LIPS: Lifestyle learning via mobile phone sensing

Xiang Sheng; Jian Tang; Jing Wang; Teng Li; Guoliang Xue; Dejun Yang

doi:10.1109/GLOCOM.2016.7841959

LIPS: Lifestyle learning via mobile phone sensing

Xiang Sheng, Jian Tang, Jing Wang, Teng Li, Guoliang Xue, Dejun Yang

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

2 Scopus citations

Abstract

In this paper, we propose to learn LIfestyles of mobile users via mobile Phone Sensing (LIPS), and we develop a system and algorithms to realize this idea. First, we present the workflow and architecture of our system, LIPS. Combining both unsupervised and supervised learning, we propose a hybrid scheme for lifestyle learning, which consists of two parts: characterization and prediction. Specifically, we present a two-stage algorithm to characterize the lifestyle of a mobile user using Places of Interest (PoIs), which leverages two different algorithms for coarse- grained and fine-grained clustering in two stages respectively. Based on discovered PoIs, we present a method to build a model to predict his/her future activities using a supervised classification algorithm. In addition, we present an adaptive sampling algorithm for improving energy efficiency, which leverages both the discovered PoIs and the lifestyle model for adaptively controlling the sampling rate. We implemented the proposed system and algorithms based on the Android platform. We have validated and evaluated LIPS via extensive field tests carried out for over 1.5 months in 6 cities of USA. The experimental results show that LIPS can 1) well discover PoIs of mobile users, 2) precisely predict their future activities, and 3) achieve significant energy savings (compared to periodic sampling).

Original language	English (US)
Title of host publication	2016 IEEE Global Communications Conference, GLOBECOM 2016 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781509013289
DOIs	https://doi.org/10.1109/GLOCOM.2016.7841959
State	Published - Feb 2 2017
Event	59th IEEE Global Communications Conference, GLOBECOM 2016 - Washington, United States Duration: Dec 4 2016 → Dec 8 2016

Other

Other	59th IEEE Global Communications Conference, GLOBECOM 2016
Country	United States
City	Washington
Period	12/4/16 → 12/8/16

Keywords

Energy Efficiency
Human-Centric Sensing
Mobile Computing
Mobile Phone Sensing

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Networks and Communications
Hardware and Architecture
Safety, Risk, Reliability and Quality

Access to Document

10.1109/GLOCOM.2016.7841959

Fingerprint Dive into the research topics of 'LIPS: Lifestyle learning via mobile phone sensing'. Together they form a unique fingerprint.

Cite this

Sheng, X, Tang, J, Wang, J, Li, T, Xue, G & Yang, D 2017, LIPS: Lifestyle learning via mobile phone sensing. in 2016 IEEE Global Communications Conference, GLOBECOM 2016 - Proceedings., 7841959, Institute of Electrical and Electronics Engineers Inc., 59th IEEE Global Communications Conference, GLOBECOM 2016, Washington, United States, 12/4/16. https://doi.org/10.1109/GLOCOM.2016.7841959

@inproceedings{2e731b72c8a846fa9b5a19b75fffabd4,

title = "LIPS: Lifestyle learning via mobile phone sensing",

abstract = "In this paper, we propose to learn LIfestyles of mobile users via mobile Phone Sensing (LIPS), and we develop a system and algorithms to realize this idea. First, we present the workflow and architecture of our system, LIPS. Combining both unsupervised and supervised learning, we propose a hybrid scheme for lifestyle learning, which consists of two parts: characterization and prediction. Specifically, we present a two-stage algorithm to characterize the lifestyle of a mobile user using Places of Interest (PoIs), which leverages two different algorithms for coarse- grained and fine-grained clustering in two stages respectively. Based on discovered PoIs, we present a method to build a model to predict his/her future activities using a supervised classification algorithm. In addition, we present an adaptive sampling algorithm for improving energy efficiency, which leverages both the discovered PoIs and the lifestyle model for adaptively controlling the sampling rate. We implemented the proposed system and algorithms based on the Android platform. We have validated and evaluated LIPS via extensive field tests carried out for over 1.5 months in 6 cities of USA. The experimental results show that LIPS can 1) well discover PoIs of mobile users, 2) precisely predict their future activities, and 3) achieve significant energy savings (compared to periodic sampling).",

keywords = "Energy Efficiency, Human-Centric Sensing, Mobile Computing, Mobile Phone Sensing",

author = "Xiang Sheng and Jian Tang and Jing Wang and Teng Li and Guoliang Xue and Dejun Yang",

year = "2017",

month = feb,

day = "2",

doi = "10.1109/GLOCOM.2016.7841959",

language = "English (US)",

booktitle = "2016 IEEE Global Communications Conference, GLOBECOM 2016 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "59th IEEE Global Communications Conference, GLOBECOM 2016 ; Conference date: 04-12-2016 Through 08-12-2016",

}

TY - GEN

T1 - LIPS

T2 - 59th IEEE Global Communications Conference, GLOBECOM 2016

AU - Sheng, Xiang

AU - Tang, Jian

AU - Wang, Jing

AU - Li, Teng

AU - Xue, Guoliang

AU - Yang, Dejun

PY - 2017/2/2

Y1 - 2017/2/2

N2 - In this paper, we propose to learn LIfestyles of mobile users via mobile Phone Sensing (LIPS), and we develop a system and algorithms to realize this idea. First, we present the workflow and architecture of our system, LIPS. Combining both unsupervised and supervised learning, we propose a hybrid scheme for lifestyle learning, which consists of two parts: characterization and prediction. Specifically, we present a two-stage algorithm to characterize the lifestyle of a mobile user using Places of Interest (PoIs), which leverages two different algorithms for coarse- grained and fine-grained clustering in two stages respectively. Based on discovered PoIs, we present a method to build a model to predict his/her future activities using a supervised classification algorithm. In addition, we present an adaptive sampling algorithm for improving energy efficiency, which leverages both the discovered PoIs and the lifestyle model for adaptively controlling the sampling rate. We implemented the proposed system and algorithms based on the Android platform. We have validated and evaluated LIPS via extensive field tests carried out for over 1.5 months in 6 cities of USA. The experimental results show that LIPS can 1) well discover PoIs of mobile users, 2) precisely predict their future activities, and 3) achieve significant energy savings (compared to periodic sampling).

AB - In this paper, we propose to learn LIfestyles of mobile users via mobile Phone Sensing (LIPS), and we develop a system and algorithms to realize this idea. First, we present the workflow and architecture of our system, LIPS. Combining both unsupervised and supervised learning, we propose a hybrid scheme for lifestyle learning, which consists of two parts: characterization and prediction. Specifically, we present a two-stage algorithm to characterize the lifestyle of a mobile user using Places of Interest (PoIs), which leverages two different algorithms for coarse- grained and fine-grained clustering in two stages respectively. Based on discovered PoIs, we present a method to build a model to predict his/her future activities using a supervised classification algorithm. In addition, we present an adaptive sampling algorithm for improving energy efficiency, which leverages both the discovered PoIs and the lifestyle model for adaptively controlling the sampling rate. We implemented the proposed system and algorithms based on the Android platform. We have validated and evaluated LIPS via extensive field tests carried out for over 1.5 months in 6 cities of USA. The experimental results show that LIPS can 1) well discover PoIs of mobile users, 2) precisely predict their future activities, and 3) achieve significant energy savings (compared to periodic sampling).

KW - Energy Efficiency

KW - Human-Centric Sensing

KW - Mobile Computing

KW - Mobile Phone Sensing

UR - http://www.scopus.com/inward/record.url?scp=85015385843&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015385843&partnerID=8YFLogxK

U2 - 10.1109/GLOCOM.2016.7841959

DO - 10.1109/GLOCOM.2016.7841959

M3 - Conference contribution

AN - SCOPUS:85015385843

BT - 2016 IEEE Global Communications Conference, GLOBECOM 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 4 December 2016 through 8 December 2016

ER -