A5055698339- Power System Optimization and Stability
- Optimal Power Flow Distribution
- Wireless Signal Modulation Classification
- Microgrid Control and Optimization
- Oil and Gas Production Techniques
- Video Surveillance and Tracking Methods
- Radar Systems and Signal Processing
- EEG and Brain-Computer Interfaces
- HVDC Systems and Fault Protection
- Machine Fault Diagnosis Techniques
- Fire Detection and Safety Systems
- Photonic and Optical Devices
- Speech Recognition and Synthesis
- Anomaly Detection Techniques and Applications
- Reservoir Engineering and Simulation Methods
- Fault Detection and Control Systems
- Frequency Control in Power Systems
- Neonatal and fetal brain pathology
- Advanced Memory and Neural Computing
- Blind Source Separation Techniques
- Digital Media Forensic Detection
- Time Series Analysis and Forecasting
- Speech and Audio Processing
- Advanced Optical Sensing Technologies
- Human Pose and Action Recognition
Shandong University
2016-2024
Xiamen University
2020-2022
Nowadays, radio broadcasting plays an important role in people's daily life. However, unauthorized stations may seriously interfere with normal broadcastings and further disrupt the management of civilian spectrum resources. Since they are easily hidden essentially same as signals, it still remains challenging to automatically effectively identify complicated electromagnetic environments. In this paper, we introduce manifold regularization-based deep convolutional autoencoder (MR-DCAE) model...
Automatic modulation classification (AMC) plays a critical role in both civilian and military applications. In this letter, we propose multi-scale radio transformer (Ms-RaT) with dual-channel representation for fine-grained (FMC). Ms-RaT, (DcR) of signals is designed to help the model learn discriminative features by converging multi-modality information, including frequency, amplitude, phase. During learning process, analysis introduced into form tighter decision boundary. Finally,...
In addition to maintaining the power balance, major tasks of multi-area automatic generation control (AGC) involve regulating exchange among subareas. This study presents a new flow model allowing for AGC that achieves cooperation participating generators, which are deployed separately in interconnected subarea networks. The formulations subareas derived from active equations tie-lines. node parameters representing level and allocation unbalanced introduced. Then, proposed is established by...
The fault detection of manned submersibles plays a very important role in protecting the safety submersible equipment and personnel. However, diving sensor data is scarce high-dimensional, so this paper proposes method, which made up feature selection module based on hierarchical clustering Autoencoder (AE), improved Deep Convolutional Generative Adversarial Networks (DCGAN)-based augmentation using Neural Network (CNN) with LeNet-5 structure. First, developed to select features that have...
Base on the power flow formulations, a new model that allows for exchanges among subareas of network and automation generation control in each subarea, is established. The proposed rendering by unified newton iteration formulation. Parameters representing level or allocation unbalancing are introduced to indicate performance generators participate control. exchange formulations derived from equations interconnected branches. Newton method used solve consist node injection equations. Because...
In recent years, Siamese trackers have shown great potentials in visual tracking. Most of these fix the template with initial target representation during on-line tracking and performance heavily depends on generalization matching network learnt off-line. this paper, we propose novel Template Diffusion Networks for adaption appearance variations To be more specific, embed new feature aggregation modules (FAMs) into a to generate accurate search region better matching. The FAMs can establish...
Abstract Deep learning has demonstrated notable success in mechanical signal processing with a large amount labelled data. However, the systems of Jiaolong deep‐sea submersible prone to malfunction are typically diverse, due high complexity its structure and operational environment. Consequently, this diversity gives rise variations types sensor signals their associated data distributions that require analysis. Unsupervised domain adaptation (UDA) uses transferable knowledge derived from...
The most common manifestation of neurological disorders in children is the occurrence epileptic seizures. In this study, we propose a multi-branch graph convolutional network (MGCNA) framework with multi-head attention mechanism for detecting seizures children. MGCNA extracts effective and reliable features from high-dimensional data, particularly by exploring relationships between EEG electrodes considering spatial temporal dependencies brains. This method incorporates three learning...
The Optimal Power Flow (OPF) problem for power systems could be expressed by a Non-Linear Programming (NLP) model, which is difficult to solved. This study presents practical algorithm solve OPF through successive linear programming (SLP), in conventional flow and linearized Sub-Problem (LSP) are solved alternating iteration. A Self-Adaptive Filter-Trust Region (SAIFT) method proposed the LSP, acceptance of current iteration point decided filter, step size controlled trust region. Wolfe...
Cover Caption: The cover image is based on the Research Article MR-DCAE: Manifold regularization-based deep convolutional autoencoder for unauthorized broadcasting identification by Qinghe Zheng et al., https://doi.org/10.1002/int.22586.