A5012669792- Infrastructure Maintenance and Monitoring
- Advanced Neural Network Applications
- Remote-Sensing Image Classification
- 3D Surveying and Cultural Heritage
- Microfluidic and Capillary Electrophoresis Applications
- Advanced Image Fusion Techniques
- Advanced biosensing and bioanalysis techniques
- Luminescence and Fluorescent Materials
- Molecular Sensors and Ion Detection
- Analytical Chemistry and Chromatography
- Grouting, Rheology, and Soil Mechanics
- Geotechnical Engineering and Analysis
- Remote Sensing and LiDAR Applications
- Geotechnical Engineering and Underground Structures
- Nanopore and Nanochannel Transport Studies
- 3D Printing in Biomedical Research
- Rock Mechanics and Modeling
- Image and Object Detection Techniques
- Infrared Target Detection Methodologies
- Industrial Vision Systems and Defect Detection
- Robotics and Sensor-Based Localization
- Soil and Unsaturated Flow
- Advanced Sensor and Energy Harvesting Materials
- Single-cell and spatial transcriptomics
- Image Processing and 3D Reconstruction
China West Normal University
2025
Tongji University
2023-2025
Hohai University
2023-2024
Dalian Institute of Chemical Physics
2018-2021
Chinese Academy of Sciences
2018-2021
China Pharmaceutical University
2016-2018
Ministry of Education of the People's Republic of China
2016-2017
Hebei University
2017
Utilizing Unmanned Aerial Vehicles (UAV) and instance segmentation for construction site monitoring(such as machinery operation surfaces) offers a significant leap in management efficiency over traditional manual supervision methods. However, UAV-based remote sensing images, the subtle presence of image features resemblances among various operational surfaces make it difficult to segment instances. To address these challenges, this study proposed novel model based on YOLOv8-seg model. Given...
Abstract This study presents a comprehensive analysis and improvement of the YOLOv8-n algorithm for object detection, focusing on integration Wasserstein Distance Loss, FasterNext, Context Aggravation strategies. Through detailed ablation study, each strategy was systematically evaluated individually collectively to assess its contribution model's performance. The results indicate that uniquely enhances performance, significantly increasing mAP reducing model complexity when all three are...
Achieving highly selective detections of Ag+ and Hg2+ is great importance because their excessive emission can cause many diseases. Herein, a novel large Stokes shift fluorescent probe DKT based on dansyl fluorophore modified peptide biomolecules (NH2-Thr-Lys-Thr-NH2) was successfully synthesized with high yield, which simultaneously detect (turn on) off) different response patterns in 100% aqueous solution. also enables quantitative detection LODs 37.1 nM 26.7 nM, respectively. Besides,...
Despite rapid progresses in single-cell analysis technologies, efforts to control the three-dimensional microenvironment for single cell measurements have been lacking. Here, we report a simple method incorporate scaffolds, including polyvinylidene fluoride (PVDF) membranes and PVDF membrane replicated analog polydimethylsiloxane, into multiplexed secretomic platforms (including microwell array barcode microchip) mimic extracellular physical matrix mechanical support cells. Applying this...
Abstract Object detection in remote sensing imagery exhibits difficulties due to complex backgrounds, diverse object scales, and intricate spatial context relationships. Motivated by the problems mentioned above, this paper introduces AeroDetectNet, a novel lightweight high-precision network custom-designed for aerial scenarios, building upon YOLOv7-tiny algorithm. It enhances performance through four key improvements: normalized Wasserstein distance consistent size sensitivity, Involution...
The objective of this study is to investigate the methods for soil liquefaction discrimination. Typically, predicting potential involves conducting standard penetration test (SPT), which requires field testing and can be time-consuming labor-intensive. In contrast, cone (CPT) provides a more convenient method offers detailed continuous information about layers. study, feature matrix based on CPT data proposed predict blow count <i>N</i>. comprises characteristic parameters at specific...
Aiming at the problem that mathematical expressions in unstructured text fields of documents are hard to be extracted automatically, rapidly and effectively, a method based on Hidden Markov Model (HMM) is proposed. Firstly, this trained HMM model through employing symbol combination features expressions. Then, some preprocessing works such as removing labels filtering words were carried out. Finally, preprocessed was converted into an observation sequence input determine which expression...
Abstract A major goal of polydimethylsiloxane (PDMS) microfabrication is to develop a simple and inexpensive method for rapid fabrication. Despite the recent advancements in this field, facile PDMS on non-planar surfaces remains elusive. Here we report prototyping microdevices via µ PLAT (microscale plasma-activated templating) through micropatterning hydrophilic/hydrophobic (HL/HB) interface by flexible polyvinyl chloride (PVC) hollow-out mask. This mask can be easily prepared with PVC film...
Abstract Soil classification is a critical issue in geological engineering, with the Cone Penetration Test (CPT) being an effective in-situ testing technique to record variation of soil characteristics. Despite many studies that have been conducted on relationship between CPT parameters and categories, analyzing specific areas essential due high uncertainty geotechnical. In this study, we analyzed categories based layers Shanghai region. The CPT-based indirect method requires additional...