Open Smartphone Data for Structured Mobility and Utilization Analysis in Ubiquitous Systems

by   Katharina Morik, et al.

The development and evaluation of new data mining methods for ubiquitous environments and systems requires real data that were collected from real users. In this work, we present an open smartphone utilization and mobility data set that was generated with several devices and participants during a 4-month study. A particularity of this data set is the inclusion of low-level operating system data. Additionally to the description of the data, we also describe the process of collection and the privacy measures we applied. To demonstrate the utility of the data, we evaluate the quality of generative spatio-temporal models for “apps” and network cells, since these are required as a building block in general predictions of the resource consumption of ubiquitous systems.



There are no comments yet.


page 7


Deep Learning for Spatio-Temporal Data Mining: A Survey

With the fast development of various positioning techniques such as Glob...

Context Data Categories and Privacy Model for Mobile Data Collection Apps

Context-aware applications stemming from diverse fields like mobile heal...

Generating synthetic mobility data for a realistic population with RNNs to improve utility and privacy

Location data collected from mobile devices represent mobility behaviors...

Spatio-Temporal Data Mining: A Survey of Problems and Methods

Large volumes of spatio-temporal data are increasingly collected and stu...

Are PETs (Privacy Enhancing Technologies) Giving Protection for Smartphones? – A Case Study

With smartphone technologies enhanced way of interacting with the world ...

Monitoring Depression in Bipolar Disorder using Circadian Measures from Smartphone Accelerometers

Current management of bipolar disorder relies on self-reported questionn...

Mining the Air -- for Research in Social Science and Networking Measurement

Smartphone apps provide a vitally important opportunity for monitoring h...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.