Detecting Mobile Crowdsensing Context in the Wild - Archive ouverte HAL Access content directly
Conference Papers Year : 2019

Detecting Mobile Crowdsensing Context in the Wild

(1) , (1) , (1) , (1) , (1)
Rachit Agarwal
Shaan Chopra
  • Function : Author
  • PersonId : 1047491
Vassilis Christophides
Nikolaos Georgantas
  • Function : Author
  • PersonId : 868414
Valérie Issarny
  • Function : Author
  • PersonId : 833417


Understanding the sensing context of raw data is crucial for assessing the quality of large crowdsourced spatio-temporal datasets and supporting context-augmented personal trajectories. Detecting sensing contexts in the wild is a challenging task and requires features from smartphone sensors that are not always available. In this paper, we propose three heuristic algorithms for detecting sensing contexts such as in/out-pocket, under/over-ground, and in/out-door for crowdsourced spatio-temporal datasets. These are unsupervised binary classifiers with a small memory footprint and execution time. Using a segment of the Ambiciti real dataset-a feature-limited crowdsourced dataset-we report that our algorithms perform equally well in terms of balanced accuracy (within 4.3%) when compared to machine learning (ML) models reported by an AutoML tool.
Fichier principal
Vignette du fichier
main.pdf (273.8 Ko) Télécharger le fichier
Origin : Explicit agreement for this submission

Dates and versions

hal-02151434 , version 1 (11-06-2019)


  • HAL Id : hal-02151434 , version 1


Rachit Agarwal, Shaan Chopra, Vassilis Christophides, Nikolaos Georgantas, Valérie Issarny. Detecting Mobile Crowdsensing Context in the Wild. 20th IEEE International Conference on Mobile Data Management (MDM) 2019, Jun 2019, Hong Kong, Hong Kong SAR China. ⟨hal-02151434⟩


91 View
282 Download


Gmail Facebook Twitter LinkedIn More