Evaluating the Potential To Predict Activity Types from GPS and GIS Data

Abstract

Current travel forecasting models have had limited sensitivity to policy decisions. One of the primary challenges is limitations in the primary data source, the daily travel diary (e.g., accuracy and sample size). The daily travel diary has known problems with underreporting, time inaccuracies, respondent fatigue, and other human errors. The Global Positioning System (GPS) has been recently used to supplement the daily travel diary. As GPS becomes more accurate, reliable, and cost effective, could it entirely replace the daily travel diary? GPS devices can be used to record times and locations of each activity and the trips in between. To use GPS data to replace the daily travel diary one needs to predict the activity types. The goal of this research is to test the feasibility of a model that predicts activity types based solely on: (1) GPS data from devices placed on the individual’s vehicle or person, (2) Land use data, such as location type, expressed as GIS data, and (3) Individual and household demographic data. This report summarizes models developed with surrogate geo-coded data using discriminant analysis and classification/ regression trees. The models predicted in which of 26 different activity types the individual participated. Accuracy for the best model was: (1) 63% for out of home activities (2) 79% when including the “at home” activity (3) 72% considering that GPS data may miss as much as 10% of trips Since travel diaries have known underreporting problems as high as 30%, GPS data with the model developed seems competitive.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 46 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.