A5100680283- Bioinformatics and Genomic Networks
- Artificial Intelligence in Healthcare
- Health, Environment, Cognitive Aging
- Gene expression and cancer classification
- Radiomics and Machine Learning in Medical Imaging
- Single-cell and spatial transcriptomics
- Microplastics and Plastic Pollution
- Recycling and Waste Management Techniques
- AI in cancer detection
- Ferroptosis and cancer prognosis
- COVID-19 epidemiological studies
- Video Surveillance and Tracking Methods
- Cell Image Analysis Techniques
- Advanced Measurement and Detection Methods
- EEG and Brain-Computer Interfaces
- Emotion and Mood Recognition
- Psychosomatic Disorders and Their Treatments
- Remote Sensing and Land Use
- Music Therapy and Health
- Image and Signal Denoising Methods
- Data-Driven Disease Surveillance
- COVID-19 impact on air quality
- Advanced Biosensing Techniques and Applications
- Image Processing Techniques and Applications
- SARS-CoV-2 and COVID-19 Research
Zhejiang University
2025
University of Michigan
2019-2024
Ministry of Ecology and Environment
2024
Langfang Normal University
2023
Sun Yat-sen University
2020
Shanghai Medical Information Center
2017
Abstract Background There is no evidence supporting that temperature changes COVID-19 transmission. Methods We collected the cumulative number of confirmed cases all cities and regions affected by in world from January 20 to February 4, 2020, calculated daily means average, minimum maximum temperatures January. Then, restricted cubic spline function generalized linear mixture model were used analyze relationships. Results total 24,139 China 26 overseas countries. In total, 16,480 (68.01%)...
Abstract Multi-omics data are good resources for prognosis and survival prediction; however, these difficult to integrate computationally. We introduce DeepProg, a novel ensemble framework of deep-learning machine-learning approaches that robustly predicts patient subtypes using multi-omics data. It identifies two optimal in most cancers yields significantly better risk-stratification than other integration methods. DeepProg is highly predictive, exemplified by liver cancer (C-index...
Influenza, a disease caused by respiratory virus, sickened over 5,043,127 citizens in Shenzhen, China, from January 2014 to April 2016. An accurate forecasting of outbreaks influenza-like illness (ILI, here we refer ILI as the upper infection) could facilitate public health officials suggest actions earlier. In this study, random forest regression constructed with one-year period factors was adopted forecast weekly rate using clinical data Shenzhen Health Information Center. The following...
This study aims to employ physiological model simulation systematically analyze the frequency-domain components of PPG signals and extract their key features. The efficacy these features in effectively distinguishing emotional states will also be investigated. A dual windkessel was employed signal frequency distinctive Experimental data collection encompassed both (PPG) psychological measurements, with subsequent analysis involving distribution patterns statistical testing (U-tests) examine...
Sadness can be a harbinger of serious medical conditions and primary manifestation depressive symptoms. Music is promising modality for regulating sadness, although its effect on participants, whether with or without long-term symptoms, remains unknown. In this study, the music sadness regulation was investigated using psychological physiological indicators between depressed non-depressed individuals. Data were collected from 149 participants (18 to 29 years old). The divided into two groups...
Abstract Pathological images are easily accessible data with the potential of prognostic biomarkers. Moreover, integration heterogeneous types from multi-modality, such as pathological image and gene expression data, is invaluable to help predicting cancer patient survival. However, analytical challenges significant. Here, we take hepatocellular carcinoma (HCC) features extracted by CellProfiler, apply them input for Cox-nnet, a neural network-based prognosis prediction model. We compare...
Abstract Multi-omics data are good resources for prognosis and survival prediction, however, these difficult to integrate computationally. We introduce DeepProg, a novel ensemble framework of deep-learning machine-learning approaches that robustly predicts patient subtypes using multi-omics data. It identifies two optimal in most cancers yields significantly better risk-stratification than other integration methods. DeepProg is highly predictive, exemplified by liver cancer (C-index...
Cox-nnet is a neural-network-based prognosis prediction method, originally applied to genomics data. Here, we propose the version 2 of Cox-nnet, with significant improvement on efficiency and interpretability, making it suitable predict based large-scale population data, including those electronic medical records (EMR) datasets. We also add permutation-based feature importance scores direction coefficients. When kidney transplantation dataset, v2.0 reduces training time up 32-folds (n =10...
Abstract The increasing popularity of spatial transcriptomics has allowed researchers to analyze transcriptome data in its tissue sample’s context. Various methods have been developed for detecting SV (spatially variable) genes, with distinct expression patterns. However, the accuracy using these genes clustering not thoroughly studied. On other hand, single cell resolution sequencing without context, analysis is usually done on highly variable (HV) genes. Here we investigate if integrating...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Spatial transcriptomics has allowed researchers to analyze transcriptome data in its tissue sample's spatial context. Various methods have been developed for detecting spatially variable genes (SV genes), whose gene expression over the space shows strong autocorrelation. Such are often used define clusters cells or spots downstream. However, highly (HV) genes, quantitative expressions show significant variation from cell cell, conventionally clustering analyses. In this report, we...
ABSTRACT Purpose Pathological images are easily accessible data with the potential as prognostic biomarkers. Moreover, integration of heterogeneous types from multi-modality, such pathological image and gene expression data, is invaluable to help predicting cancer patient survival. However, analytical challenges significant. Experimental Design Here we take hepatocellular carcinoma (HCC) features extracted by CellProfiler, apply them input for Cox-nnet, a neural network-based prognosis. We...
In complex conditions such as illumination change, target rotation, and background clutter, tracking drift or failure may occur. Convolutional neural networks (CNN) can achieve robust in scenes illumination, so on. Therefore, this paper proposes a algorithm CNNT based on convolutional network. Use CNN deep learning model to extract the features of sample complete detection task, then use kernel correlation filter (KCF) tracking. We train Visual Geometry Group (VGG), using massive image data,...