National Yang Ming Chiao Tung University

BeeLab

Minh-Tu Cao
https://ce.nycu.edu.tw/en/member/teachers/58

Research Field

Civil and Hydraulic Engineering
Introduction

Minh-Tu Cao is an accomplished academic and researcher in the field of Construction Engineering and Management. With a Bachelor's degree from the National Civil Engineering University in Vietnam, followed by a Master's and Ph.D. from the National Taiwan University of Science and Technology, Minh-Tu's educational journey laid the foundation for an impressive career. Before becoming an Assistant Professor in the Department of Civil Engineering at National Yang Ming Chiao Tung University, Minh-Tu worked in the construction industry for several years. This hands-on experience provided invaluable insights into the real-world challenges and intricacies of the field.

Currently, Minh-Tu's work revolves around the application of Artificial Intelligence in the realm of Construction Engineering and Management, as well as the strategic use of Building Information Modeling (BIM) in construction management processes. This includes exploring areas such as Computational Intelligence, Optimization in Construction, and the integration of BIM technologies to enhance project efficiency and quality.

Minh-Tu's passion for research has borne fruit in the form of many publications in high-ranking SCI journals. Additionally, Minh-Tu has received several awards for best and outstanding papers in international conferences, highlighting the impact of their work. Minh-Tu Cao's dedication to advancing the fields of Construction Engineering and Artificial Intelligence, along with their expertise in leveraging BIM for improved construction management, is both inspiring and groundbreaking, promising a future of innovation and excellence in the industry.

BeeLab is dedicated to advancing research at the intersection of Construction Engineering, Artificial Intelligence (AI), and Building Information Modeling (BIM). The BeeLab primarily focuses on leveraging cutting-edge AI technologies to address critical challenges in construction management, with a particular emphasis on optimizing project efficiency, quality, and sustainability.

The BeeLab has produced numerous high-impact publications in leading SCI journals, contributing significantly to the body of knowledge in AI applications for construction engineering. We actively collaborate with industry partners and academic institutions to bridge the gap between theory and practice, ensuring that our research advances scientific understanding and delivers practical, real-world solutions.

The BeeLab is committed to pushing the boundaries of innovation in construction engineering and management, strongly emphasizing interdisciplinary approaches and state-of-the-art AI techniques. Through our research, we aim to make a lasting impact on the construction industry, driving efficiency, safety, and sustainability.

Join Us! We welcome highly motivated graduate students and talented researchers passionate about AI, construction engineering, and BIM technologies to join our lab. Whether you're looking to pursue a Master's or Ph.D. or seeking postdoctoral opportunities, our lab provides a dynamic and collaborative environment where you can contribute to cutting-edge research and gain valuable industry-relevant experience. Together, we can push the boundaries of innovation and make meaningful contributions to the future of the construction industry.

Research Topics

Our research spans a wide range of topics, including:

Artificial Intelligence in Construction Engineering: We explore integrating AI techniques such as deep learning, machine learning, and metaheuristic optimization to solve complex problems in construction engineering, including predicting mechanical behavior, optimizing resource allocation, and enhancing structural integrity.

Building Information Modeling (BIM) for Project Efficiency: We focus on utilizing BIM technologies to improve the management and coordination of construction projects, from design through execution. Our research also investigates how BIM can be combined with AI-driven decision-making to optimize energy consumption, reduce waste, and ensure sustainable construction practices.

Computational Intelligence and Optimization: Our lab delves into computational intelligence methods like evolutionary algorithms and machine learning ensembles to solve optimization problems in construction. 

Honor

PUBLICATIONS IN sci journals

  1. M.-T. Cao*, W.-C. Wang, and S.-L. Shen, "YOLO-BFID: Real-Time Building Facade Inspection by Using an Advanced Artificial Vision Model Integrated with Drone Technology," ASCE's Journal of Computing in Civil Engineering (Accepted, 2025/12).
  2. M.-T. Cao*, W.-C. Wang, and M. Koean, "Lightweight railway defect detection model with attention-based feature fusion and GPS mapping," Automation in Construction, vol. 182, p. 106704, 2026/02/01/ 2026, doi: https://doi.org/10.1016/j.autcon.2025.106704.
  3. W.-C. Wang, S.-C. Huang, H.-P. Wang, and M.-T. Cao*, "Measuring building information modeling user satisfaction by using active interpretable machine learning," Applied Soft Computing, vol. 183, p. 113663, 2025/11/01/ 2025, doi: https://doi.org/10.1016/j.asoc.2025.113663.
  4. Y.-J. Cheng, M.-T. Cao, S.-H. Wang, N.-M. Nguyen, S.-S. Chen, and W.-C. Wang, "Integrating LINE BOT and Building Information Model to develop construction information management system," Journal of Civil Engineering and Management, vol. 31, no. 5, pp. 482–501, 06/27 2025, doi: https://doi.org/10.3846/jcem.2025.23764
  5. N.-M. Nguyen and M.-T. Cao*, "Energy use intensity analysis of office buildings using green BIM-integrated Interpretable machine learning," Journal of Building Engineering, vol. 108, p. 112760, 2025/08/15/ 2025, doi: https://doi.org/10.1016/j.jobe.2025.112760.
  6. M.-T. Cao*, C. Yen Chun, N.-D. Hoang, and T.-C. Huynh, "Integrating Transfer Learning and U-Net for Accurate Detection and Segmentation of Asphalt Pavement Bleeding," Transportation Research Record, vol. 2679, no. 11, pp. 558-575, 2025/11/01 2025, doi: https://doi.org/10.1177/03611981251348446. 
  7. N.-D. Hoang, P.-A.Pham, T.-C.Huynh, M.-T. Cao, and D.-T. Bui, "Geospatial urban heat mapping with interpretable machine learning and deep learning: a case study in Hue City, Vietnam," Earth Science Informatics, vol. 18, no. 64, 2024/12/17 2024, doi: https://doi.org/10.1007/s12145-024-01582-2.
  8. T.-H. Nguyen, D.-H. Tran, N.-M. Nguyen, H.-T. Vuong, C. Chien-Cheng, and M.-T. Cao*, "Accurately predicting the mechanical behavior of deteriorated reinforced concrete components using natural intelligence-integrated Machine learners," Construction and Building Materials, vol. 408, p. 133753, 2023/12/08/ 2023, doi: https://doi.org/10.1016/j.conbuildmat.2023.133753.
  9. M.-T. Cao*, "Drone-assisted segmentation of tile peeling on building façades using a deep learning model," Journal of Building Engineering, vol. 80, p. 108063, 2023/12/01/ 2023, doi: https://doi.org/10.1016/j.jobe.2023.108063.
  10. M.-T. Cao*, "Advanced soft computing techniques for predicting punching shear strength," Journal of Building Engineering, vol. 79, p. 107800, 2023/11/15/ 2023, doi: https://doi.org/10.1016/j.jobe.2023.107800.
  11. N.-M. Nguyen, W.-C. Wang, and M.-T. Cao*, "Early estimation of the long-term deflection of reinforced concrete beams using surrogate models," Construction and Building Materials, vol. 370, p. 130670, 2023/03/17/ 2023, doi: https://doi.org/10.1016/j.conbuildmat.2023.130670.
  12. M.-Y. Cheng, M.-T. Cao*, and N.-M. Dao-Thi, "A novel artificial intelligence-aided system to mine historical high-performance concrete data for optimizing mixture design," Expert Systems with Applications, vol. 212, p. 118605, 2023/02/01/ 2023, doi: https://doi.org/10.1016/j.eswa.2022.118605.
  13. H. Nguyen, M.-T. Cao, X.-L. Tran, T.-H. Tran, and N.-D. Hoang, "A novel whale optimization algorithm optimized XGBoost regression for estimating bearing capacity of concrete piles," Neural Computing and Applications, 2022/10/15 2022, doi: 10.1007/s00521-022-07896-w.
  14. M.-T. Cao, N.-M. Nguyen, and W.-C. Wang, "Using an evolutionary heterogeneous ensemble of artificial neural network and multivariate adaptive regression splines to predict bearing capacity in axial piles," Engineering Structures, vol. 268, p. 114769, 2022/10/01/ 2022, doi: https://doi.org/10.1016/j.engstruct.2022.114769.
  15. M.-Y. Cheng, M.-T. Cao*, and C. K. Nuralim, "Computer vision-based deep learning for supervising excavator operations and measuring real-time earthwork productivity," The Journal of Supercomputing, 2022/09/27 2022, doi: 10.1007/s11227-022-04803-x.
  16. W.-C. Wang, N.-M. Nguyen, and M.-T. Cao*, "Smart ensemble machine learner with hyperparameter-free for predicting bond capacity of FRP-to-concrete interface: Multi-national data," Construction and Building Materials, vol. 345, p. 128158, 2022/08/22/ 2022, doi: https://doi.org/10.1016/j.conbuildmat.2022.128158.
  17. M.-Y. Cheng, M.-T. Cao*, and I. F. Huang, "Hybrid artificial intelligence-based inference models for accurately predicting dam body displacements: A case study of the Fei Tsui dam," Structural Health Monitoring, vol. 21, no. 4, pp. 1738-1756, 2022/07/01 2021, doi: 10.1177/14759217211044116.
  18. H. Nguyen, N.-M. Nguyen, M.-T. Cao, N.-D. Hoang, and X.-L. Tran, "Prediction of long-term deflections of reinforced-concrete members using a novel swarm optimized extreme gradient boosting machine," Engineering with Computers, vol. 38, no. 2, pp. 1255-1267, 2022/06/01 2022, doi: 10.1007/s00366-020-01260-z.
  19. M.-T. Cao, K.-T. Chang, N.-M. Nguyen, V.-D. Tran, X.-L. Tran, and N.-D. Hoang, "Image processing-based automatic detection of asphalt pavement rutting using a novel metaheuristic optimized machine learning approach," Soft Computing, vol. 25, no. 20, pp. 12839-12855, 2021/10/01 2021, doi: 10.1007/s00500-021-06086-5.
  20. M.-T. Cao, N.-M. Nguyen, K.-T. Chang, X.-L. Tran and N.-D. Hoang (2021). "Automatic recognition of concrete spall using image processing and metaheuristic optimized LogitBoost classification tree." Advances in Engineering Software 159: 103031.
  21. M.-Y. Cheng, M.-T. Cao*, and A. Y. Jaya Mendrofa, "Dynamic feature selection for accurately predicting construction productivity using symbiotic organisms search-optimized least square support vector machine," Journal of Building Engineering, vol. 35, p. 101973, 2021/03/01/ 2021, doi: https://doi.org/10.1016/j.jobe.2020.101973.
  22. M.-T. Cao, N.-D. Hoang, V. H. Nhu, and D. T. Bui, "An advanced meta-learner based on artificial electric field algorithm optimized stacking ensemble techniques for enhancing prediction accuracy of soil shear strength," Engineering with Computers, 2020/11/02 2020, doi: 10.1007/s00366-020-01116-6.
  23. D. T. Vu, X.-L. Tran, M.-T. Cao, T. C. Tran, and N.-D. Hoang, "Machine learning based soil erosion susceptibility prediction using social spider algorithm optimized multivariate adaptive regression spline," Measurement, vol. 164, p. 108066, 2020/11/01/ 2020, doi: https://doi.org/10.1016/j.measurement.2020.108066.
  24. M.-Y. Cheng, M.-T. Cao*, and P.-K. Tsai, "Predicting load on ground anchor using a metaheuristic optimized least squares support vector regression model: a Taiwan case study," Journal of Computational Design and Engineering, vol. 8, no. 1, pp. 268-282, 2020, doi: 10.1093/jcde/qwaa077.
  25. M.-T. Cao, Q.-V. Tran, N.-M. Nguyen, and K.-T. Chang, "Survey on performance of deep learning models for detecting road damages using multiple dashcam image resources," Advanced Engineering Informatics, vol. 46, p. 101182, 2020/10/01/ 2020, doi: https://doi.org/10.1016/j.aei.2020.101182.
  26. M.-Y. Cheng, M.-T. Cao*, and J. G. Herianto, "Symbiotic organisms search-optimized deep learning technique for mapping construction cash flow considering complexity of project," Chaos, Solitons & Fractals, vol. 138, p. 109869, 2020/09/01/ 2020, doi: https://doi.org/10.1016/j.chaos.2020.109869.
  27. M.-Y. Cheng, J.-S. Chou, and M.-T. Cao*, "Nature-inspired metaheuristic multivariate adaptive regression splines for predicting refrigeration system performance," Soft Computing, vol. 21, no. 2, pp. 477-489, 2017/01/01 2017, doi: 10.1007/s00500-015-1798-y.
  28. M.-Y. Cheng and M.-T. Cao*, "Estimating strength of rubberized concrete using evolutionary multivariate adaptive regression splines," Journal of Civil Engineering and Management, vol. 22, no. 5, pp. 711-720, 2016/07/03 2016, doi: 10.3846/13923730.2014.897989.
  29. D.-H. Tran, M.-Y. Cheng, and M.-T. Cao, "Solving Resource-Constrained Project Scheduling Problems Using Hybrid Artificial Bee Colony with Differential Evolution," Journal of Computing in Civil Engineering, vol. 30, no. 4, p. 04015065, 2016/07/01 2016, doi: 10.1061/(ASCE)CP.1943-5487.0000544.
  30. M.-Y. Cheng, D.-H. Tran, and M.-T. Cao, "Chaotic initialized multiple objective differential evolution with adaptive mutation strategy (CA-MODE) for construction project time-cost-quality trade-off," Journal of Civil Engineering and Management, vol. 22, no. 2, pp. 210-223, 2016/02/17 2016, doi: 10.3846/13923730.2014.897972.
  31. M.-Y. Cheng and M.-T. Cao*, "Hybrid intelligent inference model for enhancing prediction accuracy of scour depth around bridge piers," Structure and Infrastructure Engineering, vol. 11, no. 9, pp. 1178-1189, 2015/09/02 2015, doi: 10.1080/15732479.2014.939089.
  32. M.-Y. Cheng, M.-T. Cao*, and Y.-W. Wu, "Predicting Equilibrium Scour Depth at Bridge Piers Using Evolutionary Radial Basis Function Neural Network," Journal of Computing in Civil Engineering, vol. 29, no. 5, p. 04014070, 2015/09/01 2015, doi: 10.1061/(ASCE)CP.1943-5487.0000380.
  33. M.-T. Cao, M.-Y. Cheng, and Y.-W. Wu, "Hybrid Computational Model for Forecasting Taiwan Construction Cost Index," Journal of Construction Engineering and Management, vol. 141, no. 4, p. 04014089, 2015/04/01 2015, doi: 10.1061/(ASCE)CO.1943-7862.0000948.
  34. D.-H. Tran, M.-Y. Cheng, and M.-T. Cao, "Hybrid multiple objective artificial bee colony with differential evolution for the time–cost–quality tradeoff problem," Knowledge-Based Systems, vol. 74, pp. 176-186, 2015/01/01/ 2015, doi: https://doi.org/10.1016/j.knosys.2014.11.018.
  35. M.-Y. Cheng and M.-T. Cao*, "Accurately predicting building energy performance using evolutionary multivariate adaptive regression splines," Applied Soft Computing, vol. 22, pp. 178-188, 2014/09/01/ 2014, doi: https://doi.org/10.1016/j.asoc.2014.05.015.
  36. M.-Y. Cheng, M.-T. Cao*, and D.-H. Tran, "A hybrid fuzzy inference model based on RBFNN and artificial bee colony for predicting the uplift capacity of suction caissons," Automation in Construction, vol. 41, pp. 60-69, 2014/05/01/ 2014, doi: https://doi.org/10.1016/j.autcon.2014.02.008.
  37. M.-Y. Cheng and M.-T. Cao*, "Evolutionary multivariate adaptive regression splines for estimating shear strength in reinforced-concrete deep beams," Engineering Applications of Artificial Intelligence, vol. 28, pp. 86-96, 2014/02/01/ 2014, doi: https://doi.org/10.1016/j.engappai.2013.11.001.

PUBLICATIONS IN INTERNATIONAL CONFERENCES 

  1. T.S. Ngo, C.H. Le, H.D. Tran, Minh-Tu Cao, Construction Demolition Waste Detection with Ghost-YOLOv10, The 29th Symposium Construction Engineering and Management, Kaosiung, Taiwan, July 10th 2025.
  2. Minh-Tu Cao, N.N. Mai, W.C. Wang, Unveiling Building Façade Deterioration: A Drone-Powered Deep Learning Approach for Seamless Tile Peeling Detection, The 41st International Symposium on Automation and Robotics in Construction, Lille, France, June 3rd 2024.
  3. Minh-Tu Cao, N.N. Mai, C.C. Chen, Smart Ensemble Hyperparameter-free Machine Learner for Predicting the Bond Capacity of an FRP-to-concrete Interface: Multinational Data, The 26th Symposium Construction Engineering and Management, Zhongli, Taiwan, July 22nd 2022.
  4. Minh-Tu Cao, N.N. Mai, C.C. Chen, Predicting the Long-Term Deflection of Reinforced Concrete Beams Using Feature Refinement-Based Self-tuning Machine Learning Model, The 26th Symposium Construction Engineering and Management, Zhongli, Taiwan, July 22nd 2022.
  5. Minh-Tu Cao, Nhat-Duc Hoang, Automatic Recognition of Concrete Spall Using Image Processing and Metaheuristic Optimized LogitBoost Classification Tree, The 24th Symposium Construction Engineering and Management, Taipei, Taiwan, August 05th 2020.
  6. Minh-Tu Cao, K.T. Chang, Mohammad Adhan, Multiple Dashcam Image Resource-Trained Deep Learning Models for Enhancing Road Damage Detection, The 24th Symposium Construction Engineering and Management, Taipei, Taiwan, August 05th 2020.
  7. K. T. Chang, Y. S. Chiang, M. T. Cao, C. T. Wang, Analyzing Pre- and Post-Earthquake Changes using Optical and SAR Satellite Images, CORECT-IJJSS 2019 International Conference on Sustainability Science and Management: Advanced Technology in Environmental Research, Bali, Indonesia, Nov. 14-15, 2019.
  8. K. T. Chang, M. T. Cao, Estimating Seismic Retrofitting Cost of Taiwan School Buildings Using AI-Based Inference Models, ICEO-SI 2019, 4th Symposium, Taichung, Taiwan, June 23-26, 2019.
  9. 朱詠恩、高明秀、王世旭、王維志, 營建業永續報告書GRI準則與財務績效之關聯性分析,  2024第28屆營建工程與管理學術研討會論文集，臺灣雲林(雲科) (Outstanding Paper Award)
  10. 范如伶、高明秀、阮玉梅、王維志, 應用網路犯罪調查演算法於工程專案成本之最佳化, 2024第28屆營建工程與管理學術研討會論文集，臺灣雲林(雲科) (Outstanding Paper Award)
  11. 黃柏睿、高明秀、阮玉梅、王維志, 使用結合網路犯罪調查演算法的異質集成模型和 DBSCAN 聚類演算法來預測房屋出售價格, 2024第28屆營建工程與管理學術研討會論文集，臺灣雲林(雲科)
  12. 趙芫毅, 紀乃文, 翁紹偉, 陳世昕, 鄭裕仁, 高明秀, 王維志, 運用建築資訊模型(BIM)以輔助查核營建工程估驗計價, 2023第27屆營建工程與管理學術研討會論文集，臺灣新竹(陽明交大) (Outstanding Paper Award)
  13. 陳泓志, 黃文穎, 蔡宗益, 高明秀, 王世旭, 王維志, 建築工程生命週期階段減碳策略之選擇與評估, 2023第27屆營建工程與管理學術研討會論文集，臺灣新竹(陽明交大)
  14. 鄭皓中、王世旭、張智安、高明秀、王維志, 運用BIM與電腦視覺及物件偵測技術於工程進度追蹤, 2022第26屆營建工程與管理學術研討會論文集，臺灣中壢(中央) (Outstanding Paper Award)

Awarded Research Projects

  • Granted NSTC Research Proposal-114-2221-E-A49 -020 -
2025/8~2026/7
  • Granted NSTC Research Proposal-113-2221-E-A49 -056 -
2024/8~2025/7
  • Granted NSTC Research Proposal-112-2221-E-159 -001 -
2023/8~2024/7
  • Granted NSTC Research Proposal-111-2221-E-A49 -189 -
2022/8~2023/7
  • Granted MOST Research Proposal-109-2222-E-159 -001 -
2020/8~2021/7
Educational Background

National Taiwan University of Science and Technology – Department of Construction Engineering

Educational qualification: Ph.D.2015/6
Dissertation: Artificial Intelligence-Based Inference Support Models for Construction Engineering and Management

National Taiwan University of Science and Technology – Department of Construction Engineering

Educational qualification: Master’s degree2012/6
Dissertation: Optimization of Project Cost under Time-Quality Requirement Using Advanced Constraint Handling Differential Evolution (ACH-DE)

Hanoi University of Civil Engineering - Faculty of Civil and Industrial Construction

Educational qualification: Bachelor2010/7

Job Description

This research aims to develop a distortion-aware traffic sign detection framework for Bird’s-Eye wide-angle camera images. Unlike conventional traffic sign detection methods that assume perspective camera images, the proposed approach will explicitly address geometric distortion, non-uniform object scale, and boundary-region deformation. The final goal is to improve detection accuracy and robustness for traffic signs appearing in ultra-wide road-scene images.

Fisheye or wide-angle cameras provide much larger fields of view than conventional cameras, but their optical distortion makes object detection harder; objects can change shape depending on where they appear in the image. Traffic sign recognition also faces outdoor challenges such as occlusion, distortion, lighting changes, and color fading. Prior fisheye-detection work also notes that standard bounding boxes can fail under strong radial distortion, especially near image boundaries, motivating alternative representations such as oriented boxes, ellipses, polygons, or curved boxes. A good novelty angle for your work is therefore: do not simply undistort the image first, but design the model to understand distortion directly; recent BEV/fisheye work reports that avoiding undistortion can prevent added runtime, field-of-view loss, and resampling artifacts.

 

Preferred Intern Educational Level

We welcome applications from Master’s students and early-stage Ph.D. students who are interested in computer vision, deep learning, object detection, autonomous driving, or intelligent transportation systems.

Skill sets or Qualities

Technical skills

  • Basic programming experience in Python
  • Familiarity with deep learning frameworks such as PyTorch or TensorFlow
  • Basic understanding of computer vision and object detection
  • Interest in models such as YOLO, Faster R-CNN, DETR, or Vision Transformers
  • Experience with image annotation, dataset preparation, or model evaluation is a plus
  • Basic knowledge of Linux, Git, or GPU-based training is helpful but not required