A5028546723- EEG and Brain-Computer Interfaces
- Emotion and Mood Recognition
- Blind Source Separation Techniques
- Gaze Tracking and Assistive Technology
- Face and Expression Recognition
- Neuroscience and Neural Engineering
- Image Processing Techniques and Applications
- Advanced Optical Sensing Technologies
- Neural dynamics and brain function
- Advanced Memory and Neural Computing
- Optical Systems and Laser Technology
- Neural Networks and Reservoir Computing
- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
Tianjin University of Technology
2020-2022
Hangzhou Dianzi University
2022
In recent years, many researchers have explored different methods to obtain discriminative features for electroencephalogram-based (EEG-based) emotion recognition, but a few studies been investigated on deaf subjects. this study, we established EEG data set, which contains three kinds of (positive, neutral, and negative) with 15 10 time-frequency domain 11 nonlinear dynamic system were extracted from the signals. To optimal feature combination classifier, an integrated genetic firefly...
Recent research on emotion recognition suggests that deep network-based adversarial learning has an ability to solve the cross-subject problem of recognition. This study constructed a hearing-impaired electroencephalography (EEG) dataset containing three emotions (positive, neutral, and negative) in 15 subjects. The emotional domain neural network (EDANN) was carried out identify subjects' by hidden information between labeled data with no-label. For input data, we propose spatial filter...
Emotion recognition based on electroencephalography (EEG) signals has become an interesting research topic in the field of neuroscience, psychology, neural engineering, and computer science. However, existing studies are mainly focused normal or depression subjects, few reports hearing-impaired subjects. In this work, we have collected EEG 15 subjects for categorizing three types emotions (positive, neutral, negative). To study differences functional connectivity between under different...
Traditional emotion recognition methods are mainly based on voice, expression and body movement. These physiological signals or facial expressions may hardly reveal inner emotions. In this paper, the wavelet entropy (WE) was utilized to represent characteristics associated with emotional states. The average classification accuracies of positive, neutral negative emotions 70.65%, 70.53% 70.28%, respectively. order demonstrate effectiveness proposed method, comparison experiments were carried...
Circulating tumor cells (CTCs) have important reference value in cancer diagnostics. As the existing fluorescence-based CTC detection method faces limitation of tedious staining steps and photobleaching, it's necessary to develop a stain-free identification method. This work demonstrated holographic CTCs using deep feature fusion neural network. By utilizing subtle difference between internal structures captured by microscope, proposed network fuses low-level features extracted shallow...
The brain-computer interface (BCI) plays an important role in assisting the disabled life support and entertainment. In this study, a wireless retrieval robot system for steady-state visual evoked potential (SSVEP) based BCI was proposed. order to improve recognition accuracy stability of subjects' instructions, offline online experiments are used study solve performance parameters, obstacle avoidance respectively. experiment, 5 types SSVEP data 4 subjects were used. Based on CCA algorithm,...
In this work, the Feature Pyramid Network (FPN) is proposed for improving performance of electroencephalography (EEG) emotion recognition. Specifically, Differential Entropy (DE) extracted as a basic feature, and we adopt bi-harmonic spline interpolation to interpolate features maps according real 3D electrode spatial information. The information obtained avoid loss effective Next, FPN applied fuse multiscale EEG obtaining deeper semantic features, which blind self-learning deep...