Mobility Informatics Lab

Data driven modeling, simulation, optimization and control of mobility systems.

MI Lab

The Mobility Informatics (MI) Lab is mainly involved in STATISTICS, MACHINE LEARNING, DATA SCIENCE based modeling, simulation, optimization, and control in the frame of selected MOBILITY-related COMPLEX SYSTEMS, which are: intelligent transport systems (traffic/public transport/rails) and multimodal mobility systems.

Jobs

Students and researchers who are interested in studies and research collaborations are welcome to Contact Us.

News

  • [Fund] 2024-02: Glad to receive a research project with VTI from Trafikverket on ‘Decision Making under Deep Uncertainties’ for Travel Demand Forecasting.
  • [Fund] 2024-01: Glad to receive two research projects from the region Stockholm on Personalized Information for Public Transport, and Better Traffic Information Under Disruptions.
  • 2023-10-15: Glad to be invited to speak at the conference on ‘unleashing the power of data for traffic demand forecasting in metro’ organized by the Indian Metro society and Delhi Metro. 
  • [Paper] 2023-08: A paper accepted in IEEE Transactions on ITS: Y. Ling, Z. Ma*, B. Zhang, Q. Zhang, X. Weng (2023). SA-BiGCN: Bi-Stream Graph Convolution Networks with Spatial Attentions for the Eye Contact Detection in the Wild. IEEE Transactions on Intelligent Transportation Systems. Congrats Yangcheng!
  • [Paper] 2023-08: A paper accepted in Transportation Research Part C: Z Liu, GH de Almeida Correia, Z Ma, S Li, X Ma* (2023). Integrated optimization of timetable, bus formation, and vehicle scheduling in autonomous modular public transport systems. Transportation Research Part C: Emerging Technologies, 155, 104306.
  • [Paper] 2023-08: A paper accepted in Transportation: L. Wang, X. Chen,  Z Ma*, P. Zhang, B. Mo, P. Duan (2023). Data-Driven Analysis and Modeling of Individual Longitudinal Behavior Response to Fare Incentives in Public Transport. Congrats Leizhen!
  • [Fund] 2023-08: Glad to receive a joint research fund to work with colleagues at TU Darmstadt-Germany and UPC-Spain on ‘Use of Hybrid Methods to Enhance Real-Time Railway Traffic Control (Dispatching)’, Unite! Seed Fund Initiative, European Commission, Euro 80K, 2023-2024.
  • [Paper] 2023-07: 5 paper published in a row in the railway area (urban rails and long-distance rails).
    • K.Y. Tiong*, Z. Ma and C.W. Palmqvist (2023). Analyzing factors contributing to real-time train arrival delays using seemingly unrelated regression models. Transportation Research Part A: Policy and Practice, 174, p.103751. 
    • T. Liu, Z. Ma*, H. Koutsopoulos (2023). Impact Duration Model of Unplanned Disruptions in Urban Rail Systems. Urban Rail Transit (Accepted).
    • B Liu, X Ma*, E Tan and Z Ma* (2023). Passenger flow anomaly detection in urban rail transit networks with graph convolution network–informer and Gaussian Bayes models. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.
    • K Tuncel, HN Koutsopoulos, Z Ma* (2023). An Unsupervised Learning Approach for Robust Denied Boarding Probability Estimation Using Smartcard and Operation Data in Urban Railways. IEEE Intelligent Transportation Systems Magazine, DOI: 10.1109/MITS.2023.3289969
    • K Tuncel, HN Koutsopoulos, Z Ma* (2023). Data-Driven Real-Time Denied Boarding Prediction in
      Urban Railway Systems. Transportation Research Record, https://doi.org/10.1177/03611981231184237
  • [Paper] 2023-06: 1 paper published in computers and operations research on integrated formulation of shared mobility services. K Tuncel, HN Koutsopoulos, Z Ma* (2023). An integrated ride-matching and vehicle-rebalancing model for shared mobility-on-demand services. Computers and Operations Research, DOI: 10.1016/j.cor.2023.10631
  • [Paper] 2023-05: 1 paper published in applied intelligence on knoweldge graph assisted user-station attention inference. Q. Zhang, Z. Ma*, P. Zhang, E. Jenelius, X. Ma and Y. Wen (2023). User-station attention inference using smart card data: a knowledge graph assisted matrix decomposition model. Applied Intelligence. https://doi.org/10.1007/s10489–023–04678–2. Congrats Qi.
  • [Fund] 2023-01/04: Glad to receive a project to work with colleagues at MIT and RISE on the digital twn model in Stockholm. GEMINI: DiGital twin for Emission MonItoring aNd predIction – Kista Case, Senseable Stockholm Lab (City of Stockholm, MIT and KTH), SEK 3.0M, 2023-2024.
  • [Paper] 2023-03: 2 paper published. DeepTrip: A deep learning model for the individual next trip prediction with arbitrary prediction times. IEEE Transactions on Intelligent Transportation Systems.  A review of data-driven approaches to predict train delays. Transportation Research Part C: Emerging Technologies, 148, p.104027
  • [Recuitment] 2023-01-17: We are looking for a talented and committed postdoc to join our team at KTH to develop #causalAI methodology for #mobilitybehavior analysis and modeling using #trajectorydata (collaborated with KTH Mathematics Department). https://www.kth.se/en/api/2.61673/what:job/jobID:585455/where:4/ 
  • [Fund] 2022-12/05: Digital Future (PI). Glad to receive two funds from Digital Future.  1. DIRAC: DynamIc uRban roAd trafiC noise simulation model using passive and publicly available data, Digital Future Demonstrator, SEK 2.0M, 2023–2025 (PI). 2. cAIMBER: Causal Artificial Intelligence for Human Mobility Behavior Analysis Using Trajectory Data, Digital Future Research Pairs, SEK 2.0M, 2023–2025 (PI).
  • [Recuitment] 2022-11-17: We are looking for a good PhD candidate in traffic simulation for the traffic noise assessment project funded by the EU Marie Curie program (https://euraxess.ec.europa.eu/jobs/847759).  Interested candidates could contact zhema@kth.se along with your CV.
  • [Paper] 2022-10-02: 5 papers in urban railways are accepted in the 103th Transportation Research Board Annual Meeting in 2023.  1. Mobility Knowledge Graph: Review and its Application in Public Transport (Qi Zhang), 2. Urban Rail Transit Fare Reconciliation Method Using Multi-source Data (Jiajun Liu), 3. Individual Longitudinal Adoption Pattern Analysis under Fare Incentives Using Smart Card Data (Leizhen Wang), 4. Irregular Passenger Demand Identification under Disruptions: A Robust Principal Component Analysis Approach (YangYang Zhao), 5. Statistical and Machine Learning Models for Incident Delay Prediction in Urban Railway Systems: A Methodology Review (Wei Sun)
  • [Fund] 2022-09-26: Swedish Transportation Administration (Co-PI). Glad to receive the fund support from Trafikverket on the evaluation of train arrival forecasts, together with Lund University to explore the appropriate type of method for train arrival time predictions under different conditions in railway networks.
  • [Fund] 2022-09-19: Regional Stockholm (PI). Glad to receive the fund support from SL on integrated electric public transport simulation to develop simulation and optimization models for electric public transport network and operations planning.
  • [Fund] 2022-09-12: Swedish Transportation Administration (Co-PI). Glad to receive the fund support from Trafikverket on Choice modeling for policy decision support towards attractive, reliable, and efficient public transport systems together with VTI to explore a modern and innovative data-driven approach for choice modeling that considers empirical observations that include almost all the public transport users with imputed socio-economic and activity attributes.
  • [Recuitment] 2022-07-01: Exciting opportunities at DTU! The PhD scholarship in Modelling and Simulation of Demand Responsive Electrified Multimodal Transit Systems is a collaboration with our lab and includes a 6-month stay at KTH Division of Transport Planning. and apply here.
  • [Event] 2022-06-01: We had a very fruitful cities partnership workshop on Rail Data at UCL, London with academics and students from UCL, Lund, and KTH, and practitioners at Network Rail and TfL. Discussions are around data-driven opportunities for themes of operation delay prediction, capacity management, passenger information, and offline reinforcement learning.  Read more .
  • [Fund] 2021-04-15: KTH Digitalization Platform fund (PI). Glad to receive the fund support on applied AI in transportation, together with KTH EECS department to bridge the gap between AI techniques in transportation applications (inference, prediction and controls).
  • [Paper] 2022-03-15: Paper published in Multimodal Transportation. Title: Individual mobility prediction review: Data, problem, method and application. The review synthesizes existing studies on individual mobility prediction in transport (data/problem/methodology/applications), identifies remaining research needs, as well as discusses methodological considerations and potential future transport applications.
  • [Recuitment] 2022-03-14: We are looking for a PHD student to join our Group at KTH Royal Institute of Technology: Doctoral student (licentiate) in Multimodal Autonomous Mobility Systems. You may find more information and apply here.
  • [Paper] 2022-03-07: Paper accepted in the Transportation Research Record. Title: Unplanned Disruption Analysis and Impact Modeling in Urban Railway Systems. The paper collects a complete set of unplanned disruption data for 7 years in Hong Kong and explores important factors impacting operation delays and affected areas. Congrats Xin Chen.
  • [Paper] 2022-02-15: Paper published in Transportation Research Record. Title: Naive Bayes Transition Model for Short-term Metro Passenger Flow Prediction under Planned Events. Congrats Yangyang Zhao (now lecturer at Chang’an University).
  • [Event] Join our Hackathon on Data Analytics in Public Transport (KTH-Lund-UCL, online Feb. 14-15, joining the international network, the winning team getting rewards) funded by the city partnership program between Stockholm and London, Read more and register.
  • [Fund] 2021-01-15: UCL cities partnership program fund (PI). Glad to work with researchers at the University of College London and Lund University and local industries in London and Stockholm on the seed project of Data-Driven Analytic and Modeling Approaches for Mass Transport in Cities.
  • [Paper] 2022-01-10: Paper published in Neural Computing and Applications. Title: Deep learning for short-term origin–destination passenger flow prediction under partial observability in urban railway systems. It is a comprehensive work on prediction modeling techniques (inputs, function) beyond prediction itself [pdf link]. Congrats Wenhua Jiang (now postdoc at Edinburgh University).
  • [Paper] 2021-12-26: Paper published in Transportation Research Part C. Title: Near-on-demand mobility. The benefits of user flexibility for ride-pooling services. It highlights that Near-on-Demand services (i.e. a short advance requests horizon of 5 or 15 min depending on the network and trip characteristics) capture most of the benefits for all involved (VMT, LoS and Fleet utilization).
  • [Engagement] 2021-11-15: Glad to be the co-host of the Nordic AI & Open Data Hackathon (Ramboll, Happy42, Nordic innovation, DTU, Microsoft) [Read more].
  • [Engagement] 2020-12-01: Glad to share my career experience on data science in transportation in Research Transit Podcast, RT14 – Harnessing data science in public transport operations and planning [Apple Podcast].