A5110550486- Higher Education and Teaching Methods
- Higher Education Governance and Development
- Topic Modeling
- Natural Language Processing Techniques
- Industrial Vision Systems and Defect Detection
- Antenna Design and Analysis
- Advanced Database Systems and Queries
- Advanced Graph Neural Networks
- Advanced Neural Network Applications
- Text and Document Classification Technologies
- Ideological and Political Education
- Visual Attention and Saliency Detection
- Welding Techniques and Residual Stresses
- Data Management and Algorithms
- Antenna Design and Optimization
- Semantic Web and Ontologies
- Data Quality and Management
- Enzyme Production and Characterization
- Boron Compounds in Chemistry
- Advanced SAR Imaging Techniques
- Family Business Performance and Succession
- Enzyme Catalysis and Immobilization
- Plant Disease Management Techniques
- Millimeter-Wave Propagation and Modeling
- Machine Learning in Healthcare
Shanxi Normal University
2025
Peking University
2018-2025
Xi'an Jiaotong University
2024-2025
Xi'an Polytechnic University
2023-2024
Software (Spain)
2024
Polytechnic University
2023
Beijing University of Chemical Technology
2023
Xi’an Jiaotong-Liverpool University
2023
Center for NanoScience
2022
South China University of Technology
2022
Abstract Heteroatom doping and structural modification can significantly improve the electrochemical properties of carbon materials, but it is difficult to achieve synchronous control two. To this end, N‐doped porous material (BCNK) was synthesized using bombyx mori silk as source, melamine KHCO 3 activators. When only added, prepared (BCN) increases heteroatom content. (BCK) specific surface area pore volume. The microstructure heteratom content materials be controlled simultaneously by...
In the past decades, numerous clinical researches have been conducted to illuminate effects of traditional Chinese medicine for better inheritance and promotion it, which are mostly trials designed from doctor's point view. This large-scale data mining study was real-world view in up 10 years' big sets Traditional Medicine (TCM) China, including both medical visits hospital cyberspace contemporaneous social survey data. Finally, some important interesting findings appear: (1) More Criticisms...
The regular detection of weld seams in large-scale special equipment is crucial for improving safety and efficiency, this can be achieved effectively through the use seam tracking robots. In study, a wall-climbing robot with integrated was designed, wall climbing function realized via permanent magnet array Mecanum wheel. using DeepLabv3+ semantic segmentation model. Several optimizations were implemented to enhance deployment model on embedded devices. Mobilenetv2 used replace feature...
Abstract The detection of masks is great significance to the prevention occupational diseases such as infectious and dust diseases. For problems small target size, large number targets, mutual occlusion in mask-wearing detection, a algorithm based on improved YOLOv5s proposed present work. First, ultra-lightweight attention mechanism module ECA was introduced Neck layer improve accuracy model. Second, influence different loss functions (GIoU, CIoU, DIoU) model explored, CIoU determined...
Abstract Few-shot Aspect Category Sentiment Analysis (ACSA) is a crucial task for aspect-based sentiment analysis, which aims to detect polarity given aspect category in sentence with limited data. However, few-shot learning methods focus on distance metrics between the query and support sets classify queries, heavily relying distributions embedding space. Thus, they suffer from overlapping of embeddings caused by irrelevant noise among sentences multiple aspects, leading misclassifications....
Cross-domain Consultation Systems have become essential in numerous critical applications, for instance, an online citizen complaint system. However, addressing complaints with distinct orality characteristics often necessitates retrieving and integrating knowledge from diverse professional domains. This scenario represents a typical cross-domain problem. Nevertheless, the prevailing approach of utilizing generative large language models to tackle this problem presents challenges including...
Large language models (LLMs) have demonstrated their vast potential and value in natural processing tasks beyond. However, when these are applied to develop consultation systems for industrial domains, such as e-government, intelligent diagnosis, legal consultancy, they encounter many unresolved technical issues. These include the scale of models, lack tight fusion with existing industry knowledge, along occurrences model hallucinations inadequate explainability. Unlike general-purpose...
Abstract With the rapid development of Internet Things (IoT) and cloud computing, a large amount IoT data has been stored shared in servers. However, sensitive may be leaked by untrusted servers, which is key problem hindering IoT-cloud systems. To solve this problem, searchable encryption presented, enables devices to encrypt collected before uploading them make retrievals over encrypted keyword queries. In paper, we will study attribute-based search (ABKS), relieves us from cumbersome...
Finding out the method of handling missing information is essential for system efficiency and robustness in field database. The sparsity massive data big environment makes problem more prominent. existing methods either have limited semantic expression ability or do not consider influence environment. Missing large-scale sparse tends to richer semantics, leading complex computational logic, as well affecting operations such queries. To solve these problems, this paper proposes a novel...