Xiaolin Yang | CImage analysis | Best Researcher Award

Posted on by ScienceFather

Dr. Xiaolin Yang | Image analysis | Best Researcher Award

Dr at China university of mining and technology, China

Xiaolin Yang is a skilled Business Analyst and Postdoctoral Researcher at Henan Investment Group. With a solid background in mineral process engineering, his expertise spans industry research, project management, and production optimization. Xiaolin holds a Bachelor’s and a Ph.D. in Mineral Process Engineering from the China University of Mining and Technology, specializing in mineral processing, machine learning, and image analysis. His dedication to academic excellence and practical application makes him a valuable asset in the mineral industry.

Publication Profile

scopus

Education🎓 

.Bachelor of Mineral Process Engineering | China University of Mining and Technology, 2015–2019 | Focus: Mineral separation methods and equipment. Doctor of Mineral Process Engineering | China University of Mining and Technology, 2019–2024 | Research areas: Mineral processing, machine learning, image analysis. Xiaolin’s academic journey emphasized innovation in mineral separation, blending engineering with data science to improve mineral processing efficiency and accuracy.

Experience💼 

Postdoctoral Researcher | Henan Investment Group, 2024–Present | Xiaolin’s role involves comprehensive industry research, preparing assessment reports, and offering investment insights and recommendations. His project management tasks focus on feasibility assessments and evaluating the effectiveness of production processes, aiming to optimize industrial production and implement innovative solutions in mineral processing.

Awards and Honors🏆 

Published Author | Xiaolin has authored notable academic articles, such as in Journal of Materials Research and Technology (2021), Energy (2022), and Expert Systems with Applications (2024). His work, recognized for its significance in mineral processing and machine learning, highlights his expertise in utilizing advanced algorithms for practical industry challenges.

Research Focus🔍

Research Interests | Xiaolin’s research delves into mineral processing, machine learning applications, and image analysis. His studies, including deep learning for ash determination in coal flotation, explore novel algorithms to enhance mineral processing accuracy, bridging engineering and artificial intelligence for industrial optimization.

Publication  Top Notes

Multi-scale neural network for accurate determination of ash content in coal flotation concentrate

Authors: Yang, X., Zhang, K., Thé, J., Tan, Z., Yu, H.

Journal: Expert Systems with Applications, 2025, 262, 125614

Description: This paper presents a multi-scale neural network model that accurately determines ash content in coal flotation concentrate using froth images, leveraging deep learning to enhance mineral processing efficiency.

STATNet: One-stage coal-gangue detector for real industrial applications

Authors: Zhang, K., Wang, T., Yang, X., Tan, Z., Yu, H.

Journal: Energy and AI, 2024, 17, 100388

Description: The STATNet model is introduced as a coal-gangue detection system using a one-stage deep learning algorithm, tailored for industrial application with a focus on real-time processing.

COFNet: Predicting surface area of covalent-organic frameworks

Authors: Wang, T., Yang, X., Zhang, K., Tan, Z., Yu, H.

Journal: Chemical Physics Letters, 2024, 847, 141383

Description: COFNet utilizes deep learning to predict the specific surface area of covalent-organic frameworks, combining structural image analysis with statistical features for accurate predictions.

Enhancing coal-gangue detection with GAN-based data augmentation

Authors: Zhang, K., Yang, X., Xu, L., Tan, Z., Yu, H.

Journal: Energy, 2024, 287, 129654

Description: This study employs GAN-based data augmentation and a dual attention mechanism to improve coal-gangue object detection, aiming to refine accuracy in complex industrial environments.

Multi-step carbon price forecasting using hybrid deep learning models

Authors: Zhang, K., Yang, X., Wang, T., Tan, Z., Yu, H.

Journal: Journal of Cleaner Production, 2023, 405, 136959

Description: A hybrid deep learning model for multi-step forecasting of carbon prices is proposed, integrating multivariate decomposition to enhance predictive reliability.

PM2.5 and PM10 concentration forecasting with spatial–temporal attention networks

Authors: Zhang, K., Yang, X., Cao, H., Tan, Z., Yu, H.

Journal: Environment International, 2023, 171, 107691

Description: This article introduces a spatial–temporal attention mechanism for PM2.5 and PM10 forecasting, using convolutional neural networks with residual learning to tackle air quality predictions.

Ash determination of coal flotation concentrate using hybrid deep learning model

Authors: Yang, X., Zhang, K., Ni, C., Tan, Z., Yu, H.

Journal: Energy, 2022, 260, 125027

Description: This work features a hybrid model that utilizes deep learning and attention mechanisms to determine ash content in coal flotation, contributing to process optimization.

Influence of cation valency on flotation of chalcopyrite and pyrite

Authors: Yang, X., Bu, X., Xie, G., Chehreh Chelgani, S.

Journal: Journal of Materials Research and Technology, 2021, 11, pp. 1112–1122

Description: This comparative study explores how different cation valencies affect chalcopyrite and pyrite flotation, contributing to better separation techniques in mineral processing.

Conclusion

Xiaolin Yang is a compelling candidate for the Best Researcher Award. His strengths in applying AI and image analysis to mineral processing reflect a unique skill set that is highly relevant for advancing research and industry practices. With further interdisciplinary work and expanded research visibility, Xiaolin is well-positioned to make impactful contributions and earn recognition in his field.

Jinxia Zhang | Defect detection | Best Researcher Award

Posted on by ScienceFather

Assoc Prof Dr. Jinxia Zhang | Defect detection | Best Researcher Award

 Associate Professor at Southeast University, China

Assoc Prof Dr. Jinxia Zhang is an Associate Professor at Southeast University, Nanjing, China, specializing in saliency detection, visual attention, computer vision, and deep learning. With a Ph.D. in Pattern Recognition and Intelligent Systems from Nanjing University of Science and Technology, he has extensive experience in artificial intelligence research. His journey includes time as a visiting scholar at Harvard Medical School and numerous prestigious research projects funded by national foundations. Assoc Prof Dr. Jinxia Zhang leads key AI initiatives, driving innovations in multimodal understanding, defect analysis, and object detection. His academic and professional contributions have positioned him as a prominent researcher in visual computing and AI.

Publication Profile

scholar

Education 🎓

Assoc Prof Dr. Jinxia Zhang  earned his M.Sc. and Ph.D. in Pattern Recognition and Intelligent Systems from Nanjing University of Science and Technology in 2015. His doctoral research laid a foundation for his interest in artificial intelligence, particularly in areas like visual attention and computer vision. Prior to his postgraduate work, he completed his B.Sc. in Computer Science and Technology at the same institution in 2009, where he developed a solid understanding of computational theories and applications. His education has provided him with both theoretical knowledge and practical skills that are central to his current research on AI and deep learning.Assoc Prof Dr. Jinxia Zhang  is currently an Associate Professor at Southeast University, Nanjing, a role he has held since 2019. From 2016 to 2019, he served as a Lecturer at the same university, where he significantly contributed to AI teaching and research. His early career included a prestigious stint as a Visiting Scholar at Harvard Medical School, USA, between 2012 and 2014, where he collaborated on cutting-edge AI-driven healthcare projects. His international exposure and academic roles have enriched his teaching and research, particularly in computer vision and AI, making him a key figure in the field.

Awards and Honors  🏆

Assoc Prof Dr. Jinxia Zhang  has received numerous accolades for his research excellence and contributions to the field of AI. He was awarded the National Natural Science Foundation of China grant in 2018 for his project on salient object detection. In 2017, he secured the Jiangsu Natural Science Foundation Grant for his innovative research on visual cognitive characteristics. Additionally, his work in defect diagnosis for photovoltaic modules was recognized as part of the National Key Research and Development Plan. These prestigious awards underscore his pioneering contributions in artificial intelligence and computer vision research.

Research Focus  🔬

Assoc Prof Dr. Jinxia Zhang ‘s research focuses on the intersection of visual attention, saliency detection, and deep learning within artificial intelligence. He leads projects on multimodal understanding and e-commerce applications, and is a Principal Investigator for research into AI-based fruit and vegetable recognition. His earlier work in defect diagnosis for photovoltaic modules and salient object detection in complex scenes has been supported by prominent grants. His innovative approach combines perceptual grouping and visual attention to develop cutting-edge solutions in computer vision, making significant advancements in how machines perceive and interact with visual data.

Conclusion

The candidate demonstrates an impressive body of work across several domains of artificial intelligence, particularly in salient object detection, visual cognition, and multimodal learning. Their academic achievements, project leadership, and dedication to advancing AI make them a strong contender for the Best Researcher Award. By continuing to broaden their industry collaborations and expanding the scope of their research impact, they can become a globally recognized leader in AI and computer vision.

Publication  Top Notes

  • Towards the Quantitative Evaluation of Visual Attention Models (2015)
    • Citation: 75
    • Journal: Vision Research
    • Key Contributors: Z. Bylinskii, E.M. DeGennaro, R. Rajalingham, H. Ruda, J. Zhang, J.K. Tsotsos
    • Highlights: Focuses on quantitative approaches to evaluate visual attention models, essential for improving saliency detection.
  • A Novel Graph-Based Optimization Framework for Salient Object Detection (2017)
    • Citation: 63
    • Journal: Pattern Recognition
    • Key Contributors: J. Zhang, K.A. Ehinger, H. Wei, K. Zhang, J. Yang
    • Highlights: Presents a new graph-based optimization method for enhancing the accuracy of salient object detection.
  • Salient Object Detection by Fusing Local and Global Contexts (2020)
    • Citation: 60
    • Journal: IEEE Transactions on Multimedia
    • Key Contributors: Q. Ren, S. Lu, J. Zhang, R. Hu
    • Highlights: This paper integrates both local and global visual contexts to refine salient object detection in multimedia applications.
  • Inter-Hour Direct Normal Irradiance Forecast with Multiple Data Types and Time-Series (2019)
    • Citation: 36
    • Journal: Journal of Modern Power Systems and Clean Energy
    • Key Contributors: T. Zhu, H. Zhou, H. Wei, X. Zhao, K. Zhang, J. Zhang
    • Highlights: Introduces a time-series forecasting model for direct normal irradiance, benefiting renewable energy systems.
  • Winter is Coming: How Humans Forage in a Temporally Structured Environment (2015)
    • Citation: 35
    • Journal: Journal of Vision
    • Key Contributors: D. Fougnie, S.M. Cormiea, J. Zhang, G.A. Alvarez, J.M. Wolfe
    • Highlights: Examines human visual foraging behavior in dynamically changing environments.
  • Domain Adaptation for Epileptic EEG Classification Using Adversarial Learning and Riemannian Manifold (2022)
    • Citation: 25
    • Journal: Biomedical Signal Processing and Control
    • Key Contributors: P. Peng, L. Xie, K. Zhang, J. Zhang, L. Yang, H. Wei
    • Highlights: This paper explores domain adaptation techniques to improve epileptic EEG classification through adversarial learning.
  • A Lightweight Network for Photovoltaic Cell Defect Detection in Electroluminescence Images (2024)
    • Citation: 23
    • Journal: Applied Energy
    • Key Contributors: J. Zhang, X. Chen, H. Wei, K. Zhang
    • Highlights: Develops a lightweight neural network for detecting defects in photovoltaic cells using knowledge distillation.
  • Salient Object Detection via Deformed Smoothness Constraint (2018)
    • Citation: 21
    • Journal: IEEE International Conference on Image Processing (ICIP)
    • Key Contributors: X. Wu, X. Ma, J. Zhang, A. Wang, Z. Jin
    • Highlights: Proposes a deformed smoothness constraint approach for improving salient object detection.
  • Character Recognition via a Compact Convolutional Neural Network (2017)
    • Citation: 20
    • Conference: International Conference on Digital Image Computing
    • Key Contributors: H. Zhao, Y. Hu, J. Zhang
    • Highlights: Develops a compact CNN for robust character recognition in natural scene images.
  • A Prior-Based Graph for Salient Object Detection (2014)
    • Citation: 23
    • Conference: IEEE International Conference on Image Processing (ICIP)
    • Key Contributors: J. Zhang, K.A. Ehinger, J. Ding, J. Yang
    • Highlights: Uses a prior-based graph model to enhance the performance of salient object detection algorithms.