Název:	Trilateration-based Indoor Location using Supervised Learning Algorithms
Autoři:	Landívar, Jerry Ormaza, Carolina Asanza, Víctor Ojeda, Verónica Avilés, Juan Carlos Peluffo-Ordóñez, Diego H.
Citace zdrojového dokumentu:	2022 International Conference on Applied Electronics: Pilsen, 6th – 7th September 2022, Czech Republic, p. 19-24.
Datum vydání:	2022
Nakladatel:	Fakulta elektrotechnická ZČU
Typ dokumentu:	konferenční příspěvek conferenceObject
URI:	http://hdl.handle.net/11025/49843
ISBN:	978-1-6654-9482-3
Klíčová slova:	trilaterace;strojové učení;RSSI;vnitřní polohovací systémy
Klíčová slova v dalším jazyce:	trilateration;machine learning;RSSI;Indoor Positioning Systems
Abstrakt v dalším jazyce:	The indoor positioning system (IPS) has a wide range of applications, due to the advantages it has over Global Positioning Systems (GPS) in indoor envi- ronments. Due to the biosecurity measures established by the World Health Organization (WHO), where the social distancing is provided, being stricter in indoor environ- ments. This work proposes the design of a positioning system based on trilateration. The main objective is to predict the positioning in both the ‘x’ and ‘y’ axis in an area of 8 square meters. For this purpose, 3 Access Points (AP) and a Mobile Device (DM), which works as a raster, have been used. The Received Signal Strength Indication (RSSI) values measured at each AP are the variables used in regression algorithms that predict the x and y position. In this work, 24 regression algorithms have been evaluated, of which the lowest errors obtained are 70.322 [cm] and 30.1508 [cm], for the x and y axes, respectively
Práva:	© IEEE
Vyskytuje se v kolekcích:	Applied Electronics 2022 Applied Electronics 2022

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.