A5080759198- Advanced Neural Network Applications
- Non-Destructive Testing Techniques
- Machine Fault Diagnosis Techniques
- Domain Adaptation and Few-Shot Learning
- Advanced Sensor and Energy Harvesting Materials
- Tactile and Sensory Interactions
- Advanced Image and Video Retrieval Techniques
- Evaluation Methods in Various Fields
- Energy Efficient Wireless Sensor Networks
- Spectroscopy and Chemometric Analyses
- Advanced Wireless Communication Technologies
- Advanced Graph Neural Networks
- Advanced Materials and Mechanics
- Human Pose and Action Recognition
- Innovative Energy Harvesting Technologies
- Advanced Bandit Algorithms Research
- Magnetic Field Sensors Techniques
- Visual Attention and Saliency Detection
- Space Satellite Systems and Control
- Multimodal Machine Learning Applications
- Evolutionary Algorithms and Applications
- Photoacoustic and Ultrasonic Imaging
- Spectroscopy Techniques in Biomedical and Chemical Research
- Gait Recognition and Analysis
- Advanced Wireless Network Optimization
Anhui University
2020-2024
Hefei University of Technology
2019-2024
With the widespread adoption of green and sustainable development concepts, enhancing sensing performance flexible pressure sensors while reducing manufacturing costs environmental pollution has emerged as a pressing research issue. Drawing inspiration from bamboo, naturally occurring plant, we utilized virgin bamboo pulp raw material for producing draw paper. The resulting cylinder structure serves dielectric layer. We propose an extremely low-cost, user-friendly, origami method fabricating...
This study investigates a novel image morphology texture feature extraction method to realize the demagnetization fault location and severity detection of double-sided permanent magnet synchronous linear motor (DPMSLM). Initially, according constraints DPMSLMs topology structure, three lines magnetic density signal in air gap is extracted by finite element analysis as effective signal. Then, grayscale fusion (GFI) introduced transform 1D data 2D fused which can better describe information....
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Streaming feature selection techniques have become essential in processing real-time data streams, as they facilitate the identification of most relevant attributes from continuously updating information. Despite their performance, current algorithms to streaming frequently fall short managing biases and avoiding discrimination that could be perpetuated by sensitive attributes, potentially leading unfair outcomes resulting models. To address this issue, we propose FairSFS, a novel algorithm...
Since underground environments, such as urban subways, tunnels, pipe corridors, and mine roadways, etc., are complex changeable, the software functions of sensor nodes in spaces must be updated regularly to satisfy requirements monitoring center. Software updates cannot traditionally conducted due large number nodes, wide distribution range poor environment; they can only made using wireless reprogramming. Current reprogramming protocols all designed for topologically unconstrained networks...
Raman imaging (RI) is an outstanding technique that enables molecular-level medical diagnostics and therapy assessment by providing characteristic fingerprint morphological information about molecules. However, obtaining high-quality images generally requires a long acquisition time, up to hours, which prohibitive for RI applications of timely cytopathology histopathology analyses. To address this issue, image super-resolution (SR) based on deep learning, including convolutional neural...
This paper presents a new non-invasive air gap flux density measurement method for permanent magnet synchronous linear motor (PMSLM) using tunneling magnetoresistance (TMR) sensor and convolutional neural networks-long short-term memory (CNN-LSTM) regression modeling. First, the analytical finite element models of magnetic field PMSLM are established as data basis. Second, TMR is used to measure external stray density. Gramian Angular Field combined with image similarity matching technology...
The state-of-the-art object detection frameworks often suffer from a performance decline when the feature distribution differences between source (training) domain and target (testing) are existed. To alleviate this problem, recent works proposed various adaptation methods to improve frameworks. Existing only consider discrepancy domains ignores unbalanced in class space under cross-domain settings, which can lead serious negative transfer problems. address issue, we propose novel for reduce...