A5030424204- Advanced Chemical Sensor Technologies
- Complex Network Analysis Techniques
- Gas Sensing Nanomaterials and Sensors
- Topic Modeling
- Insect Pheromone Research and Control
- Web Data Mining and Analysis
- Advanced Graph Neural Networks
- Network Security and Intrusion Detection
- Opinion Dynamics and Social Influence
- Text and Document Classification Technologies
- Spam and Phishing Detection
- Advanced Text Analysis Techniques
- Anomaly Detection Techniques and Applications
- Analytical Chemistry and Sensors
- Advanced Computational Techniques and Applications
- Rough Sets and Fuzzy Logic
- Machine Learning and ELM
- Data Quality and Management
- Spectroscopy and Chemometric Analyses
- Data Mining Algorithms and Applications
- Privacy-Preserving Technologies in Data
- Service-Oriented Architecture and Web Services
- Sentiment Analysis and Opinion Mining
- Natural Language Processing Techniques
- Advanced Decision-Making Techniques
Southwest University
2015-2025
National University of Defense Technology
2015-2025
Harbin Institute of Technology
1988-2024
Shanghai Center for Brain Science and Brain-Inspired Technology
2020-2024
Chinese Academy of Sciences
2022-2024
University of Chinese Academy of Sciences
2022-2024
Liupanshui Normal University
2024
Zhengzhou University
2022-2024
National Space Science Center
2022-2024
China University of Petroleum, East China
2020-2024
Abstract Multi-source knowledge fusion is one of the important research topics in fields artificial intelligence, natural language processing, and so on. The results multi-source can help computer to better understand human thinking, effectively promote Big Search Cyberspace, construction domain graphs (KGs), bring enormous social economic benefits. Due uncertainty acquisition, reliability confidence KG based on entity recognition relationship extraction technology need be evaluated. On...
With the recent advances in information networks, problem of community detection has attracted much attention last decade. While network been ubiquitous, task collecting complete data remains challenging many real-world applications. Usually collected is incomplete with most edges missing. Commonly, such all nodes attributes are available while only within a few local regions can be observed. In this paper, we study detecting communities networks missing edges. We first learn distance metric...
Abstract Predicting potential facts in the future, Temporal Knowledge Graph (TKG) extrapolation remains challenging because of deep dependence between temporal association and semantic patterns facts. Intuitively, (events) that happened at different timestamps have influences on future events, which can be attributed to a hierarchy among not only but also relevant entities. Therefore, it is crucial pay more attention important entities events when forecasting future. However, most existing...
Abstract Background Ovarian cancer treatment is challenged by resistance and off-target effects. Melittin shows promise against but limited its instability harmful cellular interactions. Our study introduces SiO2–alginate–melittin nano-conjugates (SAMNs), incorporating alginate lyase to enhance melittin's release mitigate drawbacks. Methods We combined melittin with mesoporous silica, using control release. Effects on SKOV3 ovarian cells were evaluated via viability, invasion, migration...
Recently, privacy preserving data publishing has received a lot of attention in both research and applications. Most the previous studies, however, focus on static sets. In this paper, we study an emerging problem continuous streams which cannot be solved by any straightforward extensions existing methods data. To tackle problem, develop novel approach considers distribution entries to published statistical stream. An extensive performance using real sets synthetic verifies effectiveness...
Abstract Graph learning is being increasingly applied to image clustering reveal intra-class and inter-class relationships in data. However, existing graph learning-based focuses on grouping images under a single view, which under-utilises the information provided by To address that, we propose self-supervised multi-view technique contrastive heterogeneous learning. Our method computes affinity for It conducts Local Feature Propagation (LFP) reasoning over local neighbourhood of each node...
Sensor drift has long been an issue that perplexed researchers attempting to implement electronic noses (e-noses). However, for cases in which the target domain is inaccessible and models must be updated frequently adapt data variations, routine subspace learning-based compensation approaches appear powerless. In this paper, we present a novel recurrent neural network consisting of layer-normalized short-term memory cells with autocompensation strategy, aiming automatically generate values...
Achieving global net-zero emissions by mid-century necessitates a variety of climate mitigation technologies, including carbon capture, utilization, and storage (CCUS) or capture (CCS). According to analyses the Intergovernmental Panel on Climate Change (IPCC), International Energy Agency (IEA) other sources, CCS will be required as part suite strategies in order meet targets (Global institute, 2023). This require significant expansion mid-century, despite numerous challenges throughout its...