A5101520275- Semantic Web and Ontologies
- Data Quality and Management
- Web Data Mining and Analysis
- Advanced Graph Neural Networks
- Data Management and Algorithms
- Advanced Database Systems and Queries
- Topic Modeling
- Information Retrieval and Search Behavior
- Advanced Neural Network Applications
- Medical Image Segmentation Techniques
- Bayesian Modeling and Causal Inference
- Reinforcement Learning in Robotics
- COVID-19 diagnosis using AI
- Image Retrieval and Classification Techniques
- Image Processing and 3D Reconstruction
- Essential Oils and Antimicrobial Activity
- Proteins in Food Systems
- Speech and Audio Processing
- Animal Diversity and Health Studies
- Natural Language Processing Techniques
- Phytochemistry and Biological Activities
- Explainable Artificial Intelligence (XAI)
- Protein Hydrolysis and Bioactive Peptides
- Traditional and Medicinal Uses of Annonaceae
- Speech Recognition and Synthesis
Wuhan Institute of Technology
2024
University of Oxford
2024
Nanjing University
2019-2022
Anhui Academy of Agricultural Sciences
2013-2017
Institute of Animal Sciences
2013
Background To isolate plant-derived compounds with antimicrobial activity from the leaves of Mikania micrantha, to determine configuration, and evaluate their against eight plant pathogenic fungi (Exserohilum turcicum, Colletotrichum lagenarium, Pseudoperonispora cubensis, Botrytis cirerea, Rhizoctonia solani, Phytophthora parasitica, Fusarium Pythium aphanidermatum,) four bacteria (gram negative bacteria: Ralstonia dolaanacearum, Xanthomonas oryzae pv. Oryzae, Campestris Vesicatoria,...
Abstract Casein micelles contribute to the physicochemical properties of milk and may also influence its functionality. At present, however, there is an incomplete understanding casein micelle associated proteins diversity among obtained from different species. Therefore, samples were collected seven dairy animals groups, fractions prepared by ultracentrifugation their constituent identified liquid chromatography tandem mass spectrometry. A total 193 distinct all preparations. Protein...
Deep learning has made significant progress in computer vision, specifically image classification, object detection, and semantic segmentation. The skip connection played an essential role the architecture of deep neural networks,enabling easier optimization through residual during training stage improving accuracy testing. Many networks have inherited idea with connections for various tasks, it been standard choice designing networks. This survey provides a comprehensive summary outlook on...
With the continuous growth of large Knowledge Graphs (KGs), extractive KG summarization becomes a trending task. Aiming at distilling compact subgraph with condensed information, it facilitates various downstream KG-based tasks. In this survey paper, we are among first to provide systematic overview its applications and define taxonomy for existing methods from interdisciplinary studies. Future directions also laid out based on our extensive comparative review.
The large volume of open data on the Web is expected to be reused and create value. Finding right reuse a non-trivial task addressed by recent dataset search systems, which retrieve datasets relevant keyword query. An important component such systems snippet generation, extracting from retrieved exemplify its content explain relevance Snippet generation algorithms have emerged but were mainly evaluated user studies. More efficient reproducible evaluation methods are needed. To meet this...
Reusing published datasets on the Web is of great interest to researchers and developers. Their data needs may be met by submitting queries a dataset search engine retrieve relevant datasets. In this ongoing work towards developing more usable engine, we characterize real annotating semantics 1,947 using novel fine-grained scheme, provide implications for enhancing search. Based findings, present query-centered framework search, explore implementation snippet generation evaluate it with...
With the continuous growth of large Knowledge Graphs (KGs), extractive KG summarization becomes a trending task. Aiming at distilling compact subgraph with condensed information, it facilitates various downstream KG-based tasks. In this survey paper, we are among first to provide systematic overview its applications and define taxonomy for existing methods from interdisciplinary studies. Future directions also laid out based on our extensive comparative review.
Abstract Background The method of semi‐supervised semantic segmentation entails training with a limited number labeled samples alongside many unlabeled samples, aiming to reduce dependence on pixel‐level annotations. Most methods primarily focus sample augmentation in spatial dimensions the shortage samples. These tend ignore structural information objects. In addition, frequency‐domain also supplies another perspective evaluate from images, which includes different properties compared...
Abstract Nowadays, with increasing open knowledge graphs (KGs) being published on the Web, users depend data portals and search engines to find KGs. However, existing systems provide services present results only metadata while ignoring contents of KGs, i.e., triples. It brings difficulty for users' comprehension relevance judgement. To overcome limitation metadata, in this paper we propose a content-based engine KGs named CKGSE. Our system provides keyword search, KG snippet generation,...
Ad hoc dataset retrieval is a trending topic in IR research. Methods and systems are evolving from metadata-based to content-based ones which exploit the data itself for improving accuracy but thus far lack specialized test collection. In this paper, we build release first collection ad retrieval, where content-oriented queries relevance judgments annotated by human experts who assisted with dashboard designed specifically comprehensively conveniently browsing both metadata of dataset. We...
Semantic parsing, which converts natural language questions into logic forms, plays a crucial role in reasoning within structured environments. However, existing methods encounter two significant challenges: reliance on extensive manually annotated datasets and limited generalization capability to unseen examples. To tackle these issues, we propose Targeted Synthetic Data Generation (TARGA), practical framework that dynamically generates high-relevance synthetic data without manual...
The escalating significance of information security has underscored the per-vasive role encryption technology in safeguarding communication con-tent. Morse code, a well-established and effective method, found widespread application telegraph various do-mains. However, transmission code images faces challenges due to diverse noises distortions, thereby hindering comprehensive clas-sification outcomes. Existing methodologies predominantly concentrate on categorizing affected by single type...
Reusing existing datasets is of considerable significance to researchers and developers. Dataset search engines help a user find relevant for reuse. They can present snippet each retrieved dataset explain its relevance the user's data needs. This emerging problem generation has not received much research attention. To provide basis future research, we introduce framework quantitatively evaluating quality snippet. The proposed metrics assess extent which matches query intent covers main...