[{"content":" Office Address # Department of Civil Engineering\nUniversity of Alberta\nEdmonton, Alberta\nCanada\nEmail # jiangyu1@ualberta.ca\nPhone # +1 (204) 869-7738\nOnline # ORCID: 0000-0001-5916-8981 LinkedIn: jiangyu-zeng Research Collaborations # Active collaboration with interdisciplinary teams integrating crowdsensing technologies with traditional structural monitoring approaches.\nPhoto Credits # Banner photos of Edmonton\u0026rsquo;s Walterdale Bridge are from Wikimedia Commons, resized for this site:\nHome: Walterdale Bridge into downtown Edmonton, Chris Woodrich, CC BY-SA 4.0 Publications: Walterdale Bridge 04-21-2023, TagaSanPedroAko, CC BY-SA 4.0 Experience: Walterdale bridge in winter, Joli Rumi, CC BY-SA 4.0 Gallery: Walterdale May 2017, Kurt Bauschardt, CC BY-SA 2.0 Contact: Walterdale bridge on North Saskatchewan river, Joli Rumi, CC BY-SA 4.0 ","externalUrl":null,"permalink":"/contact/","section":"Jiangyu Zeng","summary":"","title":"Contact","type":"page"},{"content":" Education # Ph.D. in Civil Engineering Jan 2022 – Sep 2026 University of Alberta · CGPA 4.00 Dissertation: \u0026ldquo;A Crowdsensing-Enabled Population-Based Structural Health Monitoring (CE-PBSHM) Framework Using Drive-by Measurements\u0026rdquo; M.Sc. in Civil Engineering Jan 2020 – Dec 2021 University of Alberta · CGPA 3.80 Focus on imaging-based analysis and computer vision applications in civil engineering. B.Sc. in Civil Engineering Sep 2014 – Jun 2019 University of Manitoba · CGPA 3.70 Developed foundational knowledge in civil engineering with early exposure to research through undergraduate research assistantship. Research Experience # PhD Research: Crowdsensing-Based Structural Health Monitoring Jan 2022 – Sep 2026 University of Alberta Developed a scalable model for simultaneous multi-bridge monitoring using crowdsensing and big data analytics. This research represents a paradigm shift from traditional single-structure monitoring to population-based infrastructure assessment. M.Sc. \u0026amp; Undergraduate Research: Imaging-Based Analysis and Computer Vision Sep 2015 – Dec 2021 University of Alberta \u0026amp; University of Manitoba Developed and applied machine learning and computer vision techniques for infrastructure monitoring, including pavement condition assessment and crack detection in concrete structures. Lab Safety Associate Jan 2024 – Sep 2026 University of Alberta Ensured lab safety and protocol compliance during structural health monitoring experiments, managing laboratory equipment and coordinating experimental activities. Research Assistant Spring/Summer 2018 University of Manitoba Assisted in developing machine learning models to improve the accuracy of structural health assessments, gaining early experience in applying computational methods to civil engineering problems. Teaching Experience # Teaching Assistant Sep 2020 – Apr 2026 Department of Civil Engineering, University of Alberta Courses: Civ E 130, Civ E 270, Civ E 265, Civ E 398, Civ E 779\nAssisted with various undergraduate and graduate courses, providing student support, grading assignments, and conducting tutorial sessions.\nLab Instructor Jan 2021 – Apr 2026 Department of Civil Engineering, University of Alberta Course: Civ E 270 – Mechanics of Deformable Bodies\nConducted laboratory sessions, demonstrating the practical applications of theoretical concepts in mechanics of materials and structural analysis.\nAchievements \u0026amp; Awards # Alberta Innovates Graduate Student Scholarship (2024–2025) Graduate Research Award, University of Alberta (2024) Graduate Teaching Awards, University of Alberta (2021–2023) China Scholarship Council Scholarship (2022–2025) International Undergraduate Student Scholarship, University of Manitoba (2016–2019) Technical Skills # Programming Languages\nPython MATLAB Visual Basic LaTeX Engineering Software\nAutoCAD Abaqus Geoslope Data Analysis \u0026amp; ML\nBig Data Analysis Machine Learning Computer Vision Signal Processing Research Areas\nStructural Health Monitoring Crowdsensing Infrastructure Management Volunteer Experience # Orientation Ceremony Volunteer, Civil Engineering, University of Alberta (September 2023) Mentor, Mentor and Mentee Program, University of Manitoba (2018 Academic Year) ","externalUrl":null,"permalink":"/experience/","section":"Jiangyu Zeng","summary":"","title":"Experience","type":"page"},{"content":" 9\nPublications\nJournal articles, conference papers and preprints 4.00\nPh.D. CGPA\nUniversity of Alberta, 2022–2026 5+\nYears teaching\nTeaching assistant and lab instructor 5\nAwards\nScholarships and research and teaching awards Research Focus # Drive-by crowdsensing Monitoring bridges with the responses measured by vehicles that drive across them. Population-based SHM Scalable, simultaneous monitoring of many bridges, with damage detection that accounts for temperature variability. Machine learning \u0026amp; vision Autoencoders, graph models and imaging methods for bridge damage, crack and pavement assessment. About Me # Welcome to my personal website! I am Jiangyu Zeng, and I completed my Ph.D. in the Department of Civil Engineering at the University of Alberta in September 2026. Across the globe, extensive infrastructure has been constructed to better serve society, and these structures now demand efficient and economical monitoring solutions. My research focuses on developing innovative approaches to structural health monitoring using crowdsensing technologies and big data analytics.\nMy doctoral dissertation is titled \u0026ldquo;A Crowdsensing-Enabled Population-Based Structural Health Monitoring (CE-PBSHM) Framework Using Drive-by Measurements.\u0026rdquo; This research develops a scalable model for simultaneous multi-bridge monitoring, representing a significant advancement in infrastructure monitoring technologies.\nMy work combines traditional civil engineering principles with cutting-edge technologies including machine learning, computer vision, and big data analytics to create more efficient and comprehensive infrastructure monitoring solutions.\nResearch Interests # Structural Health Monitoring Crowdsensing Technologies Machine Learning Applications Computer Vision Big Data Analytics Infrastructure Management Interactive Tool: VBI-ChatGPT # Build and solve a vehicle-bridge interaction model by chatting.\nOpen VBI-ChatGPT ","externalUrl":null,"permalink":"/","section":"Jiangyu Zeng","summary":"","title":"Jiangyu Zeng","type":"page"},{"content":"A collection of photos from my teaching, research, and conference activities.\nTeaching Linear Algebra — Presenting matrix determinants and invertibility concepts to undergraduate students. Classroom Instruction — Engaging with students during a mathematics lecture at University of Alberta. Laboratory Instruction — Providing hands-on guidance to students during engineering lab sessions. Research Presentation — Presenting research findings at an academic conference on structural health monitoring. ","externalUrl":null,"permalink":"/gallery/","section":"Jiangyu Zeng","summary":"","title":"Photo Gallery","type":"page"},{"content":"Synced from ORCID. Full record: orcid.org/0000-0001-5916-8981\nPreprints Under Review # Multi-View Mel-Filterbank Fusion for Robust Drive-By Population-Based Bridge Damage Detection J. Zeng, Q. Mei, N. Shirzad-Ghaleroudkhani, M. Jamshidi, and M. Gül\nSubmitted to Mechanical Systems and Signal Processing (SSRN preprint, 2026)\nThis paper shows that fusing several diverse mel-filterbank channels in a single shared graph autoencoder removes the single-channel bias of drive-by population-based damage detection, validated on both simulations and a field campaign on in-service bridges.\nDOI: 10.2139/ssrn.7513585 A Drive-By PBSHM Framework for Bridge Damage Detection Under Temperature Variability J. Zeng, Q. Mei, N. Shirzad Ghaleroudkhani, M. Jamshidi, and M. Gül\nSubmitted to Engineering Structures (SSRN preprint, 2026)\nThis paper presents a drive-by population-based structural health monitoring framework that detects bridge damage while explicitly addressing temperature-induced variability in structural response.\nDOI: 10.2139/ssrn.7119201 Journal Articles # Multibridge Inference Structural Health Monitoring (MISHM): A Drive-By Crowdsensing Approach at the Network Level J. Zeng, Q. Mei, and M. Gül\nStructural Control and Health Monitoring, Vol. 2025, No. 1, Article ID 8624965, 2025\nThis paper presents a novel framework for monitoring multiple bridges simultaneously using crowdsensing technologies and drive-by measurements.\nDOI: 10.1155/stc/8624965 A computer vision-based method to identify the international roughness index of highway pavements J. Zeng, M. Gül, and Q. Mei\nJournal of Infrastructure Intelligence and Resilience, Vol. 1, Issue 1, Article 100004, 2022\nThis study presents a novel approach to assess pavement roughness using imaging techniques and artificial neural networks.\nDOI: 10.1016/j.iintel.2022.100004 Conference Papers # Unsupervised temperature-aware population-based SHM using drive-by crowdsensing J. Zeng, Q. Mei, N. Shirzad-Ghaleroudkhani, M. Jamshidi, and M. Gül\nMoving Toward Smart, Resilient and Sustainable Bridges, Proceedings of the 13th International Conference on Bridge Maintenance, Safety and Management (IABMAS 2026), CRC Press, pp. 1017–1023, 2026\nConference paper on an unsupervised, temperature-aware population-based SHM framework that detects damage with a population-level autoencoder and localises the damaged bridge with leave-one-out sub-autoencoders.\nDOI: 10.1201/9781003778677-121 Multi-Bridge Indirect Structural Health Monitoring: Leveraging Big Data and Drive-By Crowdsensing Techniques J. Zeng, Q. Mei, and M. Gül\nStructural Health Monitoring \u0026amp; Machine Learning, Vol. 12, Proceedings of the 43rd IMAC, A Conference and Exposition on Structural Dynamics 2025\nConference proceedings paper on multi-bridge indirect structural health monitoring using big data and drive-by crowdsensing techniques.\nDOI: 10.13052/97887-438-0157-3_8 Bridge Damage Detection Using Passing-By Vehicles and CNN-LSTM Autoencoder J. Zeng, M. Gül, and Q. Mei\nProceedings of the Canadian Society for Civil Engineering Annual Conference 2023, Lecture Notes in Civil Engineering, Vol. 507, pp. 327–335, 2024\nThis paper presents a CNN-LSTM autoencoder approach for bridge damage detection using responses from passing-by vehicles.\nDOI: 10.1007/978-3-031-61539-9_26 Deep learning-based crack detection in a concrete tunnel structure using multispectral dynamic imaging R. Ali, J. Zeng, and Y. J. Cha\nProc. SPIE 11382, Smart Structures and NDE for Industry 4.0, Smart Cities, and Energy Systems, 2020\nApplication of deep learning techniques for automated crack detection in concrete tunnel structures using advanced imaging methods.\nDOI: 10.1117/12.2557900 Heat loss detection using thermal imaging by a small UAV prototype R. Ali, J. Zeng, M. Kavgic, and Y. J. Cha\nProc. SPIE 11382, Smart Structures and NDE for Industry 4.0, Smart Cities, and Energy Systems, 2020\nInvestigation of thermal imaging applications using unmanned aerial vehicles for building energy efficiency assessment.\nDOI: 10.1117/12.2557902 ","externalUrl":null,"permalink":"/publications/","section":"Jiangyu Zeng","summary":"","title":"Publications","type":"page"}]