A novel cell phone localization solution for trapped victims based on compressed RSSI fluctuation range and PSO-BP neural network

Abstract

With the frequent occurrence of global earthquake disasters in recent years, quickly and accurately locating trapped people is the key to reducing the mortality rate of earthquake disasters. This paper proposes a cell phone localization solution for trapped people that can be rapidly deployed after an earthquake. This solution locates the buried cell phone by collecting its received WiFi signal strength indication (RSSI) data. Reducing the fluctuation of RSSI value is crucial to accurately locating the buried cell phone. We filter RSSI data outliers by hybrid filtering and propose a fluctuation range compression factor Q to reduce the fluctuation range of RSSI data. In order to adapt to the compressed RSSI data fluctuation range, the processed RSSI data were grouped. The grouped data are then imported into the PSO-BP neural network training to build the ranging model. So that there is a mapping relationship between RSSI data and trapped distance. The established ranging model is denoted as the HFQBP ranging model. After establishing the ranging model, the cell phone is localized by an Optimized Multilateration (OM) algorithm. For simplicity, this algorithm is named HFQBP-OM. In the experimental phase, we combined the method proposed in this paper with other methods, resulting in three different localization algorithms: HFQBP-WSC, PL-OM, and PL-WSC. And compared with the algorithms in this paper. The results indicate that the algorithm HFQBP-OM proposed in this paper has improved the total average accuracy of the nine localization points by 34.7%, 54.8%, and 58.9% compared to HFQBP-WSC, PL-OM, and PL-WSC, respectively. The HFQBP-OM algorithm has higher accuracy and stability. Also, it should be noted that the localization solution proposed in this paper uses smartphones connected to WiFi probes to collect RSSI data of the WiFi signal of the buried cell phone. Use a laptop computer to solve the localization coordinates. Smartphones and laptops are so popular that WiFi probes are the only special equipment needed. WiFi probe is inexpensive. It reduces the difficulty of implementing the localization solution in this paper and increases the generalizability of the solution.