Elevator, Escalator, or Neither? Classifying Conveyor State Using Smartphone under Arbitrary Pedestrian Behavior

TL;DR

This paper introduces ELESON, a deep learning method that accurately classifies elevator, escalator, or neither states using smartphone inertial sensors, regardless of pedestrian behavior, enabling robust indoor navigation applications.

Contribution

ELESON is a novel lightweight deep-learning approach that disentangles conveyor state signals from pedestrian behaviors using causal decomposition and adversarial learning.

Findings

Achieves over 0.9 F1 score in classification accuracy

Demonstrates high confidence discriminability with 0.81 AUROC

Operates efficiently on standard smartphones

Abstract

Knowing a pedestrian's conveyor state of ''elevator,'' ''escalator,'' or ''neither'' is fundamental to many applications such as indoor navigation and people flow management. Previous studies on classifying the conveyor state often rely on specially designed body-worn sensors or make strong assumptions on pedestrian behaviors, which greatly strangles their deployability. To overcome this, we study the classification problem under arbitrary pedestrian behaviors using the inertial navigation system (INS) of the commonly available smartphones (including accelerometer, gyroscope, and magnetometer). This problem is challenging, because the INS signals of the conveyor states are entangled by the arbitrary and diverse pedestrian behaviors. We propose ELESON, a novel and lightweight deep-learning approach that uses phone INS to classify a pedestrian to elevator, escalator, or neither. Using causal decomposition and adversarial learning, ELESON extracts the motion and magnetic features of conveyor state independent of pedestrian behavior, based on which it estimates the state confidence by means of an evidential classifier. We curate a large and diverse dataset with 36,420 instances of pedestrians randomly taking elevators and escalators under arbitrary unknown behaviors. Our extensive experiments show that ELESON is robust against pedestrian behavior, achieving a high accuracy of over 0.9 in F1 score, strong confidence discriminability of 0.81 in AUROC (Area Under the Receiver Operating Characteristics), and low computational and memory requirements fit for common smartphone deployment.