Exploration and Prediction of the Elderly Travel Behavior Based on a Novel GR-GA-BP Hybrid Model

With the aging trend in megacities, travel behaviors of elderly have attracted much attention. Accurate prediction is a key link to meet traffic demand and public facilities’ optimization. The aim this paper was explore between characteristics variables daily activities elderly. Based on stratified sampling survey, internal relationship their behavior studied discussed work. A novel grey correlation degree–genetic algorithm–back propagation (GR-GA-BP) hybrid model proposed predict Then, degree module established used analyze individual behavior. results showed following: (1) Both times weekly trips (y1) average round-trip time (y2) were highly sensitive external environment, especially buses, subway stations, recreational facilities. size family less (2) Referring trips, MRE 23.12%, which 15.22% than baseline models. (3) In terms time, 7.13%, 14.00–69.41% lower (4) per week 3.5. summary, provides technical support for formulating policies facilitates configuration cities an society.