Fenghe Zhang
A5022276175- Astrophysical Phenomena and Observations
- Pulsars and Gravitational Waves Research
- Gamma-ray bursts and supernovae
- Advanced Neural Network Applications
- Industrial Vision Systems and Defect Detection
- Remote Sensing and LiDAR Applications
- Advanced Malware Detection Techniques
- Power Line Inspection Robots
- 3D Surveying and Cultural Heritage
- Mechanics and Biomechanics Studies
- Optical Network Technologies
- Indoor and Outdoor Localization Technologies
- Mobile Crowdsensing and Crowdsourcing
- Photovoltaic System Optimization Techniques
- Privacy-Preserving Technologies in Data
- Image Enhancement Techniques
- Web Application Security Vulnerabilities
- Software Engineering Research
- Advanced Photonic Communication Systems
- Photonic and Optical Devices
Lanzhou Jiaotong University
2023-2024
Liaoning Technical University
2024
Peking University
2023
Institute of High Energy Physics
2020
Chinese Academy of Sciences
2020
The detection of software vulnerability is an important and challenging problem. Existing studies have shown that deep learning-based approaches can significantly improve the performance due to their powerful capabilities automatic learning semantically rich code representation. However, source methods still limited ability for remote contextual dependency information between statements. In this paper, we propose a slice-level via Transformer, dubbed VulD-Transformer, which designed detect...
A link between magnetars and fast radio burst (FRB) sources has finally been established. In this context, one of the open issues is whether/which extra galactic FRBs exhibit X/gamma-ray outbursts whether it correlated with activity. We aim to constrain possible activity from nearest extragalactic FRB currently known over a broad energy range, by looking for bursts range timescales energies that are compatible being powerful flares magnetars. followed up as-yet source at mere 149 Mpc...
After 34 years, the black-hole candidate EXO 1846-031 went into outburst again in 2019. We investigate its spectral properties hard intermediate and soft states with NuSTAR Insight-HXMT. A reflection component has been detected two but possibly originating from different illumination spectra: state, illuminating source is attributed to a coronal component, which commonly observed other X-ray binaries, whereas state probably produced by disk self-irradiation. Both cases support as low...
To address the limitations of deep learning models in detecting aerial insulator images from Unmanned Aerial Vehicles, we present a framework dubbed DP-FedIOD, which utilizes differential privacy and federated techniques for identifying insulators. It tackles issue posed by current algorithms inspecting insulators, employ horizontal anchor frames are incapable precisely both insulators their defective parts. In addition, this study addresses data being safeguarded laws policies that impede...
Aiming at the limitation of aerial insulators detection by Unmanned Aerial Vehicle(UAV) combined with deep learning technology, we propose a federated framework for orientation detection, dubbed FedIOD. It addresses challenge utilizing original insulator image data, which cannot be involved in centralized model training due to reasons policy and confidentiality, as well horizontal anchor boxes select their defective regions inaccurately. In FedIOD, improve head structure loss function YOLOv5...
We propose a low-complexity and IF-free radio-over-fiber scheme using low-pass delta-sigma modulator RZ shaping for both sub-6GHz millimeter-wave bands. Up to 262144-QAM, 65536-QAM 4096-QAM formats are experimentally delivered at 28-GHz, 30-GHz, 48-GHz carrier frequency over 10-km IM-DD SMF link, respectively.