A comparative analysis of machine learning algorithms for faults detection in wireless sensor networks

Ehsan Ullah Warriach, Kenji Tei

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Wireless sensor networks (WSNs) deployment experiences show that collected data is prone to be faulty. Faults are due to internal and external influences, such as calibration, low battery, environmental interference and sensor aging. In this paper, we focus on faults occurred due to low battery and calibration in WSNs. Machine learning algorithms have been successfully used to identify and classify various types of faults. In this paper, we evaluate and compare the performance of k-nearest neighbour, support vector machine (SVM), and Naive Bayes machine learning algorithms by using the real-world datasets to identify and classify the faults. We present here a comparative study of the above mentioned approaches on experimental datasets. The approach is validated using real data obtained from over one month of samples from motes deployed in an actual living lab. The results show that the k-nearest neighbour (kNN) algorithm obtained a better fault detection rate than other algorithms based on given performance metrics.

Original languageEnglish
Pages (from-to)1-13
Number of pages13
JournalInternational Journal of Sensor Networks
Volume24
Issue number1
DOIs
Publication statusPublished - 2017 Jan 1
Externally publishedYes

Fingerprint

Fault detection
Learning algorithms
Learning systems
Wireless sensor networks
Calibration
Support vector machines
Aging of materials
Sensors

Keywords

  • Data analysis
  • Data and system faults
  • Fault detection
  • Internet of things
  • Machine learning
  • Reliability
  • Wireless sensor networks
  • WSNs

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

A comparative analysis of machine learning algorithms for faults detection in wireless sensor networks. / Warriach, Ehsan Ullah; Tei, Kenji.

In: International Journal of Sensor Networks, Vol. 24, No. 1, 01.01.2017, p. 1-13.

Research output: Contribution to journalArticle

@article{0f4d64e3e0eb4abc9e5e7cf1a6ff20ba,
title = "A comparative analysis of machine learning algorithms for faults detection in wireless sensor networks",
abstract = "Wireless sensor networks (WSNs) deployment experiences show that collected data is prone to be faulty. Faults are due to internal and external influences, such as calibration, low battery, environmental interference and sensor aging. In this paper, we focus on faults occurred due to low battery and calibration in WSNs. Machine learning algorithms have been successfully used to identify and classify various types of faults. In this paper, we evaluate and compare the performance of k-nearest neighbour, support vector machine (SVM), and Naive Bayes machine learning algorithms by using the real-world datasets to identify and classify the faults. We present here a comparative study of the above mentioned approaches on experimental datasets. The approach is validated using real data obtained from over one month of samples from motes deployed in an actual living lab. The results show that the k-nearest neighbour (kNN) algorithm obtained a better fault detection rate than other algorithms based on given performance metrics.",
keywords = "Data analysis, Data and system faults, Fault detection, Internet of things, Machine learning, Reliability, Wireless sensor networks, WSNs",
author = "Warriach, {Ehsan Ullah} and Kenji Tei",
year = "2017",
month = "1",
day = "1",
doi = "10.1504/IJSNET.2017.084209",
language = "English",
volume = "24",
pages = "1--13",
journal = "International Journal of Sensor Networks",
issn = "1748-1279",
publisher = "Inderscience Enterprises Ltd",
number = "1",

}

TY - JOUR

T1 - A comparative analysis of machine learning algorithms for faults detection in wireless sensor networks

AU - Warriach, Ehsan Ullah

AU - Tei, Kenji

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Wireless sensor networks (WSNs) deployment experiences show that collected data is prone to be faulty. Faults are due to internal and external influences, such as calibration, low battery, environmental interference and sensor aging. In this paper, we focus on faults occurred due to low battery and calibration in WSNs. Machine learning algorithms have been successfully used to identify and classify various types of faults. In this paper, we evaluate and compare the performance of k-nearest neighbour, support vector machine (SVM), and Naive Bayes machine learning algorithms by using the real-world datasets to identify and classify the faults. We present here a comparative study of the above mentioned approaches on experimental datasets. The approach is validated using real data obtained from over one month of samples from motes deployed in an actual living lab. The results show that the k-nearest neighbour (kNN) algorithm obtained a better fault detection rate than other algorithms based on given performance metrics.

AB - Wireless sensor networks (WSNs) deployment experiences show that collected data is prone to be faulty. Faults are due to internal and external influences, such as calibration, low battery, environmental interference and sensor aging. In this paper, we focus on faults occurred due to low battery and calibration in WSNs. Machine learning algorithms have been successfully used to identify and classify various types of faults. In this paper, we evaluate and compare the performance of k-nearest neighbour, support vector machine (SVM), and Naive Bayes machine learning algorithms by using the real-world datasets to identify and classify the faults. We present here a comparative study of the above mentioned approaches on experimental datasets. The approach is validated using real data obtained from over one month of samples from motes deployed in an actual living lab. The results show that the k-nearest neighbour (kNN) algorithm obtained a better fault detection rate than other algorithms based on given performance metrics.

KW - Data analysis

KW - Data and system faults

KW - Fault detection

KW - Internet of things

KW - Machine learning

KW - Reliability

KW - Wireless sensor networks

KW - WSNs

UR - http://www.scopus.com/inward/record.url?scp=85019739871&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019739871&partnerID=8YFLogxK

U2 - 10.1504/IJSNET.2017.084209

DO - 10.1504/IJSNET.2017.084209

M3 - Article

VL - 24

SP - 1

EP - 13

JO - International Journal of Sensor Networks

JF - International Journal of Sensor Networks

SN - 1748-1279

IS - 1

ER -