1. Incorporating World Knowledge to Document Clustering via Heterogeneous Information Networks

    • Motivation: One of the key obstacles in making learning protocols realistic in applications is the need to supervise them, a costly process that often requires hiring domain experts.
    • Proposed method: We consider the framework to use the world knowledge as indirect supervision.
      • We provide three ways to specify the world knowledge to domains by resolving the ambiguity of the entities and their types, and represent the data with world knowledge as a heterogeneous information network.
      • incorporating world knowledge as indirect supervision can significantly outperform the state-of-the-art clustering algorithms as well as clustering algorithms enhanced with world knowledge features.

  2. Multimodal divide: Reproduction of transport poverty in smart mobility trends

    • Motivation: the discussion about the transition from an automobile society to a multimodal society in Western transport and mobility research, which is characterised by a flexible use of different transport options.
    • Research gaps: transport poverty
    • Research findings: The theses challenge the often-postulated potential ubiquity of multimodal behaviours:
      • (i) Transport poverty – represented by a lack of mode options – inhibits the potential production of multimodal behaviours, particularly by socially marginalised people (low income, low education, precarious job situation, etc.).
      • (ii) A multimodal divide describes the reproduction of transport poverty in the guise of modernisation, as the transport poor – with few mode options – also lack certain ICTs that provide central access media to smart mobility.
      • (iii) Another (perfidious) form of social exclusion from participation in smart mobility concerns critical thinkers who avoid installing mobility applications to protect their privacy. This exclusion occurs because these apps do not have an alternative as access software to smart mobility.

  3. Assessing the relationships between young adults’ travel and use of the internet over time

    • Motivation: use internet while traveling
    • Research gap: the relationship between changes in the use of ICT over time and young people’s travel patterns
    • Research findings: consistently high levels of Internet use between adolescence and young adulthood is associated with the formation of environmental attitudes.

  4. Crowd Counting With Limited Labeling Through Submodular Frame Selection

    • Motivation: Automated crowd counting is valuable for intelligent transportation systems, as it can help to improve the emergency planning and prevent congestion in transit hubs such as train stations and airports.
    • Research gap: existing methods do not incorporate ways to effectively select informative frames as labeled training samples, resulting in low accuracy on unseen crowd scenes.
    • Proposed method: submodular method to select the most informative frames from the image sequences of crowds.

  5. Model and analysis of labor supply for ride-sharing platforms in the presence of sample self-selection and endogeneity

    • Motivation: With the popularization of ride-sharing services, drivers working as freelancers on ride-sharing platforms can design their schedules flexibly.
    • Research gap: evaluation of the impacts of hourly income rate on labor supply becomes important.
    • Research work: we propose an econometric framework with closed-form measures to estimate both the participation elasticity (i.e., extensive margin elasticity) and working-hour elasticity (i.e., intensive margin elasticity) of labor supply.

  6. Group-to-group reviewer assignment problem

    • Motivation: Reviewer Assignment Problem
    • Research gap: group-to-group reviewer assignment problem
    • Proposed method: multi-objective mixed integer programming model, which is proven NP-hard. An effective two-phase stochastic-biased greedy algorithm is then proposed to solve the problem.