A5021112142- Animal Vocal Communication and Behavior
- Marine animal studies overview
- Urban Green Space and Health
- Land Use and Ecosystem Services
- Noise Effects and Management
- Music and Audio Processing
- Conservation, Biodiversity, and Resource Management
- Cancer-related molecular mechanisms research
- RNA modifications and cancer
- Urban Agriculture and Sustainability
- Olfactory and Sensory Function Studies
- Atmospheric chemistry and aerosols
- Botany and Plant Ecology Studies
- Air Quality and Health Impacts
- Colorectal Cancer Treatments and Studies
- Speech and Audio Processing
- Bryophyte Studies and Records
- Avian ecology and behavior
- Mycobacterium research and diagnosis
- Brain Tumor Detection and Classification
- Ferroptosis and cancer prognosis
- Plant responses to elevated CO2
- Lichen and fungal ecology
- Melanoma and MAPK Pathways
- Applied Advanced Technologies
Shanghai University of Medicine and Health Sciences
2022-2025
University of Shanghai for Science and Technology
2022-2025
Jiading District Central Hospital
2024-2025
Chinese Academy of Forestry
2019-2024
Research Institute of Tropical Forestry
2022-2024
Research Institute of Forestry
2019-2022
State Forestry and Grassland Administration
2019-2021
South China University of Technology
2020
The shifts of bird song frequencies in urbanized areas provide a unique system to understand avian acoustic responses urbanization. Using passive monitoring and automatic sound recognition technology, we explored the frequency variations six common urban species their associations with habitat structures. Our results demonstrated that were significantly higher than those peri-urban rural areas. Anthropogenic noise structure identified as crucial factors shaping space for birds. We found...
Passive acoustic monitoring serves as a minimally invasive and effective method for biodiversity assessment, particularly in bird through the application of indices. However, use different recording devices types environmental noise (e.g., rain, wind, stream, traffic noise) lead to signal distortions that affect ecoacoustics Currently, there are no established guidelines specifying technical requirements signal-to-noise ratio (SNR) threshold accurate calculation To enhance accuracy indices...
Abstract Intensified human activities have been seriously threatening the structure and ecological processes of ecosystems, resulting in habitat degradation. Therefore, coordinating coupling between quality (HQ) is crucial for high‐quality sustainable regional development well‐being. This study evaluated HQ Pearl River Delta (PRD) urban agglomeration China from 2000 to 2020 using footprint index (HFI) integrated valuation ecosystem services tradeoffs model. Then, we employed bivariate...
Introduction Human brain activities are always difficult to recognize due its diversity and susceptibility disturbance. With unique capability of measuring activities, magnetoencephalography (MEG), as a high temporal spatial resolution neuroimaging technique, has been used identify multi-task activities. Accurately robustly classifying motor imagery (MI) cognitive (CI) from MEG signals is significant challenge in the field brain-computer interface (BCI). Methods In this study, graph-based...
The use of passive acoustic monitoring (PAM) can compensate for the shortcomings traditional survey methods on spatial and temporal scales achieve all-weather wide-scale assessment prediction environmental dynamics. Assessing impact human activities biodiversity by analyzing characteristics scenes in environment is a frontier hotspot urban forestry. However, with accumulation data, selection parameter setting deep learning model greatly affect content efficiency sound scene classification....
Monitoring biodiversity and assessing the impact of human activities using acoustics is a promising area in field urban ecology. Previous studies on are often limited by data continuity survey scope, making it difficult to answer questions about relationships between bird population dynamics environmental factors. To some extent, big methods such as continuous acoustic monitoring have bridged this gap provided new research paths address problem. In study, we proposed machine learning (ML)...
Abstract To explore the application value of convolutional neural network combined with residual attention mechanism and Xception model for automatic classification benign malignant gastric ulcer lesions in common digestive endoscopy images under condition insufficient data. For problems uneven illumination low resolution endoscopic images, original image is preprocessed by Sobel operator, etc. The algorithm implemented Pytorch, used as input based on diagnosis small number images. accuracy,...
Abstract As a crucial component of terrestrial ecosystems, urban forests play pivotal role in protecting biodiversity by providing suitable habitats for acoustic spaces. Previous studies note that vegetation structure is key factor influencing bird sounds forests; hence, adjusting the frequency composition may be strategy birds to avoid anthropogenic noise mask their songs. However, it unknown whether response mechanisms vocalizations remain consistent despite being impacted noise. It was...
Bird sounds have obvious characteristics per species, and they are an important way for birds to communicate transmit information. However, the recorded bird in field usually mixed, which making it challenging identify different species perform associated tasks. In this study, based on supervised learning framework, we propose a sound separation network, dual-path tiny transformer directly end-to-end mixed time-domain. This network is mainly composed of simplified structure, greatly reduces...
This study aimed to address the issue of larger prediction errors existing in intelligent predictive tasks related Alzheimer's disease (AD). A cohort 487 enrolled participants was categorized into three groups: normal control (138 individuals), mild cognitive impairment (238 patients), and AD (111 patients) this study. An improved multifeature squeeze-and-excitation-dilated residual network (MFSE-DRN) proposed for two important predictions: clinical scores conversion probability. The model...
As an important biomarker of neural aging, the brain age reflects integrity and health human brain. Accurate prediction could help to understand underlying mechanism aging. In this study, a cross-stratified ensemble learning algorithm with staking strategy was proposed obtain derived predicted difference (PAD) using T1-weighted magnetic resonance imaging (MRI) data. The approach characterized as by implementing two modules: one three base learners 3D-DenseNet, 3D-ResNeXt, 3D-Inception-v4;...
Forests can affect soil organic carbon (SOC) quality and distribution through forest types traits. However, much less is known about the influence of urban forests on SOC, especially in effects different types, such as coniferous broadleaved forests. Our objectives were to assess variability SOC content (SOC concentration (SOCC) density (SOCD)) determine key traits influencing SOC. Data from 168 plots or located Beijing area used predict three layers, 0–10 cm, 10–20 20–30 cm. The analysis...
Leaf color is a key trait that determines the ornamental quality of landscape tree species such as Acer tutcheri, and anthocyanin main pigment for red leaf coloration. Red fading significantly reduces value A. tutcheri leaves in spring; however, physiological mechanism causes discoloration this still unclear. Only anabolic or degradative metabolism has been studied terms changes. In study, from four color-change stages during spring were selected by average sampling method, which involves...
Lung adenocarcinoma represents a significant global health challenge. Despite advances in diagnosis and treatment, the prognosis remains poor for many patients. In this study, we aimed to identify cuproptosis-related genes develop deep neural network model predict of lung adenocarcinoma. We screened differentially expressed from The Cancer Genome Atlas data through differential analysis genes. then used information establish prognostic using network, which validated Gene Expression Omnibus....
This study has developed and optimized a machine learning model to accurately predict the final colors of CAD-CAM ceramics determine their required minimum thicknesses cover different clinical backgrounds.