Publicação
L/F-CIPS: Collaborative indoor positioning for smartphones with lateration and fingerprinting
| Resumo: | The demand for indoor location-based services and the wide availability of mobile devices have triggered research into new positioning systems able to provide accurate indoor positions using smartphones. However, accurate solutions require a complex implementation and long-term maintenance of their infrastructure. Collaborative systems may help to alleviate these drawbacks. In this paper, we propose a smartphone-based collaborative architecture using neural networks and received signal strength, which exploits the built-in wireless communication technologies in smartphones and the collaboration between devices to improve traditional positioning systems without additional deployment. Experiments are carried out in two real-world scenarios, demonstrating that our proposed architecture enhances the position accuracy of traditional indoor positioning systems. |
|---|---|
| Autores principais: | Pascacio, Pavel |
| Outros Autores: | Torres-Sospedra, Joaquín; Casteleyn, Sven; Lohan, Elena Simona; Nurmi, Jari |
| Assunto: | Calibration Collaboration Collaborative Indoor Positioning Computer architecture Fingerprint recognition Fingerprinting Lateration Neural Networks Received Signal Strength Sensors Smart phones Wireless fidelity |
| Ano: | 2023 |
| País: | Portugal |
| Tipo de documento: | artigo |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade do Minho |
| Idioma: | inglês |
| Origem: | RepositóriUM - Universidade do Minho |
| Resumo: | The demand for indoor location-based services and the wide availability of mobile devices have triggered research into new positioning systems able to provide accurate indoor positions using smartphones. However, accurate solutions require a complex implementation and long-term maintenance of their infrastructure. Collaborative systems may help to alleviate these drawbacks. In this paper, we propose a smartphone-based collaborative architecture using neural networks and received signal strength, which exploits the built-in wireless communication technologies in smartphones and the collaboration between devices to improve traditional positioning systems without additional deployment. Experiments are carried out in two real-world scenarios, demonstrating that our proposed architecture enhances the position accuracy of traditional indoor positioning systems. |
|---|