A5100539153- Human Mobility and Location-Based Analysis
- Traffic Prediction and Management Techniques
- Transportation Planning and Optimization
- Transportation and Mobility Innovations
- Urban Transport and Accessibility
- Immune Cell Function and Interaction
- Smart Parking Systems Research
- Energy Harvesting in Wireless Networks
- Electric Vehicles and Infrastructure
- Data Management and Algorithms
- Reproductive System and Pregnancy
- Privacy-Preserving Technologies in Data
- Natural product bioactivities and synthesis
- Stock Market Forecasting Methods
- Traffic control and management
- Financial Markets and Investment Strategies
- Ecology and Vegetation Dynamics Studies
- Ideological and Political Education
- CAR-T cell therapy research
- Immune responses and vaccinations
- Automated Road and Building Extraction
- Vehicular Ad Hoc Networks (VANETs)
- Gut microbiota and health
- Physics of Superconductivity and Magnetism
- Radiomics and Machine Learning in Medical Imaging
Jinzhong College of Information
2025
First Affiliated Hospital of Zhengzhou University
2024-2025
Jinzhong University
2025
Shenzhen Third People’s Hospital
2025
Southern University of Science and Technology
2025
Shenzhen Institutes of Advanced Technology
2014-2024
Chinese Academy of Sciences
2010-2024
Donghua University
2024
Guizhou Forestry Science Research Institute
2024
Cedars-Sinai Medical Center
2022-2023
In recent years, various deep learning architectures have been proposed to solve complex challenges (e.g. spatial dependency, temporal dependency) in traffic domain, which achieved satisfactory performance. These are composed of multiple techniques order tackle tasks. Traditionally, convolution neural networks (CNNs) utilized model dependency by decomposing the network as grids. However, many graph-structured nature. utilize such information fully, it's more appropriate formulate graphs...
Metro systems have become one of the most important public transit services in cities. It is to understand individual metro passengers' spatio-temporal travel patterns. More specifically, for a specific passenger: what are temporal patterns? spatial there any relationship between and passenger's patterns normal or special? Answering all these questions can help improve services, such as evacuation policy making marketing. Given set massive smart card data over long period, how effectively...
Metro systems play an important role in meeting the demand for urban transportation large cities. The understanding of passenger route choice is critical public transit management. wide deployment automated fare collection (AFC) opens up a new opportunity. However, only each trip's tap-in and tap-out time stamp stations can be directly obtained from AFC system records; train chosen by are unknown, information necessary to solve our problem. While existing methods work well some specific...
As the booming of deep learning era, especially advances in convolutional neural networks (CNNs), CNNs have been applied medicine fields like radiology and pathology. However, application dermatology, which is also based on images, very limited. Inflammatory skin diseases, such as psoriasis (Pso), eczema (Ecz), atopic dermatitis (AD), are easily to be mis-diagnosed practice.Based EfficientNet-b4 CNN algorithm, we developed an artificial intelligence dermatology diagnosis assistant (AIDDA)...
The emerging trend towards moving from monolithic applications to microservices has raised new performance challenges in cloud computing environments. Compared with traditional applications, the are lightweight, fine-grained, and must be executed a shorter time. Efficient scaling approaches required ensure microservices’ system under diverse workloads strict Quality of Service (QoS) requirements optimize resource provisioning. To solve this problem, we investigate trade-offs between dominant...
Abstract Epithelial plasticity has been suggested in lungs of mice following genetic depletion stem cells but is unknown physiological relevance. Viral infection and chronic lung disease share similar pathological features cell loss alveoli, basal (BC) hyperplasia small airways, innate immune activation, that contribute to epithelial remodeling function. We show a subset distal airway secretory cells, intralobar serous (IS) are activated assume BC fates influenza virus infection....
Data-driven modeling usually suffers from data sparsity, especially for large-scale urban phenomena based on single-source infrastructure under fine-grained spatial-temporal contexts. To address this challenge, we motivate, design and implement UrbanCPS, a cyber-physical system with heterogeneous model integration, extremely-large multi-source infrastructures in Chinese city Shenzhen, involving 42 thousand vehicles, 10 million residents, 16 smartcards. Based temporal, spatial contextual...
Contactless smart card systems have gained universal prevalence in modern metros. In addition to its original goal of ticketing, the large amount transaction data collected by system can be utilized for many operational and management purposes. This paper investigates an important problem: how extract spatiotemporal segmentation information trips inside a metro system. More specifically, given trip, we want answer several key questions: How long does it take passenger walk from station...
Subway passenger flow forecasting, an essential component of intelligent transportation system, is critical for traffic management, public safety, urban planning. However, it very challenging due to the high nonlinearities and complex dynamic spatio-temporal dependencies flows. In this paper, we model subway system as a directed weighted graph propose novel deep learning framework, Multi-STGCnet, forecasting short-term at station level. Specifically, Multi-STGCnet mainly composed two...
Stock price movement prediction is commonly accepted as a very challenging task due to the volatile nature of financial markets. Previous works typically predict stock mainly based on its own information, neglecting cross effect among involved stocks. However, it well known that an individual correlated with prices other stocks in complex ways. To take into consideration, we propose deep learning framework, called Multi-GCGRU, which comprises graph convolutional network (GCN) and gated...
Heightened wakefulness in response to stressors is essential for survival but can also lead sleep disorders like insomnia. The paraventricular thalamus (PVT) both a critical thalamic area and stress-sensitive brain region. However, whether the PVT its neural circuitries are involved controlling stress conditions remains unknown. Here, we find that neurons projecting central amygdala (CeA) activated by different stressors. These wakefulness-active increase their activities upon transitions....
Abstract Background Several approaches are being explored for engineering off-the-shelf chimeric antigen receptor (CAR) T cells. In this study, we engineered Fcγ (FcγR) cells and tested their potential as a versatile platform universal cell therapy. Methods Chimeric FcγR (CFR) constructs were generated using three distinct forms of FcγR, namely CD16A, CD32A, CD64. The functionality CFR was evaluated through degranulation assays, specific target lysis experiments, in vitro cytokine production...
Regulatory T cells (Tregs) play a crucial role in maintaining immune tolerance by suppressing responses against pathogens. The fluctuation of Treg proportions COVID-19 remains topic debate, and the mechanisms triggering activation are still unclear. Understanding these issues is essential for better managing patients. We collected cohort patients with varying disease severity stage to explore transcriptomic functional traits Tregs individuals. Using analysis, we evaluated proportion...
The future generation of transportation system will be featured by electrified public transportation. To fulfill metropolitan transit demands, electric vehicles (EVs) must continuously operable without recharging downtime. Wireless Power Transfer (WPT) techniques for in-motion EV charging is a solution. It however brings up challenge: how to deploy lanes in road network minimize the deployment cost while enabling EVs' continuous operability. In this paper, we propose CatCharger, which first...
For electric taxicabs, the idle time spent on cruising for passengers, seeking chargers, and charging is wasteful. Previous works can only save through better routing, or charger proper deployment, but not both. With advancement of wireless techniques, efficient opportunistic vehicles at their parked positions becomes possible. This enables a taxicab to get charged while waiting next passenger. In this paper, we present an deployment scheme in city, which both maximizes taxicabs' opportunity...
Real-time human mobility modeling is essential to various urban applications. To model such mobility, numerous data-driven techniques have been proposed. However, existing are mostly driven by data from a single view, e.g., transportation view or cellphone which leads over-fitting of these single-view models. address this issue, we propose technique based on generic multi-view learning framework called coMobile. In coMobile, first improve the performance models tensor decomposition with...
In this paper, we propose a transit service Feeder to tackle the last-mile problem, i.e., passengers' destinations lay beyond walking distance from public station. utilizes ridesharing-based vehicles (e.g., minibus) deliver passengers existing stations selected stops closer their destinations. We infer real-time passenger demand exiting and times) for design by utilizing extreme-scale urban infrastructures, which consist of 10 million cellphones, 27 thousand vehicles, 17 smartcard readers 16...