A5044207756- Human Mobility and Location-Based Analysis
- Urban Transport and Accessibility
- Data Visualization and Analytics
- Computer Graphics and Visualization Techniques
- Advanced Vision and Imaging
- Transportation Planning and Optimization
- Nanoplatforms for cancer theranostics
- Autonomous Vehicle Technology and Safety
- Generative Adversarial Networks and Image Synthesis
- Transportation and Mobility Innovations
- Advanced Nanomaterials in Catalysis
- 3D Shape Modeling and Analysis
- Advanced Neural Network Applications
- Color perception and design
- Video Surveillance and Tracking Methods
- Traffic Prediction and Management Techniques
- Digital Media and Visual Art
- Domain Adaptation and Few-Shot Learning
- Single-cell and spatial transcriptomics
- Tensor decomposition and applications
- Central Asia Education and Culture
- Face recognition and analysis
- MicroRNA in disease regulation
- Green IT and Sustainability
- Remote Sensing and LiDAR Applications
Wuxi Vocational Institute of Commerce
2024
Hangzhou Dianzi University
2015-2023
Shanghai Jiao Tong University
2023
Tongji University
2022
Tongji Hospital
2022
Dalian Maritime University
2020
Ministry of Education of the People's Republic of China
2016-2019
Dalian University
2018
Dalian University of Technology
2018
Zhejiang University of Technology
2011-2016
External stimulation, mood swing, and physiological arousal are closely related induced by each other. The exploration of internal relations between these three aspects is interesting significant. Currently, video the most popular multimedia stimuli that can express rich emotional semantics its visual auditory features. Apart from features, human electroencephalography (EEG) features provide useful information for emotion recognition, as they direct instant authentic feedback on perception...
Acute myeloid leukemia (AML) is a highly heterogeneous disease. MicroRNAs function as important biomarkers in the clinical prognosis of AML. This study identified miR-425 prognostic factor AML by screening TCGA dataset. A total 162 patients with were enrolled for and divided into chemotherapy allogeneic hematopoietic stem cell transplantation (allo-HSCT) groups. In group, high expression had significantly longer overall survival (OS) event-free (EFS) compared low expression. multivariate...
An understanding of the evolutionary patterns in areas urban activity is crucial for official decision makers and planners. The origin-destination (OD) datasets generated by human daily travel behavior reflect dynamics. Previous spatio-temporal analysis methods utilize these to extract popular city areas, with ignorance flow relationships between areas. Several have been unable determine time steps similar spatial characteristics automatically or failed recognize various modalities a city....
High-resolution remote sensing technology is an efficient and low-cost space-to-earth observation strategy, which can carry out simultaneous monitoring of large-scale areas. It has incomparable advantages over ground solutions. Traditional road extraction methods are mainly based on image processing techniques. These usually only use one or a few features images, difficult to fully deal with the real situation roads. This work proposes two-steps network for extraction. First, we optimize...
The stereo vision could obtain the 3-D coordinate of detected object by computing disparity corresponding image points. However, on account time complexity and low robustness matching algorithm, it is seldom used in large-scale scene. This paper puts forward a new vehicle detection method, which simplifies massive Fourier transformation process. method converts 2-D to 1-D with dimensionality reduction reused transformation. Meanwhile, fast model also derived. coarse-to-fine pyramid search...
Non-small-cell lung cancer (NSCLC) has become the second most diagnosed malignant tumors worldwide. As our long-term interests in seeking nanomaterials to develop strategies of therapies, we herein constructed novel CoFe2O4-quantum dots (QDs) with outstanding synergistic photothermal/photodynamic property which suppressed NSCLC efficiently without apparent toxicity. We showed that combination CoFe2O4-QDs + NIR treatment induces apoptosis cells. In addition, also promotes reactive oxygen...
Traditional methods of inverse kinematics robots always adopt analytical approach and numerical to solve the continuous state action problems with experience experiment mostly, which require much time work in reality scene, especially for complex structure. This paper proposes a method based on reinforcement learning TD3 network, is constructed by PyTorch find solution from another point view. A set improved distributed multiple rewards choose position difference between adjacent joints as...
Information concerning the home and workplace of residents is basis analyzing urban job-housing spatial relationship. Traditional methods conduct time-consuming user surveys to obtain personal job housing location information. Some new define rules detect places based on human mobility data. However, because travel patterns are variable, simple rule-based unable generalize highly changing complex modes. In this paper, we propose a visual analysis approach assist analyzer in inferring...
Dockless bike sharing (DBS) is convenient for users because it can solve their last-mile problems. However, dockless bikes that are disorderly parked in public spaces disturb normal traffic. In planning electric fences DBS systems, the maximum coverage location problem (MCLP) identifies locations suitable fences. MCLP model ignores regional boundaries of use and causes substantial errors assessments. this article, we present a novel framework fences, accounting both trip distribution area...
Dockless bike-sharing system has dramatically increased around the world since 2015, with advantage of "free to leave" and "no fixed berth". Understanding users' travel behavior is invaluable for policy makers related companies. However, it difficult capture spatio-temporal cycling patterns based on sparse data. In this paper, we analyze dockless data using tensor decomposition method. A three-dimensional constructed first, a method employed detect underlying patterns. Several visual...
Abstract In resource constrained edge environment, multiple service providers can compete to rent the limited resources cache their instances on servers close end users, thereby significantly reducing delay and improving quality of (QoS). However, renting different deploy incur usage costs delay. To make full use further reduce costs, an server form a coalition share server. this paper, we investigate caching problem in propose independent learners-based services scheme (ILSCS) which adopts...
In recent years, deep reinforcement learning (DRL) models are enjoying great interest as their success in a variety of challenging tasks.Deep Q-Network (DQN) is widely used model, which trains an intelligent agent that executes optimal actions while interacting with environment.This model well known for its ability to surpass skilled human players across many Atari 2600 games.Although DQN has achieved excellent performance practice, there lacks clear understanding why the works.In this...