English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Passenger flow allows the study of users' behavior through the public networkand assists in designing new facilities and services. This flow is observedthrough interactions between passengers and infrastructure. For this task,Bluetooth technology and smartphones represent the ideal solution. The lattercomponent allows users' identification, authentication, and billing, while theformer allows short-range implicit interactions, device-to-device. To assessthe potential of such a use case, we need to verify how robust Bluetooth signaland related machine learning (ML) classifiers are against the noise ofrealistic contexts. Therefore, we model binary passenger states with respect toa public vehicle, where one can either be-in or be-out (BIBO). The BIBO labelidentifies a fundamental building block of continuously-valued passenger flow.This paper describes the Human-Computer interaction experimental setting in asemi-controlled environment, which involves: two autonomous vehicles operatingon two routes, serving three bus stops and eighteen users, as well as aproprietary smartphone-Bluetooth sensing platform. The resulting datasetincludes multiple sensors' measurements of the same event and two ground-truthlevels, the first being validation by participants, the second by threevideo-cameras surveilling buses and track. We performed a Monte-Carlosimulation of labels-flip to emulate human errors in the labeling process, asis known to happen in smartphone surveys; next we used such flipped labels forsupervised training of ML classifiers. The impact of errors on modelperformance bias can be large. Results show ML tolerance to label flips causedby human or machine errors up to 30%.

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