Detecting activity type from GPS traces using spatial and temporal information

Abstract

Detecting activity types from GPS traces has been important topic in travel surveys. Compared to inferring transport mode, existing methods are still relatively inaccurate in detecting activity types due to the simplicity of their assumptions and/or lack of background information. To reduce this gap, this paper reports the results of an endeavour to infer activity type by incorporating both spatial information and aggregated temporal information. Three machine learning algorithms, Bayesian belief network, decision tree and random forest, are used to investigate the performance of these approaches in detecting activity types. The test is based on GPS traces and prompted recall data, collected in the Rijnmond region, The Netherlands. Results show that the random forest model has the highest accuracy. The model incorporating spatial and temporal information can predict activity types with an accuracy of 96.8% for the used dataset. These findings are expected to benefit research on the use of GPS technology to collect activity-travel diary data.

A systematic review of machine learning in logistics and supply chain management: current trends and future directions

“…This authenticates an enhanced concentration amongst current and future researchers into all four main focused areas, especially detection. Feng and Timmermans (2015), used learning algorithms, Bayesian belief network, DT and random forest to detect activity types from GPS traces. Carbonneau et al (2008) concluded in their research that the neural network and support vector machines show the best…”

“…However, there is as yet no highlight on which ML techniques or models should be best adopted to undertake anomaly detection in the field of LSCM. One of the few papers with a focus on detection was conducted by Feng and Timmermans (2015) which was written about the incorporation of three ML algorithms, namely Bayesian belief network,decision tree and random forest to detect activity types from GPS traces. The difference in main areas of focus resembles the imbalance in the popularity of the exploited ML techniques.…”