Most calls are local (But Some Are Regional): Dissecting cellular communication patterns

Arvind Narayanan, Saurabh Verma, Zhi-Li Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We conduct a detailed analysis of cellular communication patterns using (voice/text based) call detail records (CDR) dataset from a nationwide cellular network. We analyze a 5-month large dataset containing over hundreds of millions of CDRs with a user population of over 5 million to dissect meaningful communication patterns, with the goal to understand their impact on - and better manage - cellular network resources. What makes this dataset interesting is that we have both location and timestamp information of the caller and the callee. This allows us to associate communication patterns of users with geographic locations. The enormous size and diversity inherent in the (big)data set, however, makes extracting communication patterns a challenging task. We illustrate this diversity by analyzing tower-level activities and communication patterns between towers and find certain patterns emerging. However, due to the complex structure of the data, extracting them becomes non-trivial. By providing structures to the data in the form of matrices, we adopt machine learning techniques to extract "latent" patterns from the data, while accounting for the inherent non-linearity and skewed data distributions. Our main results reveal the existence of interesting regional communication patterns of varying localities and sizes, out of which one pattern scatters across the entire nation.

Original languageEnglish (US)
Title of host publication2016 IEEE Global Communications Conference, GLOBECOM 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509013289
DOIs
StatePublished - Jan 1 2016
Event59th IEEE Global Communications Conference, GLOBECOM 2016 - Washington, United States
Duration: Dec 4 2016Dec 8 2016

Other

Other59th IEEE Global Communications Conference, GLOBECOM 2016
CountryUnited States
CityWashington
Period12/4/1612/8/16

Fingerprint

Cellular radio systems
Communication
Towers
Learning systems

Cite this

Narayanan, A., Verma, S., & Zhang, Z-L. (2016). Most calls are local (But Some Are Regional): Dissecting cellular communication patterns. In 2016 IEEE Global Communications Conference, GLOBECOM 2016 - Proceedings [7842004] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GLOCOM.2016.7842004

Most calls are local (But Some Are Regional) : Dissecting cellular communication patterns. / Narayanan, Arvind; Verma, Saurabh; Zhang, Zhi-Li.

2016 IEEE Global Communications Conference, GLOBECOM 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. 7842004.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Narayanan, A, Verma, S & Zhang, Z-L 2016, Most calls are local (But Some Are Regional): Dissecting cellular communication patterns. in 2016 IEEE Global Communications Conference, GLOBECOM 2016 - Proceedings., 7842004, 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.2016.7842004
Narayanan A, Verma S, Zhang Z-L. Most calls are local (But Some Are Regional): Dissecting cellular communication patterns. In 2016 IEEE Global Communications Conference, GLOBECOM 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2016. 7842004 https://doi.org/10.1109/GLOCOM.2016.7842004
Narayanan, Arvind ; Verma, Saurabh ; Zhang, Zhi-Li. / Most calls are local (But Some Are Regional) : Dissecting cellular communication patterns. 2016 IEEE Global Communications Conference, GLOBECOM 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016.
@inproceedings{82dba10db55346d89dbcdffdfa456bb7,
title = "Most calls are local (But Some Are Regional): Dissecting cellular communication patterns",
abstract = "We conduct a detailed analysis of cellular communication patterns using (voice/text based) call detail records (CDR) dataset from a nationwide cellular network. We analyze a 5-month large dataset containing over hundreds of millions of CDRs with a user population of over 5 million to dissect meaningful communication patterns, with the goal to understand their impact on - and better manage - cellular network resources. What makes this dataset interesting is that we have both location and timestamp information of the caller and the callee. This allows us to associate communication patterns of users with geographic locations. The enormous size and diversity inherent in the (big)data set, however, makes extracting communication patterns a challenging task. We illustrate this diversity by analyzing tower-level activities and communication patterns between towers and find certain patterns emerging. However, due to the complex structure of the data, extracting them becomes non-trivial. By providing structures to the data in the form of matrices, we adopt machine learning techniques to extract {"}latent{"} patterns from the data, while accounting for the inherent non-linearity and skewed data distributions. Our main results reveal the existence of interesting regional communication patterns of varying localities and sizes, out of which one pattern scatters across the entire nation.",
author = "Arvind Narayanan and Saurabh Verma and Zhi-Li Zhang",
year = "2016",
month = "1",
day = "1",
doi = "10.1109/GLOCOM.2016.7842004",
language = "English (US)",
booktitle = "2016 IEEE Global Communications Conference, GLOBECOM 2016 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Most calls are local (But Some Are Regional)

T2 - Dissecting cellular communication patterns

AU - Narayanan, Arvind

AU - Verma, Saurabh

AU - Zhang, Zhi-Li

PY - 2016/1/1

Y1 - 2016/1/1

N2 - We conduct a detailed analysis of cellular communication patterns using (voice/text based) call detail records (CDR) dataset from a nationwide cellular network. We analyze a 5-month large dataset containing over hundreds of millions of CDRs with a user population of over 5 million to dissect meaningful communication patterns, with the goal to understand their impact on - and better manage - cellular network resources. What makes this dataset interesting is that we have both location and timestamp information of the caller and the callee. This allows us to associate communication patterns of users with geographic locations. The enormous size and diversity inherent in the (big)data set, however, makes extracting communication patterns a challenging task. We illustrate this diversity by analyzing tower-level activities and communication patterns between towers and find certain patterns emerging. However, due to the complex structure of the data, extracting them becomes non-trivial. By providing structures to the data in the form of matrices, we adopt machine learning techniques to extract "latent" patterns from the data, while accounting for the inherent non-linearity and skewed data distributions. Our main results reveal the existence of interesting regional communication patterns of varying localities and sizes, out of which one pattern scatters across the entire nation.

AB - We conduct a detailed analysis of cellular communication patterns using (voice/text based) call detail records (CDR) dataset from a nationwide cellular network. We analyze a 5-month large dataset containing over hundreds of millions of CDRs with a user population of over 5 million to dissect meaningful communication patterns, with the goal to understand their impact on - and better manage - cellular network resources. What makes this dataset interesting is that we have both location and timestamp information of the caller and the callee. This allows us to associate communication patterns of users with geographic locations. The enormous size and diversity inherent in the (big)data set, however, makes extracting communication patterns a challenging task. We illustrate this diversity by analyzing tower-level activities and communication patterns between towers and find certain patterns emerging. However, due to the complex structure of the data, extracting them becomes non-trivial. By providing structures to the data in the form of matrices, we adopt machine learning techniques to extract "latent" patterns from the data, while accounting for the inherent non-linearity and skewed data distributions. Our main results reveal the existence of interesting regional communication patterns of varying localities and sizes, out of which one pattern scatters across the entire nation.

UR - http://www.scopus.com/inward/record.url?scp=85015456790&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015456790&partnerID=8YFLogxK

U2 - 10.1109/GLOCOM.2016.7842004

DO - 10.1109/GLOCOM.2016.7842004

M3 - Conference contribution

AN - SCOPUS:85015456790

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

PB - Institute of Electrical and Electronics Engineers Inc.

ER -