A5037223634- Advanced Memory and Neural Computing
- EEG and Brain-Computer Interfaces
- Neural dynamics and brain function
- Neuroscience and Neural Engineering
- Advanced Image Fusion Techniques
- Retinal Imaging and Analysis
- Topic Modeling
- Recommender Systems and Techniques
- Remote-Sensing Image Classification
- Image Retrieval and Classification Techniques
- Remote Sensing and Land Use
Xi'an Polytechnic University
2024
East China University of Science and Technology
2024
City University of Hong Kong
2024
Commercial Aircraft Corporation of China (China)
2022
Event-related potentials (ERPs) reflect neurophysiological changes of the brain in response to external events and their associated underlying complex spatiotemporal feature information is governed by ongoing oscillatory activity within brain. Deep learning methods have been increasingly adopted for ERP-based brain-computer interfaces (BCIs) due excellent representation abilities, which allow deep analysis Features with higher frequencies usually represent detailed localized information,...
Abstract Objective. Event-related potentials (ERPs) are cerebral responses to cognitive processes, also referred as potentials. Accurately decoding ERPs can help advance research on brain-computer interfaces (BCIs). The spatial pattern of ERP varies with time. In recent years, convolutional neural networks (CNNs) have shown promising results in electroencephalography (EEG) classification, specifically for ERP-based BCIs. Approach. This study proposes an auto-segmented multi-time window...
Event-related potentials (ERPs) reflect electropotential changes within specific cortical regions in response to events or stimuli during cognitive processes. The P300 speller is an important application of ERP-based brain-computer interfaces (BCIs), offering potential assistance individuals with severe motor disabilities by decoding their electroencephalography (EEG) communicate. This study introduced a novel paradigm using dynamically growing bubble (GB) visualization as the stimulus,...
Hyperspectral imagery (HSI) classification is essential for remote sensing analysis, utilizing various image bands. Convolutional Neural Networks (CNNs) are prevalent in deep learning visual data processing, with recent applications HSI primarily employing 2D and 3D CNNs. However, CNNs demand significant computational resources due to their complexity. This paper introduces a two-branch spatial-spectral joint convolutional neural network (SSDB) leveraging an attention mechanism...
Objective: To develop and validate a deep learning model based on fundus photos for the identification of coronary heart disease (CHD) associated risk factors. Methods: Subjects aged>18 years with complete clinical examination data from 149 hospitals medical centers in China were included this retrospective study. Two radiologists, who not aware study design, independently evaluated angiography images each subject to make CHD diagnosis. A using convolutional neural networks (CNN) was used...