A5100440801- Wireless Signal Modulation Classification
- Radar Systems and Signal Processing
- Advanced MIMO Systems Optimization
- Topic Modeling
- Advanced Wireless Communication Techniques
- Advanced Sensor and Control Systems
- Advanced Computational Techniques and Applications
- Wireless Communication Security Techniques
- Cooperative Communication and Network Coding
- Full-Duplex Wireless Communications
- Advanced Measurement and Detection Methods
- Blind Source Separation Techniques
- Advanced Algorithms and Applications
- Antenna Design and Analysis
- Advanced SAR Imaging Techniques
- Wireless Communication Networks Research
- Direction-of-Arrival Estimation Techniques
- Advanced Wireless Communication Technologies
- Infrared Target Detection Methodologies
- Speech and Audio Processing
- Neural Networks and Applications
- Anomaly Detection Techniques and Applications
- Network Security and Intrusion Detection
- Antenna Design and Optimization
- Optical Systems and Laser Technology
Nanjing University of Information Science and Technology
2018-2025
Xidian University
2015-2025
Liupanshui Normal University
2025
Jiaxing University
2025
Wuhan Ship Development & Design Institute
2016-2024
Tianjin University of Technology
2024
Qinghai New Energy (China)
2024
Sinopec (China)
2024
Hunan University of Science and Technology
2023-2024
Hubei University of Technology
2009-2024
Mine water influx is a significant geological hazard during mine development, influenced by various factors such as conditions, hydrology, climate, and mining techniques. This phenomenon characterized non-linearity high complexity, leading to frequent accidents in coal mines. These not only impact production quality but also jeopardize the safety of staff. In order better predict amount surging mines provide an important basis for damage prevention work, based on time series data from...
Recent studies have demonstrated that using deep-learning (DL) methods to classify drones based on the radio-frequency (RF) signal is effective. As known, rich and diverse data an important guarantee for good identification performance. In reality, due complexity high dynamic of wireless environments, costs collection labeling with sufficient diversity are often unacceptable. this work, we propose a low-cost augmentation (DA) method improve robustness neural network (NN). It generates extra...
In this paper, we study the automatic modulation classification in a non-orthogonal multiple access system. To mitigate effect of interference, likelihood-based algorithm and fourth-order cumulant-based are proposed. Different from maximum likelihood classifier for single signal without function far near users' signals is derived. Then, marginal probability user obtained by using Bayesian formula. Hence, type can be determined maximizing probability. The high computational complexity renders...
The feature-based (FB) algorithms are widely used in modulation classification due to their low complexity. As a prerequisite step of FB, feature selection can reduce the computational complexity without significant performance loss. In this paper, according linear separability cumulant features, hyperplane support vector machine is classify types, and contribution different features ranked through weight vector. Then, selected using recursive elimination (RFE) identify type employed at...
Machine learning has demonstrated tremendous potential in solving real-world problems. However, with the exponential growth of data amount and increase model complexity, processing efficiency machine declines rapidly. Meanwhile, emergence quantum computing given rise to learning, which relies on superposition entanglement, exhibiting optimisation compared traditional learning. Therefore, paper, we survey basic concepts, algorithms, applications challenges Concretely, first review concepts...
In this paper, a nonlinear stochastic Markov switching system with Lévy noise is considered, and its stability investigated the assistance of Lyapunov theory. Firstly, sliding mode surface for designed, mean square exponential dynamics verified. Moreover, it proved that state can converge from initial to surface. After discretising continuous controller, demonstrated second moment difference bounded between states under discrete controller controller. Next, also ensured, maximum sampling...
With cybersecurity situation more and complex, data-driven security has become indispensable. Numerous data exists in textual sources analysis is difficult for both analyst the machine. To convert information into structured further automatic analysis, we extract cybersecurity-related entities propose a self-attention-based neural network model named entity recognition cybersecurity. Considering single word feature not enough identifying entity, introduce CNN to character which then...
With the increasing popularity of civilian unmanned aerial vehicles (UAVs), safety issues arising from unsafe operations and terrorist activities have received growing attention. To address this problem, an accurate classification positioning system is needed. Considering that UAVs usually use radio frequency (RF) signals for video transmission, in paper, we design a passive distributed monitoring can classify locate according to their RF signals. Specifically, three receivers are arranged...