Kanghui Zhang

ORCID: 0000-0003-1367-2036
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Mineral Processing and Grinding
  • Metal Extraction and Bioleaching
  • Minerals Flotation and Separation Techniques
  • Image and Object Detection Techniques
  • Advanced oxidation water treatment
  • Metallurgical Processes and Thermodynamics
  • Congenital Heart Disease Studies
  • Energy, Environment, and Transportation Policies
  • Electric Vehicles and Infrastructure
  • Cleft Lip and Palate Research
  • Fluid Dynamics and Mixing
  • Fetal and Pediatric Neurological Disorders
  • Advanced X-ray and CT Imaging
  • Digital Imaging for Blood Diseases
  • Prenatal Screening and Diagnostics
  • Water Quality Monitoring Technologies
  • Arsenic contamination and mitigation
  • Coal Properties and Utilization
  • Domain Adaptation and Few-Shot Learning
  • Brain Tumor Detection and Classification
  • Congenital heart defects research
  • Phonocardiography and Auscultation Techniques
  • Advanced Photocatalysis Techniques
  • Infrastructure Maintenance and Monitoring
  • Spectroscopy and Chemometric Analyses

China University of Mining and Technology
2020-2024

Wuhan Institute of Technology
2024

Beijing General Research Institute of Mining and Metallurgy
2024

Wuhan University
2022-2023

China University of Mining and Technology - Beijing
2021-2023

Henan Agricultural University
2021

University of Science and Technology Beijing
2018

10.1016/j.engappai.2021.104242 article EN Engineering Applications of Artificial Intelligence 2021-04-23

Ultrasonic flotation was an effective method to float fine coal. In this study, the effects of standing waves with different frequencies on ultrasonic were investigated. The dynamic processes bubble and coal-bubble revealed by a high-speed camera. results showed that under action Bjerknes force, aggregates formed within 450 ms coal 20 ms. statistically analyzed image processing method. number small bubbles in field at 100 kHz greater than those 80 120 kHz. Besides, achieved highest yields...

10.1016/j.ultsonch.2020.105459 article EN cc-by-nc-nd Ultrasonics Sonochemistry 2021-01-14

A global survey indicates that genetic syndromes affect approximately 8% of the population, but most diagnoses can only be performed after babies are born. Abnormal facial characteristics have been identified in various diseases; however, current identification technologies cannot applied to prenatal diagnosis. We developed Pgds-ResNet, a fully automated screening algorithm based on deep neural networks, detect high-risk fetuses affected by variety diseases. In for Trisomy 21, 18, 13, and...

10.3390/biomedicines11061756 article EN cc-by Biomedicines 2023-06-19

With the increasing diversification of ore types and complexity processing techniques in mining industry, traditional decision-making methods for mineral flowsheets can no longer meet high efficiency intelligence requirements. This paper proposes a knowledge graph-based framework constructing mineral-processing design base reasoning, aiming at providing intelligent efficient decision support engineers. integrates Chinese NLP models text vectorization, optimizes prompt generation through...

10.3390/min15040374 article EN Minerals 2025-04-03

With the advancement of medicine, more and researchers have turned their attention to study fetal genetic diseases in recent years. However, it is still a challenge detect fetus, especially an area lacking access healthcare. The existing research primarily focuses on using teenagers’ or adults’ face information screen for diseases, but there are no relevant directions disease detection facial information. To fill vacancy, we designed two-stage ensemble learning model based sonography,...

10.3390/ijerph20032377 article EN International Journal of Environmental Research and Public Health 2023-01-29

Abstract Duct-dependent congenital heart diseases (CHDs) are a serious form of CHD with low detection rate, especially in underdeveloped countries and areas. Although existing studies have developed models for fetal structure identification, there is lack comprehensive evaluation the long axis aorta. In this study, total 6698 images 48 videos collected to develop test two-stage deep transfer learning model named DDCHD-DenseNet screening critical duct-dependent CHDs. The achieves sensitivity...

10.1038/s41746-023-00883-y article EN cc-by npj Digital Medicine 2023-08-12

This study presents a novel Fe-CNs-P/S carbon composite material, synthesized by doping elements P and S into NH2-MIL-101 (Fe) using the carbonization method. The material’s application in sustainable water treatment was evaluated, focusing on its effectiveness activating persulfate for pollutant degradation. research thoroughly investigates synthesis process, structural characteristics, performance degrading pollutants. results indicate that Fe-CNs-P/S-5 with 50% co-doping is higher than of...

10.3390/su16209051 article EN Sustainability 2024-10-18

To explore the feasibility of hot metal desulfurization using red mud, sulfur distribution ratio (LS) between CaO-SiO2-Al2O3-Na2O-TiO2 slag and carbon-saturated iron is evaluated in this paper. First, theoretical liquid areas CaO-SiO2-Al2O3 (-Na2O-TiO2) are discussed fluxing effects Al2O3, Na2O, TiO2 confirmed. Then, LS measured via slag-metal equilibrium experiments. The experimental results show that significantly increases with increase temperature, basicity, Na2O content, whereas it...

10.3390/met8121068 article EN cc-by Metals 2018-12-15

Gas-liquid two-phase flow is widely involved in many scientific and technological fields, such as energy, electricity, nuclear aerospace environmental protection. In some extracting the accurate position of bubbles space can not only accurately capture characteristics flow, but also plays an important role subsequent research like bubble tracking. It has got progresses to use Convolutional Neural Network (CNNs) identify gas-liquid while pixel segmentation map identification problem more...

10.34028/iajit/20/4/7 article EN The International Arab Journal of Information Technology 2023-01-01

This study presents a novel Fe-CNs-P/S carbon composite material, synthesized by doping elements P and S into NH2-MIL-101 (Fe) using carbonization method. The material's application in sustainable water treatment was evaluated, focusing on its effectiveness activating persulfate for pollutant degradation. research thoroughly investigates the synthesis process, structural characteristics, performance degrading pollutants. Results indicate that Fe-CNs-P/S-5 with 50% co-doping is...

10.20944/preprints202409.0934.v1 preprint EN 2024-09-12
Coming Soon ...