IoT 18(16): e5

Research Article

Improving Indoor Localization Based on Artificial Neural Network Technology

Download101 downloads
  • @ARTICLE{10.4108/eai.31-10-2018.159633,
        author={Chi  Han  Chen and Rung  Shiang  Cheng},
        title={Improving Indoor Localization Based on Artificial Neural Network Technology},
        journal={EAI Endorsed Transactions on Internet of Things},
        volume={4},
        number={16},
        publisher={EAI},
        journal_a={IOT},
        year={2018},
        month={10},
        keywords={Internet of things, Sensors, Smart devices, Machine-Type Communications, Prototypes and demonstrators, Embedded systems.},
        doi={10.4108/eai.31-10-2018.159633}
    }
    
  • Chi Han Chen
    Rung Shiang Cheng
    Year: 2018
    Improving Indoor Localization Based on Artificial Neural Network Technology
    IOT
    EAI
    DOI: 10.4108/eai.31-10-2018.159633
Chi Han Chen1, Rung Shiang Cheng2,*
  • 1: Department of Information Technology, Overseas Chinese University, Taiwan
  • 2: Overseas Chinese University, Taiwan
*Contact email: rscheng@ocu.edu.tw

Abstract

Wireless networks are ubiquitous nowadays and hence provide a promising approach for indoor localization. Many algorithms have been proposed for exploiting wireless signals for localization purposes. Among the methods, ANNbased methods have attracted particular attention due to their robustness in complex signal environments. However, their accuracy is still degraded by multi-path effects, signal fluctuations, and so on. Accordingly, this study commences by examining the effects of fluctuations in the received signal strength indicator (RSSI) measurement on the accuracy of an ANN-based localization algorithm. This study list some strategies and illustrate by simulation experiment. Based on the investigation results, a systematic methodology is proposed for improving the localization performance by increasing the number of APs. The feasibility of the proposed method is demonstrated by means of numerical simulations.