Sensor-Based Approach for Predicting Departure Time of Smartphone Users

Ron Biton; Gilad Katz; Asaf Shabtai

doi:10.1109/MobileSoft.2015.37

Sensor-Based Approach for Predicting Departure Time of Smartphone Users

Ron Biton
, Gilad Katz
, Asaf Shabtai

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

While location prediction of smartphone users has made great strides in recent years, a major challenge remains. As users spend the majority of their time is several fixed locations (home, work), existing algorithms are unable to identify the exact time in which a person is likely to depart from one place to another. In this work we present a sensor-based approach designed to predict the departure time of users. By using location and accelerometer sensors we were able to train a generic classification model that is able to predict whether the user will stay put or move to a different location with true positive rate of 0.73 and false positive rate of 0.3.

Original language	American English
Title of host publication	Proceedings - 2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015
Pages	146-147
Number of pages	2
ISBN (Electronic)	9781479919345
DOIs	https://doi.org/10.1109/MobileSoft.2015.37
State	Published - 28 Sep 2015
Event	2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015 - Florence, Italy Duration: 16 May 2015 → 17 May 2015

Publication series

Name	Proceedings - 2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015

Conference

Conference	2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015
Country/Territory	Italy
City	Florence
Period	16/05/15 → 17/05/15

Keywords

Location Prediction
Machine Learning

ASJC Scopus subject areas

Computer Networks and Communications
Software

Access to Document

10.1109/MobileSoft.2015.37

Cite this

Biton, R., Katz, G., & Shabtai, A. (2015). Sensor-Based Approach for Predicting Departure Time of Smartphone Users. In Proceedings - 2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015 (pp. 146-147). Article 7283050 (Proceedings - 2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015). https://doi.org/10.1109/MobileSoft.2015.37

@inproceedings{1b92d48a7b60440bb104b7fe42692316,

title = "Sensor-Based Approach for Predicting Departure Time of Smartphone Users",

abstract = "While location prediction of smartphone users has made great strides in recent years, a major challenge remains. As users spend the majority of their time is several fixed locations (home, work), existing algorithms are unable to identify the exact time in which a person is likely to depart from one place to another. In this work we present a sensor-based approach designed to predict the departure time of users. By using location and accelerometer sensors we were able to train a generic classification model that is able to predict whether the user will stay put or move to a different location with true positive rate of 0.73 and false positive rate of 0.3.",

keywords = "Location Prediction, Machine Learning",

author = "Ron Biton and Gilad Katz and Asaf Shabtai",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015 ; Conference date: 16-05-2015 Through 17-05-2015",

year = "2015",

month = sep,

day = "28",

doi = "10.1109/MobileSoft.2015.37",

language = "American English",

series = "Proceedings - 2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015",

pages = "146--147",

booktitle = "Proceedings - 2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015",

}

Biton, R, Katz, G & Shabtai, A 2015, Sensor-Based Approach for Predicting Departure Time of Smartphone Users. in Proceedings - 2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015., 7283050, Proceedings - 2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015, pp. 146-147, 2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015, Florence, Italy, 16/05/15. https://doi.org/10.1109/MobileSoft.2015.37

Sensor-Based Approach for Predicting Departure Time of Smartphone Users. / Biton, Ron; Katz, Gilad ; Shabtai, Asaf.
Proceedings - 2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015. 2015. p. 146-147 7283050 (Proceedings - 2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Sensor-Based Approach for Predicting Departure Time of Smartphone Users

AU - Biton, Ron

AU - Katz, Gilad

AU - Shabtai, Asaf

PY - 2015/9/28

Y1 - 2015/9/28

N2 - While location prediction of smartphone users has made great strides in recent years, a major challenge remains. As users spend the majority of their time is several fixed locations (home, work), existing algorithms are unable to identify the exact time in which a person is likely to depart from one place to another. In this work we present a sensor-based approach designed to predict the departure time of users. By using location and accelerometer sensors we were able to train a generic classification model that is able to predict whether the user will stay put or move to a different location with true positive rate of 0.73 and false positive rate of 0.3.

AB - While location prediction of smartphone users has made great strides in recent years, a major challenge remains. As users spend the majority of their time is several fixed locations (home, work), existing algorithms are unable to identify the exact time in which a person is likely to depart from one place to another. In this work we present a sensor-based approach designed to predict the departure time of users. By using location and accelerometer sensors we were able to train a generic classification model that is able to predict whether the user will stay put or move to a different location with true positive rate of 0.73 and false positive rate of 0.3.

KW - Location Prediction

KW - Machine Learning

UR - https://www.scopus.com/pages/publications/84961120912

U2 - 10.1109/MobileSoft.2015.37

DO - 10.1109/MobileSoft.2015.37

M3 - Conference contribution

T3 - Proceedings - 2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015

SP - 146

EP - 147

BT - Proceedings - 2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015

T2 - 2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015

Y2 - 16 May 2015 through 17 May 2015

ER -

Biton R, Katz G , Shabtai A. Sensor-Based Approach for Predicting Departure Time of Smartphone Users. In Proceedings - 2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015. 2015. p. 146-147. 7283050. (Proceedings - 2nd ACM International Conference on Mobile Software Engineering and Systems, MOBILESoft 2015). doi: 10.1109/MobileSoft.2015.37

Sensor-Based Approach for Predicting Departure Time of Smartphone Users

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this