Jinfu Liu

ORCID: 0000-0002-4590-5343
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Energy Load and Power Forecasting
  • Solar Radiation and Photovoltaics
  • Fault Detection and Control Systems
  • Rough Sets and Fuzzy Logic
  • Integrated Energy Systems Optimization
  • Machine Fault Diagnosis Techniques
  • Wind Energy Research and Development
  • Smart Grid Energy Management
  • Electric Power System Optimization
  • Advanced Algorithms and Applications
  • Engineering Diagnostics and Reliability
  • Imbalanced Data Classification Techniques
  • Power Systems and Renewable Energy
  • Aquatic Ecosystems and Phytoplankton Dynamics
  • Data Mining Algorithms and Applications
  • Geochemistry and Elemental Analysis
  • Industrial Technology and Control Systems
  • Photovoltaic System Optimization Techniques
  • Advanced Combustion Engine Technologies
  • Building Energy and Comfort Optimization
  • Microgrid Control and Optimization
  • Smart Grid and Power Systems
  • Advanced Sensor Technologies Research
  • Forest ecology and management
  • Wind and Air Flow Studies

Harbin Institute of Technology
2014-2024

Education Department of Fujian Province
2024

Fujian Agriculture and Forestry University
2016-2024

Ministry of Natural Resources
2024

Nanchang Institute of Technology
2020-2024

Jiangxi Academy of Environmental Sciences
2023

Sichuan Normal University
2022

Guangxi University
2021

Guangxi University of Chinese Medicine
2021

Facing Our Risk of Cancer Empowered
2021

Abstract Solar flares originate from the release of energy stored in magnetic field solar active regions, triggering mechanism for these flares, however, remains unknown. For this reason, conventional flare forecast is essentially based on statistic relationship between and measures extracted observational data. In current work, deep learning method applied to set up forecasting model, which patterns can be learned line-of-sight magnetograms regions. order obtain a large amount data train...

10.3847/1538-4357/aaae00 article EN cc-by The Astrophysical Journal 2018-03-20

Rough set theory has proven to be an efficient tool for modeling and reasoning with uncertainty information. By introducing probability into fuzzy approximation space, a about probabilistic spaces is proposed in this paper, which combines three types of uncertainty: probability, fuzziness, roughness rough model. We introduce Shannon's entropy measure information quantity implied Pawlak's then present novel representation relation matrix. Based on the modified formulas, some generalizations...

10.1109/tfuzz.2005.864086 article EN IEEE Transactions on Fuzzy Systems 2006-04-01

10.1016/j.knosys.2007.07.001 article EN Knowledge-Based Systems 2007-08-04

The tumor microenvironment (TME) has important effects on the tumorigenesis and development of osteosarcoma (OS). However, dynamic mechanism regulating TME immune matrix components remains unclear. In this study, we collected quantitative data gene expression 88 OS samples from Cancer Genome Atlas (TCGA) database downloaded relevant clinical cases TARGET database. proportions tumor-infiltrating cells (TICs) numbers were determined by CIBERSORT ESTIMATE calculation methods. Protein-protein...

10.3389/fonc.2021.642144 article EN cc-by Frontiers in Oncology 2021-05-17

Short-term wind speed prediction plays an important role in large-scale power penetration. However, there is still a large gap between the requirement of performance and current techniques. In this paper, we propose pattern-based approach to short-term prediction. It well accepted that varies different patterns weather conditions. Thus, should use models describe these patterns, whereas most works conduct with single model. Based on observation, introduce generalized principal component...

10.1109/tste.2013.2295402 article EN IEEE Transactions on Sustainable Energy 2014-04-08

Mangroves are an essential component of coastal ecosystems. Accurate and effective identification extraction mangrove areas from remote sensing imagery is crucial for monitoring changes in the nearshore ecological environment. High-resolution often difficult or expensive to obtain usually lacks sufficient temporal coverage, so most forests still relies on medium- low-resolution imagery, resulting inaccurate distribution extracted areas. The super-resolution (SR) images generated by...

10.1016/j.ecolind.2024.111714 article EN cc-by Ecological Indicators 2024-02-01

Day-ahead prediction of wind speed is a basic and key problem large-scale power penetration. Many current techniques fail to satisfy practical engineering requirements because speed's strong nonlinear features, influenced by many complex factors, the general model's inability automatically learn features. It well recognized that varies in different patterns. In this paper, we propose deep feature learning (DFL) approach forecasting its advantages at both multi-layer extraction unsupervised...

10.1142/s0218001416500117 article EN International Journal of Pattern Recognition and Artificial Intelligence 2016-01-21
Coming Soon ...