01629516

Component

https://doi.org/10.3141/2668-05

Analysis of the time use activity patterns of urbanites will contribute greatly to the modeling of urban transportation demands by linking activity generation and activity scheduling modules in the overall activity-based modeling framework. This paper develops a framework for novel pattern recognition modeling to identify groups of individuals with homogeneous daily activity patterns. The framework consists of four modules: initialization of the total cluster number and cluster centroids, identification of individuals with homogeneous activity patterns and grouping of them into clusters, identification of sets of representative activity patterns, and exploration of interdependencies among the attributes in each identified cluster. Numerous new machine-learning techniques, such as the fuzzy C-means clustering algorithm and the classification and regression tree classifier, are employed in the process of pattern recognition. The 24-h activity patterns are split into 288 intervals of 5-min duration. Each interval includes information on activity types, duration, start time, location, and travel mode, if applicable. Aggregated statistical evaluation and Kolmogorov–Smirnov tests are performed to determine statistical significance of clustered data. Results show a heterogeneous diversity in eight identified clusters in relation to temporal distribution and significant differences in a variety of sociodemographic variables. The insights gained from this study include important information on activities—such as activity type, start time, duration, location, and travel distance—that are essential for the scheduling phase of the activity-based model. Finally, the results of this paper are expected to be implemented within the activity-based travel demand model for Halifax, Nova Scotia.

01646167

17-05558

English

pp 38–50

2017

Transportation Research Record: Journal of the Transportation Research Board

9780309441643

Digital/other

Figures (4) ; References (35) ; Tables (4)

Activity choices; Algorithms; Cluster analysis; Demographics; Location; Mode choice; Time duration; Travel demand; Trip length; Urban transportation

Halifax (Canada)

Planning and Forecasting; Transportation (General)

TRIS, TRB, ATRI

Dec 8 2016 12:12PM

• Conceptual Framework for Understanding Latent Demand: Accounting for Unrealized Activities and Travel
• Estimating Household Travel Energy Consumption in Conjunction with a Travel Demand Forecasting Model
• Incorporating Land Use into Methods of Synthetic Population Generation and of Transfer of Behavioral Data
• Latest Urban Rail Demand Forecast Model System in the Tokyo Metropolitan Area
• Multimodal Trip Generation Model to Assess Travel Impacts of Urban Developments in the District of Columbia
• Peer-to-Peer Ridesharing with Ride-Back on High-Occupancy-Vehicle Lanes: Toward a Practical Alternative Mode for Daily Commuting
• Who is Picking Up the Child from Day Care? Understanding the Intrahousehold Dynamics in Drop-Off and Pickup Allocation for Households with Dependent Children