A5060950799- Misinformation and Its Impacts
- Topic Modeling
- Spam and Phishing Detection
- Digital Media Forensic Detection
- Non-Invasive Vital Sign Monitoring
- Telecommunications and Broadcasting Technologies
- Wireless Signal Modulation Classification
- Gold and Silver Nanoparticles Synthesis and Applications
- Heart Rate Variability and Autonomic Control
- UAV Applications and Optimization
- Biosensors and Analytical Detection
- Video Surveillance and Tracking Methods
- Big Data and Digital Economy
- Advanced Measurement and Detection Methods
- Remote Sensing and LiDAR Applications
- Hemodynamic Monitoring and Therapy
- Photonic Crystals and Applications
- Image and Object Detection Techniques
- Image Processing Techniques and Applications
- Advanced biosensing and bioanalysis techniques
- Plant Surface Properties and Treatments
- Forest Insect Ecology and Management
- Insect behavior and control techniques
- Data-Driven Disease Surveillance
- Advanced Malware Detection Techniques
Nanjing Forestry University
2024-2025
Fudan University
2023-2024
Beijing University of Posts and Telecommunications
2021-2023
China Astronaut Research and Training Center
2013-2014
Fake news detection (FND) has attracted much research interests in social forensics. Many existing approaches introduce tailored attention mechanisms to fuse unimodal features. However, they ignore the impact of cross-modal similarity between modalities. Meanwhile, potential pretrained multimodal feature learning models FND not been well exploited. This paper proposes an FND-CLIP framework, i.e., a News Detection network based on Contrastive Language-Image Pretraining (CLIP). extracts deep...
The easy sharing of multimedia content on social media has caused a rapid dissemination fake news, which threatens society's stability and security. Therefore, news detection garnered extensive research interest in the field forensics. Current methods primarily concentrate integration textual visual features but fail to effectively exploit multi-modal information at both fine-grained coarse-grained levels. Furthermore, they suffer from an ambiguity problem due lack correlation between...
Labor shortages in the Chinese tea industry have accelerated need for crop protection unmanned aerial vehicles (CP-UAVs), which can greatly improve working efficiency. However, CP-UAV operational parameters must be optimized effective pest control. In this study, spraying performance of two CP-UAVs (DJI T30 and T40) under different were compared gardens. Additionally, utility controlling leafhoppers was investigated. Droplet coverage size increased as spray volume both (from 30 L·ha−1 to 90...
Deceptive images can be shared in seconds with social networking services, posing substantial risks. Tampering traces, such as boundary artifacts and high-frequency information, have been significantly emphasized by massive networks the Image Manipulation Localization (IML) field. However, they are prone to image post-processing operations, which limit generalization robustness of existing methods. We present a novel Prompt-IML framework. observe that humans tend discern authenticity an...
Pioneer researches recognize evidences as crucial elements in fake news detection apart from patterns. Existing evidence-aware methods either require laborious pre-processing procedures to assure relevant and high-quality evidence data, or incorporate the entire spectrum of available all cases, regardless quality quantity retrieved data. In this paper, we propose an approach named \textbf{SEE} that retrieves useful information web-searched annotation-free with early-termination mechanism....
The fluctuation of heart rate within each respiratory cycle that called sinus arrhythmia (RSA) is often observed in healthy persons. present study investigated the modulation on time span and amplitude indices Electrocardiogram (ECG) Photoplethysmogram (PPG). Totally 25 from ECG lead V5 PPG left finger were extracted 32 subjects during a controlled respiration test with breathing frequency at 0.09 Hz, 0.17 0.25 Hz 0.32 orderly sequence, effort signal was simultaneously recordings by...
The signal-to-noise ratio (SNR) is an effective evaluation index for channel status and communication quality, plays important role in signal analysis. Under the gradual complexity of unmanned aerial vehicle (UAV) remote control environment rapid development neural network models deep learning, this paper proposes a convolutional (CNN) model-based SNR estimation method UAV environment. We construct simulation dataset with different SNRs, then train model its parameters, save better...
In this paper, an Unmanned Aerial Vehicles (UAV) control signal detection scheme is proposed with Convolutional Neural Network (CNN). More specifically, the sampled images of UAV are considered to train classical LeNet network under various signal-to-noise ratios (SNR). The simulation experiments state that performance greatly improved. addition, conclusion drawn increase in image size helps improve performance.
With the development of information technology, unmanned aerial vehicles (UAVs) have become an indispensable and important part daily life they brought great convenience to life. Evaluating signal-to-noise ratio (SNR) UAV communication link is vital improve performance between user. The classical SNR evaluation schemes are limited in terms performance, while deep learning (DL) based always at expense computation complexity. To solve issues mentioned above, a two-path convolution neural...