Effect of different signal weighting function of magnetic field using KNN for indoor localization

The present work aimed to investigate the signal weighting function based on magnetic field (MF) models to obtain accurate location estimates for indoor positioning system. We compare the state-of-the-art Euclidean distance and three proposed different signal weighting function namely actual weight,...

Full description

Bibliographic Details
Main Authors: Bundak, Caceja Elyca, Abd Rahman, Mohd Amiruddin, Abd Karim, Muhammad Khalis, Osman, Nurul Huda
Format: Article
Published: Springer 2022
_version_ 1796984022114500608
author Bundak, Caceja Elyca
Abd Rahman, Mohd Amiruddin
Abd Karim, Muhammad Khalis
Osman, Nurul Huda
author_facet Bundak, Caceja Elyca
Abd Rahman, Mohd Amiruddin
Abd Karim, Muhammad Khalis
Osman, Nurul Huda
author_sort Bundak, Caceja Elyca
collection UPM
description The present work aimed to investigate the signal weighting function based on magnetic field (MF) models to obtain accurate location estimates for indoor positioning system. We compare the state-of-the-art Euclidean distance and three proposed different signal weighting function namely actual weight, square weight and square root weight which used to estimate location using MF. Additionally, the effect of signal weighting function is investigated further using multiple k value of K nearest neighbor (KNN) algorithm. According to the results, the square root weighting function have low position error of 8.156 m than Euclidean distance with improvement of 5.5%. We also found that the use of (k = 5) of KNN for square weight of my distance measure give the lowest mean estimation error of 7.188 m.
first_indexed 2024-03-06T11:14:40Z
format Article
id upm.eprints-101100
institution Universiti Putra Malaysia
last_indexed 2024-03-06T11:14:40Z
publishDate 2022
publisher Springer
record_format dspace
spelling upm.eprints-1011002023-06-17T23:29:43Z http://psasir.upm.edu.my/id/eprint/101100/ Effect of different signal weighting function of magnetic field using KNN for indoor localization Bundak, Caceja Elyca Abd Rahman, Mohd Amiruddin Abd Karim, Muhammad Khalis Osman, Nurul Huda The present work aimed to investigate the signal weighting function based on magnetic field (MF) models to obtain accurate location estimates for indoor positioning system. We compare the state-of-the-art Euclidean distance and three proposed different signal weighting function namely actual weight, square weight and square root weight which used to estimate location using MF. Additionally, the effect of signal weighting function is investigated further using multiple k value of K nearest neighbor (KNN) algorithm. According to the results, the square root weighting function have low position error of 8.156 m than Euclidean distance with improvement of 5.5%. We also found that the use of (k = 5) of KNN for square weight of my distance measure give the lowest mean estimation error of 7.188 m. Springer 2022-07-16 Article PeerReviewed Bundak, Caceja Elyca and Abd Rahman, Mohd Amiruddin and Abd Karim, Muhammad Khalis and Osman, Nurul Huda (2022) Effect of different signal weighting function of magnetic field using KNN for indoor localization. Lecture Notes in Electrical Engineering, 730. 571 - 581. ISSN 1876-1100; ESSN: 1876-1119 https://link.springer.com/chapter/10.1007/978-981-33-4597-3_52 10.1007/978-981-33-4597-3_52
spellingShingle Bundak, Caceja Elyca
Abd Rahman, Mohd Amiruddin
Abd Karim, Muhammad Khalis
Osman, Nurul Huda
Effect of different signal weighting function of magnetic field using KNN for indoor localization
title Effect of different signal weighting function of magnetic field using KNN for indoor localization
title_full Effect of different signal weighting function of magnetic field using KNN for indoor localization
title_fullStr Effect of different signal weighting function of magnetic field using KNN for indoor localization
title_full_unstemmed Effect of different signal weighting function of magnetic field using KNN for indoor localization
title_short Effect of different signal weighting function of magnetic field using KNN for indoor localization
title_sort effect of different signal weighting function of magnetic field using knn for indoor localization
work_keys_str_mv AT bundakcacejaelyca effectofdifferentsignalweightingfunctionofmagneticfieldusingknnforindoorlocalization
AT abdrahmanmohdamiruddin effectofdifferentsignalweightingfunctionofmagneticfieldusingknnforindoorlocalization
AT abdkarimmuhammadkhalis effectofdifferentsignalweightingfunctionofmagneticfieldusingknnforindoorlocalization
AT osmannurulhuda effectofdifferentsignalweightingfunctionofmagneticfieldusingknnforindoorlocalization