A5101607811- Topic Modeling
- Industrial Vision Systems and Defect Detection
- Web Data Mining and Analysis
- Engineering Diagnostics and Reliability
- Advanced machining processes and optimization
- Simulation and Modeling Applications
- Energetic Materials and Combustion
- IPv6, Mobility, Handover, Networks, Security
- Metal-Organic Frameworks: Synthesis and Applications
- CO2 Reduction Techniques and Catalysts
- Image Processing Techniques and Applications
- RFID technology advancements
- Combustion and Detonation Processes
- Natural Language Processing Techniques
- Advanced Measurement and Detection Methods
- Structural Response to Dynamic Loads
- Leadership, Behavior, and Decision-Making Studies
- Power Systems and Technologies
- Technology and Security Systems
- Carbon Dioxide Capture Technologies
- Sentiment Analysis and Opinion Mining
- Data Quality and Management
- Multimodal Machine Learning Applications
- Advanced Research in Science and Engineering
Nanyang Normal University
2025
Shandong University of Science and Technology
2023-2024
China Electronics Technology Group Corporation
2017-2020
Multimodal Aspect-Based Sentiment Analysis (MABSA), as an emerging task in the field of sentiment analysis, has recently received widespread attention. Its aim is to combine relevant multimodal data determine polarity a given aspect text. Researchers have surveyed both aspect-based analysis and but, best our knowledge, there no survey on MABSA. Therefore, order assist related researchers know MABSA better, we research work recent years. Firstly, concepts were introduced. Secondly, existing...
Abstract Nested named entity recognition (NNER) aims to identify potentially overlapping entities. Sequence labeling method and span-based are two commonly used methods in nested recognition. However, the linear structure of sequence results relatively poor performance, requires traversing all spans, which brings very high time complexity. All them fail effectively leverage positional dependencies between internal external In order improve these issues, this paper proposed a based on...
Abstract Fuel air explosive has unique damage characteristics because of its different action mechanism. In this paper, through analyzing the mechanism and fuel explosive, efficiency was quantitatively described by using overpressure specific impulse. combination with theoretical calculation experimental fitting, corresponding effectiveness model established. According to actual application group personnel selected as pseudomorphic target, distribution area relevant parameters target were...
<title>Abstract</title> Nested named entity recognition (NNER) aims to identify possibly overlapping entities, which is a crucial and challenging sub-task in the field of recognition. Traditional sequence labeling methods are unable effectively deal with NNER due their linear structure; span-based require traversing verifying every possible span, leads high complexity data imbalance issues. To address these issues, this paper proposed nested method based on Multidimensional Features Fuzzy...
Abstract Under the condition of single source information, this paper studies and analyzes target damage evaluation model based on image proposes an automatic algorithm change detection analysis geometric features texture before after is hit. The consists two parts: extraction matching algorithm. For algorithm, gradient, definition corner point structure feature technology are introduced in detail. we mainly consider gray-based feature-based information source, helpful to make up deficiency...