Deriving rules from activity diary data: A learning algorithm and results of computer experiments

Operationalization of the Albatross model—a rule-based model of activity-travel scheduling—is described for applications on a national scale. For this purpose, the original model was extended to include the generation of schedule skeletons and travel cost variables. Furthermore, to account for the increase of scale of the study area, the location decision component of the model was completely restructured. The complete set of 27 decision trees involved in the decision process model were newly induced from several pooled existing activity diary data sets in the Netherlands. The results indicate that the goodness of fit of the model is satisfactory at the level of individual decisions as well as aggregate distributions.

Download Full-text

Does the social context help with understanding and predicting the choice of activity type and duration? An application of the Multiple Discrete-Continuous Nested Extreme Value model to activity diary data

Transportation Research Part A Policy and Practice ◽

10.1016/j.tra.2017.07.003 ◽

2017 ◽

Vol 104 ◽

pp. 1-20 ◽

Cited By ~ 8

Author(s):

Chiara Calastri ◽

Stephane Hess ◽

Andrew Daly ◽

Juan Antonio Carrasco

Keyword(s):

Social Context ◽

Extreme Value ◽

Activity Type ◽

Diary Data ◽

The Social ◽

Extreme Value Model ◽

Value Model ◽

Activity Diary

Download Full-text

E-coder for Automatic Scoring Physical Activity Diary Data

Medicine & Science in Sports & Exercise ◽

10.1249/01.mss.0000273709.05036.8d ◽

2007 ◽

Vol 39 (Supplement) ◽

pp. S190

Author(s):

Weimo Zhu ◽

Mark Hasegawa-Johnson ◽

Arthur Kantor ◽

Dan Roth ◽

Youngsik Park ◽

...

Keyword(s):

Physical Activity ◽

Diary Data ◽

Automatic Scoring ◽

Activity Diary

Download Full-text

Multiagent-Based Simulation of Temporal-Spatial Characteristics of Activity-Travel Patterns Using Interactive Reinforcement Learning

Mathematical Problems in Engineering ◽

10.1155/2014/951367 ◽

2014 ◽

Vol 2014 ◽

pp. 1-11 ◽

Cited By ~ 5

Author(s):

Min Yang ◽

Yingxiang Yang ◽

Wei Wang ◽

Haoyang Ding ◽

Jian Chen

Keyword(s):

Reinforcement Learning ◽

Traffic Flow ◽

Learning Algorithm ◽

Activity Patterns ◽

Temporal Distribution ◽

Travel Patterns ◽

Spatial Characteristics ◽

Diary Data ◽

Road Congestion ◽

Reinforcement Learning Algorithm

We propose a multiagent-based reinforcement learning algorithm, in which the interactions between travelers and the environment are considered to simulate temporal-spatial characteristics of activity-travel patterns in a city. Road congestion degree is added to the reinforcement learning algorithm as a medium that passes the influence of one traveler’s decision to others. Meanwhile, the agents used in the algorithm are initialized from typical activity patterns extracted from the travel survey diary data of Shangyu city in China. In the simulation, both macroscopic activity-travel characteristics such as traffic flow spatial-temporal distribution and microscopic characteristics such as activity-travel schedules of each agent are obtained. Comparing the simulation results with the survey data, we find that deviation of the peak-hour traffic flow is less than 5%, while the correlation of the simulated versus survey location choice distribution is over 0.9.

Download Full-text

Stationary and Time-Varying Patterns in Activity Diary Panel Data: Explorative Analysis with Association Rules

Transportation Research Record Journal of the Transportation Research Board ◽

10.3141/1807-02 ◽

2002 ◽

Vol 1807 (1) ◽

pp. 9-15 ◽

Cited By ~ 5

Author(s):

Bertold Keuleers ◽

Geert Wets ◽

Harry Timmermans ◽

Theo Arentze ◽

Koen Vanhoof

Keyword(s):

Panel Data ◽

Association Rules ◽

Activity Patterns ◽

Time Varying ◽

Diary Data ◽

Econometric Methods ◽

Before And After ◽

Scant Attention ◽

Activity Diary ◽

Daily Activity Patterns

The question of identifying temporal patterns in activity diary data has received only scant attention in the transportation literature, but interest is rapidly increasing. Most of the existing research uses well-known econometric methods to quantify change. Use of association rules to explore activity diary panel data, involving two waves, for possible stationary and time-varying patterns in activity-travel patterns is reported. The data for this analysis stem from the municipality of Voorhout in the Netherlands. Data were collected in 1997 and 1998 before and after opening of a new railway station. Results of the analysis indicate that specific household and individual attributes have a larger effect on daily activity patterns than others and that the effect of these attributes has significantly changed. Because changes in other sociodemographic attributes are almost nonexistent and activity patterns for communities are known to be stable, this study claims that the observed shifts in dependencies come from this new station.

Download Full-text