A5049920351- EEG and Brain-Computer Interfaces
- Advanced Memory and Neural Computing
- Energy Load and Power Forecasting
- Gaze Tracking and Assistive Technology
- Neuroscience and Neural Engineering
- ECG Monitoring and Analysis
- Power Systems and Renewable Energy
- Blind Source Separation Techniques
- Neural dynamics and brain function
- Gear and Bearing Dynamics Analysis
- Digital Marketing and Social Media
- Functional Brain Connectivity Studies
- Infrared Target Detection Methodologies
- Remote-Sensing Image Classification
- Fault Detection and Control Systems
- Electric Power System Optimization
- Asymmetric Hydrogenation and Catalysis
- Advanced Measurement and Detection Methods
- Renal cell carcinoma treatment
- Radiomics and Machine Learning in Medical Imaging
- Video Surveillance and Tracking Methods
- Structural Health Monitoring Techniques
- Nanomaterials for catalytic reactions
- Fungal Plant Pathogen Control
- Sport and Mega-Event Impacts
National University of Defense Technology
2016-2025
Baotou Teachers College
2019-2025
Chinese PLA General Hospital
2025
North University of China
2025
Qilu University of Technology
2024
Shandong Academy of Sciences
2024
Hunan University
2020-2024
Beijing University of Posts and Telecommunications
2024
Shandong University
2024
Shaanxi Institute of International Trade & Commerce
2024
This paper presents a hybrid brain-computer interface (BCI) that combines motor imagery (MI) and P300 potential for the asynchronous operation of brain-controlled wheelchair whose design is based on Mecanum wheel. paradigm completely user-centric. By sequentially performing MI tasks or paying attention to flashing, user can use eleven functions control wheelchair: move forward/backward, left/right, left45/right45, accelerate/decelerate, turn stop. The practicality effectiveness proposed...
In cross-domain hyperspectral image (HSI) classification, the labeled samples of target domain are very limited, and it is a worthy attention to obtain sufficient class information from source categorize classes (both same new unseen classes). This article investigates this problem by employing few-shot learning (FSL) in meta-learning paradigm. However, most existing FSL methods extract statistical features based on convolutional neural networks (CNNs), which typically only consider local...
Electroencephalography (EEG) datasets are characterized by low signal-to-noise signals and unquantifiable noisy labels, which hinder the classification performance in rapid serial visual presentation (RSVP) tasks. Previous approaches primarily relied on supervised learning (SL), may result overfitting reduced generalization performance. In this paper, we propose a novel multi-task collaborative network (MTCN) that integrates both SL self-supervised (SSL) to extract more generalized EEG...
The multisource remote sensing classification task has two main challenges. 1) How to capture hyperspectral image (HSI) and light detection ranging (LiDAR) features cooperatively fully mine the complementary information between data. 2) adaptively fuse features, which should not only overcome imbalance HSI LiDAR data but also avoid generation of redundant information. local interaction transformer (LIIT) model proposed herein can effectively address these above issues. Specifically,...
Abstract Objectives To determine whether 3D-CT multi-level anatomical features can provide a more accurate prediction of surgical decision-making for partial or radical nephrectomy in renal cell carcinoma. Methods This is retrospective study based on multi-center cohorts. A total 473 participants with pathologically proved carcinoma were split into the internal training and external testing set. The set contains 412 cases from five open-source cohorts two local hospitals. includes 61 another...
To improve the accuracy of short-term wind speed forecasting, we proposed a Gated Recurrent Unit network forecasting method, based on ensemble empirical mode decomposition and Grid Search Cross Validation parameter optimization algorithm. In this study, first, in process decomposing, set was introduced to divide time series into high-frequency modal, low-frequency trend using Pearson correlation coefficient. Second, during optimization, grid algorithm employed GRU model search for...
As a critical component in mechanical equipment, the fault diagnosis of rolling bearings is great significance. Due to presence substantial noise vibration signals, extracting features becomes particularly challenging. This paper proposes method combining Variational Mode Decomposition (VMD) and Support Vector Machine (SVM) based on envelope entropy selection criterion for bearing diagnosis. First, VMD used decompose signal into several Intrinsic Function (IMF) components, spectrum these...
A practical approach is presented for the highly selective hydrogenation of various unsaturated compounds using a cutting-edge Ru/PNN catalytic system, resulting in high turnover numbers and substantial production valuable pharmaceuticals.
Accurate and efficient medium- long-term forecasts of wind power can provide technical support for the development utilization resources. Considering regional characteristics resources, regional-similarity factor was introduced into study wind-power forecasting, and, to assess dependence power, long-short-term-memory method selected forecasting trends in a case carried out Northwest China. The results showed that error presented reduced by an average 20.80%, compared with individual...
Convolutional neural networks (CNNs) have shown great potential in the field of brain-computer interfaces (BCIs) due to their ability directly process raw electroencephalogram (EEG) signals without artificial feature extraction. Some CNNs achieved better classification accuracy than that traditional methods. Raw EEG are usually represented as a two-dimensional (2-D) matrix composed channels and time points, ignoring spatial topological information electrodes. Our goal is make CNN takes...
Abstract Background Current research related to electroencephalogram (EEG)-based driver’s emergency braking intention detection focuses on recognizing from normal driving, with little attention differentiating braking. Moreover, the classification algorithms used are mainly traditional machine learning methods, and inputs manually extracted features. Methods To this end, a novel EEG-based strategy is proposed in paper. The experiment was conducted simulated driving platform three different...
Achieving carbon neutrality has become a major national strategy for sustainability, and the recycling of recyclable resources is an important direction toward doing so. Due to huge amounts generated every year low rate, new Internet model with great potential increase rate developed rapidly in China. However, participation from residents hinders sustainable development recycling. Through this study, we aim uncover avenues improving behavior. The factors influencing perspective technologies...
Currently, distributed multi-robot systems (MRSs) can meet the requirements of various tasks in complex environments. Nevertheless, inevitable disadvantages robot sensor errors, communication delays, and obstructive environmental factors hinder operation MRSs. Therefore, a shared control approach supported by human intention has emerged, relying on experience knowledge to improve cooperation. With firefighting as application background, this letter considers brain-computer interface means...
With the rapid development of multi-robot systems (MRSs), they can be widely used to perform various tasks in typical environments. However, inevitable disadvantages onboard sensor errors, communication delays, and underspecified environmental factors seriously affect operation MRSs. Therefore, this letter considers a shared control framework suitable for human-multirobot foraging with brain-computer interface (BCI) as means allowing human operator express opinions, permitting robots rely on...