A5089221278- Energy Efficient Wireless Sensor Networks
- Advanced Image and Video Retrieval Techniques
- Animal Vocal Communication and Behavior
- Fire Detection and Safety Systems
- Domain Adaptation and Few-Shot Learning
- Video Surveillance and Tracking Methods
- Metallurgical Processes and Thermodynamics
- Iron and Steelmaking Processes
- Wireless Sensor Networks and IoT
- Advanced Sensor and Control Systems
- Advanced Neural Network Applications
- Indoor and Outdoor Localization Technologies
- Robotic Path Planning Algorithms
- Music and Audio Processing
- Remote Sensing and LiDAR Applications
- Visual Attention and Saliency Detection
- Advanced Computational Techniques and Applications
- Fire effects on ecosystems
- Remote-Sensing Image Classification
- Marine animal studies overview
- Water Quality Monitoring Technologies
- Remote Sensing and Land Use
- Species Distribution and Climate Change
- Multimodal Machine Learning Applications
- Advanced Algorithms and Applications
Beijing Forestry University
2014-2025
HBIS (China)
2020-2025
State Forestry and Grassland Administration
2022-2024
Beijing Municipal Ecological and Environmental Monitoring Center
2022
Institute of Microbiology
2010
Chinese Academy of Sciences
2010
Jilin Academy of Agricultural Sciences
2009
As we all know, the forest is considered as one of most important and indispensable resources, prevention detection fire, have been researched hotly in worldwide fire departments. Based on deficiencies conventional real time monitoring accuracy, wireless sensor network technique for was introduced, together with satellite monitoring, aerial patrolling manual watching, an omni-bearing stereoscopic air ground forest-fire pattern found so that decision fire-extinguishing or can be made rightly...
Unmanned air vehicle (UAV) systems for performing forestry applications have expanded in recent decades and great economic benefits. They are validated to be more appealing than traditional platforms various aspects, such as repeat rate, spatial resolution, accuracy. This paper consolidates the state-of-the-art unmanned field with a major focus on UAV heterogeneous platforms, which applied variety of applications, wood production, tree quantification, disease control, wildfire management,...
Camera traps serve as a valuable tool for wildlife monitoring, generating vast collection of images ecologists to conduct ecological investigations, such species identification and population estimation. However, the sheer volume poses challenge, integration deep learning into automated investigation tasks remains complex, particularly when dealing with low-quality in long-term monitoring programs. Existing approaches often struggle strike balance between image enhancement tasks, thereby...
Accurate prediction of alloying element yield has a significant impact on steel product quality, production costs, and refining efficiency. In this study, the stacking ensemble learning SHapley Additive exPlanations (SHAP) analysis are utilized, along with Bayesian optimization, to develop high‐precision explainable model for yield. Different evaluation criterion is applied compare other existing models. The findings indicate that outperforms models in predicting yield, achieving accuracy...
The Internet of Things (IoT)-based passive acoustic monitoring (PAM) has shown great potential in large-scale remote bird monitoring. However, field recordings often contain overlapping signals, making precise information extraction challenging. To solve this challenge, first, the inter-channel spatial feature is chosen as complementary to spectral obtain additional correlations between sources. Then, an end-to-end model named BACPPNet built based on Deeplabv3plus and enhanced with polarized...
Path planning of unmanned aerial vehicles (UAVs) in threatening and adversarial areas is a constrained nonlinear optimal problem which takes great amount static dynamic constraints into account. Quantum-behaved pigeon-inspired optimization (QPIO) has been widely applied to such problems. However, conventional QPIO suffering low global convergence speed local optimum. In order solve the above problems, an improved algorithm, adaptive operator QPIO, proposed this paper. Firstly, new...
Live fuel moisture content (LFMC) is an important index used to evaluate the wildfire risk and fire spread rate. In order further improve retrieval accuracy, two ensemble models combining deep learning were proposed. One a stacking model based on LSTM, TCN LSTM-TCN models, other Adaboost model. Measured LFMC data, MODIS, Landsat-8, Sentinel-1 remote sensing data auxiliary such as canopy height land cover of forest-fire-prone areas in Western United States, selected for our study, results...
Abstract To enhance the efficiency and sustainability, technical preparations were made for eliminating Temperature, Sample, Oxygen test of basic oxygen furnace (BOF) steelmaking process in this work. Utilizing data from 13,528 heats state-of-the-art (SOTA) machine learning (ML) deep algorithms, data-driven models with different types inputs developed, marking first use time series (off-gas profiles blowing practice related curves) BOF steelmaking’s endpoint prediction, tabular features...
Precision agriculture is the frontier of international contemporary in twentieth century. The development precision a significant strategic choice and agricultural science new stage China. As novel technology information acquisition processing, WSN possesses great meaning overall improving modernize level agriculture. Routing protocol an indispensable part which ensures normal operation wireless sensor network high efficient transmission information. existing routing protocols for are...
Desulphurization is essential in the steelmaking process for high-quality steel production, and sulphide capacity has proven to be an effective index evaluate desulphurization ability of molten slag or flux. Several analytical empirical models have been proposed calculate capacity. However, these usually show insufficient generalization when new variables/data are introduced, which limits their practical application. In this work, experimental data were collected from literature a...