A5005856697- Infrared Target Detection Methodologies
- Video Surveillance and Tracking Methods
- Customer Service Quality and Loyalty
- Advanced Neural Network Applications
- Distributed Control Multi-Agent Systems
- Transportation and Mobility Innovations
- Radiomics and Machine Learning in Medical Imaging
- Gait Recognition and Analysis
- Endometrial and Cervical Cancer Treatments
- Fuel Cells and Related Materials
- Membrane-based Ion Separation Techniques
- Consumer Behavior in Brand Consumption and Identification
- Traffic Prediction and Management Techniques
- Transportation Planning and Optimization
- Robotic Path Planning Algorithms
- Digital Marketing and Social Media
- Cervical Cancer and HPV Research
- Domain Adaptation and Few-Shot Learning
- Fire Detection and Safety Systems
- Dye analysis and toxicity
- Reinforcement Learning in Robotics
- Remote-Sensing Image Classification
- Advanced battery technologies research
- Advanced Image Fusion Techniques
- Topic Modeling
Xi'an University of Science and Technology
2023-2025
Shanxi University
2024
Xi'an International Studies University
2024
Central South University
2019
China University of Geosciences (Beijing)
2015
Taxi demand can be divided into pick-up and drop-off demand, which are firmly related to human’s travel habits. Accurately predicting taxi is of great significance passengers, drivers, ride-hailing platforms urban managers. Most the existing studies only forecast for separate interaction between spatial correlation temporal correlation. In this paper, we first analyze historical data select three highly relevant parts each time interval, namely closeness, period trend. We then construct a...
Abstract To address the phenomenon of many small and hard-to-detect objects in infrared visible light images, we propose an object detection algorithm CDYL (Convolution to Fully Connect-ed-Deformable Convolution You only Look once) based on CFC-DC Connected-Deformable Convolution) module. The core operator is CFC-DC, making our model not have a large effective receptive field but also adaptive spatial aggregation conditioned by input task information. As result, reduces strict inductive bias...
Abstract To tackle Congo red contamination in dye wastewater, this study undertook the modification of ACP by adding β‐cyclodextrin (β‐CD), citric acid (CA), and polyethylene glycol (PEG), with objective augmenting its adsorption efficiency for (CR). Adsorption experiments were performed based on various factors, such as initial concentration, solution pH, temperature, contact time. The results demonstrated that β‐CD‐ACP had excellent properties could quantitatively remove from wastewater a...
with the advent of era live e-commerce and experience economy, many enterprises in world have resorted to broadcast sell their products. As an important information source, streamer not only introduces sells products during broadcast, but also affects consu
<sec> <title>BACKGROUND</title> Machine learning (ML) has been gradually applied to cervical cancer research, but rarely combines both clinical parameters and image data. Meanwhile, more robust accurate preoperative assessment of parametrial invasion lymph node metastasis, as well postoperative prognosis prediction are also in urgent need. </sec> <title>OBJECTIVE</title> We aimed develop an integrated ML model that integrates clinicopathological MR images includes pre- post-operation...
Most of the existing deep learning-based infrared and visible image fusion methods use convolutional neural networks for feature extraction, but perceptual field becomes smaller as depth layers increases, it is difficult to focus on global features source image. To address above problems, this paper proposes a self-encodering based combination dense connection module Transformer module, can extract non-local interaction relationship from entire image, more features, better understands local...
With the development of capital's subway system and rampant terrorist activities at home abroad, has become one important targets violence attacks.Although Beijing initially constructed video surveillance systems currently, there are deficiencies in intelligence analysis.This study pans to use algorithm innovation integrate intelligent analysis technology system, which can enhance overall level anti-terrorism counter-terrorism subway.