KOMPARASI ALGORITMA MENGGUNAKAN METODE FINGERPRINTING PADA INDOOR POSITIONING SYSTEM

M Rizky Astari, NIM.: 21206051010 (2023) KOMPARASI ALGORITMA MENGGUNAKAN METODE FINGERPRINTING PADA INDOOR POSITIONING SYSTEM. Masters thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (KOMPARASI ALGORITMA MENGGUNAKAN METODE FINGERPRINTING PADA INDOOR POSITIONING SYSTEM) 21206051010_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf - Published Version Download (3MB) | Preview
	Text (KOMPARASI ALGORITMA MENGGUNAKAN METODE FINGERPRINTING PADA INDOOR POSITIONING SYSTEM) 21206051010_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf - Published Version Restricted to Registered users only Download (4MB) | Request a copy

Abstract

Today's most commonly applied positioning system is the Global Positioning System (GPS) which is an outdoor positioning technology that is considered accurate by the public, but it will be a problem if the device is located indoors which will certainly be difficult to read by GPS because GPS signals cannot penetrate walls properly. Indoor positioning systems are currently being developed by many researchers to overcome the shortcomings of GPS. Wi-Fi Access Point signals are used as research material because they are the most common to be used by several studies. This study aims to compare the classification algorithms KNN, SVM, Random Forest and C 4.5 to find out which algorithm is superior in providing accuracy calculations. The method used is fingerprinting which is the process of taking signal strength data in each room, the data is used for location determination calculations using several algorithms. The research was conducted in the Integrated Laboratory Building of UIN Sunan Kalijaga using 30 rooms with a total dataset of 5977 data. The experimental results show that the Random Forest algorithm gets an accuracy rate of 83%, C4.5 81%, KNN 80% and the lowest accuracy rate is obtained by the SVM algorithm with an accuracy value of 57%.

Share this knowledge with your friends :

Actions (login required)

View Item