Energy-Efficient Indoor Localization WiFi-Fingerprint System: An Experimental Study
In order to apply indoor localization systems in real environments it is necessary to provide an accurate location without implying a high impact on the user's normal behaviour. To achieve this goal, in this paper, a combination of battery saving techniques with a system based on WiFi ngerprint...
| Autores: | , , , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2019 |
| País: | España |
| Institución: | Universidad de Sevilla (US) |
| Repositorio: | idUS. Depósito de Investigación de la Universidad de Sevilla |
| OAI Identifier: | oai:idus.us.es:11441/125569 |
| Acceso en línea: | https://hdl.handle.net/11441/125569 https://doi.org/10.1109/ACCESS.2019.2952221 |
| Access Level: | acceso abierto |
| Palabra clave: | Indoor localization WiFi ngerprinting RSSI battery life KNN naive Bayes dataset |
| Sumario: | In order to apply indoor localization systems in real environments it is necessary to provide an accurate location without implying a high impact on the user's normal behaviour. To achieve this goal, in this paper, a combination of battery saving techniques with a system based on WiFi ngerprinting is proposed. This is done by transferring the location calculation workload to the server, leaving user's mobile devices the only responsibility of making periodic WiFi network scans at dynamic intervals based on user activity, through an application running on background. There are not many studies analyzing energy consumption of existing localization systems, even though it is an important factor in real applications. In this paper, both energy consumption and accuracy are analyzed, having an energy consumption of only 0.8 Wh (having a 3.7 V battery) during a 24-hour cycle and an average localization error of 4.51 meters. Worth to mention that as computation is done on server side the system can be expanded to multiple buildings and oors. Finally, the dataset used in this paper has been published making possible to test new algorithms in the same environment. |
|---|