A5084878606- EEG and Brain-Computer Interfaces
- Sparse and Compressive Sensing Techniques
- Particle accelerators and beam dynamics
- Particle Accelerators and Free-Electron Lasers
- Advanced Chemical Sensor Technologies
- Blind Source Separation Techniques
- Microwave Engineering and Waveguides
- Insect Pheromone Research and Control
- Superconducting Materials and Applications
- Neuroscience and Neural Engineering
- Aquatic Ecosystems and Phytoplankton Dynamics
- Advanced Memory and Neural Computing
- Marine and coastal ecosystems
- Neural dynamics and brain function
- Spectroscopy and Chemometric Analyses
- Digital Media Forensic Detection
- Radio Frequency Integrated Circuit Design
- Analog and Mixed-Signal Circuit Design
- Spectroscopy Techniques in Biomedical and Chemical Research
- Advanced Adaptive Filtering Techniques
- Plasma Diagnostics and Applications
- Gold and Silver Nanoparticles Synthesis and Applications
- Magnetic confinement fusion research
- Olfactory and Sensory Function Studies
- Photonic Crystal and Fiber Optics
Tianjin University
2016-2025
Inner Mongolia Agricultural University
2009-2024
Knoxville College
2024
University of Tennessee at Knoxville
2024
China Shipbuilding Industry Corporation (China)
2017-2022
State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering
2022
Hohai University
2018-2021
Huainan Normal University
2021
Singapore Institute of Manufacturing Technology
2018-2019
East China University of Science and Technology
2019
This paper reviews the first challenge on image dehazing (restoration of rich details in hazy image) with focus proposed solutions and results. The had 2 tracks. Track 1 employed indoor images (using I-HAZE dataset), while outdoor O-HAZE dataset). have been captured presence real haze, generated by professional haze machines. dataset contains 35 scenes that correspond to domestic environments, objects different colors specularities. 45 depicting same visual content recorded haze-free...
Motion artifacts (MAs) are strong interference sources in wearable photoplethysmography (PPG) signals, significantly affecting estimation of heart rate (HR) and other physiological parameters. In this paper, a novel method called SPECTRAP is proposed for accurate motion-tolerant HR using PPG signal simultaneous acceleration signal. The first calculates the spectra signal, then removes MA spectral components from spectrum new subtraction algorithm. algorithm based on asymmetric least square...
Classification of electroencephalogram-based motor imagery (MI-EEG) tasks is crucial in brain–computer interface (BCI). EEG signals require a large number channels the acquisition process, which hinders its application practice. How to select optimal channel subset without serious impact on classification performance an urgent problem be solved field BCIs. This article proposes end-to-end deep learning framework, called active inference neural network (EEG-ARNN), based graph convolutional...
An accelerator-driven subcritical system (ADS) program was launched in China 2011, which aims to design and build an ADS demonstration facility with the capability of more than 1000 MW thermal power multiple phases lasting about 20 years. The driver linac is defined be 1.5 GeV energy, 10 mA current cw operation mode. To meet extremely high reliability availability, designed much installed margin fault tolerance, including hot-spare injectors local compensation method for key element...
Objective. Modern motor imagery (MI)-based brain computer interface systems often entail a large number of electroencephalogram (EEG) recording channels. However, irrelevant or highly correlated channels would diminish the discriminatory ability, thus reducing control capability external devices. How to optimally select and extract associated features remains big challenge. This study aims propose validate deep learning-based approach automatically recognize two different MI states by...
In low-power wireless neural recording tasks, signals must be compressed before transmission to extend battery life. Recently, sensing (CS) theory has successfully demonstrated its potential in applications. this paper, a deep learning framework of quantized CS, termed BW-NQ-DNN, is proposed, which consists binary measurement matrix, non-uniform quantizer, and non-iterative recovery solver. By training the three parts are jointly optimized. Experimental results on synthetic real datasets...
Classification of electroencephalogram-based motor imagery (MI-EEG) tasks raises a big challenge in the design and development brain-computer interfaces (BCIs). In view characteristics nonstationarity, time-variability, individual diversity EEG signals, deep learning framework termed SSD-SE-convolutional neural network (CNN) is proposed for MI-EEG classification. The consists three parts: 1) sparse spectrotemporal decomposition (SSD) algorithm feature extraction, overcoming drawbacks...
Optimizing HVAC operation becomes increasingly important because of the rising energy cost and comfort requirements. In this paper, an innovative event-based approach is developed within Lagrangian relaxation framework to minimize HVAC's day-ahead cost. To solve optimization problem based on events challenging since with time-dependent uncertainties in weather, cooling load, etc., optimal policy not stationary. The nonstationary space extremely large, it time consuming find policy. overcome...
On-chip neural data compression is an enabling technique for wireless interfaces that suffer from insufficient bandwidth and power budgets to transmit the raw data. The algorithm its implementation should be area efficient functionally reliable over different datasets. Compressed sensing emerging has been applied compress various neurophysiological However, state-of-the-art compressed (CS) encoders leverage random but dense binary measurement matrices, which incur substantial costs on both...
Classification of electroencephalogram-based motor imagery (MI-EEG) tasks is crucial in brain computer interfaces (BCI). In view the characteristics non-stationarity, time-variability and individual diversity EEG signals, a novel framework based on graph neural network proposed for MI-EEG classification. First, an adaptive convolutional layer (AGCL) constructed, by which electrode channel information are integrated dynamically. We further propose spatiotemporal (ASTGCN), fully exploits...
Deep learning (DL) shows promise for quantitating anatomical features and functional parameters of tissues in quantitative optoacoustic tomography (QOAT), but its application to deep tissue is hindered by a lack ground truth data. We propose DL-based “QOAT-Net,” which functions without labeled experimental data: dual-path convolutional network estimates absorption coefficients after training with data-label pairs generated via unsupervised “simulation-to-experiment” data translation. In...
The applications of myoelectrical interfaces are majorly limited by the efficacy decoding motion intent in electromyographic (EMG) signal. Currently, EMG classification methods often rely substantially on handcrafted features or ignore key channel and interfeature information for tasks. To address these issues, a multiscale feature extraction network (MSFEnet) based channel-spatial attention is proposed to decode signal task gesture recognition classification. Specifically, we fuse...
The study of seasonal variations in Chlorophyll-a (Chl.a) concentration and its influencing factors is particularly important for lake management. showed that there was a strong non-linear relationship between Chl.a environmental spring autumn, whereas linear summer winter. redistributed during the ice period, water generally exceeded sheet. Characteristics sheet, including thermal insulation, transparency, nutrient migration into water, positively impact phytoplankton growth reproduction....
The study of lake-trophic status drivers and their variable effects over space time can assist in the management lake eutrophication. Winter dynamics trophic are rarely evaluated, yet they could vary drastically from more commonly sampled summer patterns. This represents a key blindspot our knowledge because ice sheets affect nutrient distribution (e.g., nitrogen phosphorus), light infiltration (translucency), phytoplankton propagation (Chl-a concentration). We examined long-term (2011–2020)...
Shallow lakes, one of the most widespread water bodies in world, are easily shifted to a new trophic state due external interferences. Shifting hydrologic conditions and climate change can cause cyanobacterial harmful algal blooms (CyanoHABs) shallow which pose serious threats ecological integrity human health. This study analyzed effects meteorological variables on Yangtze-connected lakes (Lake Dongting Poyang) isolated Chao Tai). The results show that (i) chlorophyll-a (Chl-a)...
This study measured the primary productivity (PPeu) of phytoplankton in Wuliangsuhai Lake from April 2014 to January 2019 based on monitoring and on-site exploration 20 sampling points entire lake using a vertically generalized production model (VGPM). The relationship between spatiotemporal variation PPeu environmental factors was also analyzed. Our findings indicated that temporal heterogeneity strong, average annual four seasons significantly different (P < 0.05, F = 54.74), exhibiting...
Abstract The optoacoustic imaging (OAI) methods are rapidly evolving for resolving optical contrast in medical applications. In practice, measurement strategies commonly implemented under limited‐view conditions due to oversized image objectives or system design limitations. Data acquired by detection may impart artifacts and distortions reconstructed (OA) images. We propose a hybrid data‐driven deep learning approach based on generative adversarial network (GAN), termed as LV‐GAN,...