A5042905113- Advanced Decision-Making Techniques
- Neural Networks and Reservoir Computing
- Advanced Algorithms and Applications
- Magnetic Properties of Alloys
- Tryptophan and brain disorders
- Ferroelectric and Negative Capacitance Devices
- Face and Expression Recognition
- Biosimilars and Bioanalytical Methods
- Advanced Memory and Neural Computing
- Cardiac Health and Mental Health
- Gait Recognition and Analysis
- Advanced Computational Techniques and Applications
- Topic Modeling
- Magnetic properties of thin films
- Advanced Sensor and Control Systems
- Magnetic and transport properties of perovskites and related materials
- Anomaly Detection Techniques and Applications
- Biosensors and Analytical Detection
- Technology and Data Analysis
- Advanced Text Analysis Techniques
- Single-cell and spatial transcriptomics
- Rough Sets and Fuzzy Logic
- Sentiment Analysis and Opinion Mining
Beihang University
2009-2024
Changchun University of Science and Technology
2024
Dalian Jiaotong University
2024
Permanent-magnet materials are essential for modern technologies, such as robotics, electric vehicles, and wind power generators. Over the last 100 years, pursuit stronger magnets mainly lies in enhancing their coercivity by alloying different elements with Fe Co. Despite continued endeavor, of state-of-the-art NdFeB SmCo can only reach 20%–25% anisotropy field (Ha, theoretical limit coercivity), known famous Brown's paradox. On other hand, abnormally high was observed consisting nanograins...
Against the application problems of support vector machine in fault diagnosis, paper introduces a new diagnosis method, which combines latent semantic analysis with improved machine. With realizing sample datum feature extraction and dimensionality reduction to solve training diagnosing speed problem, resulted from number high-dimensional datum; max-wins-voting strategy one-versus-one classification unclassifiable problem conventional improving efficiency accuracy diagnosis. Applying above...
With the rapid proliferation of substantial textual data from sources such as social media, online comments, and news articles, sentiment analysis has become increasingly crucial. However, existing deep learning methods have overlooked significance part-of-speech (POS) emotional words in understanding emotion text. Based on this, this paper proposes a approach that combines multiple features with dual-channel network. Firstly, vector representation text is obtained through Robustly Optimized...
In this study, three-factor and three-level orthogonal experiment was used to optimize the detection system of clinical renal function marker β2-microglobulin latex enhanced immune turbidity, so as prepare a with wider linear range, solve false negative problem in high-concentration samples, improve accuracy. Based on immunoturbidimetry, automatic biochemical analyzer establish relationship between standard different concentrations absorbance change value 546 nm, antibody source, microsphere...
In order to solve the application problems of gray relation theory and support vector machine in fault diagnosis, paper introduces a new method, which combines latent semantic analysis with machine. With realizing sample data feature extraction dimensionality reduction training diagnosing speed problem resulted from number high-dimensional data. And principle classification can not achieve. Applying method diagnosis for certain type aircraft, accuracy could reach more than 94%,and...