TOYOTA - Analysis of individual mobility data to understand the driving patterns of users (DIT.AD004.108)

Area tematica

Ingegneria, ICT e tecnologie per l'energia e i trasporti

Area progettuale

Struttura responsabile del progetto di ricerca

Istituto di scienza e tecnologie dell'informazione "Alessandro Faedo" (ISTI)

Responsabile di progetto

MIRCO NANNI
Telefono: 0506212843
E-mail: mirco.nanni@isti.cnr.it

Abstract

The project objective is the analysis of individual mobility data to understand the driving patterns of users. (1) Spatial driving patterns analysis: (a) (Spatial) Where do users drive: start, end and intermediate stops (b) (Spatial) What are the main locations for each driver (Home, work, school, etc.) (c) (Spatial) Which locations are visited after being in a particular location, with which frequency/probability (d) (Spatial) What routes they follow (e) (Temporal) When do people drive (probability distributions): start, end, travel durations, stay durations, including confidence measures for temporal predictability on each location. (f) (Temporal) Flexibility measure, expressed as the amount of time the user spends staying at home or work, provided both as overall aggregate and per location type (home and work). (2) Prediction and simulation: (a) (Position probabilities) What is the probability of being at a certain location according to the time of the day and the day of the week? (b) (One-day prediction) For each user, predict the most likely mobility of a typical day. (c) (Multiple-days simulation) For each user, simulate a realistic mobility for several consecutive days.

Obiettivi

The project objective is the analysis of individual mobility data to understand the driving patterns of users. (1) Spatial driving patterns analysis: (a) (Spatial) Where do users drive: start, end and intermediate stops (b) (Spatial) What are the main locations for each driver (Home, work, school, etc.) (c) (Spatial) Which locations are visited after being in a particular location, with which frequency/probability (d) (Spatial) What routes they follow (e) (Temporal) When do people drive (probability distributions): start, end, travel durations, stay durations, including confidence measures for temporal predictability on each location. (f) (Temporal) Flexibility measure, expressed as the amount of time the user spends staying at home or work, provided both as overall aggregate and per location type (home and work). (2) Prediction and simulation: (a) (Position probabilities) What is the probability of being at a certain location according to the time of the day and the day of the week? (b) (One-day prediction) For each user, predict the most likely mobility of a typical day. (c) (Multiple-days simulation) For each user, simulate a realistic mobility for several consecutive days.

Data inizio attività

25/02/2020

Parole chiave

mobility data, driving patterns

Ultimo aggiornamento: 03/01/2025