윤규근 교수

Given the lack of demand forecasting models for e-scooter sharing systems, we address this research gap using data from Portland, OR, and New York City. A log-log regression model is estimated for e-scooter trips based on user age, income, labor force participation, and health insurance coverage, with an adjusted R squared value of 0.663. When applied to the Manhattan market, the model predicts 66K daily e-scooter trips, which would translate to 67 million USD in annual revenue (based on average

While public transit network design has a wide literature, the study of line planning and route generation under uncertainty is not so well covered. Such uncertainty is present in planning for emerging transit technologies or operating models in which demand data is largely unavailable to make predictions on. In such circumstances, this paper proposes a sequential route generation process in which an operator periodically expands the route set and receives ridership feedback. Using this sensor l

Despite the proliferation of publicly available Big Data in Mobility-as-a-Service systems, few studies in the urban mobility service literature deal with unlimited usage price plan strategies. We conduct an experimental case study to design such a strategy: an unlimited-ride X-Day pass pricing for bike-share usage especially targeting short-term casual users. Public data from Citi Bike is used to estimate a pass choice model for bike-share services. As disaggregate data for riders have not been

With Mobility-as-a-Service platforms moving toward vertical service expansion, we propose a destination recommender system for Mobility-on-Demand (MOD) services that explicitly considers dynamic vehicle routing constraints as a form of a “physical internet search engine”. It incorporates a routing algorithm to build vehicle routes and an upper confidence bound based algorithm for a generalized linear contextual bandit algorithm to identify alternatives which are acceptable to passengers. As a co

• A sequential network design combined with reinforcement learning. • Respond to uncertain demand, serially available budget, and new mobility service. • Three reinforcement learning policies used for directing network expansion. • Experiment with 5-by-5 toy network and New York City-based realistic network. • Consideration of correlations among OD demand leads to better performances. Mobility service route design requires demand information to operate in a service region. Transit planners and o

Estimating multimodal distributions of travel times from real-world data is critical for understanding and managing congestion. Mixture models can estimate the overall distribution when distinct peaks exist in the probability density function, but no transfer of mixture information under epistemic uncertainty across different spatiotemporal scales has been considered for capturing unobserved heterogeneity. In this paper, a physics-informed and -regularized prediction model is developed that shar

With advances in emerging technologies, options for operating public transit services have broadened from conventional fixed-route service through semi-flexible service to on-demand microtransit. Nevertheless, guidelines for deciding between these services remain limited in the real implementation. An open-source simulation sandbox is developed that can compare state-of-the-practice methods for evaluating between the different types of public transit operations. For the case of the semi-flexible

본 연구에서는 과속방지턱으로 인해 통과차량이 제한속도 이하로 주행하게 되는 구간을 영 향구간이라 정의하였다. 이를 과속방지턱 통과 전 구간 · 사이 구간 · 통과 후 구간으로 구분한 뒤, 단독 및 연속 설치 여부· 차종· 시간대 등 다양한 요인들로 인한 변화를 분석하였다. 특히, 사이 구간에서는 구간 내에서 제한속도 이하로 주행한 거리의 비율을 유효영향구간비율로 정 의하여 분석하였다. 스피드건으로 과속방지턱을 통과하는 차량들의 속도궤적을 수집하여 영향 구간의 길이를 산출하였고, 생존분석을 이용하여 추정한 영향구간의 생존함수를 비교하였다. 설치 형태에 따른 변 화 분석 결과, 50m 간격 연속형 과속방지턱의 통과 전 평균 영향구간 길이는 단일형보다 75.3% 길었으며, 통과 후 평균 영향구간은 18.9% 긴 것으로 나타났다. 연속형 과속방지턱의 유효영향구간비율은 30m와 50m 간격에서 각각 81.0%와 76.0%로 큰 차이가 없었으나, 제한속도 이하로 주행한 절대적 길이

This dataset is generated for the simulation of three different mobility services along the MTA Bus route B63 in Brooklyn, NY. Each includes the information of origin and destination of passengers within the service area and reflects different levels of demand (80, 200, and 400 passenger/hr). The dataset is produced based on MATLAB.

Current free and subscription-based trip planners have heavily focused on providing available transit options to improve the first- and last-mile connectivity to the destination. However, those trip planners may not truly be multimodal to vulnerable road users (VRU)s since those selected sidewalk routes may not be accessible or feasible for people with disability. Depending on the level of availability of digital twin of travelers behaviors and sidewalk inventory, providing the personalized sugg

Mobility service route design requires demand information to operate in a service region. Transit planners and operators can access various data sources including household travel survey data and mobile device location logs. However, when implementing a mobility system with emerging technologies, estimating demand becomes harder because of limited data resulting in uncertainty. This study proposes an artificial intelligence-driven algorithm that combines sequential transit network design with op