Using the MNL model in a mobile device's indoor positioning

• Main Authors: Xie, Feng, Xie, Ming, Wang, Cheng
• Other Authors: School of Mechanical and Aerospace Engineering
• Format: Article
• Language: English
• Published: 2023
• Subjects: Engineering::Mechanical engineering; Mobile Devices; Indoor Positioning
• Online Access: https://hdl.handle.net/10356/171697
• Institution: Nanyang Technological University

Indoor Positioning Services (IPS) allow mobile devices or bionic robots to locate themselves quickly and accurately in large commercial complexes, shopping malls, supermarkets, exhibition venues, parking garages, airports, or train hubs, and access surrounding information. Wi-Fi-based indoor positioning technology can use existing WLAN networks, and has promising prospects for broad market applications. This paper presents a method using the Multinomial Logit Model (MNL) to generate Wi-Fi signal fingerprints for positioning in real time. In an experiment, 31 locations were randomly selected and tested to validate the model, showing mobile devices could determine their locations with an accuracy of around 3 m (2.53 m median).