Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleSeptember 2024
Adversarial sample attacks algorithm based on cycle-consistent generative networks
AbstractIn recent years, the application of deep neural networks in the field of image classification has become increasingly widespread. However, existing researches have exposed the inherent vulnerabilities and opacity of these network models, ...
Highlights- We proposed an optimized cycle-consistent generative network for adversarial attacks, ultimately enhancing the success rate against other diverse black-box models.
- Our algorithm offers support for both targeted and non-targeted ...
- research-articleFebruary 2024
Robust multi-task learning network for complex LiDAR point cloud data preprocessing
Expert Systems with Applications: An International Journal (EXWA), Volume 237, Issue PBhttps://doi.org/10.1016/j.eswa.2023.121552AbstractThe utilization of 3D point clouds acquired via Light Detection and Ranging (LiDAR) is widespread in the fields of autonomous driving, satellite remote sensing, and spatial mapping. However, due to hardware limitations of the laser launch system ...
Highlights- Propose a multi-task learning network for point cloud robust pre-processing.
- Design the three branch network structures based on the preprocessing functions.
- Devise two flexible network training methods.
- Analysis model ...
- research-articleDecember 2023
Homomorphic Compression: Making Text Processing on Compression Unlimited
Proceedings of the ACM on Management of Data (PACMMOD), Volume 1, Issue 4Article No.: 271, Pages 1–28https://doi.org/10.1145/3626765Lossless data compression is an effective way to handle the huge transmission and storage overhead of massive text data. Its utility is even more significant today when data volumes are skyrocketing. The concept of operating on compressed data infuses ...
- research-articleOctober 2023
Enabling Efficient Random Access to Hierarchically Compressed Text Data on Diverse GPU Platforms
- Yihua Hu,
- Feng Zhang,
- Yifei Xia,
- Zhiming Yao,
- Letian Zeng,
- Haipeng Ding,
- Zhewei Wei,
- Xiao Zhang,
- Jidong Zhai,
- Xiaoyong Du,
- Siqi Ma
IEEE Transactions on Parallel and Distributed Systems (TPDS), Volume 34, Issue 10Pages 2699–2717https://doi.org/10.1109/TPDS.2023.3294341The tremendous computing capacity of GPU offers significant potential in processing hierarchically compressed text data without decompression. However, current GPU techniques offer only traversal-based text data analytics; random access is exceedingly ...
- research-articleSeptember 2023
Bio-inspired multi-level interactive contour detection network
AbstractEncoding-decoding convolutional neural network structures have shown powerful performance in contour detection tasks, however, the design of models in the past seems to have little reference to physiological mechanisms, especially ...
-
- research-articleAugust 2023
A surrogate-assisted evolutionary algorithm based on multi-population clustering and prediction for solving computationally expensive dynamic optimization problems
Expert Systems with Applications: An International Journal (EXWA), Volume 223, Issue Chttps://doi.org/10.1016/j.eswa.2023.119815AbstractThe computationally expensive dynamic optimization problems (CEDOPs) arise when the objective function of a dynamic optimization problem is prohibitively expensive, or even almost impossible, to obtain. Such problems are extremely challenging ...
- research-articleJanuary 2023
Trajectory planning method of 6-DOF modular manipulator based on polynomial interpolation
Journal of Computational Methods in Sciences and Engineering (JOCMSE), Volume 23, Issue 3Pages 1589–1600https://doi.org/10.3233/JCM-226672Robots are widely used in all walks of life, and their excellent work efficiency has been paid attention to. As the key component of robot, manipulator plays an important role in the running performance of robot. In order to effectively improve ...
- research-articleJanuary 2023
An Intersatellite Link Assignment Design for Megaconstellation Based on NSGA-II
The exploitation of intersatellite links (ISLs) makes the LEO satellite constellation based Internet service widely favored due to its advantages of low-latency and high-speed communications. However, considering the time-varying network topology, limited ...
Optimizing random access to hierarchically-compressed data on GPU
SC '22: Proceedings of the International Conference on High Performance Computing, Networking, Storage and AnalysisArticle No.: 18, Pages 1–15GPU's powerful computational capacity holds great potentials for processing hierarchically-compressed data without decompression in data science domain. Unfortunately, existing GPU approaches offer only traversal-based data analytics; random access is ...
- research-articleAugust 2022
Bio-inspired feature enhancement network for edge detection
Applied Intelligence (KLU-APIN), Volume 52, Issue 10Pages 11027–11042https://doi.org/10.1007/s10489-022-03202-2AbstractAs the basis of mid-level and high-level vision tasks, edge detection has great significance in the field of computer vision. Edge detection methods based on deep learning usually adopt the structure of the encoding-decoding network, among which ...
- research-articleJanuary 2022
Application of Image Fusion Algorithm Combined with Visual Saliency in Target Extraction of Reflective Tomography Lidar Image
Reflective tomography Lidar has been proved to be a new Lidar system with long distance and high resolution. The reflective tomography Lidar image is prone to clutter and artifacts; thus, it is important for space target recognition to extract the target ...
- research-articleOctober 2021
A Direct Starting Method of Doubly-Fed Induction Machine for Shipboard Propulsion System Application
2021 24th International Conference on Electrical Machines and Systems (ICEMS)Pages 949–954https://doi.org/10.23919/ICEMS52562.2021.9634642This paper proposes a method to start a doubly-fed induction machine (DFIM) directly. Firstly, by applying the open-loop control, the three-phase rotor currents are measured at the instant when the stator voltages are close to the DFIM starting voltages. ...
- research-articleOctober 2021
An Improved Sliding Mode Observer for Position Sensorless Synchronous Reluctance Motor Drives
2021 24th International Conference on Electrical Machines and Systems (ICEMS)Pages 844–849https://doi.org/10.23919/ICEMS52562.2021.9634580To improve the position estimation for synchronous reluctance motor (SynRM) drives, an new full-order sliding mode observer (SMO) designed by using sinusoidal saturation function is presented. Firstly, the full-order SMO taking the extended electromotive ...
- research-articleOctober 2021
Beat Phenomenon Suppression Method Based on Repetitive Control for Reduced DC-link Capacitance IPMSM Drives
2021 24th International Conference on Electrical Machines and Systems (ICEMS)Pages 626–631https://doi.org/10.23919/ICEMS52562.2021.9634525The stator current harmonics can be caused by the sampling mode and control delay of the DC-link voltage. The interaction between the stator current harmonics and the fundamental current stimulates the beat phenomenon, which causes additional noise and ...
- research-articleOctober 2021
Adaptive PLL for High-Frequency Signal Injection Based Sensorless PMSM Drives
2021 24th International Conference on Electrical Machines and Systems (ICEMS)Pages 850–855https://doi.org/10.23919/ICEMS52562.2021.9634466In order to improve the performance for high-frequency signal injection based sensorless permanent magnet synchronous motor (PMSM) drive, an improved position demodulation scheme is presented to track the position without the phase delay. On this basis, a ...
- research-articleOctober 2021
Field-Weakening Control Strategy of High-Speed Permanent Magnet Synchronous Motor Based on Improved Voltage Phase Angle Control
2021 24th International Conference on Electrical Machines and Systems (ICEMS)Pages 641–646https://doi.org/10.23919/ICEMS52562.2021.9634325Aiming at the poor voltage regulation ability of permanent magnet synchronous motor (PMSM) at high speed, an improved flux-weakening strategy based on the voltage angle control (VAC) method is proposed. The closed-loop transfer function of the control ...
- research-articleDecember 2020
Multi-source, multi-object and multi-domain (M-SOD) electromagnetic interference system optimised by intelligent optimisation approaches
Natural Computing: an international journal (NATC), Volume 19, Issue 4Pages 713–732https://doi.org/10.1007/s11047-019-09728-8AbstractWith the wide use of electromagnetic information equipment, a large number of wireless radiation systems coexisting in the same region produce intentional or unintentional interference on electronic receivers. For the purpose of intentional ...
- research-articleNovember 2020
Direct Power Control of Fault-Tolerant Converter-Based Doubly-Fed Induction Machine Electric Drivetrain for Ship Propulsion
2020 23rd International Conference on Electrical Machines and Systems (ICEMS)Pages 1269–1274https://doi.org/10.23919/ICEMS50442.2020.9291198The safe operation is the primary concern for a shipboard propulsion system (SPS), and fast dynamic response is also required to ensure the actual output power can track the reference value instantly. This paper proposes a modified space vector modulation-...
- research-articleJanuary 2020
Riddled Attraction Basin and Multistability in Three-Element-Based Memristive Circuit
By coupling a diode bridge-based second-order memristor and an active voltage-controlled memristor with a capacitor, a three-element-based memristive circuit is synthesized and its system model is then built. The boundedness of the three-element-based ...
- research-articleOctober 2019
Control of Doubly-Fed Induction Motor Based Shipboard Propulsion System for More-Electric Ships
IECON 2019 - 45th Annual Conference of the IEEE Industrial Electronics SocietyPages 3187–3192https://doi.org/10.1109/IECON.2019.8927754In this paper, a doubly-fed induction motor (DFIM) based shipboard propulsion system (SPS) is proposed for more-electric ships (MESs). Two power flow paths are presented, which are based on direct AC power transmission and power decoupling with back-to-...