A5017939192- Machine Learning and ELM
- EEG and Brain-Computer Interfaces
- ECG Monitoring and Analysis
- 3D Surveying and Cultural Heritage
- Advanced Image and Video Retrieval Techniques
- Robotics and Sensor-Based Localization
- Machine Learning and Algorithms
- Optical measurement and interference techniques
- Robotic Path Planning Algorithms
- Domain Adaptation and Few-Shot Learning
- Photovoltaic System Optimization Techniques
- Solar Radiation and Photovoltaics
- Optical Systems and Laser Technology
University of Science and Technology Beijing
2021-2023
Nankai University
2021
Automatic heartbeat classification via electrocardiogram (ECG) can help diagnose and prevent cardiovascular diseases in time. Many approaches have been proposed for classification, based on feature extraction. However, the existing face challenges of high dimensions slow recognition speeds. In this paper, we propose an efficient extreme learning machine (ELM) approach with multiple classes, hybrid time-domain wavelet time-frequency features. The contains two sequential modules: (1)...
Solar energy, which is one of the greatest potential renewable energies, has widely attracted attention in current years. Accurate prediction solar radiation premise exploiting and utilization energy. However, most research works on focus offline prediction, not practical suitable real world applications. In order to tackle this issue, paper, we implement a new kind machine learning algorithm, online sequential extreme (OS-ELM), realize real-time radiation. Comparing with existing batch...
The quality of rotor is key to ensuring the and stability blower. Point cloud-based detection utilizes three-dimensional depth information, making it time-saving, efficient, particularly suitable for inspection. In order ensure efficient accurate detection, collected point cloud needs be preprocessed. preprocessing includes filtering hole filling. Therefore, tackle problem outliers isolated points in on surface, this paper proposes a straight-through algorithm based region selection. Our...
Unlabeled samples are often readily available in our daily lives. However, valuable information contained a large number of unlabeled tends to be ignored by general supervised learning models. To make full use samples, we propose novel framework that combines active with semi-supervised learning. On one hand, expect label as few possible while achieving guaranteed classification performance, hence it's vital importance design specific strategy select only the most batch for expert labeling....