"Is not the truth the truth?": Analyzing the Impact of User Validations for Bus In/Out Detection in Smartphone-based Surveys

TL;DR

This study evaluates Bluetooth-based machine learning classifiers for detecting passenger in/out states on buses, analyzing robustness against human and machine labeling errors in a semi-controlled experiment.

Contribution

It introduces a novel dataset with multi-sensor measurements and ground-truth validation, and assesses ML classifier robustness to label noise in passenger flow detection.

Findings

ML classifiers tolerate up to 30% label noise

Human validation errors significantly impact model performance

Bluetooth signals combined with ML can reliably detect passenger states

Abstract

Passenger flow allows the study of users' behavior through the public network and assists in designing new facilities and services. This flow is observed through interactions between passengers and infrastructure. For this task, Bluetooth technology and smartphones represent the ideal solution. The latter component allows users' identification, authentication, and billing, while the former allows short-range implicit interactions, device-to-device. To assess the potential of such a use case, we need to verify how robust Bluetooth signal and related machine learning (ML) classifiers are against the noise of realistic contexts. Therefore, we model binary passenger states with respect to a public vehicle, where one can either be-in or be-out (BIBO). The BIBO label identifies a fundamental building block of continuously-valued passenger flow. This paper describes the Human-Computer interaction experimental setting in a semi-controlled environment, which involves: two autonomous vehicles operating on two routes, serving three bus stops and eighteen users, as well as a proprietary smartphone-Bluetooth sensing platform. The resulting dataset includes multiple sensors' measurements of the same event and two ground-truth levels, the first being validation by participants, the second by three video-cameras surveilling buses and track. We performed a Monte-Carlo simulation of labels-flip to emulate human errors in the labeling process, as is known to happen in smartphone surveys; next we used such flipped labels for supervised training of ML classifiers. The impact of errors on model performance bias can be large. Results show ML tolerance to label flips caused by human or machine errors up to 30%.