Artificial Intelligence in Mathematics Award
Manliang Cao
Shanghai Dianji University, China
Manliang Cao is a researcher affiliated with Shanghai Dianji University, China, whose indexed scholarly output reflects research activity in data science and computational approaches. His publication record includes work involving multimodal information processing, machine learning, neural signal classification, and artificial intelligence-based analytical methods. These research themes demonstrate the application of computational techniques to complex scientific data and interdisciplinary problems. His research profile is considered in connection with the Artificial Intelligence in Mathematics Award presented through the Math Scientist Awards.
Abstract
This research profile examines the scholarly contributions of Manliang Cao in data science, with particular attention to artificial intelligence, multimodal learning, computational modelling, and advanced data classification. His selected publications address graph-based structural representation learning, multimodal brain-signal analysis, and hyperspectral data classification. These studies illustrate the application of intelligent computational frameworks to information integration and complex analytical challenges. His documented scholarly indicators include 15 publications, 168 citations, and an h-index of 4, according to the supplied Scopus profile information.[1]
Keywords
Artificial Intelligence; Data Science; Computational Mathematics; Machine Learning; Multimodal Learning; Graph Representation Learning; Neural Signal Processing; Hyperspectral Classification; Intelligent Data Analysis.
Introduction
Artificial intelligence has increasingly influenced mathematical and computational research through advanced algorithms, predictive modelling, pattern recognition, and data-driven analysis. Its integration with mathematics provides opportunities to investigate complex relationships, improve computational efficiency, and develop systematic approaches to multidisciplinary scientific problems. Research involving multimodal data and intelligent classification contributes to this evolving field by combining mathematical structures with computational learning techniques.
Within this broader research landscape, Manliang Cao’s publications demonstrate engagement with computational methods applied to visual, tactile, neurological, and remote-sensing information. These research directions provide a basis for examining the relationship between artificial intelligence, mathematical modelling, and practical scientific applications.[2]
Research Profile
Manliang Cao’s research profile is associated with data-driven computational investigation and intelligent information processing. His selected scholarly work explores techniques for representing complex datasets, integrating information from multiple sensing modalities, and classifying scientific signals. Such research requires the application of mathematical representations, algorithmic structures, feature extraction, and computational evaluation.
The combination of graph-based learning, transformer architectures, wavelet processing, and multimodal analysis across his listed publications reflects several complementary approaches to computational intelligence. These approaches are relevant to the development of analytical systems capable of processing heterogeneous information and identifying meaningful patterns in complex datasets.[3]
Research Contributions
The selected publications indicate contributions across three principal research directions:
- Multimodal representation learning: The VTGCN study investigates graph-based structural representation learning for visual-tactile multimodal fusion, addressing the integration of complementary information sources.
- Biomedical signal classification: Research on EEG-fNIRS bimodal brain signals examines wavelet transformation and spatio-temporal processing for motor imagery classification.
- Remote-sensing data analysis: The MMTNet study presents a dual-branch multimodal mutual-transformer network for hyperspectral and LiDAR land-cover classification.
Together, these research directions demonstrate the use of computational learning architectures and mathematical processing techniques across different scientific application areas.[4]
Publications
Three selected journal articles illustrate the researcher’s recent scholarly activities:
- VTGCN: Graph-based structural representation learning for visual-tactile multimodal fusion. Knowledge-Based Systems, June 2026.[4]
- Classification of EEG-fNIRS bimodal brain signals for motor imagery tasks based on wavelet transform and spatio-temporal domain processing. Neuroscience, February 2026.[5]
- MMTNet: A Dual-Branch Multimodal Mutual-Transformer Network for Hyperspectral–LiDAR Land-Cover Classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2026.[6]
Research Impact
The supplied Scopus indicators report 15 indexed documents, 168 citations, and an h-index of 4. These metrics provide quantitative context for assessing the visibility and citation activity of the researcher’s indexed scholarly output. The three selected publications further demonstrate research engagement across computational intelligence, biomedical information processing, and remote-sensing applications. Citation indicators should be interpreted alongside publication quality, research originality, methodological contributions, and relevance to scientific advancement.
Award Suitability
Manliang Cao’s research activities provide relevant evidence for consideration under the Artificial Intelligence in Mathematics Award at the Math Scientist Awards. The combination of graph-based learning, mathematical signal processing, multimodal fusion, and transformer-based classification reflects the application of computational intelligence to complex scientific challenges. His publication record and citation indicators offer additional measurable evidence of scholarly activity. Collectively, these elements establish a relevant research foundation for recognition in artificial intelligence and computational mathematics.
Conclusion
Manliang Cao’s selected research demonstrates interdisciplinary engagement with artificial intelligence, data science, and computational methods. His work on multimodal representation, neurological signal classification, and remote-sensing analysis illustrates the application of advanced mathematical and machine-learning techniques to diverse scientific problems. His documented scholarly indicators and selected publications provide a foundation for evaluating his contributions in relation to the Artificial Intelligence in Mathematics Award.
External Links
References
- Elsevier. (n.d.). Scopus author details: Manliang Cao, Author ID 57020685300. Scopus.
https://www.scopus.com/authid/detail.uri?authorId=57020685300
- ORCID. (n.d.). Manliang Cao – ORCID researcher record.
https://orcid.org/0009-0002-5998-270X
- Shanghai Dianji University. Institutional affiliation information.
- VTGCN: Graph-based structural representation learning for visual-tactile multimodal fusion. (2026). Knowledge-Based Systems.
https://doi.org/10.1016/j.knosys.2026.115987
- Classification of EEG-fNIRS bimodal brain signals for motor imagery tasks based on wavelet transform and spatio-temporal domain processing. (2026). Neuroscience.
https://doi.org/10.1016/j.neuroscience.2025.12.036
- MMTNet: A Dual-Branch Multimodal Mutual-Transformer Network for Hyperspectral–LiDAR Land-Cover Classification. (2026). IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.
https://doi.org/10.1109/JSTARS.2026.3740737