A5042679796- Text and Document Classification Technologies
- High voltage insulation and dielectric phenomena
- Advanced Measurement and Detection Methods
- Image Retrieval and Classification Techniques
- Advanced Image Fusion Techniques
- Face and Expression Recognition
- Plasma Diagnostics and Applications
- Machine Fault Diagnosis Techniques
- Infrared Target Detection Methodologies
- Image Enhancement Techniques
- Plasma Applications and Diagnostics
- Remote-Sensing Image Classification
- Advanced Sensor and Control Systems
- Fault Detection and Control Systems
- Global Trade and Competitiveness
- Advanced Computational Techniques and Applications
- Machine Learning in Bioinformatics
- Power Transformer Diagnostics and Insulation
- Remote Sensing and Land Use
- Machine Learning and ELM
- Smart Grid and Power Systems
- Optical Systems and Laser Technology
- Spam and Phishing Detection
- High-Voltage Power Transmission Systems
- Advanced Malware Detection Techniques
Anhui University
2020-2024
Northwestern Polytechnical University
2005-2022
Shandong Academy of Sciences
2018-2022
Qilu University of Technology
2018-2022
BaiCheng Normal University
2022
Guangzhou University
2022
Beijing University of Posts and Telecommunications
2022
Academy of Military Medical Sciences
2022
Harbin Engineering University
2015-2021
National University of Defense Technology
2021
This article presents a novel path planning algorithm for autonomous land vehicles. There are four main contributions: Firstly, an evaluation standard is introduced to measure the performance of different algorithms and select appropriate parameters proposed algorithm. Secondly, guideline generated by human or global employed develop heuristic function overcome shortcoming traditional A-Star algorithms. Thirdly, improving obstacle avoidance performance, key points around employed, which...
Remaining Useful Life (RUL) prediction is one of the difficulties in prognostics and system health management (PHM) bearings. Moreover, due to limitations test cost equipment, it isn't easy obtain abundant full life cycle experimental samples bearings, which cannot provide enough training further improve accuracy RUL prediction. To address these problem, this paper proposes a rolling bearing method based on coupled diffusion probabilistic model time attention mechanism (CDTA). This first...
In the multi-view multi-label (MVML) classification problem, multiple views are simultaneously associated with semantic representations. Multi-view learning inevitably has problems of consistency, diversity, and non-alignment among correlation labels. Most existing methods for non-aligned assume that each view a common or shared label set, but because single cannot contain entire information, they often learn suboptimal results. Based on this, this paper proposes method learns view-specific...
We consider the problem of unsupervised domain adaptation for image classification. To learn target-domain-aware features from unlabeled data, we create a self-supervised pretext task by augmenting data with certain type transformation (specifically, rotation) and ask learner to predict properties transformation. However, obtained feature representation may contain large amount irrelevant information respect main task. provide further guidance, force augmented be consistent that original...
Abstract The maintenance costs, productivity, health, and safety of mechanical equipment all heavily rely on the remaining usable life (RUL) bearings. Recently, transformer has been widely used in RUL field due to its ability capture some degradation information bearing. However, is weak acquiring local fails extract temporal features from process. To solve above problems, this paper proposes a spatio-temporal convolutional (STCT) model, which mainly consists dual network (DCSTN) multi-scale...
Abstract Maximum average kurtosis deconvolution (MAKD) effectively enhances periodic impulses in vibration signals. However, under conditions of random impulse interference, MAKD tends to amplify within a single period. To address this problem, paper proposes maximum morphological (MAKMD) method. First, on the basis proposing time-varying structural element more line with characteristics signals and constructing new gradient squared operator, an enhanced filtering (ETVMF) is proposed. Then,...
Enhancing the contrast and projecting edge is two important functions of lateral inhibition network. Some image details are lost when infrared processed based on traditional algorithm. A new method that weightingly added to original one proposed. The algorithm can not only project edge, but also overcome above-mentioned shortage. simulation results show its effectivity.