modeled, including plurality of sensors tasks. Next, according to each...
Abnormal crops image data play crucial role in controlling crop diseases and pest for smart agriculture. However, current agricultural acquisition methods suffer from low-value data. This article presents a new strategy collect high-quality abnormal crops. First, novel Internet of Things (IoT) system is proposed, that integrates edge intelligence, motion–static synergy, which enables both coarse fine acquisition. To enhance efficiency value the IoT, this proposes an method based on...
Forest aboveground biomass (AGB) is a key indicator for evaluating carbon sequestration capacity and forest productivity. Accurate regional-scale AGB estimation crucial advancing research on global climate change, ecosystem cycles, ecological conservation. Traditional methods, whether based LiDAR or optical remote sensing, estimate using planar density (t/ha) multiplied by pixel area, which fails to account vertical structure variability. This study proposes novel “stereoscopic (stereo) ×...
The traditional production paradigm of large batch does not offer flexibility towards satisfying the requirements individual customers. A new generation smart factories is expected to support multi-variety and small-batch customized modes. For that, Artificial Intelligence (AI) enabling higher value-added manufacturing by accelerating integration information communication technologies, including computing, communication, control. characteristics a factory are include self-perception,...
Deep neural networks (DNNs) have been extremely successful in solving many challenging AI tasks natural language processing, speech recognition, and computer vision nowadays. However, DNNs are typically computation intensive, memory demanding, power hungry, which significantly limits their usage on platforms with constrained resources. Therefore, a variety of compression techniques (e.g., quantization, pruning, knowledge distillation) proposed to reduce the size consumption DNNs. Blockwise...
Signal measurement appearing in the form of time series is one most common types data used medical machine learning applications. Such datasets are often small size, expensive to collect and annotate, might involve privacy issues, which hinders our ability train large, state-of-the-art deep models for biomedical For time-series data, suite augmentation strategies we can use expand size dataset limited by need maintain basic properties signal. Generative Adversarial Networks (GANs) be...
Currently, the detection and localization of tea buds within unstructured plantation environment are greatly challenged due to their small size, significant morphological growth height variations, dense spatial distribution. To solve this problem, study applies an enhanced version YOLOv5 algorithm for bud in a wide field view. Also, small-size based on 3D point cloud technology is used facilitate identification picking points renowned tea-picking robot. enhance network, Efficient Channel...
Water quality sampling and monitoring are fundamental to water environmental protection. The purpose of this study was develop a multi-parameter system mounted on multi-rotor unmanned aerial vehicle (UAV). consisted the UAV, detection device, path planning algorithm. device composed rotating drum, direct current (DC) reduction motor, suction hose, high-pressure isolation pump, bottles, microcontroller. sensors for potential hydrogen (pH), turbidity, total dissolved solids (TDS), flight UAV...
In smart agricultural systems, the macroinformation sensing by adopting a mobile robot with multiple types of sensors is key step for sustainable development agriculture. Also, in region monitoring strategy that meets real-scene requirements, optimal operation robots necessary. this paper, cloud-assisted greenhouse presented. First, hybrid framework contains cloud, wireless network, and multisensor deployed to monitor wide-region greenhouse. Then, novel two phases designed ensure valid meet...
In an orchard environment with a complex background and changing light conditions, the banana stalk, fruit, branches, leaves are very similar in color. The fast accurate detection segmentation of stalk crucial to realize automatic picking using robot. this paper, method based on lightweight multi-feature fusion deep neural network (MFN) is proposed. proposed mainly composed encoding decoding networks, which sandglass bottleneck design adopted alleviate information loss high dimension....
Real-time object detection plays an indispensable role in facilitating the intelligent harvesting process of passion fruit. Accordingly, this paper proposes FSOne-YOLOv7 model designed to facilitate real-time The addresses challenges arising from diverse appearance characteristics fruit complex growth environments. An enhanced version YOLOv7 architecture serves as foundation for model, with ShuffleOne serving novel backbone network and slim-neck operating neck network. These architectural...