A5079554908- EEG and Brain-Computer Interfaces
- Blind Source Separation Techniques
- Gaze Tracking and Assistive Technology
- Fault Detection and Control Systems
- Muscle activation and electromyography studies
- Brain Tumor Detection and Classification
- Gear and Bearing Dynamics Analysis
- Neuroscience and Neural Engineering
- Neural Networks and Applications
- Machine Fault Diagnosis Techniques
- Electricity Theft Detection Techniques
- Anomaly Detection Techniques and Applications
- Imbalanced Data Classification Techniques
Xi’an Jiaotong-Liverpool University
2020-2024
University of Liverpool
2020-2022
In the large amount of available data, information insensitive to faults in historical data interferes gear fault feature extraction. Furthermore, as most diagnosis models are learned from offline collected under single/fixed working condition only, this may cause unsatisfactory performance for complex conditions (including multiple and unknown conditions) if not properly dealt with. This paper proposes a transfer learning-based method reduce negative effects abovementioned problems....
The classification of motor imagery (MI) signal is a representative problem in brain-computer interface (BCI) systems. Because one main application field MI-based BCI medical rehabilitation, it often difficult to obtain large amount labeled data from the same subject. Moreover, there are huge individual differences among subjects, so other subjects can not be directly used train classifier target A transfer learning approach which based on alignment and deep proposed solve above problem,...
The classification problem of imbalanced data is a popular issue in the field machine learning recent years. For data, traditional algorithms tend to classify minority class samples into majority class, which result misclassification many by classifier. problems, this paper proposes Density Based Safe Level Synthetic Minority Oversampling TEchnique (DB-SLSMOTE). First, algorithm clusters through Density-Based Spatial Clustering Applications with Noise (DBSCAN). Then, (Safe-Level- SMOTE)...