A5101905108- Natural Language Processing Techniques
- Topic Modeling
- Robotic Path Planning Algorithms
- Robotics and Sensor-Based Localization
- Virtual Reality Applications and Impacts
- Advanced Algorithms and Applications
- Infrared Target Detection Methodologies
- Metaheuristic Optimization Algorithms Research
- Mobile Crowdsensing and Crowdsourcing
- Microplastics and Plastic Pollution
- Text and Document Classification Technologies
- Multimodal Machine Learning Applications
- Video Surveillance and Tracking Methods
- Text Readability and Simplification
- Water Quality Monitoring Technologies
- Distributed Control Multi-Agent Systems
- Advanced Neural Network Applications
- Evacuation and Crowd Dynamics
Jiangsu University
2025
Tongji University
2022-2025
Yanbian University
2022
Guizhou University
2022
Xi'an High Tech University
2019
With the rapid development of edge computing technology, edge-assisted unmanned aerial vehicle (UAV) networks have become popular, helping with fast and cost-effective data collection in mobile crowdsensing (MCS) environments. This paper investigates online problem for MCS over an UAV network architecture, where UAVs work to collect required by tasks at different on-ground point-of-interests (PoIs) autonomous cooperative manner. Different from conventional networks, nodes our help...
This paper proposes a dynamic unmanned aerial vehicle (UAV) clustering model for multi-target localization in complex 3D environments, where mobility-aware cluster formation is integrated to enhance collaborative accuracy. We derive the Cramér–Rao lower bound (CRLB) performance analysis under measurement and motion-induced uncertainties. To solve NP-hard problem, we develop MDQPSO-ASA algorithm, which combines multi-swarm discrete quantum-inspired particle swarm optimization with adaptive...
As China’s voluntary greenhouse gas emission reduction mechanism undergoes institutional revitalization, the accurate valuation of carbon assets such as China Certified Emission Reductions (CCERs) becomes increasingly critical for effective climate finance and sustainability-oriented investment. This study proposes an integrated value assessment model CCERs that combines Long Short-Term Memory (LSTM) neural network-based price forecasting with both discounted net cash flow method...
Abstract Recognizing named entities (NEs) is commonly treated as a classification problem, and class tag for word or an NE candidate in sentence predicted. In recent neural network developments, deep structures that map categorized features into continuous representations have been adopted. Using this approach, dense space saturated with high-order abstract semantic information unfolded, the prediction based on distributed feature representations. paper, positions of NEs are represented...
Recognizing named entities (NEs) is commonly conducted as a classification problem that predicts class tag for word or NE candidate in sentence. In shallow structures, categorized features are weighted to support the prediction. Recent developments neural networks have adopted deep structures map into continuous representations. This approach unfolds dense space saturated with high-order abstract semantic information, where prediction based on distributed feature this paper, positions of NEs...
Aiming at the disadvantage of premature convergence basic genetic algorithm, an adaptive simulated annealing tabu search algorithm is proposed. This fully combines global and adaptability strong climbing ability high efficiency strategy. It has adaptability. The simulation results are given compared with algorithm. show that better optimization performance, can solve combinatorial problem.
Mobile robots have been widely used in hazardous environments to obtain information about surroundings for humans. The volume and efficiency of sensing data can be significantly increased if multiple mobile collaboration are exploited. In recent years, deep learning reinforcement techniques applied the field robotics, which perform well many tasks including exploration unknown environments. this paper, address multi-robot problem, a multi-agent (MADRL) based method with centralized training...
With the rapid development of economy and society, output garbage increases with it, more flows into water. In order to facilitate multi-platform deployment extend detection underwater garbage, this paper improves on YOLOX-S algorithm as a lightweight algorithm, which has higher speed accuracy while having smaller number parameters. Firstly, Shufflenetv2 is experimentally selected enhance backbone feature extraction network reduce parameters model. Secondly, ECA attention mechanism effective...