Online Change Detection for Energy-Efficient Mobile Crowdsensing

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

5 Citations (Scopus)
20 Downloads (Pure)

Abstract

Mobile crowdsensing is power hungry since it requires continuously and simultaneously sensing, processing and uploading fused data from various sensor types including motion sensors and environment sensors. Realizing that being able to pinpoint change points of contexts enables energy-efficient mobile crowdsensing, we modify histogram-based techniques to efficiently detect changes, which has less computational complexity and performs better than the conventional techniques. To evaluate our proposed technique, we conducted experiments on real audio databases comprising 200 sound tracks. We also compare our change detection with multivariate normal distribution and one-class support vector machine. The results show that our proposed technique is more practical for mobile crowdsensing. For example, we show that it is possible to save 80% resource compared to standard continuous sensing while remaining detection sensitivity above 95%. This work enables energy-efficient mobile crowdsensing applications by adapting to contexts.
Original languageEnglish
Title of host publicationMobile Web Information Systems
Subtitle of host publication11th International Conference on Mobile Web and Information Systems, MobiWIS 2014
EditorsIrfan Awan, Muhammad Younas, Xavier Franch, Carme Quer
Place of PublicationLondon
PublisherSpringer
Pages1-16
Number of pages16
ISBN (Electronic)978-3-319-10359-4
ISBN (Print)978-3-319-10358-7
DOIs
Publication statusPublished - 27 Aug 2014
Event11th International Conference on Mobile Web and Information Systems, MobiWIS 2014 - Barcelona, Spain
Duration: 27 Aug 201429 Aug 2014
Conference number: 11

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Verlag
Volume8640
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference11th International Conference on Mobile Web and Information Systems, MobiWIS 2014
Abbreviated titleMobiWIS
CountrySpain
CityBarcelona
Period27/08/1429/08/14

Fingerprint

Sensors
Normal distribution
Support vector machines
Computational complexity
Acoustic waves
Processing
Experiments

Keywords

  • CAES-PS: Pervasive Systems
  • EWI-25022
  • Energy Efficiency
  • Resource Constraints
  • METIS-309573
  • Change Detection
  • Adaptive Sensing
  • Computational Complexity
  • Mobile Crowdsensing
  • IR-92420

Cite this

Le Viet Duc, D. V., Scholten, J., & Havinga, P. J. M. (2014). Online Change Detection for Energy-Efficient Mobile Crowdsensing. In I. Awan, M. Younas, X. Franch, & C. Quer (Eds.), Mobile Web Information Systems: 11th International Conference on Mobile Web and Information Systems, MobiWIS 2014 (pp. 1-16). (Lecture Notes in Computer Science; Vol. 8640). London: Springer. https://doi.org/10.1007/978-3-319-10359-4_1
Le Viet Duc, Duc Viet ; Scholten, Johan ; Havinga, Paul J.M. / Online Change Detection for Energy-Efficient Mobile Crowdsensing. Mobile Web Information Systems: 11th International Conference on Mobile Web and Information Systems, MobiWIS 2014. editor / Irfan Awan ; Muhammad Younas ; Xavier Franch ; Carme Quer. London : Springer, 2014. pp. 1-16 (Lecture Notes in Computer Science).
@inproceedings{e97381c660ba4773a0560a04ac3c8d6b,
title = "Online Change Detection for Energy-Efficient Mobile Crowdsensing",
abstract = "Mobile crowdsensing is power hungry since it requires continuously and simultaneously sensing, processing and uploading fused data from various sensor types including motion sensors and environment sensors. Realizing that being able to pinpoint change points of contexts enables energy-efficient mobile crowdsensing, we modify histogram-based techniques to efficiently detect changes, which has less computational complexity and performs better than the conventional techniques. To evaluate our proposed technique, we conducted experiments on real audio databases comprising 200 sound tracks. We also compare our change detection with multivariate normal distribution and one-class support vector machine. The results show that our proposed technique is more practical for mobile crowdsensing. For example, we show that it is possible to save 80{\%} resource compared to standard continuous sensing while remaining detection sensitivity above 95{\%}. This work enables energy-efficient mobile crowdsensing applications by adapting to contexts.",
keywords = "CAES-PS: Pervasive Systems, EWI-25022, Energy Efficiency, Resource Constraints, METIS-309573, Change Detection, Adaptive Sensing, Computational Complexity, Mobile Crowdsensing, IR-92420",
author = "{Le Viet Duc}, {Duc Viet} and Johan Scholten and Havinga, {Paul J.M.}",
note = "Best Paper Award",
year = "2014",
month = "8",
day = "27",
doi = "10.1007/978-3-319-10359-4_1",
language = "English",
isbn = "978-3-319-10358-7",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "1--16",
editor = "Irfan Awan and Muhammad Younas and Xavier Franch and Carme Quer",
booktitle = "Mobile Web Information Systems",

}

Le Viet Duc, DV, Scholten, J & Havinga, PJM 2014, Online Change Detection for Energy-Efficient Mobile Crowdsensing. in I Awan, M Younas, X Franch & C Quer (eds), Mobile Web Information Systems: 11th International Conference on Mobile Web and Information Systems, MobiWIS 2014. Lecture Notes in Computer Science, vol. 8640, Springer, London, pp. 1-16, 11th International Conference on Mobile Web and Information Systems, MobiWIS 2014, Barcelona, Spain, 27/08/14. https://doi.org/10.1007/978-3-319-10359-4_1

Online Change Detection for Energy-Efficient Mobile Crowdsensing. / Le Viet Duc, Duc Viet; Scholten, Johan; Havinga, Paul J.M.

Mobile Web Information Systems: 11th International Conference on Mobile Web and Information Systems, MobiWIS 2014. ed. / Irfan Awan; Muhammad Younas; Xavier Franch; Carme Quer. London : Springer, 2014. p. 1-16 (Lecture Notes in Computer Science; Vol. 8640).

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Online Change Detection for Energy-Efficient Mobile Crowdsensing

AU - Le Viet Duc, Duc Viet

AU - Scholten, Johan

AU - Havinga, Paul J.M.

N1 - Best Paper Award

PY - 2014/8/27

Y1 - 2014/8/27

N2 - Mobile crowdsensing is power hungry since it requires continuously and simultaneously sensing, processing and uploading fused data from various sensor types including motion sensors and environment sensors. Realizing that being able to pinpoint change points of contexts enables energy-efficient mobile crowdsensing, we modify histogram-based techniques to efficiently detect changes, which has less computational complexity and performs better than the conventional techniques. To evaluate our proposed technique, we conducted experiments on real audio databases comprising 200 sound tracks. We also compare our change detection with multivariate normal distribution and one-class support vector machine. The results show that our proposed technique is more practical for mobile crowdsensing. For example, we show that it is possible to save 80% resource compared to standard continuous sensing while remaining detection sensitivity above 95%. This work enables energy-efficient mobile crowdsensing applications by adapting to contexts.

AB - Mobile crowdsensing is power hungry since it requires continuously and simultaneously sensing, processing and uploading fused data from various sensor types including motion sensors and environment sensors. Realizing that being able to pinpoint change points of contexts enables energy-efficient mobile crowdsensing, we modify histogram-based techniques to efficiently detect changes, which has less computational complexity and performs better than the conventional techniques. To evaluate our proposed technique, we conducted experiments on real audio databases comprising 200 sound tracks. We also compare our change detection with multivariate normal distribution and one-class support vector machine. The results show that our proposed technique is more practical for mobile crowdsensing. For example, we show that it is possible to save 80% resource compared to standard continuous sensing while remaining detection sensitivity above 95%. This work enables energy-efficient mobile crowdsensing applications by adapting to contexts.

KW - CAES-PS: Pervasive Systems

KW - EWI-25022

KW - Energy Efficiency

KW - Resource Constraints

KW - METIS-309573

KW - Change Detection

KW - Adaptive Sensing

KW - Computational Complexity

KW - Mobile Crowdsensing

KW - IR-92420

U2 - 10.1007/978-3-319-10359-4_1

DO - 10.1007/978-3-319-10359-4_1

M3 - Conference contribution

SN - 978-3-319-10358-7

T3 - Lecture Notes in Computer Science

SP - 1

EP - 16

BT - Mobile Web Information Systems

A2 - Awan, Irfan

A2 - Younas, Muhammad

A2 - Franch, Xavier

A2 - Quer, Carme

PB - Springer

CY - London

ER -

Le Viet Duc DV, Scholten J, Havinga PJM. Online Change Detection for Energy-Efficient Mobile Crowdsensing. In Awan I, Younas M, Franch X, Quer C, editors, Mobile Web Information Systems: 11th International Conference on Mobile Web and Information Systems, MobiWIS 2014. London: Springer. 2014. p. 1-16. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-319-10359-4_1