A5100429537- EEG and Brain-Computer Interfaces
- Advanced Image Fusion Techniques
- Blind Source Separation Techniques
- Remote-Sensing Image Classification
- Non-Invasive Vital Sign Monitoring
- ECG Monitoring and Analysis
- Image and Signal Denoising Methods
- Heart Rate Variability and Autonomic Control
- Image Enhancement Techniques
- Emotion and Mood Recognition
- Gaze Tracking and Assistive Technology
- Brain Tumor Detection and Classification
- Microwave Imaging and Scattering Analysis
- Advanced Sensor and Energy Harvesting Materials
- Remote Sensing and Land Use
- Functional Brain Connectivity Studies
- Neonatal and fetal brain pathology
- Epilepsy research and treatment
- Hemodynamic Monitoring and Therapy
- Sparse and Compressive Sensing Techniques
- Spectroscopy and Chemometric Analyses
- Electromagnetic Scattering and Analysis
- Groundwater and Isotope Geochemistry
- Advanced Memory and Neural Computing
- Atmospheric chemistry and aerosols
Hefei University of Technology
2018-2025
Nanchang University
2022-2025
Shenyang Jianzhu University
2024
Suzhou University of Science and Technology
2022-2024
Shandong University
2024
Hunan University
2023
Illinois Institute of Technology
2023
Key Laboratory of Guangdong Province
2023
Zhengzhou University
2022-2023
Anhui University
2020-2023
Emotion recognition based on electroencephalography (EEG) is a significant task in the brain-computer interface field. Recently, many deep learning-based emotion methods are demonstrated to outperform traditional methods. However, it remains challenging extract discriminative features for EEG recognition, and most ignore useful information channel time. This article proposes an attention-based convolutional recurrent neural network (ACRNN) more from signals improve accuracy of recognition....
Infrared and visible image fusion aims to describe the same scene from different aspects by combining complementary information of multi-modality images. The existing Generative adversarial networks (GAN) based infrared methods cannot perceive most discriminative regions, hence fail highlight typical parts in To this end, we integrate multi-scale attention mechanism into both generator discriminator GAN fuse images (AttentionFGAN). not only capture comprehensive spatial help focus on...
Recently, deep neural networks (DNNs) have been applied to emotion recognition tasks based on electroencephalography (EEG), and achieved better performance than traditional algorithms. However, DNNs still the disadvantages of too many hyperparameters lots training data. To overcome these shortcomings, in this article, we propose a method for multi-channel EEG-based using forest. First, consider effect baseline signal preprocess raw artifact-eliminated EEG with removal. Secondly, construct...
Remote photoplethysmography (rPPG) is a non-contact technique for measuring cardiac signals from facial videos. High-quality rPPG pulse are urgently demanded in many fields, such as health monitoring and emotion recognition. However, most of the existing methods can only be used to get average heart rate (HR) values due limitation inaccurate signals. In this paper, new framework based on generative adversarial network, called PulseGAN, introduced generate realistic through denoising...
Identifying the political perspective shaping way news events are discussed in media is an important and challenging task. In this paper, we highlight importance of contextualizing social information, capturing how information disseminated networks. We use Graph Convolutional Networks, a recently proposed neural architecture for representing relational to capture documents’ context. show that can be used effectively as source distant supervision, when direct supervision available, even...
Remote photoplethysmography (rPPG) is a kind of noncontact technique to measure heart rate (HR) from facial videos. As the demand for long-term health monitoring grows, rPPG attracts much attention researchers. However, performance conventional methods easily degenerated due noise interference. Recently, some deep learning-based have been introduced and they revealed good against noise. In this article, we propose new method with convolutional neural networks (CNNs) build mapping between...
Methods based on generative adversarial network (GAN) have been widely used in infrared and visible images fusion. However, these methods cannot perceive the discriminative parts of an image. Therefore, we introduce a multigrained attention module into encoder-decoder to fuse (MgAN-Fuse). The are encoded by two independent encoder networks due their diverse modalities. Then, results encoders concatenated calculate fused result decoder. To exploit features multiscale layers fully force model...
Emotion recognition based on electroencephalogram (EEG) plays an increasingly important role in the field of brain–computer interfaces. Recently, deep learning has been widely applied to EEG decoding owning its excellent capabilities automatic feature extraction. Transformer holds great superiority processing time-series signals due long-term dependencies extraction ability. However, most existing transformer architectures are designed manually by human experts, which is a time-consuming and...
Deep learning has been successfully applied to infrared and visible image fusion due its powerful ability of feature representation. Existing most deep based methods mainly utilize pure convolution model or transformer model, which leads that the fused cannot preserve long-range dependencies (global context) local features simultaneously. To this end, we propose a convolution-guided framework for (CGTF), aims combine convolutional network dependency produce satisfactory image. In CGTF, are...
Deep learning (DL) methods have been widely used in the field of seizure prediction from electroencephalogram (EEG) recent years. However, DL usually numerous multiplication operations resulting high computational complexity. In addtion, most current approaches this focus on designing models with special architectures to learn representations, ignoring use intrinsic patterns data. study, we propose a simple and effective end-to-end adder network supervised contrastive (AddNet-SCL). The...
With the improvement of quality life, people are more and concerned about sleep. The electroencephalogram (EEG)-based sleep stage classification is a good guide for disorders. At this stage, most automatic staging neural networks designed by human experts, process time-consuming laborious. In paper, we propose novel architecture search (NAS) framework based on bilevel optimization approximation EEG-based classification. proposed NAS mainly performs architectural through approximation, model...