A5100730688- EEG and Brain-Computer Interfaces
- Functional Brain Connectivity Studies
- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
- Generative Adversarial Networks and Image Synthesis
- Epilepsy research and treatment
- Microbial Natural Products and Biosynthesis
- Pregnancy and preeclampsia studies
- Human Pose and Action Recognition
- Data Management and Algorithms
- Multimodal Machine Learning Applications
- Advanced Graph Neural Networks
- Advanced Vision and Imaging
- Video Analysis and Summarization
- Plant biochemistry and biosynthesis
- Image Retrieval and Classification Techniques
- Advanced Image Processing Techniques
- Neural dynamics and brain function
- Graph Theory and Algorithms
- Computer Graphics and Visualization Techniques
- Face and Expression Recognition
- Fungal Biology and Applications
- Computational Drug Discovery Methods
- Retinal Diseases and Treatments
- Human Motion and Animation
University of California, Los Angeles
2021-2025
Nanyang Technological University
2025
North China Electric Power University
2024
Gansu Provincial Hospital
2024
Gansu University of Traditional Chinese Medicine
2024
Xuzhou No.1 People's Hospital
2020-2024
Xuzhou Medical College
2020-2024
Huazhong Agricultural University
2021-2024
Zhongyuan University of Technology
2023
Guangxi University of Chinese Medicine
2021-2023
Large-scale deep neural networks (DNNs) are both compute and memory intensive. As the size of DNNs continues to grow, it is critical improve energy efficiency performance while maintaining accuracy. For DNNs, model an important factor affecting performance, scalability efficiency. Weight pruning achieves good compression ratios but suffers from three drawbacks: 1) irregular network structure after pruning, which affects throughput; 2) increased training complexity; 3) lack rigirous guarantee...
In this paper, we propose a novel nonlocal patch tensor-based visual data completion algorithm and analyze its potential problems. Our consists of two steps: the first step is initializing image with triangulation-based linear interpolation second grouping similar patches as tensor then applying proposed technique. Specifically, treating group matrices tensor, impose low-rank constraint on through recently nuclear norm. Moreover, observe that after step, gets blurred and, thus, have found...
Image inpainting is a challenging computer vision task that aims to fill in missing regions of corrupted images with realistic contents. With the development convolutional neural networks, many deep learning models have been proposed solve image issues by information from large amount data. In particular, existing algorithms usually follow an encoding and decoding network architecture which some operations standard schemes are employed, such as static convolution, only considers pixels fixed...
The optimization of the membrane electrode assembly (MEA) is crucial for enhancing performance proton exchange water electrolysis. Nevertheless, achieving global all manufacturing parameters MEA poses challenges due to their high-dimensional complexity and limited experimental data. In this study, machine learning (ML) techniques were introduced tackle intricate engineering challenge. 58 MEAs fabricated tested construct a comprehensive database enriched with features ample This was achieved...
Ship detection in synthetic aperture radar (SAR) images has attracted widespread attention due to its significance and challenges. In recent years, numerous detectors based on deep learning have achieved good performance the field of SAR ship detection. However, targets same type always various representations under different imaging conditions, while types ships may a high degree similarity, which considerably complicates target recognition. Meanwhile, image is also obscured by background...
Abstract Here, we performed N6-methyladenosine (m6A) RNA sequencing to determine the circRNA m6A methylation changes in placentas during pathogenesis of preeclampsia (PE). We verified expression circPAPPA2 using quantitative reverse transcription-PCR. An invasion assay was carried out identify role development PE. Mechanistically, investigated cause altered modification through overexpression and knockdown cell experiments, immunoprecipitation, fluorescence situ hybridization stability...
Abstract Objective. Intracranially-recorded interictal high-frequency oscillations (HFOs) have been proposed as a promising spatial biomarker of the epileptogenic zone. However, HFOs can also be recorded in healthy brain regions, which complicates interpretation HFOs. The present study aimed to characterize salient features physiological using deep learning (DL). Approach. We studied children with neocortical epilepsy who underwent intracranial strip/grid evaluation. Time-series EEG data...
Abstract Background Preeclampsia is a severe disease in pregnant women, which primarily managed by early screening and prevention. Circular RNAs (circRNAs) have increasingly been shown to be important biological regulators involved numerous diseases. Further, increasing evidence has demonstrated that circRNAs can used as diagnostic biomarkers. This study was conducted evaluate the potential of circCRAMP1L, previously identified downregulated preeclampsia, novel biomarker for predicting...
Intracranially recorded interictal high-frequency oscillations have been proposed as a promising spatial biomarker of the epileptogenic zone. However, its visual verification is time-consuming and exhibits poor inter-rater reliability. Furthermore, no method currently available to distinguish generated from zone (epileptogenic oscillations) those other areas (non-epileptogenic oscillations). To address these issues, we constructed deep learning-based algorithm using chronic intracranial EEG...
Extracting meaning from a dynamic and variable flow of incoming information is major goal both natural artificial intelligence. Computer vision (CV) guided by deep learning (DL) has made significant strides in recognizing specific identity despite highly attributes. This the same challenge faced nervous system partially addressed concept cells-neurons exhibiting selective firing response to persons/places, described human medial temporal lobe (MTL) . Yet, access neurons representing...
. This study aims to develop and validate an end-to-end software platform, PyHFO, that streamlines the application of deep learning (DL) methodologies in detecting neurophysiological biomarkers for epileptogenic zones from EEG recordings.
Graph matching is an important and persistent problem in computer vision pattern recognition for finding node-to-node correspondence between graphs. However, graph that incorporates pairwise constraints can be formulated as a quadratic assignment (QAP), which NP-complete results intrinsic computational difficulties. This paper presents functional representation (FRGM) aims to provide more geometric insights on the reduce space time complexities. To achieve these goals, we represent each by...
As the population ages globally, there seem to be more people with Alzheimer’s disease. Unfortunately, is currently no specific treatment for At present, Huperzine A (HupA) one of best drugs used disease and has been in clinical trials several years China. HupA was first separated from Huperzia serrata, a traditional medicinal herb that cure fever, contusions, strains, hematuria, schizophrenia, snakebite hundreds China, confirmed have acetylcholinesterase inhibitory activity. With very slow...
Abstract Chaenomeles speciosa (2n = 34), a medicinal and edible plant in the Rosaceae, is commonly used traditional Chinese medicine. To date, lack of genomic sequence genetic studies has impeded efforts to improve its value. Herein, we report use an integrative approach involving PacBio HiFi (third-generation) sequencing Hi-C scaffolding assemble high-quality telomere-to-telomere genome C. speciosa. The comprised 650.4 Mb with contig N50 35.5 Mb. Of these, 632.3 were anchored 17...