Xiaojun Shi

ORCID: 0000-0001-8575-1812
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Advanced Computational Techniques and Applications
  • Advanced Sensor and Control Systems
  • Power Systems and Technologies
  • Video Surveillance and Tracking Methods
  • Wind and Air Flow Studies
  • Advanced Text Analysis Techniques
  • Sentiment Analysis and Opinion Mining
  • Text and Document Classification Technologies
  • Advanced Measurement and Detection Methods
  • Embedded Systems and FPGA Design
  • Autonomous Vehicle Technology and Safety
  • Anomaly Detection Techniques and Applications
  • Human Pose and Action Recognition
  • Coal Combustion and Slurry Processing
  • Offshore Engineering and Technologies
  • Smart Grid and Power Systems
  • Text Readability and Simplification
  • Climate Change and Health Impacts
  • Methane Hydrates and Related Phenomena
  • Wildlife Ecology and Conservation
  • Urban Heat Island Mitigation
  • IoT-based Smart Home Systems
  • Mining and Gasification Technologies
  • Coal and Coke Industries Research
  • Energy Efficient Wireless Sensor Networks

Beijing University of Chinese Medicine
2024

University of Electronic Science and Technology of China
2023

China Academy of Information and Communications Technology
2023

University of International Business and Economics
2021

Beijing Union University
2018-2020

North University of China
2013

PLA Army Engineering University
2007-2012

China University of Mining and Technology
2010

Southeast University
2004-2008

Jiangsu University of Technology
2007

The development of autonomous driving has brought with it requirements for intelligence, safety, and stability. One example this is the need to construct effective forms interactive cognition between pedestrians vehicles in dynamic, complex, uncertain environments. Pedestrian action detection a form that fundamental success technologies. Specifically, detect pedestrians, recognize their limb movements, understand meaning actions before making appropriate decisions response. In survey, we...

10.26599/tst.2019.9010018 article EN Tsinghua Science & Technology 2020-06-12

The detection of grammatical errors in English composition is an important task the field NLP. main purpose this to check out sentences and correct them. Grammatical error correction are applications automatic proofreading texts learning aids. With increasing influence on a global scale, huge breakthrough has been made detecting errors. Based machine learning, paper designs new method for composition. First, implements model based Seq2Seq. Second, scheme Transformer model. performs better...

10.1155/2021/4213791 article EN Scientific Programming 2021-12-18

Computer vision is an important part of the autonomous vehicles to gain perception surrounding environment. In order satisfy adaptability lane detection system under different illumination and road conditions, effective method based on image classification hybrid isomeric operators proposed. Camera correction matrix distortion coefficient are obtained by using checkerboard grid images, they will be cached shared with subsequent streams improve speed real-time detection. process...

10.1109/access.2018.2885568 article EN cc-by IEEE Access 2018-12-27

Introduction Heatstroke is a serious clinical condition caused by exposure to high temperature and humidity environment, which leads rapid increase of the core body more than 40°C, accompanied skin burning, consciousness disorders other organ system damage. This study aims analyze effect meteorological factors on incidence heatstroke using machine learning, construct forecasting model provide reference for prevention. Methods The data in city South China from May September 2014–2019 were...

10.3389/fpubh.2024.1420608 article EN cc-by Frontiers in Public Health 2024-07-22

Wildlife poaching is threatening key species that play important roles in the ecosystem. With historical ranger patrol records, it possible to provide data-driven predictions of threats and plan patrols combat poaching. However, patrollers often a multimodal way, which combines driving walking. It tedious task for domain experts manually such as result, planned routes are far from optimal. In this paper, we propose approach planning. We first use machine learning models predict then novel...

10.1609/aaai.v35i17.17792 article EN Proceedings of the AAAI Conference on Artificial Intelligence 2021-05-18

Aspect-based sentiment classification is a crucial problem in fine-grained analysis, which aims to predict the polarity of given aspect according its context. Previous works have made remarkable progress leveraging attention mechanism extract opinion words for different aspects. However, persistent challenge effective management semantic mismatches, stem from mechanisms that fall short adequately aligning opinions with their corresponding multi-aspect sentences. To address this issue, we...

10.48550/arxiv.2308.11447 preprint EN other-oa arXiv (Cornell University) 2023-01-01
Coming Soon ...