A5110962639- Machine Fault Diagnosis Techniques
- Advanced Graph Neural Networks
- Brain Tumor Detection and Classification
- Opinion Dynamics and Social Influence
- Sentiment Analysis and Opinion Mining
- Simulation and Modeling Applications
- Spam and Phishing Detection
- Power Quality and Harmonics
- Advanced Decision-Making Techniques
- Advanced Measurement and Detection Methods
- Vehicle Noise and Vibration Control
- Complex Network Analysis Techniques
- Automated Road and Building Extraction
- Fault Detection and Control Systems
- Misinformation and Its Impacts
- Medical Image Segmentation Techniques
- Educational and Technological Research
- Power Transformer Diagnostics and Insulation
- Handwritten Text Recognition Techniques
- Anomaly Detection Techniques and Applications
Capital University of Physical Education and Sports
2024-2025
Northwestern Polytechnical University
2025
Shandong University of Science and Technology
2025
Xiangtan University
2024
Shanghai Ocean University
2024
With the development of research on multi-modal data fusion and its combination with online management, application big in information management systems is more extensive. How to integrate effectively key technology building an efficient system. In this paper, based a multi-support vector machine convolution neural network, feature-level multi-source heterogeneous implemented, it applied real set test relevant model. Experimental results show that method can not only realize integration...
Throughout its service life, an aero-engine will experience a series of health conditions due to the inevitable performance degradation major components, and characteristics deviate from their initial states. For improving tracking accuracy self-tunning on-board engine model on output variables throughout new method based separability index reverse search algorithm was proposed in this paper. By using method, qualified training set neural networks created basis eSTORM (enhanced Self Tuning...
In modern industries, bearings are often subjected to challenges from environmental noise and variations in operating conditions during their operation, which affects existing fault diagnosis methods that rely on signals single types of sensors. These fail provide comprehensive stable information, thereby affecting the diagnostic performance. To address this issue, paper introduces a multi-source multi-domain information fusion method for (M2IFD) bearings, integrating an attention mechanism...
ABSTRACT Seed variety purity is an important indicator of seed quality, and mixing soybean seeds at different maturity stages can affect crop growth food quality. This study investigated the feasibility recognizing five varieties using hyperspectral imaging. Hyperspectral data from 3600 were collected in range 395.5–1003.7 nm. First, potential to qualitatively distinguish was assessed visual cluster analyses based on principal component analysis (PCA), t‐distributed stochastic neighbor...
Ontology user portraits describe the semantic structure of users’ interests. It is very important to study similar relationship between find communities with overlapping The hierarchical characteristics interest can generate multiple similarity relations, which conducive formation clusters. This paper proposed a method community detection combining and module distribution entropy node. First, model was constructed based on ontology knowledge base measure multi-granularity topic users. Then,...
Fake news is widely spread on social media. Much research works have been done automatic fake detection in single domain. However, exists various domains, so the model based domain less effective multiple scenes. To improve ability of multi-domain news, we propose a perspective collaboration for (PCMFND) method to detect across domains by combining powerful feature extraction expert systems. The extracts features different perspectives from content separately, then interactively combines...
To effectively solve the problem of a small proportion substantia nigra and midbrain regions in Magnetic Resolution Imaging (MRI) images Parkinson’s disease (PD) patients, unclear boundaries with surrounding tissues, difficulty accurately delineating boundaries, an improved U 2 -Net algorithm for image segmentation was proposed. This first improves Residual U-blocks (RSU) RSU-4F modules using Shuffle Attention (SA) module, enhancing network’s attention to blurry encoding decoding layers....