Analysis of an Indoor Positioning System for Forklifts Using WiFi Fingerprinting

This paper presents a preliminary analysis of an Indoor Positioning System (IPS) designed for forklifts using Wi-Fi signal fingerprinting and the K-Nearest Neighbors (KNN) algorithm. The system utilizes M5stack (ESP32) devices programmed with MicroPython and collects Wi-Fi signal data from multiple...

Full description

Saved in:
Bibliographic Details
Published in2024 International Visualization, Informatics and Technology Conference (IVIT) pp. 134 - 137
Main Authors Zuhairi, Megat F., Jikaraji, Arfip, Dao, Hassan, Sulong, Amart
Format Conference Proceeding
LanguageEnglish
Published IEEE 07.08.2024
Subjects
Accuracy
Fingerprint recognition
Indoor positioning system
Indoor positioning systems
K-Nearest Neighbors
Navigation
Nearest neighbor methods
Received Signal Strength Identification
Reliability
Signal processing
Signal processing algorithms
System performance
WIFI
Wireless fidelity
Online AccessGet full text
DOI10.1109/IVIT62102.2024.10692721

Cover

More Information
Summary:This paper presents a preliminary analysis of an Indoor Positioning System (IPS) designed for forklifts using Wi-Fi signal fingerprinting and the K-Nearest Neighbors (KNN) algorithm. The system utilizes M5stack (ESP32) devices programmed with MicroPython and collects Wi-Fi signal data from multiple access points. By creating a fingerprint database and employing KNN for position determination, the system achieved a location accuracy rate of 86% in a precision test of 15 reference points and an overall accuracy rate of 90% with an average error of 1.5 meters. These results demonstrate the system's potential for enhancing navigation and efficiency in warehouse operations.
DOI:10.1109/IVIT62102.2024.10692721