Personalized Landmark Sequence Recommendation Method using LSTM-based Network for Navigating in Large Hospitals

Litao Zhu,Georg Gartner,Yingxu Hou,Jie Shen

doi:10.5194/ica-abs-3-328-2021

Abstract

Personalized Landmark Sequence Recommendation Method using LSTM-based Network for Navigating in Large Hospitals

Highlights

Location-based behavior is influenced by different factors, such as user preferences (Sun et al, 2020), geographical information (Liu et al, 2020), temporal information (Li et al, 2017; Ying et al, 2017), and sequential information (Feng et al, 2018)
It is critical to incorporate various types of contextual information to improve the performance of location recommendations
Few studies of indoor location recommendations focus on the hospital navigation process

Summary

Introduction

Landmarks are defined as an entity distinct from its background, which can be used as reference points to describe the positions of nearby spaces and orient (Presson & Montello, 1988). Users’ wayfinding behavior in hospitals has complex Spatio-temporal sequence patterns. Location-based behavior is influenced by different factors, such as user preferences (Sun et al, 2020), geographical information (Liu et al, 2020), temporal information (Li et al, 2017; Ying et al, 2017), and sequential information (Feng et al, 2018). An indoor landmark is a location in indoor space and has contextual information about a specific place, service, facility, or event.

Objectives

Results

Conclusion