Short-long term anomaly detection in wireless sensor networks based on machine learning and multi-parameterized edit distance

Francesco Cauteruccio, Giancarlo Fortino, Antonio Guerrieri, A. Liotta, D.C. Mocanu, Cristian Perra, Giorgio Terracina (Corresponding author), M. Torres Vega

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

2 Citaties (Scopus)

Uittreksel

Heterogeneous wireless sensor networks are a source of large amount of different information representing environmental aspects such as light, temperature, and humidity. A very important research problem related to the analysis of the sensor data is the detection of relevant anomalies. In this work, we focus on the detection of unexpected sensor data resulting either from the sensor system itself or from the environment under scrutiny. We propose a novel approach for automatic anomaly detection in heterogeneous sensor networks based on coupling edge data analysis with cloud data analysis. The former exploits a fully unsupervised artificial neural network algorithm, whereas cloud data analysis exploits the multi-parameterized edit distance algorithm. The experimental evaluation of the proposed method is performed applying the edge and cloud analysis on real data that has been acquired in an indoor building environment and then distorted with a range of synthetic impairments. The obtained results show that the proposed method can self-adapt to the environment variations and correctly identify the anomalies. We show how the combination of edge and cloud computing can mitigate the drawbacks of purely edge-based analysis or purely cloud-based solutions.
TaalEngels
Pagina's13-30
TijdschriftInformation Fusion
Volume52
DOI's
StatusGepubliceerd - 1 jan 2019

Vingerafdruk

Learning systems
Wireless sensor networks
Sensors
Heterogeneous networks
Cloud computing
Sensor networks
Atmospheric humidity
Neural networks
Temperature

Citeer dit

Cauteruccio, Francesco ; Fortino, Giancarlo ; Guerrieri, Antonio ; Liotta, A. ; Mocanu, D.C. ; Perra, Cristian ; Terracina, Giorgio ; Torres Vega, M./ Short-long term anomaly detection in wireless sensor networks based on machine learning and multi-parameterized edit distance. In: Information Fusion. 2019 ; Vol. 52. blz. 13-30
@article{0e73ac875958460583834d3c8df18e26,
title = "Short-long term anomaly detection in wireless sensor networks based on machine learning and multi-parameterized edit distance",
abstract = "Heterogeneous wireless sensor networks are a source of large amount of different information representing environmental aspects such as light, temperature, and humidity. A very important research problem related to the analysis of the sensor data is the detection of relevant anomalies. In this work, we focus on the detection of unexpected sensor data resulting either from the sensor system itself or from the environment under scrutiny. We propose a novel approach for automatic anomaly detection in heterogeneous sensor networks based on coupling edge data analysis with cloud data analysis. The former exploits a fully unsupervised artificial neural network algorithm, whereas cloud data analysis exploits the multi-parameterized edit distance algorithm. The experimental evaluation of the proposed method is performed applying the edge and cloud analysis on real data that has been acquired in an indoor building environment and then distorted with a range of synthetic impairments. The obtained results show that the proposed method can self-adapt to the environment variations and correctly identify the anomalies. We show how the combination of edge and cloud computing can mitigate the drawbacks of purely edge-based analysis or purely cloud-based solutions.",
author = "Francesco Cauteruccio and Giancarlo Fortino and Antonio Guerrieri and A. Liotta and D.C. Mocanu and Cristian Perra and Giorgio Terracina and {Torres Vega}, M.",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/j.inffus.2018.11.010",
language = "English",
volume = "52",
pages = "13--30",
journal = "Information Fusion",
issn = "1566-2535",
publisher = "Elsevier",

}

Short-long term anomaly detection in wireless sensor networks based on machine learning and multi-parameterized edit distance. / Cauteruccio, Francesco; Fortino, Giancarlo; Guerrieri, Antonio; Liotta, A.; Mocanu, D.C.; Perra, Cristian; Terracina, Giorgio (Corresponding author); Torres Vega, M.

In: Information Fusion, Vol. 52, 01.01.2019, blz. 13-30.

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

TY - JOUR

T1 - Short-long term anomaly detection in wireless sensor networks based on machine learning and multi-parameterized edit distance

AU - Cauteruccio,Francesco

AU - Fortino,Giancarlo

AU - Guerrieri,Antonio

AU - Liotta,A.

AU - Mocanu,D.C.

AU - Perra,Cristian

AU - Terracina,Giorgio

AU - Torres Vega,M.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Heterogeneous wireless sensor networks are a source of large amount of different information representing environmental aspects such as light, temperature, and humidity. A very important research problem related to the analysis of the sensor data is the detection of relevant anomalies. In this work, we focus on the detection of unexpected sensor data resulting either from the sensor system itself or from the environment under scrutiny. We propose a novel approach for automatic anomaly detection in heterogeneous sensor networks based on coupling edge data analysis with cloud data analysis. The former exploits a fully unsupervised artificial neural network algorithm, whereas cloud data analysis exploits the multi-parameterized edit distance algorithm. The experimental evaluation of the proposed method is performed applying the edge and cloud analysis on real data that has been acquired in an indoor building environment and then distorted with a range of synthetic impairments. The obtained results show that the proposed method can self-adapt to the environment variations and correctly identify the anomalies. We show how the combination of edge and cloud computing can mitigate the drawbacks of purely edge-based analysis or purely cloud-based solutions.

AB - Heterogeneous wireless sensor networks are a source of large amount of different information representing environmental aspects such as light, temperature, and humidity. A very important research problem related to the analysis of the sensor data is the detection of relevant anomalies. In this work, we focus on the detection of unexpected sensor data resulting either from the sensor system itself or from the environment under scrutiny. We propose a novel approach for automatic anomaly detection in heterogeneous sensor networks based on coupling edge data analysis with cloud data analysis. The former exploits a fully unsupervised artificial neural network algorithm, whereas cloud data analysis exploits the multi-parameterized edit distance algorithm. The experimental evaluation of the proposed method is performed applying the edge and cloud analysis on real data that has been acquired in an indoor building environment and then distorted with a range of synthetic impairments. The obtained results show that the proposed method can self-adapt to the environment variations and correctly identify the anomalies. We show how the combination of edge and cloud computing can mitigate the drawbacks of purely edge-based analysis or purely cloud-based solutions.

U2 - 10.1016/j.inffus.2018.11.010

DO - 10.1016/j.inffus.2018.11.010

M3 - Article

VL - 52

SP - 13

EP - 30

JO - Information Fusion

T2 - Information Fusion

JF - Information Fusion

SN - 1566-2535

ER -