Lianhui Liang | Deep learning or Image processing | Excellence in Research Award

Dr. Lianhui Liang | Deep learning or Image processing | Excellence in Research Award

Guangxi University | China 

Lianhui Liang is an academic researcher in electrical and information engineering with a strong focus on intelligent remote sensing analysis and advanced signal interpretation. His work centers on hyperspectral, multispectral, and LiDAR data understanding, Deep learning or Image processing  with applications spanning environmental monitoring, land surface analysis, and complex scene interpretation. His research integrates signal processing, pattern recognition, and deep learning techniques to enhance feature extraction, classification accuracy, and information fusion in high-dimensional remote sensing imagery. He has contributed significantly to spectral intelligence, including algorithm development for image inversion, target detection, and data fusion across heterogeneous sensors. His interdisciplinary approach bridges theoretical modeling with practical engineering applications, particularly in optical and microwave remote sensing. Through sustained collaboration with international research groups, his work reflects a global perspective on emerging challenges in remote sensing and artificial intelligence. He has actively engaged in advanced training programs related to remote sensing data processing, deep learning frameworks, and intelligent interpretation systems, strengthening the transfer of cutting-edge methods into applied research. His scholarly contributions include peer-reviewed publications, intellectual property development, and participation in research and development projects supported by public and industrial partners. Overall, his research advances intelligent remote sensing systems and contributes to the broader fields of geospatial analytics and artificial intelligence-driven Earth observation.

Citation Metrics (Google Scholar)

400
300
200
100
0

Citations
271

Documents
7

h-index
7

Citations

Documents

h-index


View Google Scholar Profile

Featured Publications


Prototype Similarity-Constraint Enhancement Network: A Few-Shot Class-Incremental Learning for Hyperspectral Image Classification

– Expert Systems with Applications, 2025

L. Yang, Y. Tan, L. Liang, H. Xu, T. Wu, Z. Huang, X. Li, Y. Tang

Cross-Stage Attention Edge Enhancement and Fourier-Wavelet Transformer Integrated Network for Hyperspectral Image Classification

– IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025

L. Liang, S. Yuan, Y. Zeng, Y. Lin, Y. Zhang, P. Xie, T. X. Wu

LHCF: Liquid Neural Network with Hierarchical Collaborative Fusion for Hyperspectral Image Classification

– Authorea Preprints, 2025

L. Liang, J. Zhang, S. Zhang, B. Tu, L. Yang, J. Li, A. Plaza

LKMA: Learnable Kernel and Mamba with Spatial-Spectral Attention Fusion for Hyperspectral Image Classification

– IEEE Transactions on Geoscience and Remote Sensing, 2025

L. Liang, J. Zhang, P. Duan, X. Kang, T. X. Wu, J. Li, A. Plaza

Cross-Domain Few-Shot Hyperspectral Image Classification with Local Entropy Adaptation Metric

– Authorea Preprints, 2025

Y. Zhang, Z. Liu, P. Duan, L. Lian

Sunawar Khan | Computer Science | Research Excellence Award

Mr. Sunawar Khan | Computer Science | Research Excellence Award

National College of Business Administration | Pakistan

Sunawar Khan is a research-oriented academic and practitioner with strong expertise in artificial intelligence, machine learning, deep learning, cybersecurity, smart grid technologies, Computer Science and intelligent systems. His research interests center on applying advanced computational intelligence techniques to real-world problems, particularly in healthcare analytics, intrusion detection systems, software reliability, and smart city security. He has worked extensively with neural networks, ensemble learning, explainable AI, and hybrid deep learning architectures such as CNN- and BiGRU-based models. His projects include deep learning–based disease detection using benchmark medical datasets, facial expression recognition with neural AdaBoost methods, and software defect prediction using industrial datasets. In cybersecurity, his research focuses on robust intrusion detection for smart environments, emphasizing accuracy, scalability, and interpretability. He also has experience designing and implementing intelligent management systems and applying machine learning to large, structured datasets. His academic background reflects a strong foundation in artificial intelligence, image processing, computer vision, data mining, algorithm analysis, and computational theory, complemented by practical experience in programming and system development. Overall, his research profile demonstrates a commitment to innovative, data-driven solutions that bridge theoretical models and applied intelligent technologies across interdisciplinary domains.

Citation Metrics (Google Scholar)

800
600
400
200
0

Citations
554

Documents
11

h-index
13

Citations

Documents

h-index


View Google Scholar Profile

Featured Publications


Antenna Systems for IoT Applications: A Review


Discover Sustainability, Vol. 5(1), Article 412, 2024

Generative AI, IoT, and Blockchain in Healthcare: Applications, Issues, and Solutions


Discover Internet of Things, Vol. 5(1), Article 5, 2025

Vikas Mehta | Statistical Computing and Programming | Research Excellence Award

Dr. Vikas Mehta | Statistical Computing and Programming | Research Excellence Award

Korean National Institute for International Education | South Korea

Dr. Vikas Mehta is a structural engineer and researcher specializing in seismic performance optimization, sustainable construction materials, and the application of advanced computational and machine learning methodologies to civil infrastructure systems. He completed his Ph.D. in Civil Engineering at Keimyung University, South Korea, where his award-winning doctoral research introduced innovative modifier-based and data-driven techniques for improving shear strength prediction and design accuracy in reinforced concrete beam-column joints. His expertise spans nonlinear finite element modeling, fragility analysis, physics-informed and graph-based machine learning, geospatial analytics, and performance-based seismic assessment, supported by strong proficiency in ETABS, OpenSees, SeismoSoft, Abaqus, MATLAB, Q-GIS, SPSS, Python, PyTorch, WEKA, and OriginPro. Dr. Mehta serves as a Postdoctoral Researcher at the Chonnam National University R&BD Foundation, contributing to advanced safety technologies for nuclear power plant structures under extreme hazard scenarios, including buckling resistance enhancement, retrofit optimization, and complex wind–terrain interaction studies. His professional background includes academic appointments in structural and construction engineering, where he taught subjects in earthquake engineering, finite element analysis, and structural systems while supervising graduate research and contributing to curriculum and laboratory development. Dr. Mehta has authored a substantial body of SCI-indexed research on seismic damage prediction, torsional behavior modeling, hybrid AI-mechanics frameworks, recycled and sustainable materials, computational methods, and structural performance evaluation, complemented by multiple patents in construction materials, damping devices, and waste-based composites. He has presented at leading international and national conferences and contributed to funded collaborative research, including projects involving global academic and industry partners. His professional affiliations include membership in ASCE, the Institute of Physics (AMInstP), IAEME (Fellow), and licensure as a Class-A engineer under the Himachal Pradesh Town and Country Planning Act. Dr. Mehta’s contributions to structural engineering and computational mechanics continue to gain international visibility, reflected in an h-index of 7, over 172 citations, and more than 19 published documents, underscoring his growing influence in machine learning–driven structural design, seismic resilience, and sustainable construction innovation.

Profiles: Scopus | Orcid

Featured Publications

Mehta, V., Jang, S. H., & Chey, M. H. (2025). Corrigendum to “Adaptive simulation and data-driven hybrid modeling for predicting shear strength and failure modes of interior reinforced concrete beam-column joints”.

Mehta, V., Jang, S. H., & Chey, M. H. (2025). Predictive framework for shear strength and failure modes of exterior reinforced concrete beam–column joints using machine learning. Structural Concrete. h.

Sagar, G. S., Mukthi, S., & Mehta, V. (2025). Analyzing compressive, flexural, and tensile strength of concrete incorporating used foundry sand: Experimental and machine learning insights. Archives of Computational Methods in Engineering.

Mehta, V., Thakur, M. S., & Chey, M. H. (2025). Enhancing seismic design accuracy of RC beam-column joints: Modifier-based approach for shear strength predictions. Structures.

Mehta, V., Jang, S. H., & Chey, M. H. (2025). Adaptive simulation and data-driven hybrid modeling for predicting shear strength and failure modes of interior reinforced concrete beam-column joints. Structures.