An Approach to Modeling Call Response Behavior on Mobile Phones Based on Multi-Dimensional Contexts

Iqbal H. Sarker, Muhammad Ashad Kabir, Alan Colman, Jun Han

Research output: Book chapter/Published conference paperConference paper

4 Citations (Scopus)

Abstract

Due to the popularity of context-aware computing and the rapid growth of the smart phone devices, modeling an individual's phone call response behavior may assist them in their daily activities for managing call interruptions. A key step of such modeling is to discovering call response behavioral rules based on multi-dimensional contexts related to individual's behavior. Currently, researchers use classification rule learners for modeling individual's mobile phone behavior. However, the problem is that such learning techniques produce only rules that include maximal number of contexts albeit ordered by relevance. This results in many rules with low-reliability that decrease the accuracy of the modeling approach. In this paper, we propose an approach (Tmodel) to modeling individual's phone call response behavior utilizing mobile phone data. This approach produces not only general rules that capture individual's behavior at a particular level of confidence with a minimal number of contexts, but also produce rules that express specific exceptions to the general rules when more context-dimensions are taken into account. Experimental evaluation shows that our approach outperforms existing approaches to modelling individual's phone call response behavior based on multidimensional contexts.
Original languageEnglish
Title of host publicationProceedings of the 2017 IEEE/ACM 4th International Conference on Mobile Software Engineering and Systems (MOBILESoft 2017)
Place of PublicationUnited States
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages91-95
Number of pages5
ISBN (Electronic)9781538626696
DOIs
Publication statusPublished - 11 Jul 2017
Event4th IEEE/ACM International Conference on Mobile Software Engineering and Systems: MOBILESoft 2017 - Pontificia Universidad Católica Argentina (UCA), Buenos Aires, Argentina
Duration: 22 May 201723 May 2017
http://mobilesoftconf.org/2017/ (Conference website)
https://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7961439 (Conference proceedings)

Conference

Conference4th IEEE/ACM International Conference on Mobile Software Engineering and Systems
CountryArgentina
CityBuenos Aires
Period22/05/1723/05/17
OtherIn recent years, the massive increase in the use of mobile applications has greatly influenced the way people go about their daily life. The number of available mobile applications has grown enormously since the establishment of app stores and marketplaces that enable users to download and seamlessly install apps. Mobile platforms are rapidly changing and include diverse capabilities such as GPS, cameras, several wireless communications (WLAN, 4G, RFID etc), a variety of on-device memory and disk capacities, and various sensors.

Innovative mobile services and exciting mobile applications are emerging as a result of the ingenious use of these technologies. Consequently, the development of mobile applications has also been growing at a fast pace, presenting new challenges to Software Engineering. Developing versatile and robust mobile applications requires formally grounded methods, as well as advanced practices and tools.

MOBILESoft provides a working conference-style forum for the discussion and presentation of innovative contributions to the research and practice of the design, development, validation, execution, and evolution of mobile applications.
Internet address

Fingerprint

Mobile phones

Cite this

Sarker, I. H., Kabir, M. A., Colman, A., & Han, J. (2017). An Approach to Modeling Call Response Behavior on Mobile Phones Based on Multi-Dimensional Contexts. In Proceedings of the 2017 IEEE/ACM 4th International Conference on Mobile Software Engineering and Systems (MOBILESoft 2017) (pp. 91-95). [7972722] United States: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/MOBILESoft.2017.38
Sarker, Iqbal H. ; Kabir, Muhammad Ashad ; Colman, Alan ; Han, Jun. / An Approach to Modeling Call Response Behavior on Mobile Phones Based on Multi-Dimensional Contexts. Proceedings of the 2017 IEEE/ACM 4th International Conference on Mobile Software Engineering and Systems (MOBILESoft 2017). United States : IEEE, Institute of Electrical and Electronics Engineers, 2017. pp. 91-95
@inproceedings{e8c7bb8f9ca94b278055fd4edcd07772,
title = "An Approach to Modeling Call Response Behavior on Mobile Phones Based on Multi-Dimensional Contexts",
abstract = "Due to the popularity of context-aware computing and the rapid growth of the smart phone devices, modeling an individual's phone call response behavior may assist them in their daily activities for managing call interruptions. A key step of such modeling is to discovering call response behavioral rules based on multi-dimensional contexts related to individual's behavior. Currently, researchers use classification rule learners for modeling individual's mobile phone behavior. However, the problem is that such learning techniques produce only rules that include maximal number of contexts albeit ordered by relevance. This results in many rules with low-reliability that decrease the accuracy of the modeling approach. In this paper, we propose an approach (Tmodel) to modeling individual's phone call response behavior utilizing mobile phone data. This approach produces not only general rules that capture individual's behavior at a particular level of confidence with a minimal number of contexts, but also produce rules that express specific exceptions to the general rules when more context-dimensions are taken into account. Experimental evaluation shows that our approach outperforms existing approaches to modelling individual's phone call response behavior based on multidimensional contexts.",
keywords = "behavior modeling, contexts, machine learning, mobile data mining, phone call response, rule discovery",
author = "Sarker, {Iqbal H.} and Kabir, {Muhammad Ashad} and Alan Colman and Jun Han",
year = "2017",
month = "7",
day = "11",
doi = "10.1109/MOBILESoft.2017.38",
language = "English",
pages = "91--95",
booktitle = "Proceedings of the 2017 IEEE/ACM 4th International Conference on Mobile Software Engineering and Systems (MOBILESoft 2017)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Sarker, IH, Kabir, MA, Colman, A & Han, J 2017, An Approach to Modeling Call Response Behavior on Mobile Phones Based on Multi-Dimensional Contexts. in Proceedings of the 2017 IEEE/ACM 4th International Conference on Mobile Software Engineering and Systems (MOBILESoft 2017)., 7972722, IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 91-95, 4th IEEE/ACM International Conference on Mobile Software Engineering and Systems, Buenos Aires, Argentina, 22/05/17. https://doi.org/10.1109/MOBILESoft.2017.38

An Approach to Modeling Call Response Behavior on Mobile Phones Based on Multi-Dimensional Contexts. / Sarker, Iqbal H.; Kabir, Muhammad Ashad; Colman, Alan; Han, Jun.

Proceedings of the 2017 IEEE/ACM 4th International Conference on Mobile Software Engineering and Systems (MOBILESoft 2017). United States : IEEE, Institute of Electrical and Electronics Engineers, 2017. p. 91-95 7972722.

Research output: Book chapter/Published conference paperConference paper

TY - GEN

T1 - An Approach to Modeling Call Response Behavior on Mobile Phones Based on Multi-Dimensional Contexts

AU - Sarker, Iqbal H.

AU - Kabir, Muhammad Ashad

AU - Colman, Alan

AU - Han, Jun

PY - 2017/7/11

Y1 - 2017/7/11

N2 - Due to the popularity of context-aware computing and the rapid growth of the smart phone devices, modeling an individual's phone call response behavior may assist them in their daily activities for managing call interruptions. A key step of such modeling is to discovering call response behavioral rules based on multi-dimensional contexts related to individual's behavior. Currently, researchers use classification rule learners for modeling individual's mobile phone behavior. However, the problem is that such learning techniques produce only rules that include maximal number of contexts albeit ordered by relevance. This results in many rules with low-reliability that decrease the accuracy of the modeling approach. In this paper, we propose an approach (Tmodel) to modeling individual's phone call response behavior utilizing mobile phone data. This approach produces not only general rules that capture individual's behavior at a particular level of confidence with a minimal number of contexts, but also produce rules that express specific exceptions to the general rules when more context-dimensions are taken into account. Experimental evaluation shows that our approach outperforms existing approaches to modelling individual's phone call response behavior based on multidimensional contexts.

AB - Due to the popularity of context-aware computing and the rapid growth of the smart phone devices, modeling an individual's phone call response behavior may assist them in their daily activities for managing call interruptions. A key step of such modeling is to discovering call response behavioral rules based on multi-dimensional contexts related to individual's behavior. Currently, researchers use classification rule learners for modeling individual's mobile phone behavior. However, the problem is that such learning techniques produce only rules that include maximal number of contexts albeit ordered by relevance. This results in many rules with low-reliability that decrease the accuracy of the modeling approach. In this paper, we propose an approach (Tmodel) to modeling individual's phone call response behavior utilizing mobile phone data. This approach produces not only general rules that capture individual's behavior at a particular level of confidence with a minimal number of contexts, but also produce rules that express specific exceptions to the general rules when more context-dimensions are taken into account. Experimental evaluation shows that our approach outperforms existing approaches to modelling individual's phone call response behavior based on multidimensional contexts.

KW - behavior modeling

KW - contexts

KW - machine learning

KW - mobile data mining

KW - phone call response

KW - rule discovery

UR - http://www.scopus.com/inward/record.url?scp=85027014788&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027014788&partnerID=8YFLogxK

UR - https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7972699

UR - http://mobilesoftconf.org/2017/conference-program/

UR - http://mobilesoftconf.org/2017/

U2 - 10.1109/MOBILESoft.2017.38

DO - 10.1109/MOBILESoft.2017.38

M3 - Conference paper

AN - SCOPUS:85027014788

SP - 91

EP - 95

BT - Proceedings of the 2017 IEEE/ACM 4th International Conference on Mobile Software Engineering and Systems (MOBILESoft 2017)

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - United States

ER -

Sarker IH, Kabir MA, Colman A, Han J. An Approach to Modeling Call Response Behavior on Mobile Phones Based on Multi-Dimensional Contexts. In Proceedings of the 2017 IEEE/ACM 4th International Conference on Mobile Software Engineering and Systems (MOBILESoft 2017). United States: IEEE, Institute of Electrical and Electronics Engineers. 2017. p. 91-95. 7972722 https://doi.org/10.1109/MOBILESoft.2017.38