Zhibin Li

Research summary

This project will develop data analytics technologies to use to manage condition-based monitoring for rail maintenance. This will involve collecting data from sensors installed along the railways and infrastructure components, including different track switches for train operation. Advanced data analysis technologies on historical and sensing data and related condition-based maintenance will be developed.

Expected completion date

September 2020

Key achievements

• Collected, connected and cleaned several datasets of railway points from multiple sources, including data on  equipment details, maintenance logs, weather data, movement logs and failure records.
• Designed a framework to combine multiple-source data for predicting failures of railway points.
• Designed several algorithms on predicting failures of railway points, including those with incomplete and high dimensional data.
• Published and submitted several peer-reviewed research papers on failure prediction and machine learning area.

Publications

Gong, Y., Li, Z., Zhang, J., Liu, W., Chen, B. and Dong, X. A Spatial Missing Value Imputation Method for Multi-view Urban Statistical Data. 29th International Joint Conference on Artificial Intelligence. 2020.

Gong, Y., Li, Z., Zhang, J., Liu, W., & Kirsch, C. Network-wide crowd flow prediction of Sydney trains via customized online non-negative matrix factorization. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management, pages 1243–1252, 2018.

Gong, Y., Li, Z., Zhang, J., Liu, W. and Yi, J. Potential passenger flow prediction: A novel study for urban transportation development. Proceedings of the 34th AAAI Conference on Artificial Intelligence, pages 4020–4027, 2020.

Gong, Y., Li, Z., Zhang, J., Liu, W. and Zheng, Y. Online Spatio-temporal Crowd Flow Distribution Prediction for Complex Metro System, IEEE Transactions on Knowledge and Data Engineering, 2020.

Li, Z., Zhang, J., Wu, Q., Gong, Y., Yi, J. and Kirsch, C. (2019). Sample Adaptive Multiple Kernel Learning for Failure Prediction of Railway Points. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD ’19). ACM, New York, NY, USA, pp.2848-2856.

Li, Z., Zhang, J., Wu, Q., and Kirsch, C. Field-Regularised Factorization Machines for Mining the Maintenance Logs of Equipment. In: Mitrovic T., Xue B., Li X. (eds) AI 2018: Advances in Artificial Intelligence. AI 2018. Lecture Notes in Computer Science, pp. 172-183 vol 11320. Springer, Cham.

Zhang, L., Zhang, J., Li, Z. and Xu, J. Towards Better Graph Representation: Two-branch Collaborative Graph Neural Networks for Multimodal Marketing Intention Detection. 21st IEEE International Conference on Multimedia & Expo. 2020.