文章基本信息

标题：Indoor Wireless LAN Fingerprints Parameterisation and Classification in Academic Environments
本地全文：下载
作者：Moses E. Ekpenyong
期刊名称：Research Journal of Applied Sciences
印刷版ISSN：1815-932X
电子版ISSN：1993-6079
出版年度：2018
卷号：13
期号：9
页码：499-512
DOI：10.3923/rjasci.2018.499.512
语种：English
出版社：Medwell Journals
摘要：In this study, we explore Machine Learning (ML) techniques to indoor Wireless Local Area Network(WLAN) Fingerprints (FPs) parameterisation and classification in academic environments. First, relevant indoorlocation (received signal strength indication and site specific) features were abstracted from the proposed areaof study (University of Uyo, Nigeria) in a previous research to serve as fingerprints to the current research.Second, an unsupervised principal component analysis methodology was employed to produce PrincipalComponent Dominant Features (PCDFs) for the first three principal components (components with eigenvaluesof at least unity). These components revealed the degree of variances exhibited by the selected FPs. Third,using three ML classifiers (Support Vector Machine: SVM, k-Nearest Neighbour: k-NN, decision tree andAdaptive Neuro-Fuzzy Inference System: ANFIS) a classification of the PCDFs was performed. Results obtainedshowed that decision tree and linear SVM classifiers were excellent at predicting large datasets an importantprecursor to accommodating scalability in WLAN environments and areas with localisation challenges suchas difficult terrains, heavy interference and spatial or uneven distribution of wireless infrastructure as theseclassifiers maintained high classification accuracies of above 90%. For small datasets, ANFIS gave goodclassification accuracy when compared with other classifiers.
关键词：Fingerprint;indoor localisation;pattern classification;principal component analysis;receivedsignal strength;machine learning