Leo Yu

Leo (Qiqin) Yu

Sessional Teaching Associate at Monash University and Western Sydney University

Biography

Leo (Qiqin) Yu is a Sessional Teaching Associate at Monash University and Western Sydney University. His research and teaching sit at the intersection of construction engineering and management, infrastructure digitalisation, and data-driven road asset management.

He received his PhD from Monash University under the supervision of Dr Yihai Fang at the ICON Research Lab, where he developed smartphone- and vehicle-based methods for pavement roughness characterisation and road condition monitoring. His doctoral work—supported by the ARC Smart Pavements Australia Research Collaboration (SPARC Hub) and the National Transport Research Organisation (NTRO)—advanced low-cost, crowdsourcing-based alternatives to conventional pavement survey vehicles, combining signal processing, machine learning, and field validation across real-world road networks.

Before and during his PhD, Leo worked as a civil engineer in Melbourne on land development and structural design projects. He completed a visiting research period at the University of Cambridge (Digital Road of Future initiative), an industry placement at Beca developing computer-vision and large-language-model tools for road asset inspection, and a postdoctoral fellowship at City University of Hong Kong, where he developed maintenance-oriented pavement digital twin prototypes integrating fleet-vehicle sensing data. He now teaches across civil engineering, construction management, and infrastructure information management at Monash and Western Sydney University.

Education

Research Vision

Leo’s research aims to make infrastructure monitoring more scalable, affordable, and actionable through digital sensing and intelligent analytics.

His work seeks to transform everyday vehicles and mobile devices into distributed sensors for the built environment, enabling road authorities and construction organisations to move from infrequent, high-cost inspections toward continuous, data-informed asset management. By connecting domain knowledge in pavement engineering with IoT sensing, deep learning, and digital twin technologies, his research contributes to smarter, safer, and more resilient transport infrastructure.

Research Specialities

Smartphone- and Vehicle-Based Infrastructure Sensing

Developing accelerometric and profilometric methods to estimate pavement roughness, detect surface anomalies, and characterise road condition using data from smartphones and public vehicles. Applying machine learning, semi-supervised learning, and deep learning to estimate the International Roughness Index (IRI) and roughness profiles from crowdsourced vehicle response data under varying vehicle types, speeds, and mounting configurations.

Infrastructure Digital Twins and BIM

Building digital representations of road assets that integrate multi-source sensing data, computer vision outputs, and maintenance analytics to support decision-making across the asset lifecycle.

Industry-Integrated Research Translation

Connecting academic research with road authorities and engineering consultancies through field trials, open-source tools, and deployable prototypes that address real maintenance and monitoring challenges.

Selected Publications

  1. Yu, Q., Fang, Y., Ranasinghe, R., & Wix, R. (2026). Characterising and mitigating mounting’s impact on smartphone-based evaluation of pavement roughness. Journal of Computing in Civil Engineering, 40(3), 04026015.
  2. Sang, Y., Yu, Q., Fang, Y., Vo, V., & Wix, R. (2024). Smartphone-based IRI estimation for pavement roughness monitoring: A data-driven approach. IEEE Internet of Things Journal, 11(11), 19708–19720. (co-first author)
  3. Yu, Q., Fang, Y., & Wix, R. (2023). Evaluation framework for smartphone-based road roughness index estimation systems. International Journal of Pavement Engineering, 24(1), 2183402.
  4. Yu, Q., Fang, Y., & Wix, R. (2022). Pavement roughness index estimation and anomaly detection using smartphones. Automation in Construction, 141, 104409.
  5. Yu, Q., Sang, Y., Fang, Y., Vo, V., & Wix, R. (2024). Estimate road roughness using smartphone response data: A semi-supervised learning approach. Proceedings of the European Conference on Computing in Construction (EC3 2024).

Selected Awards and Grants

Links

Email: leo.yu@monash.edu

Personal website: qyu38.github.io

Google Scholar: Leo Yu