Data Imputation in Wireless Sensor Networks Using a Machine Learning-Based Virtual Sensor

Data Imputation in Wireless Sensor Networks Using a Machine Learning-Based Virtual Sensor

Data integrity in wireless sensor networks (WSN) is very important because incorrect or missing values could result in the system making suboptimal or catastrophic decisions. Data imputation allows for a system to counteract the effect of data loss by substituting faulty or missing sensor values wit...

Full description

Bibliographic Details
Main Authors: Michael Matusowsky, Daniel T. Ramotsoela, Adnan M. Abu-Mahfouz
Format: Article
Language:English
Published: MDPI AG 2020-05-01
Series:Journal of Sensor and Actuator Networks
Subjects:
data imputation
wireless sensor network
machine learning
neural network
virtual sensor
Online Access:https://www.mdpi.com/2224-2708/9/2/25
id doaj-3bf3e933c1254878ab46baf6afd90ed0
record_format Article
spelling doaj-3bf3e933c1254878ab46baf6afd90ed02020-11-25T02:48:59ZengMDPI AGJournal of Sensor and Actuator Networks2224-27082020-05-019252510.3390/jsan9020025Data Imputation in Wireless Sensor Networks Using a Machine Learning-Based Virtual SensorMichael Matusowsky0Daniel T. Ramotsoela1Adnan M. Abu-Mahfouz2Department of Electrical, Electronic and Computer Engineering, University of Pretoria, Pretoria 0002, South AfricaDepartment of Electrical, Electronic and Computer Engineering, University of Pretoria, Pretoria 0002, South AfricaDepartment of Electrical, Electronic and Computer Engineering, University of Pretoria, Pretoria 0002, South AfricaData integrity in wireless sensor networks (WSN) is very important because incorrect or missing values could result in the system making suboptimal or catastrophic decisions. Data imputation allows for a system to counteract the effect of data loss by substituting faulty or missing sensor values with system-defined virtual values. This paper proposes a virtual sensor system that uses multi-layer perceptrons (MLP) to impute sensor values in a WSN. The MLP was trained using a genetic algorithm which efficiently reached an optimal solution for each sensor node. The system was able to successfully identify and replace physical sensor nodes that were disconnected from the network with corresponding virtual sensors. The virtual sensors imputed values with very high accuracies when compared to the physical sensor values.https://www.mdpi.com/2224-2708/9/2/25data imputationwireless sensor networkmachine learningneural networkvirtual sensor
collection DOAJ
language English
format Article
sources DOAJ
author Michael Matusowsky
Daniel T. Ramotsoela
Adnan M. Abu-Mahfouz
spellingShingle Michael Matusowsky
Daniel T. Ramotsoela
Adnan M. Abu-Mahfouz
Data Imputation in Wireless Sensor Networks Using a Machine Learning-Based Virtual Sensor
Journal of Sensor and Actuator Networks
data imputation
wireless sensor network
machine learning
neural network
virtual sensor
author_facet Michael Matusowsky
Daniel T. Ramotsoela
Adnan M. Abu-Mahfouz
author_sort Michael Matusowsky
title Data Imputation in Wireless Sensor Networks Using a Machine Learning-Based Virtual Sensor
title_short Data Imputation in Wireless Sensor Networks Using a Machine Learning-Based Virtual Sensor
title_full Data Imputation in Wireless Sensor Networks Using a Machine Learning-Based Virtual Sensor
title_fullStr Data Imputation in Wireless Sensor Networks Using a Machine Learning-Based Virtual Sensor
title_full_unstemmed Data Imputation in Wireless Sensor Networks Using a Machine Learning-Based Virtual Sensor
title_sort data imputation in wireless sensor networks using a machine learning-based virtual sensor
publisher MDPI AG
series Journal of Sensor and Actuator Networks
issn 2224-2708
publishDate 2020-05-01
description Data integrity in wireless sensor networks (WSN) is very important because incorrect or missing values could result in the system making suboptimal or catastrophic decisions. Data imputation allows for a system to counteract the effect of data loss by substituting faulty or missing sensor values with system-defined virtual values. This paper proposes a virtual sensor system that uses multi-layer perceptrons (MLP) to impute sensor values in a WSN. The MLP was trained using a genetic algorithm which efficiently reached an optimal solution for each sensor node. The system was able to successfully identify and replace physical sensor nodes that were disconnected from the network with corresponding virtual sensors. The virtual sensors imputed values with very high accuracies when compared to the physical sensor values.
topic data imputation
wireless sensor network
machine learning
neural network
virtual sensor
url https://www.mdpi.com/2224-2708/9/2/25
work_keys_str_mv AT michaelmatusowsky dataimputationinwirelesssensornetworksusingamachinelearningbasedvirtualsensor
AT danieltramotsoela dataimputationinwirelesssensornetworksusingamachinelearningbasedvirtualsensor
AT adnanmabumahfouz dataimputationinwirelesssensornetworksusingamachinelearningbasedvirtualsensor
_version_ 1724745449423765504

Similar Items