A5028481810- Human Mobility and Location-Based Analysis
- Service-Oriented Architecture and Web Services
- Geographic Information Systems Studies
- Energy Load and Power Forecasting
- Urban Transport and Accessibility
- Neural Networks and Applications
- Immune Cell Function and Interaction
- Advanced Computational Techniques and Applications
- Immune Response and Inflammation
- Urban Design and Spatial Analysis
- Immunotherapy and Immune Responses
- Stock Market Forecasting Methods
- Asthma and respiratory diseases
- Neutrophil, Myeloperoxidase and Oxidative Mechanisms
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Neonatal Respiratory Health Research
- Complex Network Analysis Techniques
- Respiratory Support and Mechanisms
- Embedded Systems Design Techniques
- Vibration and Dynamic Analysis
- Embedded Systems and FPGA Design
- Machine Fault Diagnosis Techniques
- Chemokine receptors and signaling
- Caching and Content Delivery
- Data Management and Algorithms
Taiyuan University of Technology
2013-2025
Sichuan University
2025
Henan University of Science and Technology
2023-2024
Army Medical College
2023
Army Medical University
2007-2023
Peking University
2011-2021
State Key Laboratory of Remote Sensing Science
2011-2021
Beijing Chang'an Integrated Traditional Chinese and Western Medicine Hospital
2018
The University of Melbourne
2018
University of Georgia
2013-2014
Abstract In the age of B ig D ata, widespread use location‐awareness technologies has made it possible to collect spatio‐temporal interaction data for analyzing flow patterns in both physical space and cyberspace. This research attempts explore interpret embedded network phone‐call phone‐users’ movements, by considering geographical context mobile phone cells. We adopt an agglomerative clustering algorithm based on a N ewman‐ G irvan modularity metric propose alternative function...
In this study we estimate urban traffic flow using GPS-enabled taxi trajectory data in Qingdao, China, and examine the capability of betweenness centrality street network to predict flow. The results show that is not a good predictor variable for flow, which has, theoretically, been pointed out existing literature. With critique as predictor, further analyze characteristics point ‘gap’ between measure actual Rather than considering only topological properties network, take into account two...
The distinction between mild pathogenic mtDNA mutations and population polymorphisms can be ambiguous because both are homoplasmic, alter conserved functions, correlate with disease. One possible explanation for this ambiguity is that the same variant may have different consequences in contexts. NADH dehydrogenase subunit 1 (ND1) nucleotide 3394 T > C (Y30H) such a case. This has been associated Leber hereditary optic neuropathy it reduces complex I activity cellular respiration 7% 28% on...
Inferring the unknown properties of a place relies on both its observed attributes and characteristics places to which it is connected. Because are unstructured metrics for connections can be diverse, challenging incorporate them in spatial prediction task where results could affected by how neighborhoods delineated true relevance among hard identify. To bridge gap, we introduce graph convolutional neural networks (GCNNs) model as graph, each formalized node, encoded node features,...
Transformers were initially introduced for natural language processing, leveraging the self-attention mechanism. They require minimal inductive biases in their design and can function effectively as set-based architectures. Additionally, transformers excel at capturing long-range dependencies enabling parallel which allows them to outperform traditional models, such long short-term memory (LSTM) networks, on sequence-based tasks. In recent years, have been widely adopted computer vision,...
Location prediction based on spatio-temporal footprints in social media is instrumental to various applications, such as travel behavior studies, crowd detection, traffic control, and location-based service recommendation. In this study, we propose a model that uses geotags of predict the potential area containing users' next locations. model, utilize HiSpatialCluster algorithm identify clustering areas (CAs) from check-in points. CA basic spatial unit for predicting Then, use LINE...
Delirium is a common and distressing mental disorder in palliative care. To date, no delirium prediction model available for thepalliative care population. The research aimed to develop validate nomogram predicting the occurrence of advanced cancer patients admitted units. This was prospective, multicenter, observational study. Logistic regression used identify independent risk factors incident among Advanced units between February 2021 January 2023 were recruited from four hospitals...
Airway inflammation and mucus hyperproduction play the central role in development of asthma, although mechanisms remain unclear. The aquaporin (AQP)-5 may be involved process due to its contribution volume liquid secreted from airways. present study firstly found overexpression AQP5 airway epithelium submucosal glands asthmatics. Furthermore, we aimed at evaluating mucous hyperproductions during chronic allergic responses house dust mite (HDM). Bronchoalveolar lavage levels interleukin...
This paper improves stock market prediction based on genetic algorithms (GA) and wavelet neural networks (WNN) reports significantly better accuracies compared to existing approaches prediction, including the hierarchical GA (HGA) WNN. Specifically, we added information such as trading volume inputs used Morlet function instead of Morlet-Gaussian in our model. We also employed a smaller number hidden nodes WNN other research work. The system is tested using Shenzhen Composite Index data.
This study uses delayed neural network models to predict public housing prices in Singapore. The networks are used estimate the trend of resale price index (RPI) Singapore from Housing Development Board (HDB), with nine independent economic and demographic variables. results show that model is able produce a good fit predictions.
Secreted phospholipase A2-IIA (sPLA2-IIA) is an inducible enzyme released under several inflammatory conditions. It has been shown that sPLA2-IIA from rat brain astrocytes after stimulus, and lipopolysaccharide (LPS) nitric oxide (NO) have implicated in regulation of this release. Here, microvascular endothelial cells (BMVECs) were treated with LPS to uncover whether was released, regulated release, any related signal mechanisms. Supernatants collected primary cultures BMVECs. The release...
Urban transit networks need to be upgraded in accordance with urban development. While methods have been studied design an optimal network given the locations of stations, these focus on whole as optimization object. However, strategy improve parts existing based gap between travel demand and infrastructure supply is rarely investigated. Different same should not priority upgraded. An evaluation method required for this purpose decide which a first. We argue that Ollivier-Ricci curvature,...