A hybrid of neuro-fuzzy inference system and hidden Markov Model for activity-based mobility modeling of cellphone users

The aim of this paper is to develop an activity-based travel demand model by receiving cellular network data. Our contribution is to model the uncertainty of human behaviors and also the ambiguity in features affecting users' activities. We used probabilities to model the first aspect and fuzzy theory to treat with the second; therefore, a hybrid model is proposed based on the Hidden Markov Model (HMM) and Fuzzy Inference System (FIS) such that FIS is used in the emission model of HMM. To show the efficiency of this model, we applied the model to the data collected by Irancell operator and validated the results with four different data sources; labeled data collected from volunteers, ground truth data labeled by an expert, activity-based number of trips generated from/attracted to different regions and reported traffic volume of highways. We have shown that the activity recognition accuracy of the model is 83% and an average error of 5% is obtained when comparing the statistics of the model generated activity plans and the corresponding statistics provided in reports. Generated activity plans are also converted to traffic volumes on transportation network links through MATSIM simulation software and the promising R2 value of 0.83 is observed.

Automated summary

This paper aims to develop an activity-based travel demand model using cellular network data. The model incorporates probabilities and fuzzy theory to account for uncertainties in human behaviors and ambiguity in features affecting users' activities. Results show high accuracy in activity recognition and promising efficiency in converting activity plans to traffic volumes on transportation network links.