ClariSense: Clarifying sensor anomalies using social network feeds

Prasanna Giridhar, Md Tanvir Amin, Tarek Abdelzaher, Lance Kaplan, Jemin George, Raghu Ganti

Research output: Contribution to conferencePaper

Abstract

The explosive growth in social networks that publish real-time content begs the question of whether their feeds can complement traditional sensors to achieve augmented sensing capabilities. One such capability is to explain anomalous sensor readings. Towards that end, in this paper, we build an automated anomaly clarification service, called ClariSense. It explains sensor anomalies using social network feeds. Explanation goes beyond detection. When a sensor network detects anomalous conditions, our system automatically suggests hypotheses that explain the likely causes of the anomaly to a human by identifying unusual social network feeds that seem to be correlated with the sensor anomaly in time and in space. To evaluate this service, we use real-time data feeds from the California traffic system that shares vehicle count and traffic speed on major California highways at 5 minute intervals. When anomalies are detected, our system automatically diagnoses their root cause by correlating the anomaly with feeds on Twitter. The identified cause is then compared to official traffic and incident reports, showing a great correspondence with ground truth.

Original languageEnglish (US)
Pages395-400
Number of pages6
DOIs
StatePublished - Jan 1 2014
Event2014 IEEE International Conference on Pervasive Computing and Communication Workshops, PERCOM WORKSHOPS 2014 - Budapest, Hungary
Duration: Mar 24 2014Mar 28 2014

Other

Other2014 IEEE International Conference on Pervasive Computing and Communication Workshops, PERCOM WORKSHOPS 2014
CountryHungary
CityBudapest
Period3/24/143/28/14

Fingerprint

Sensors
Sensor networks

ASJC Scopus subject areas

  • Software

Cite this

Giridhar, P., Amin, M. T., Abdelzaher, T., Kaplan, L., George, J., & Ganti, R. (2014). ClariSense: Clarifying sensor anomalies using social network feeds. 395-400. Paper presented at 2014 IEEE International Conference on Pervasive Computing and Communication Workshops, PERCOM WORKSHOPS 2014, Budapest, Hungary. https://doi.org/10.1109/PerComW.2014.6815239

ClariSense : Clarifying sensor anomalies using social network feeds. / Giridhar, Prasanna; Amin, Md Tanvir; Abdelzaher, Tarek; Kaplan, Lance; George, Jemin; Ganti, Raghu.

2014. 395-400 Paper presented at 2014 IEEE International Conference on Pervasive Computing and Communication Workshops, PERCOM WORKSHOPS 2014, Budapest, Hungary.

Research output: Contribution to conferencePaper

Giridhar, P, Amin, MT, Abdelzaher, T, Kaplan, L, George, J & Ganti, R 2014, 'ClariSense: Clarifying sensor anomalies using social network feeds' Paper presented at 2014 IEEE International Conference on Pervasive Computing and Communication Workshops, PERCOM WORKSHOPS 2014, Budapest, Hungary, 3/24/14 - 3/28/14, pp. 395-400. https://doi.org/10.1109/PerComW.2014.6815239
Giridhar P, Amin MT, Abdelzaher T, Kaplan L, George J, Ganti R. ClariSense: Clarifying sensor anomalies using social network feeds. 2014. Paper presented at 2014 IEEE International Conference on Pervasive Computing and Communication Workshops, PERCOM WORKSHOPS 2014, Budapest, Hungary. https://doi.org/10.1109/PerComW.2014.6815239
Giridhar, Prasanna ; Amin, Md Tanvir ; Abdelzaher, Tarek ; Kaplan, Lance ; George, Jemin ; Ganti, Raghu. / ClariSense : Clarifying sensor anomalies using social network feeds. Paper presented at 2014 IEEE International Conference on Pervasive Computing and Communication Workshops, PERCOM WORKSHOPS 2014, Budapest, Hungary.6 p.
@conference{519c4ee759c149d988d017522b84ff49,
title = "ClariSense: Clarifying sensor anomalies using social network feeds",
abstract = "The explosive growth in social networks that publish real-time content begs the question of whether their feeds can complement traditional sensors to achieve augmented sensing capabilities. One such capability is to explain anomalous sensor readings. Towards that end, in this paper, we build an automated anomaly clarification service, called ClariSense. It explains sensor anomalies using social network feeds. Explanation goes beyond detection. When a sensor network detects anomalous conditions, our system automatically suggests hypotheses that explain the likely causes of the anomaly to a human by identifying unusual social network feeds that seem to be correlated with the sensor anomaly in time and in space. To evaluate this service, we use real-time data feeds from the California traffic system that shares vehicle count and traffic speed on major California highways at 5 minute intervals. When anomalies are detected, our system automatically diagnoses their root cause by correlating the anomaly with feeds on Twitter. The identified cause is then compared to official traffic and incident reports, showing a great correspondence with ground truth.",
author = "Prasanna Giridhar and Amin, {Md Tanvir} and Tarek Abdelzaher and Lance Kaplan and Jemin George and Raghu Ganti",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/PerComW.2014.6815239",
language = "English (US)",
pages = "395--400",
note = "2014 IEEE International Conference on Pervasive Computing and Communication Workshops, PERCOM WORKSHOPS 2014 ; Conference date: 24-03-2014 Through 28-03-2014",

}

TY - CONF

T1 - ClariSense

T2 - Clarifying sensor anomalies using social network feeds

AU - Giridhar, Prasanna

AU - Amin, Md Tanvir

AU - Abdelzaher, Tarek

AU - Kaplan, Lance

AU - George, Jemin

AU - Ganti, Raghu

PY - 2014/1/1

Y1 - 2014/1/1

N2 - The explosive growth in social networks that publish real-time content begs the question of whether their feeds can complement traditional sensors to achieve augmented sensing capabilities. One such capability is to explain anomalous sensor readings. Towards that end, in this paper, we build an automated anomaly clarification service, called ClariSense. It explains sensor anomalies using social network feeds. Explanation goes beyond detection. When a sensor network detects anomalous conditions, our system automatically suggests hypotheses that explain the likely causes of the anomaly to a human by identifying unusual social network feeds that seem to be correlated with the sensor anomaly in time and in space. To evaluate this service, we use real-time data feeds from the California traffic system that shares vehicle count and traffic speed on major California highways at 5 minute intervals. When anomalies are detected, our system automatically diagnoses their root cause by correlating the anomaly with feeds on Twitter. The identified cause is then compared to official traffic and incident reports, showing a great correspondence with ground truth.

AB - The explosive growth in social networks that publish real-time content begs the question of whether their feeds can complement traditional sensors to achieve augmented sensing capabilities. One such capability is to explain anomalous sensor readings. Towards that end, in this paper, we build an automated anomaly clarification service, called ClariSense. It explains sensor anomalies using social network feeds. Explanation goes beyond detection. When a sensor network detects anomalous conditions, our system automatically suggests hypotheses that explain the likely causes of the anomaly to a human by identifying unusual social network feeds that seem to be correlated with the sensor anomaly in time and in space. To evaluate this service, we use real-time data feeds from the California traffic system that shares vehicle count and traffic speed on major California highways at 5 minute intervals. When anomalies are detected, our system automatically diagnoses their root cause by correlating the anomaly with feeds on Twitter. The identified cause is then compared to official traffic and incident reports, showing a great correspondence with ground truth.

UR - http://www.scopus.com/inward/record.url?scp=84901362167&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901362167&partnerID=8YFLogxK

U2 - 10.1109/PerComW.2014.6815239

DO - 10.1109/PerComW.2014.6815239

M3 - Paper

AN - SCOPUS:84901362167

SP - 395

EP - 400

ER -