A Comprehensive and Reproducible Comparison of Clustering and Optimization Rules in Wi-Fi Fingerprinting
| Autor: | Philipp Richter, Adriano Moreira, Miguel Matey-Sanz, Elena Simona Lohan, Germán Martín Mendoza-Silva, Joaquín Torres-Sospedra, Joaquín Huerta, Sergio Trilles |
|---|---|
| Přispěvatelé: | Tampere University, Electrical Engineering, Universidade do Minho |
| Rok vydání: | 2020 |
| Předmět: |
Science & Technology
Indoor positioning Computer Networks and Communications Computer science Computational costs 213 Electronic automation and communications engineering electronics Library science 020206 networking & telecommunications 02 engineering and technology Benchmarking Engenharia Eletrotécnica Eletrónica e Informática [Engenharia e Tecnologia] Clustering Reproducibility Insignia Wi-Fi fingerprinting Time complexity 0202 electrical engineering electronic engineering information engineering Electrical and Electronic Engineering Cluster analysis Software Engenharia e Tecnologia::Engenharia Eletrotécnica Eletrónica e Informática |
| Zdroj: | Repositório Científico de Acesso Aberto de Portugal Repositório Científico de Acesso Aberto de Portugal (RCAAP) instacron:RCAAP |
| Popis: | Wi-Fi fingerprinting is a well-known technique used for indoor positioning. It relies on a pattern recognition method that compares the captured operational fingerprint with a set of previously collected reference samples (radio map) using a similarity function. The matching algorithms suffer from a scalability problem in large deployments with a huge density of fingerprints, where the number of reference samples in the radio map is prohibitively large. This paper presents a comprehensive comparative study of existing methods to reduce the complexity and size of the radio map used at the operational stage. Our empirical results show that most of the methods reduce the computational burden at the expense of a degraded accuracy. Among the studied methods, only k-means, affinity propagation, and the rules based on the strongest access point properly balance the positioning accuracy and computational time. In addition to the comparative results, this paper also introduces a new evaluation framework with multiple datasets, aiming at getting more general results and contributing to a better reproducibility of new proposed solutions in the future. This project have been funded by: Ministerio de Ciencia, Innovacion y Universidades – INSIGNIA project (Programa Torres-Quevedo, PTQ2018-009981), Academy of Finland – PRISMA project (#313039); FCT – Fundação para a Ciencia e a Tecnologia within the R&D Units Project Scope: UIDB/00319/2020; UJI’s research programme (PREDOC/2016/55 and POSDOC-B/2018/12). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|