ADF: An Anomaly Detection Framework for Large-Scale PM2.5 Sensing Systems

Ling-Jyh Chen, Yao Hua Ho, Hsin Hung Hsieh, Shih Ting Huang, Hu Cheng Lee, Sachit Mahajan

Research output: Contribution to journalArticle

  • 5 Citations

Abstract

As the population density continues to grow in the urban settings, air quality is degrading and becoming a serious issue. Air pollution, especially fine particulate matter (PM2.5), has raised a series of concerns for public health. As a result, a number of large-scale, low cost PM2.5 monitoring systems have been deployed in several international smart city projects. One of the major challenges for such environmental sensing systems is ensuring the data quality. In this paper, we propose an anomaly detection framework (ADF) for large-scale, real-world environmental sensing systems. The framework is composed of four modules: 1) time-sliced anomaly detection (TSAD), which detects spatial, temporal, and spatio-temporal anomalies in the real-time sensor measurement data stream; 2) real-time emission detection, which detects potential regional emission sources; 3) device ranking, which provides a ranking for each sensing device; and 4) malfunction detection, which identifies malfunctioning devices. Using real world measurement data from the AirBox project, we demonstrate that the proposed framework can effectively identify outliers in the raw measurement data as well as infer anomalous events that are perceivable by the general public and government authorities. Because of its simple design, ADF is highly extensible to other advanced applications, and it can be exploited to support various large-scale environmental sensing systems.

LanguageEnglish
Pages559-570
Number of pages12
JournalIEEE Internet of Things Journal
Volume5
Issue number2
DOIs
Publication statusPublished - 2018 Apr 1

Fingerprint

Public health
Air pollution
Air quality
Monitoring
Sensors
Costs
Smart city

Keywords

  • Anomaly detection
  • PM2.5
  • data analysis
  • smart city

ASJC Scopus subject areas

  • Signal Processing
  • Information Systems
  • Hardware and Architecture
  • Computer Science Applications
  • Computer Networks and Communications

Cite this

ADF : An Anomaly Detection Framework for Large-Scale PM2.5 Sensing Systems. / Chen, Ling-Jyh; Ho, Yao Hua; Hsieh, Hsin Hung; Huang, Shih Ting; Lee, Hu Cheng; Mahajan, Sachit.

In: IEEE Internet of Things Journal, Vol. 5, No. 2, 01.04.2018, p. 559-570.

Research output: Contribution to journalArticle

Chen, Ling-Jyh ; Ho, Yao Hua ; Hsieh, Hsin Hung ; Huang, Shih Ting ; Lee, Hu Cheng ; Mahajan, Sachit. / ADF : An Anomaly Detection Framework for Large-Scale PM2.5 Sensing Systems. In: IEEE Internet of Things Journal. 2018 ; Vol. 5, No. 2. pp. 559-570.
@article{b9d4fda0fc0b46339f108dcc57363358,
title = "ADF: An Anomaly Detection Framework for Large-Scale PM2.5 Sensing Systems",
abstract = "As the population density continues to grow in the urban settings, air quality is degrading and becoming a serious issue. Air pollution, especially fine particulate matter (PM2.5), has raised a series of concerns for public health. As a result, a number of large-scale, low cost PM2.5 monitoring systems have been deployed in several international smart city projects. One of the major challenges for such environmental sensing systems is ensuring the data quality. In this paper, we propose an anomaly detection framework (ADF) for large-scale, real-world environmental sensing systems. The framework is composed of four modules: 1) time-sliced anomaly detection (TSAD), which detects spatial, temporal, and spatio-temporal anomalies in the real-time sensor measurement data stream; 2) real-time emission detection, which detects potential regional emission sources; 3) device ranking, which provides a ranking for each sensing device; and 4) malfunction detection, which identifies malfunctioning devices. Using real world measurement data from the AirBox project, we demonstrate that the proposed framework can effectively identify outliers in the raw measurement data as well as infer anomalous events that are perceivable by the general public and government authorities. Because of its simple design, ADF is highly extensible to other advanced applications, and it can be exploited to support various large-scale environmental sensing systems.",
keywords = "Anomaly detection, PM2.5, data analysis, smart city",
author = "Ling-Jyh Chen and Ho, {Yao Hua} and Hsieh, {Hsin Hung} and Huang, {Shih Ting} and Lee, {Hu Cheng} and Sachit Mahajan",
year = "2018",
month = "4",
day = "1",
doi = "10.1109/JIOT.2017.2766085",
language = "English",
volume = "5",
pages = "559--570",
journal = "IEEE Internet of Things Journal",
issn = "2327-4662",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - ADF

T2 - IEEE Internet of Things Journal

AU - Chen, Ling-Jyh

AU - Ho, Yao Hua

AU - Hsieh, Hsin Hung

AU - Huang, Shih Ting

AU - Lee, Hu Cheng

AU - Mahajan, Sachit

PY - 2018/4/1

Y1 - 2018/4/1

N2 - As the population density continues to grow in the urban settings, air quality is degrading and becoming a serious issue. Air pollution, especially fine particulate matter (PM2.5), has raised a series of concerns for public health. As a result, a number of large-scale, low cost PM2.5 monitoring systems have been deployed in several international smart city projects. One of the major challenges for such environmental sensing systems is ensuring the data quality. In this paper, we propose an anomaly detection framework (ADF) for large-scale, real-world environmental sensing systems. The framework is composed of four modules: 1) time-sliced anomaly detection (TSAD), which detects spatial, temporal, and spatio-temporal anomalies in the real-time sensor measurement data stream; 2) real-time emission detection, which detects potential regional emission sources; 3) device ranking, which provides a ranking for each sensing device; and 4) malfunction detection, which identifies malfunctioning devices. Using real world measurement data from the AirBox project, we demonstrate that the proposed framework can effectively identify outliers in the raw measurement data as well as infer anomalous events that are perceivable by the general public and government authorities. Because of its simple design, ADF is highly extensible to other advanced applications, and it can be exploited to support various large-scale environmental sensing systems.

AB - As the population density continues to grow in the urban settings, air quality is degrading and becoming a serious issue. Air pollution, especially fine particulate matter (PM2.5), has raised a series of concerns for public health. As a result, a number of large-scale, low cost PM2.5 monitoring systems have been deployed in several international smart city projects. One of the major challenges for such environmental sensing systems is ensuring the data quality. In this paper, we propose an anomaly detection framework (ADF) for large-scale, real-world environmental sensing systems. The framework is composed of four modules: 1) time-sliced anomaly detection (TSAD), which detects spatial, temporal, and spatio-temporal anomalies in the real-time sensor measurement data stream; 2) real-time emission detection, which detects potential regional emission sources; 3) device ranking, which provides a ranking for each sensing device; and 4) malfunction detection, which identifies malfunctioning devices. Using real world measurement data from the AirBox project, we demonstrate that the proposed framework can effectively identify outliers in the raw measurement data as well as infer anomalous events that are perceivable by the general public and government authorities. Because of its simple design, ADF is highly extensible to other advanced applications, and it can be exploited to support various large-scale environmental sensing systems.

KW - Anomaly detection

KW - PM2.5

KW - data analysis

KW - smart city

UR - http://www.scopus.com/inward/record.url?scp=85032447751&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032447751&partnerID=8YFLogxK

U2 - 10.1109/JIOT.2017.2766085

DO - 10.1109/JIOT.2017.2766085

M3 - Article

VL - 5

SP - 559

EP - 570

JO - IEEE Internet of Things Journal

JF - IEEE Internet of Things Journal

SN - 2327-4662

IS - 2

ER -