A5027879510- EEG and Brain-Computer Interfaces
- Emotion and Mood Recognition
- Soft Robotics and Applications
- Teleoperation and Haptic Systems
- Gaze Tracking and Assistive Technology
- Robotics and Sensor-Based Localization
- Blind Source Separation Techniques
- Adaptive Control of Nonlinear Systems
- Surgical Simulation and Training
- Advanced Algorithms and Applications
- Intraoperative Neuromonitoring and Anesthetic Effects
- Advanced Vision and Imaging
- Advanced Sensor and Control Systems
- Robotic Path Planning Algorithms
- 3D Surveying and Cultural Heritage
- Advanced Image and Video Retrieval Techniques
- Neuroscience and Neural Engineering
- Image Processing Techniques and Applications
- Target Tracking and Data Fusion in Sensor Networks
- Robot Manipulation and Learning
- Neural dynamics and brain function
- Advanced Measurement and Detection Methods
- Evaluation Methods in Various Fields
- Vascular Malformations Diagnosis and Treatment
- Network Security and Intrusion Detection
State Grid Corporation of China (China)
2025
Tianjin University of Technology
2013-2025
Tianjin University
2016-2024
Xi'an Jiaotong University
2014-2024
Guangdong Academy of Sciences
2024
Changchun University of Science and Technology
2022-2024
Southeast University
2024
TEDA International Cardiovascular Hospital
2023
Jiangsu University
2023
Weifang University
2019-2022
The spatial information of Electroencephalography (EEG) is essential for emotion recognition model to learn discriminative feature. convolutional networks and recurrent are the conventional choices complex dependencies through a number electrodes brain regions. However, these models have difficulty in capturing long-range due operations local feature learning. To enhance EEG improve accuracy recognition, we propose transformer- based hierarchically from electrode level brain-region-level. In...
Existing simultaneous localization and mapping (SLAM) algorithms are not robust in challenging low-texture environments because there only few salient features. The resulting sparse or semi-dense map also conveys little information for motion planning. Though some work utilize plane scene layout dense regularization, they require decent state estimation from other sources. In this paper, we propose real-time monocular SLAM to demonstrate that understanding could improve both especially...
The robot-assisted endovascular catheterization system (RAECS) has the potential to address some of procedural challenges and separate interventionalists from X-ray radiation during surgery. However, employment robotic systems is partly changing natural gestures behavior medical professionals. This paper presents a RAECS that augments surgeon's motions using conventional catheter as well generates haptic force feedback ensure surgery safety. magnetorheological fluids based...
The temporal and spatial information of electroencephalogram (EEG) are essential for the emotion recognition model to learn discriminative features. Hence, we propose a novel hybrid spatial-temporal feature fusion neural network (STFFNN) extract features integrate complementary information. generated power topographic maps, which capture dependencies among electrodes, fed convolutional (CNN) learning. Furthermore, instance normalizations (INs) batch (BNs) within CNN appropriately combined...
With the development of affective computing, discriminative feature selection is critical for electroencephalography (EEG) emotion recognition. In this article, we fused four EEG matrices constructed by preprocessed signal, differential entropy (DE), symmetric difference, and quotient based on International 10–20 system, which integrates time-, frequency-, spatial-domain information signals. For classification model, used space-to-depth (S2D) layer instead convolutional neural network (CNN)...
State estimation is the most critical capability for MAV (Micro-Aerial Vehicle) localization, autonomous obstacle avoidance, robust flight control and 3D environmental mapping. There are three main challenges state estimation: (1) it can deal with aggressive 6 DOF (Degree Of Freedom) motion; (2) should be to intermittent GPS (Global Positioning System) (even GPS-denied) situations; (3) work well both low- high-altitude flight. In this paper, we present a technique by fusing long-range stereo...
Recently, the study of emotion recognition has received increasing attentions by rapid development noninvasive sensor technologies, machine learning algorithms and compute capability computers. Compared with single modal recognition, multimodal paradigm introduces complementary information for recognition. Hence, in this work, we presented a decision level fusion framework detecting emotions continuously fusing Electroencephalography (EEG) facial expressions. Three types movie clips...
With the development of sensor technology and learning algorithms, multimodal emotion recognition has attracted widespread attention. Many existing studies on mainly focused normal people. Besides, due to hearing loss, deaf people cannot express emotions by words, which may have a greater need for recognition. In this paper, deep belief network (DBN) was utilized classify three category through electroencephalograph (EEG) facial expressions. Signals from 15 subjects were recorded when they...
Emotion analysis has been employed in many fields such as human-computer interaction, rehabilitation, and neuroscience. But most emotion methods mainly focus on healthy controls or depression patients. This paper aims to classify the emotional expressions individuals with hearing impairment based EEG signals facial expressions. Two kinds of were collected simultaneously when subjects watched affective video clips, we labeled clips discrete states (fear, happiness, calmness, sadness). We...
To address the power supply-demand imbalance caused by uncertainty in wind turbine and photovoltaic generation regional integrated energy system, this study proposes a bi-level optimization strategy that considers uncertainties as well demand response. The upper-level model analyzes these modeling short-term long-term output errors using robust theory, applies an improved stepwise carbon trading to control emissions, finally constructs electricity-hydrogen-carbon cooperative scheduling...
ABSTRACT The supermaneuver flight control problem of fighter aircraft with thrust vector is addressed by proposing a cascade strategy that incorporates disturbance compensation and allocation technology. Firstly, an active rejection (ADRC) introduced, which employs predefined time extended state observer (PTESO) to ensure the convergence estimation errors within time. Secondly, technology implemented address challenges in over‐actuated system aircraft. In addition, efficient utilized...