论文部分内容阅读
目前,基于RSSI(received signal strength indication)的指纹定位算法由于低成本、易实施的特性,逐渐成为室内定位技术的研究热点。然而,基于RSSI的WiFi指纹定位受到指纹点观测质量的影响,RSSI抖动较大时引起定位精度较低。考虑到GPR(Gaussian process regression)模型能够有效地平滑时间序列信号,提出了基于GPR模型的WiFi指纹定位改进算法。实验结果表明,该算法能够有效提高定位精度,定位精度可达到1m,点位误差在小于1.5m限差时,其可靠度可达到83.3%。
At present, the fingerprinting algorithm based on received signal strength indication (RSSI) has gradually become a research hotspot in indoor positioning technology due to its low cost and easy implementation. However, the location of WiFi fingerprints based on RSSI is affected by the quality of the fingerprints observed. When the RSSI jitter is greater, the positioning accuracy is lower. Considering that the GPR (Gaussian process regression) model can effectively smooth the time series signals, an improved algorithm based on the GPR model for WiFi fingerprinting is proposed. Experimental results show that the proposed algorithm can effectively improve the positioning accuracy and the positioning accuracy can reach 1m. When the error is less than 1.5m, the reliability of the algorithm can reach 83.3%.