A5077961856- EEG and Brain-Computer Interfaces
- Emotion and Mood Recognition
- Sentiment Analysis and Opinion Mining
- Gaze Tracking and Assistive Technology
- Simulation and Modeling Applications
- Robot Manipulation and Learning
- Occupational Health and Safety Research
- Functional Brain Connectivity Studies
- Tunneling and Rock Mechanics
- Risk and Safety Analysis
- Safety and Risk Management
- Industrial Technology and Control Systems
- Hand Gesture Recognition Systems
- 3D Surveying and Cultural Heritage
- Neonatal and fetal brain pathology
Xi'an University of Science and Technology
2025
Hebei University
2023-2024
This work proposes a novel multi-camera system-based method for relative pose estimation and virtual–physical collision detection anchor digging equipment. It is dedicated to addressing the critical challenges of achieving accurate reliable between multiple devices during collaborative operations in coal mines. The key innovation that multi-target system established collect images, completed by EPNP (Efficient Perspective N-Point) algorithm based on infrared LED targets. At same time,...
This paper proposes a cutting trajectory planning method for boom-type roadheaders using an improved Nondominated Sorting Genetic Algorithm II (NSGA-II) with elitist strategy. Existing methods often overlook constraints related to cutterhead dimensions and target sections, affecting section formation quality. We develop kinematic model coordinate transformations design simplified constraint generate feasible points. Bi-objective functions—minimizing length turning angle—are formulated as...
Occupational health risk prediction of miners is a core issue to ensure the safety high-risk operations. Current assessment methodologies face critical limitations, as conventional unimodal systems frequently demonstrate limited efficacy in capturing multifactorial nature occupational deterioration. This study presents novel stacked ensemble architecture employing dual-phase algorithmic optimization address these muti-parametric interactions. The proposed framework implements hierarchical...
Electroencephalogram (EEG) is widely utilized in emotion recognition owing to its unique advantages. To achieve more optimal cross-subject recognition, a cross subject method based on interconnection dynamic domain adaptation (IDDA) proposed. In IDDA, graph convolution (DGC) employed dynamically learn the intrinsic relationships between different EEG channels and extract invariant features. And (DDA) align source target domain, at same time emotional sub-domains aligned, achieving...
ABSTRACT Brain fingerprinting is a promising approach for characterizing the uniqueness of individual brain functioning using functional magnetic resonance imaging (fMRI) data. Here, we propose novel deep learning framework, metric-BoIT, and demonstrate its effectiveness in capturing variability among early adolescents undergoing dramatic changes. Utilizing resting-state fMRI data from Adolescent Cognitive Development (ABCD) dataset, identified fingerprints that achieved remarkable...