Multi-task Recurrent Neural Networks to Simultaneously Infer Mode and Purpose in GPS Trajectories
This study addresses the problem of travel behavior analysis for urban planners and transportation researchers, showing that the common assumption of multi-task learning superiority is not supported in this domain, making it an incremental contribution.
This research tackled the problem of inferring mode and purpose from GPS trajectories using multi-task learning, finding that multi-task learners did not significantly outperform single-task models, with the best multi-task Bi-GRU achieving F1-scores of 84.33% for mode and 78.28% for purpose, while single-task models reached 86.50% for mode and 77.38% for purpose.
Multi-task learning is assumed as a powerful inference method, specifically, where there is a considerable correlation between multiple tasks, predicting them in an unique framework may enhance prediction results. This research challenges this assumption by developing several single-task models to compare their results against multi-task learners to infer mode and purpose of trip from smartphone travel survey data collected as part of a smartphone-based travel survey. GPS trajectory data along with socio-demographics and destination-related characteristics are fed into a multi-input neural network framework to predict two outputs; mode and purpose. We deployed Recurrent Neural Networks (RNN) that are fed by sequential GPS trajectories. To process the socio-demographics and destination-related characteristics, another neural network, with different embedding and dense layers is used in parallel with RNN layers in a multi-input multi-output framework. The results are compared against the single-task learners that classify mode and purpose independently. We also investigate different RNN approaches such as Long-Short Term Memory (LSTM), Gated Recurrent Units (GRU) and Bi-directional Gated Recurrent Units (Bi-GRU). The best multi-task learner was a Bi-GRU model able to classify mode and purpose with an F1-measures of 84.33% and 78.28%, while the best single-task learner to infer mode of transport was a GRU model that achieved an F1-measure of 86.50%, and the best single-task Bi-GRU purpose detection model that reached an F1-measure of 77.38%. While there's an assumption of higher performance of multi-task over sing-task learners, the results of this study does not hold such an assumption and shows, in the context of mode and trip purpose inference from GPS trajectory data, a multi-task learning approach does not bring any considerable advantage over single-task learners.