A5002223818- Complex Network Analysis Techniques
- Misinformation and Its Impacts
- Opinion Dynamics and Social Influence
- PAPR reduction in OFDM
- Advanced Text Analysis Techniques
- Face and Expression Recognition
- Traffic Prediction and Management Techniques
- Target Tracking and Data Fusion in Sensor Networks
- Network Security and Intrusion Detection
- Telecommunications and Broadcasting Technologies
- Recommender Systems and Techniques
- Inertial Sensor and Navigation
- Wireless Communication Networks Research
- Advanced Malware Detection Techniques
- Advanced Wireless Communication Techniques
- Advanced Vision and Imaging
- Computational and Text Analysis Methods
- Evolutionary Psychology and Human Behavior
- Remote-Sensing Image Classification
- Domain Adaptation and Few-Shot Learning
- Spam and Phishing Detection
- Orbital Angular Momentum in Optics
- Digital Marketing and Social Media
- Brain Tumor Detection and Classification
- Anomaly Detection Techniques and Applications
Chongqing University of Posts and Telecommunications
2012-2025
Chang'an University
2025
Northwestern Polytechnical University
2020-2025
Nanjing University of Aeronautics and Astronautics
2018-2024
Chongqing Medical University
2024
Second Affiliated Hospital of Chongqing Medical University
2024
Dalian Medical University
2024
Army Medical University
2024
Nantong University
2024
Hengyang Normal University
2024
The development of social networks has prompted a shift in marketing strategies, with surging demand for vertical domains characterized by high user stickiness and specialization. To address this, we propose traceability model based on domain preference heterogeneous networks. Firstly, considering the problem topic features metric influence users' degree propagation, are treated as latent semantics, user-topic association matrix sparse is densified using factor to mine information...
In order to solve the problem of low efficiency and accuracy in manual data collection traditional logistics management systems warehouse management, author proposes application artificial intelligence optimization research. The designed an RFID based system that includes layer, intermediate physical focusing on warehousing operations production manufacturing workshop. This can optimize process, dynamically intelligently perceive objects, achieve effective monitoring management. Establish a...
The accuracy and fault tolerance of filters are directly affected by the filter architecture algorithm, thus influencing navigation performance. chi square detection used in conventional reset federated is not sensitive to soft faults, it easy cause health subsystem be polluted through information sharing. It a challenge design an adaptive improve performance system. Therefore, taking Strapdown Inertial Navigation System/Global Positioning System/Celestial System/Synthetic Aperture Radar...
We propose and experimentally demonstrate the singular surface plasmon beam that presents a dark channel generated by point dislocation long diffraction-free propagation distance up to 70λ(sp). The is result of interference two polariton (SPP) plane waves, which are launched coupling gratings with lateral displacement. An aperture-type near-field scanning optical microscope used map intensity distribution SPP waves. propagating embedded in shown full-wave calculations later verified experiment.
The authors present a novel cardinalised probability hypothesis density (CPHD) algorithm under the assumption of glint measurement noise model with unknown inverse covariance. Noise parameters are assumed to have Gamma prior distribution so that predicted and updated PHDs can mixture Gaussians representations. A variational Bayesian expectation maximisation procedure is applied iteratively estimate distributions through random hypersurface CPHD prediction update steps. Simulation results...
Vertical federated learning can aggregate participant data features. To address the issue of insufficient overlapping in vertical learning, this study presents a generative adversarial network model that allows distributed augmentation. First, proposes FeCGAN for multiple participants with data, considering fact generate simulation samples. This is suitable sources and augment participants' local data. Second, to problem divergence caused by different distributions sources, aggregation...