Outlier detection in indoor localization and Internet of Things (IoT) using machine learning

Bhatti, Mansoor Ahmed and Riaz, Rabia and Rizvi, Sanam Shahla and Shokat, Sana and Riaz, Farina ORCID: https://orcid.org/0000-0001-9223-7117 and Kwon, Se Jin (2020) Outlier detection in indoor localization and Internet of Things (IoT) using machine learning. Journal of Communications and Networks, 22 (3). pp. 236-243. ISSN 1229-2370

[img]
Preview
Text (Published Version)
Outlier_detection_in_indoor_localization_and_Internet_of_Things_IoT_using_machine_learning.pdf
Available under License Creative Commons Attribution Non-commercial 4.0.

Download (860kB) | Preview

Abstract

In Internet of things (IoT) millions of devices are intel- ligently connected for providing smart services. Especially in in- door localization environment, that is one of the most concerning topic of smart cities, internet of things and wireless sensor net- works. Many technologies are being used for localization purpose in indoor environment and Wi-Fi using received signal strengths (RSSs) is one of them. Wi-Fi RSSs are sensitive to reflection, re- fraction, interference and channel noise that cause irregularity in signal strengths. The irregular and anomalous RSS values, used in a Wi-Fi indoor localization environment, cannot define the location of any unknown node correctly. Therefore, this research has de- veloped an outlier detection technique named as iF_Ensemble for Wi-Fi indoor localization environment by analyzing RSSs us- ing the combination of supervised, unsupervised and ensemble ma- chine learning methods. In this research isolation forest (iForest) is used as an unsupervised learning method. Supervised learning method includes support vector machine (SVM), K-nearest neigh- bor (KNN) and random forest (RF) classifiers with stacking that is an ensemble learning method. For the evaluation purpose accu- racy, precision, recall, F-score and ROC-AUC curve are used. The evaluation of used machine learning method provides high accu- racy of 97.8 percent with proposed outlier detection methods and almost 2 percent improvement in the accuracy of localization pro- cess in indoor environment after eliminating outliers.


Statistics for USQ ePrint 44024
Statistics for this ePrint Item
Item Type: Article (Commonwealth Reporting Category C)
Refereed: Yes
Item Status: Live Archive
Faculty/School / Institute/Centre: No Faculty
Faculty/School / Institute/Centre: No Faculty
Date Deposited: 02 Nov 2021 01:37
Last Modified: 03 Nov 2021 06:37
Uncontrolled Keywords: Internet of things, localization, outliers, outliers de- tection
Fields of Research (2008): 08 Information and Computing Sciences > 0805 Distributed Computing > 080503 Networking and Communications
08 Information and Computing Sciences > 0805 Distributed Computing > 080505 Web Technologies (excl. Web Search)
Fields of Research (2020): 46 INFORMATION AND COMPUTING SCIENCES > 4606 Distributed computing and systems software > 460609 Networking and communications
Identification Number or DOI: https://doi.org/10.1109/JCN.2020.000018
URI: http://eprints.usq.edu.au/id/eprint/44024

Actions (login required)

View Item Archive Repository Staff Only