A5100605502- EEG and Brain-Computer Interfaces
- melanin and skin pigmentation
- Blind Source Separation Techniques
- Intellectual Property and Patents
- Safety and Risk Management
- Nuclear and radioactivity studies
- Graphite, nuclear technology, radiation studies
- Radiation Dose and Imaging
- Radioactive contamination and transfer
- Biochemical Analysis and Sensing Techniques
- Advanced X-ray and CT Imaging
- Methane Hydrates and Related Phenomena
- Recommender Systems and Techniques
- Smart Grid Energy Management
- Mesenchymal stem cell research
- Currency Recognition and Detection
- RNA regulation and disease
- Amyloidosis: Diagnosis, Treatment, Outcomes
- Reliability and Maintenance Optimization
- ECG Monitoring and Analysis
- Hair Growth and Disorders
- Remote Sensing and Land Use
- IgG4-Related and Inflammatory Diseases
- Retinal Imaging and Analysis
- Innovation and Knowledge Management
First Affiliated Hospital of Zhengzhou University
2024-2025
Third People's Hospital of Hefei
2025
Tsinghua University
1998-2024
Beijing Anzhen Hospital
2017-2024
Capital Medical University
2006-2024
Kunming University of Science and Technology
2024
Tianjin Medical University
2024
Nankai University
2024
City University of Macau
2024
Hangzhou City University
2024
It is essential to utilize deep-learning algorithms based on big data for the implementation of new generation artificial intelligence. Effective utilization deep learning relies considerably number labeled samples, which restricts application in an environment with a small sample size. In this paper, we propose approach generative adversarial network (GAN) combined neural (DNN). First, original samples were divided into training set and test set. The GAN was trained generate synthetic data,...
Abstract Deep learning can be used to forecast emerging technologies based on patent data. However, it requires a large amount of labeled data as training set, which is difficult obtain due various constraints. This study proposes novel approach that integrates augmentation and deep methods, overcome the problem lacking samples when applying technologies. First, sample set was constructed using Gartner’s hype cycle multiple features. Second, generative adversarial network generate many...
Eye blink is one of the most common artifacts in electroencephalogram (EEG) and significantly affects performance EEG related applications, such as epilepsy recognition, spike detection, encephalitis diagnosis, etc. To achieve an accurate efficient eye a novel unsupervised learning algorithm based on hybrid thresholding followed with Gaussian mixture model (GMM) presented this paper. The signal priliminarily screened by cascaded method built distributions amplitude, amplitude displacement,...
The convergence of multi-disciplinary knowledge may spur emerging technologies. It is important to understand this process that helps identify these emergent technologies; however, relevant research remains sparse. Therefore, study aims develop a novel framework reveal the scientific knowledge. This integrates machine-learning topology clustering and visualization methods, analyzes paper citation networks. selects biological–informatics domain (bioinformatics) conduct empirical analysis....
Epilepsy is a disease in which patients undergo seizures caused by brain functionality disorder. Clinically, it usually diagnosed experienced clinicians according to continuous electroencephalography (cEEG), time consuming even for doctors. Meanwhile, amplitude integrated (aEEG) has shown potential detect epileptic seizures. Therefore, the paper proposes hybrid seizure detection algorithm combining cEEG-based and aEEG-based In algorithm, cEEG signals are divided into 5 s epoch with 4 overlap...
Tyrosinase (TYR), tyrosinase‐related protein‐1 (TYRP1/gp75) and dopachrome tautomerase (DCT/TYRP2) belong to a family of melanocyte‐specific gene products involved in melanin pigmentation. During melanocyte development expression tyrosinase genes is thought be orchestrated part by the binding shared basic helix–loop–helix transcription factor MITF M box, regulatory element conserved among these genes. In transformed melanocytes, TYRPs highly variable. Whereas TYR melanoma cells regulated...
Benign childhood epilepsy with centro-temporal spikes (BECT) is one of the most common syndromes in which typically characterized by localized discharges central and temporal regions. Traditionally, recognition requires visual assessment long-term EEG recordings time consuming subjective because it depends on knowledge experience doctor. Therefore, a novel multi-step spike detection algorithm based average reference (AV) channel bipolar (BP) BECT proposed, including candidate algorithm,...
The present cohort study aimed to evaluate the value of CCL23 in diagnosis, disease activity, and prognosis patients with antineutrophil cytoplasmic antibody-associated vasculitis (AAV). levels serum samples from 317 AAV 83 healthy controls (HCs) were measured using a customized immune response kit. Patients had significantly elevated CL23 compared HCs. level was closely related activity better than birmingham score (BVAS) distinguishing relapse remission (area under curve: = 0.942, BVAS...
Mucosal contact of the tip colonoscopy causes red-out views, and more pressure may result in perforation. There is still a lack quantitative analysis methods for views. We aimed to develop an artificial intelligence (AI)-based system assess views during intubation colonoscopy. Altogether, 479 colonoscopies performed by 34 colonoscopists were analysed using proposed semi-supervised AI-based system. compared avoiding scores among novice, intermediate, experienced colonoscopists. The mean...
Melastatin 1 (MLSN1), originally identified as melanoma metastasis suppressor, represents a TRPM subfamily of transient receptor potential (TRP) proteins which serve diverse biological roles in wide variety cell types. Down-regulation MLSN1 expression human cutaneous melanoma, indicated by situ hybridization, appears to be prognostic marker for metastasis. However, the exact physiological function(s) MLSN1, mechanism(s) involved regulation its and role tumour progression are not yet clear....
Treatment of human melanoma cells with the differentiation‐inducing agent hexamethylene bisacetamide (HMBA) results in reciprocal changes expression melanocyte‐specific genes tyrosinase‐related proteins‐1 and ‐2 ( TYRP1 TYRP2 ). In this study, we investigated effects HMBA on cultured neonatal cutaneous melanocytes. Flow cytometric analysis showed that inhibited 12‐ O ‐tetradecanoylphorbol‐13‐acetate (TPA)‐dependent growth melanocytes by reducing population entering DNA synthesis phase cell...
A contextual bandit problem is studied in a highly non-stationary environment, which ubiquitous various recommender systems due to the time-varying interests of users. Two models with disjoint and hybrid payoffs are considered characterize phenomenon that users' preferences towards different items vary differently over time. In payoff model, reward playing an arm determined by arm-specific preference vector, piecewise-stationary asynchronous distinct changes across arms. An efficient...
With the increasment of epilepsy patients, traditional epileptic seizure recognition is generally completed by encephalography (EEG) technicians, which time-consuming and labor-intensive, so automatic detection imminent. This paper proposes a method constructs multi-layer network extracts same features in each optimized improved genetic algorithm (IGA). Among them, refers to three-layer constructed pearson correlation coefficient, mutual information permutation disalignment index...
Abstract T-helper 17 cells play a dual role in immunological responses, serving as essential components tissue homeostasis and host defense against microbial pathogens while also contributing to proinflammatory conditions autoimmunity. While transforming growth factor β1 is pivotal for the differentiation of nonpathogenic cells, β3 activin steering toward pathogenic phenotype has been acknowledged. However, molecular mechanisms governing this dichotomy remain elusive. In study, we...
Abstract We examined the effect of hydroxysafflor yellow A (HSYA) on inflammatory response to strike-induced acute soft tissue injury in rats. Soft was induced rat leg muscles using a strike hammer, followed by intraperitoneal administration HSYA at 16, 32, or 64 mg/kg. After 24 h, rats were anaesthetized, blood and muscle samples taken. Plasma levels interleukin (IL)-6, IL-1β, tumour necrosis factor (TNF)-αwere measured enzyme-linked immunosorbent assay. Total RNA protein isolated from...
Objective This study aimed to identify plasma biomarkers that are significantly altered in patients with antineutrophil cytoplasmic antibody (ANCA)-associated vasculitis (AAV) and closely associated AAV disease activity, as well explore their role the pathogenesis of AAV. Methods Cytokines were measured using Human Immune Response Panel 80-Plex from 59 20 healthy controls (HCs). The differentially expressed cytokines between two groups possible signaling pathway involved analyzed by...
Recent research applies patent autoclassification using machine learning to map the technological landscape of an industry value chain. However, when these methods are applied emerging industries, available sample data small-scale and unevenly distributed, which cause overfitting reduce accuracy classification. Therefore, this article proposes a framework chain through analysis with deep learning, integrates generative adversarial network as data-augmentation method overcome problem...