Edge-assisted detection and summarization of key global events from distributed crowd-sensed data

Abdelrahman Fahim, Ajaya Neupane, Evangelos Papalexakis, Lance Kaplan, Srikanth V. Krishnamurthy, Tarek Abdelzaher

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

Abstract

This paper introduces a novel service for distributed detection and summarization of crowd-sensed events. The work is motivated by the proliferation of microblogging media, such as Twitter, that can be used to detect and describe events in the physical world, such as protests, disasters, or civil unrest. Since crowd-sensed data is likely to be distributed, we consider an architecture, where the data first accumulates across a plurality of edge servers (e.g. cloudlets or repositories) and is then summarized, rather than being shipped directly to its ultimate destination (e.g., in a remote cloud). The architecture allows graceful handling of overload and bandwidth limitations (e.g., in scenarios where capacity is impaired, as the case might be after a disaster). When bandwidth is scarce, our service, BigEye, only transfers very limited metadata from the distributed edge repositories to the central summarizer and yet supports highly accurate detection and concise summarization of key events of global interest. These summaries can then be sent to consumers (e.g., rescue personnel). Our emulations show that BigEye achieves the same precision and recall values in detecting key events as a system where all data is available centrally, while consuming only 1% of the bandwidth needed to transmit all raw data.

Original languageEnglish (US)
Title of host publicationProceedings - 2019 IEEE International Conference on Cloud Engineering, IC2E 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages76-85
Number of pages10
ISBN (Electronic)9781728102184
DOIs
StatePublished - Jun 2019
Event7th IEEE International Conference on Cloud Engineering, IC2E 2019 - Prague, Czech Republic
Duration: Jun 24 2019Jun 27 2019

Publication series

NameProceedings - 2019 IEEE International Conference on Cloud Engineering, IC2E 2019

Conference

Conference7th IEEE International Conference on Cloud Engineering, IC2E 2019
CountryCzech Republic
CityPrague
Period6/24/196/27/19

Fingerprint

Bandwidth
Disasters
Metadata
Servers
Personnel
Summarization
Repository
Disaster
Protest
Overload
Proliferation
Destination
Twitter
Plurality
Emulation
Scenarios
Microblogging

Keywords

  • Crowd sensing
  • Data mining
  • Data summarization
  • Distributed computing
  • Event detection

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality

Cite this

Fahim, A., Neupane, A., Papalexakis, E., Kaplan, L., Krishnamurthy, S. V., & Abdelzaher, T. (2019). Edge-assisted detection and summarization of key global events from distributed crowd-sensed data. In Proceedings - 2019 IEEE International Conference on Cloud Engineering, IC2E 2019 (pp. 76-85). [8789993] (Proceedings - 2019 IEEE International Conference on Cloud Engineering, IC2E 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IC2E.2019.00021

Edge-assisted detection and summarization of key global events from distributed crowd-sensed data. / Fahim, Abdelrahman; Neupane, Ajaya; Papalexakis, Evangelos; Kaplan, Lance; Krishnamurthy, Srikanth V.; Abdelzaher, Tarek.

Proceedings - 2019 IEEE International Conference on Cloud Engineering, IC2E 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 76-85 8789993 (Proceedings - 2019 IEEE International Conference on Cloud Engineering, IC2E 2019).

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

Fahim, A, Neupane, A, Papalexakis, E, Kaplan, L, Krishnamurthy, SV & Abdelzaher, T 2019, Edge-assisted detection and summarization of key global events from distributed crowd-sensed data. in Proceedings - 2019 IEEE International Conference on Cloud Engineering, IC2E 2019., 8789993, Proceedings - 2019 IEEE International Conference on Cloud Engineering, IC2E 2019, Institute of Electrical and Electronics Engineers Inc., pp. 76-85, 7th IEEE International Conference on Cloud Engineering, IC2E 2019, Prague, Czech Republic, 6/24/19. https://doi.org/10.1109/IC2E.2019.00021
Fahim A, Neupane A, Papalexakis E, Kaplan L, Krishnamurthy SV, Abdelzaher T. Edge-assisted detection and summarization of key global events from distributed crowd-sensed data. In Proceedings - 2019 IEEE International Conference on Cloud Engineering, IC2E 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 76-85. 8789993. (Proceedings - 2019 IEEE International Conference on Cloud Engineering, IC2E 2019). https://doi.org/10.1109/IC2E.2019.00021
Fahim, Abdelrahman ; Neupane, Ajaya ; Papalexakis, Evangelos ; Kaplan, Lance ; Krishnamurthy, Srikanth V. ; Abdelzaher, Tarek. / Edge-assisted detection and summarization of key global events from distributed crowd-sensed data. Proceedings - 2019 IEEE International Conference on Cloud Engineering, IC2E 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 76-85 (Proceedings - 2019 IEEE International Conference on Cloud Engineering, IC2E 2019).
@inproceedings{5d908dae9c2345a6b4235bc3e4275ea3,
title = "Edge-assisted detection and summarization of key global events from distributed crowd-sensed data",
abstract = "This paper introduces a novel service for distributed detection and summarization of crowd-sensed events. The work is motivated by the proliferation of microblogging media, such as Twitter, that can be used to detect and describe events in the physical world, such as protests, disasters, or civil unrest. Since crowd-sensed data is likely to be distributed, we consider an architecture, where the data first accumulates across a plurality of edge servers (e.g. cloudlets or repositories) and is then summarized, rather than being shipped directly to its ultimate destination (e.g., in a remote cloud). The architecture allows graceful handling of overload and bandwidth limitations (e.g., in scenarios where capacity is impaired, as the case might be after a disaster). When bandwidth is scarce, our service, BigEye, only transfers very limited metadata from the distributed edge repositories to the central summarizer and yet supports highly accurate detection and concise summarization of key events of global interest. These summaries can then be sent to consumers (e.g., rescue personnel). Our emulations show that BigEye achieves the same precision and recall values in detecting key events as a system where all data is available centrally, while consuming only 1{\%} of the bandwidth needed to transmit all raw data.",
keywords = "Crowd sensing, Data mining, Data summarization, Distributed computing, Event detection",
author = "Abdelrahman Fahim and Ajaya Neupane and Evangelos Papalexakis and Lance Kaplan and Krishnamurthy, {Srikanth V.} and Tarek Abdelzaher",
year = "2019",
month = "6",
doi = "10.1109/IC2E.2019.00021",
language = "English (US)",
series = "Proceedings - 2019 IEEE International Conference on Cloud Engineering, IC2E 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "76--85",
booktitle = "Proceedings - 2019 IEEE International Conference on Cloud Engineering, IC2E 2019",
address = "United States",

}

TY - GEN

T1 - Edge-assisted detection and summarization of key global events from distributed crowd-sensed data

AU - Fahim, Abdelrahman

AU - Neupane, Ajaya

AU - Papalexakis, Evangelos

AU - Kaplan, Lance

AU - Krishnamurthy, Srikanth V.

AU - Abdelzaher, Tarek

PY - 2019/6

Y1 - 2019/6

N2 - This paper introduces a novel service for distributed detection and summarization of crowd-sensed events. The work is motivated by the proliferation of microblogging media, such as Twitter, that can be used to detect and describe events in the physical world, such as protests, disasters, or civil unrest. Since crowd-sensed data is likely to be distributed, we consider an architecture, where the data first accumulates across a plurality of edge servers (e.g. cloudlets or repositories) and is then summarized, rather than being shipped directly to its ultimate destination (e.g., in a remote cloud). The architecture allows graceful handling of overload and bandwidth limitations (e.g., in scenarios where capacity is impaired, as the case might be after a disaster). When bandwidth is scarce, our service, BigEye, only transfers very limited metadata from the distributed edge repositories to the central summarizer and yet supports highly accurate detection and concise summarization of key events of global interest. These summaries can then be sent to consumers (e.g., rescue personnel). Our emulations show that BigEye achieves the same precision and recall values in detecting key events as a system where all data is available centrally, while consuming only 1% of the bandwidth needed to transmit all raw data.

AB - This paper introduces a novel service for distributed detection and summarization of crowd-sensed events. The work is motivated by the proliferation of microblogging media, such as Twitter, that can be used to detect and describe events in the physical world, such as protests, disasters, or civil unrest. Since crowd-sensed data is likely to be distributed, we consider an architecture, where the data first accumulates across a plurality of edge servers (e.g. cloudlets or repositories) and is then summarized, rather than being shipped directly to its ultimate destination (e.g., in a remote cloud). The architecture allows graceful handling of overload and bandwidth limitations (e.g., in scenarios where capacity is impaired, as the case might be after a disaster). When bandwidth is scarce, our service, BigEye, only transfers very limited metadata from the distributed edge repositories to the central summarizer and yet supports highly accurate detection and concise summarization of key events of global interest. These summaries can then be sent to consumers (e.g., rescue personnel). Our emulations show that BigEye achieves the same precision and recall values in detecting key events as a system where all data is available centrally, while consuming only 1% of the bandwidth needed to transmit all raw data.

KW - Crowd sensing

KW - Data mining

KW - Data summarization

KW - Distributed computing

KW - Event detection

UR - http://www.scopus.com/inward/record.url?scp=85071423548&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071423548&partnerID=8YFLogxK

U2 - 10.1109/IC2E.2019.00021

DO - 10.1109/IC2E.2019.00021

M3 - Conference contribution

AN - SCOPUS:85071423548

T3 - Proceedings - 2019 IEEE International Conference on Cloud Engineering, IC2E 2019

SP - 76

EP - 85

BT - Proceedings - 2019 IEEE International Conference on Cloud Engineering, IC2E 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -