Search for: All records

Abstract Individual passenger travel patterns have significant value in understanding passenger’s behavior, such as learning the hidden clusters of locations, time, and passengers. The learned clusters further enable commercially beneficial actions such as customized services, promotions, data-driven urban-use planning, peak hour discovery, and so on. However, the individualized passenger modeling is very challenging for the following reasons: 1) The individual passenger travel data are multi-dimensional spatiotemporal big data, including at least the origin, destination, and time dimensions; 2) Moreover, individualized passenger travel patterns usually depend on the external environment, such as the distances and functions of locations, which are ignored in most current works. This work proposes a multi-clustering model to learn the latent clusters along the multiple dimensions of Origin, Destination, Time, and eventually, Passenger (ODT-P). We develop a graph-regularized tensor Latent Dirichlet Allocation (LDA) model by first extending the traditional LDA model into a tensor version and then applies to individual travel data. Then, the external information of stations is formulated as semantic graphs and incorporated as the Laplacian regularizations; Furthermore, to improve the model scalability when dealing with massive data, an online stochastic learning method based on tensorized variational Expectation-Maximization algorithm is developed. Finally, a case study based on passengers in the Hong Kong metro system is conducted and demonstrates that a better clustering performance is achieved compared to state-of-the-arts with the improvement in point-wise mutual information index and algorithm convergence speed by a factor of two. 

As HCI pedagogy research grows, so too does an emerging set of evidence-based teaching and curricular recommendations. Yet, few studies have implemented and examined these recommendations in the classroom. In this paper, we present a Research Through Design investigation of a studio-based HCI course, which was revised based on HCI education literature. Drawing on reflection surveys, video recordings of student-led user sessions, final project artifacts, and student interviews, we explore how students responded to key educational changes, the strategies that supported and hindered their reflective practices, and how reflection afforded new student insights. Our findings highlight the utility of video-based reflection exercises to support student learning in designing and running user sessions, the importance of multi-faceted reflection prompts, and how students noticed moments of inclusion and exclusion by attending to users’ non-verbal cues. Additionally, we empirically demonstrate the importance of implementing and studying HCI education research recommendations in the classroom.