Institutional Repository of Vilnius University
Navigacija patalpose naudojant Bluetooth stotelių ir išmaniojo įrenginio jutiklių duomenis /
Abstract
dc:descriptionAsthesizeandcomplexityofthepremisesincreases,theneedforaconvenientwaytonavigate in such premises increases. Indoor navigation can be accomplished using Bluetooth stations and smart device sensors. This work analyzes the aforementioned indoors navigation method using a fingerprintmapbasedonavailableandcollecteddata. Themainpurposeofthisworkistofindout theinfluenceofsmartdevicesensorsforindoornavigation. Pythonprogramminglanguageandthe "scikit-learn"machinelearninglibrarywereusedtoachievethat. Theworkanalyzesandcompares the accuracy of the classification and regression model coordinate predictions with and without compassdata. Theinfluenceofdatanormalizationisalsoinvestigated. Thestudyconcludedthatit is best to use the k-nearest neighbor regression algorithm to determine the coordinates. There was no benefit in using compass data to predict longitude, but when predicting latitude, the benefits were significant. Regression algorithms did not benefit from data normalization for prediction accuracy.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2020
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Alenskas, Domantas,
- Contributors dc:contributor
-
- Raila, Tomas
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD81918339&prefLang=en_US