A RSSI ranging algorithm based on GWO-BP neural network

doi:10.11947/j.AGCS.2024.20220693

Abstract

Abstract:

Recently, the research on received signal strength indication (RSSI) based ranging has received a significant attention, especially in the field of Internet of things and indoor positioning. Precise distance measurement is the basis for high-precision positioning based on ranging algorithms, but the RSSI signal is highly fluctuating due to measurement noise and multi-path effects, which leads to a non-uniform mapping relationship between RSSI and the real physical distance in space. In order to enhance the mapping relationship between RSSI and real physical distance and improve the precision of RSSI ranging, this paper proposes a RSSI ranging algorithm based on GWO-BP neural network, which makes use of back propagation (BP) neural network and gray wolf optimization (GWO) algorithm. GWO algorithm has faster convergence and greater stability than particle swarm optimization (PSO), genetic algorithm (GA), differential evolution (DE), evolutionary programming (EP) and evolution strategy (ES). Furthermore, in this paper, the results of the experiments conducted in two different environments by collecting real data through the developed smartphone software show that: the root mean square error (RMSE) of the path loss model (PLM) based ranging were 2.218, 2.059 m, the RMSE of the traditional BP neural network ranging algorithm were 1.541, 1.551 m, and the RMSE of the GA algorithm-based optimized BP neural network ranging algorithm were 1.269, 1.201 m, respectively, and the RMSE of the GWO-BP neural network ranging algorithm proposed in this paper were 1.054, 0.833 m, respectively. The results indicate that the RSSI ranging algorithm proposed in this paper has higher ranging precision and better robustness.

Key words: path loss model, optimization algorithm, BP neural network, RSSI ranging, indoor positioning

CLC Number:

P228

Yiruo LIN, Kegen YU, Feiyang ZHU, Jinwei BU. A RSSI ranging algorithm based on GWO-BP neural network[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(8): 1564-1573.

Figures/Tables 11

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Tab.1

Fig.7

Tab.2

Tab.3

Fig.8

References 32

[1]	郝廉效, 余科根, 林贻若. 基于邻近点特征的地磁室内定位方法及性能分析[J]. 导航定位与授时, 2022, 9(3): 100-106.
	HAO Lianxiao, YU Kegen, LIN Yiruo. Geomagnetic indoor positioning method and performance analysis based on proximity points feature[J]. Navigation Positioning and Timing, 2022, 9(3): 100-106.
[2]	LIN Yiruo, YU Kegen, HAO Lianxiao, et al. An indoor Wi-Fi localization algorithm using ranging model constructed with transformed RSSI and BP neural network[J]. IEEE Transactions on Communications, 2022, 70(3): 2163-2177.
[3]	王彦坤, 樊红, 樊勇, 等. 一种“附近”空间关系增强的多源融合室内定位方法[J]. 测绘学报, 2024, 53(1): 118-125. DOI: 10.11947/j.AGCS.2024.20230019.
	WANG Yankun, FAN Hong, FAN Yong, et al. A “near” relation enhanced multi-sourced data fusion indoor positioning method[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(1): 118-125. DOI: 10.11947/j.AGCS.2024.20230019.
[4]	陈锐志, 钱隆, 牛晓光, 等. 基于数据与模型双驱动的音频/惯性传感器耦合定位方法[J]. 测绘学报, 2022, 51(7): 1160-1171. DOI: 10.11947/j.AGCS.2022.20220169.
	CHEN Ruizhi, QIAN Long, NIU Xiaoguang, et al. Fusing acoustic ranges and inertial sensors using a data and model dual-driven approach[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(7): 1160-1171. DOI: 10.11947/j.AGCS.2022.20220169.
[5]	SANTORO L, NARDELLO M, BRUNELLI D, et al. UWB-based indoor positioning system with infinite scalability[J]. IEEE Transactions on Instrumentation Measurement, 2023, 72: 3282299.
[6]	YU B, HUANG L, BAO Y, et al. Research status and trends of indoor positioning and navigation technology in China[J]. Journal of Geodesy and Geoinformation Science, 2023, 6(3): 87-101.
[7]	曹鸿基. 智能手机Wi-Fi RTT/PDR室内混合定位优化问题研究[D]. 徐州: 中国矿业大学, 2022.
	CAO Hongji. Research on optimization problem of smartphone indoor hybrid positioning using Wi-Fi RTT and PDR[D]. Xuzhou: China University of Mining and Technology, 2022.
[8]	龙坡, 何晶. 基于RSSI测距的最大似然估计的节点定位算法[J]. 导航定位学报, 2022, 10(4): 187-191.
	LONG Po, HE Jing. RSSI ranging-based approximate maximum-likelihood estimator node localization algorithm[J]. Journal of Navigation and Positioning, 2022, 10(4): 187-191.
[9]	常波, 张智尧, 张新荣. 一种基于接收信号强度指示测距机制的空气质量监测系统节点定位算法[J]. 电子器件, 2023, 46(4): 1056-1061.
	CHANG Bo, ZHANG Zhiyao, ZHANG Xinrong. A node positioning algorithm of air quality monitoring system based on received signal strength indicator ranging mechanism[J]. Chinese Journal of Electron Devices, 2023, 46(4): 1056-1061.
[10]	倪云峰, 王志刚, 王静, 等. 基于RSSI的井下人员定位算法改进[J]. 无线电工程, 2023, 53(3): 663-668.
	NI Yunfeng, WANG Zhigang, WANG Jing, et al. Improvement of underground personnel location algorithm based on RSSI[J]. Radio Engineering, 2023, 53(3): 663-668.
[11]	DIAGO-MOSQUERA M, ARAGON-ZAVALA A, AZPILICUETA L, et al. A 3D indoor analysis of path loss modeling using Kriging techniques[J]. IEEE Antennas and Wireless Propagation Letters, 2022, 21(6): 1218-1222.
[12]	邹东尧, 陈鹏伟, 刘宽. 一种改进的RSSI测距定位算法[J]. 电讯技术, 2019, 59(10): 1191-1196.
	ZOU Dongyao, CHEN Pengwei, LIU Kuan. An improved RSSI ranging location algorithm[J]. Telecommunication Engineering, 2019, 59(10): 1191-1196.
[13]	COLUCCIA A. Reduced-bias ML-based estimators with low complexity for self-calibrating RSS ranging[J]. IEEE Transactions on Wireless Communications, 2013, 12(3): 1220-1230.
[14]	李英玉, 陈刚. 基于人工神经网络的RSSI测距的牛顿定位算法[J]. 仪表技术与传感器, 2017(8): 122-126.
	LI Yingyu, CHEN Gang. Newton localization algorithm based on artificial neural network RSSI ranging[J]. Instrument Technique and Sensor, 2017(8): 122-126.
[15]	赵珊, 付敬奇. 基于粒子滤波模型的RSSI测距优化研究[J]. 电子测量技术, 2016, 39(3): 122-126.
	ZHAO Shan, FU Jingqi. Study of RSSI ranging optimization techniques based on particle filter model[J]. Electronic Measurement Technology, 2016, 39(3): 122-126.
[16]	费扬, 杜庆治. 基于BP神经网络模型的RSSI测距方法研究[J]. 电波科学学报, 2018, 33(2): 195-201.
	FEI Yang, DU Qingzhi. RSSI ranging method based on BP neural network model[J]. Chinese Journal of Radio Science, 2018, 33(2): 195-201.
[17]	余振宝, 卢小平, 刘英, 等. 一种改进BP神经网络的接收信号强度测距算法[J]. 测绘科学, 2020, 45(11): 48-52, 67.
	YU Zhenbao, LU Xiaoping, LIU Ying, et al. A ranging algorithm of received signal strength based on improved BP neural network[J]. Science of Surveying and Mapping, 2020, 45(11): 48-52, 67.
[18]	余振宝, 卢小平, 陶晓晓, 等. 一种GA-BP神经网络模型的RSSI测距算法[J]. 导航定位学报, 2020, 8(2): 63-68.
	YU Zhenbao, LU Xiaoping, TAO Xiaoxiao, et al. RSSI ranging algorithm based on GA-BP neural network model[J]. Journal of Navigation and Positioning, 2020, 8(2): 63-68.
[19]	姚军, 甄梓越, 马宇静. 基于BP神经网络的RSSI测距优化算法[J]. 电波科学学报, 2022, 37(4): 663-669.
	YAO Jun, ZHEN Ziyue, MA Yujing. RSSI ranging optimization algorithm based on BP neural network[J]. Chinese Journal of Radio Science, 2022, 37(4): 663-669.
[20]	GUIDARA A, FERSI G, BEN JEMAA M, et al. A new deep learning-based distance and position estimation model for range-based indoor localization systems[J]. Ad Hoc Networks, 2021, 114: 102445.
[21]	DANG Jiahao, XUE Wei, CI Longfei, et al. RSSI distance model based on BP neural network[C]//Proceedings of 2022 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA). Dalian: IEEE, 2022: 291-294.
[22]	MIRJALILI S, MIRJALILI S M, LEWIS A. Grey wolf optimizer[J]. Advances in Engineering Software, 2014, 69: 46-61.
[23]	徐文染, 陈燚涛. 基于Friis传输公式的RSSI测距模型研究[J]. 武汉纺织大学学报, 2022, 35(4): 38-42.
	XU Wenran, CHEN Yitao. Research on RSSI ranging model based on friis transmission formula[J]. Journal of Wuhan Textile University, 2022, 35(4): 38-42.
[24]	朱梦豪, 卢小平, 路泽忠, 等. 融合小波变换与神经网络的RSSI室内测距算法[J]. 测绘通报, 2020(1): 50-54.
	ZHU Menghao, LU Xiaoping, LU Zezhong, et al. RSSI indoor ranging algorithm based on wavelet transform and neural network[J]. Bulletin of Surveying and Mapping, 2020(1): 50-54.
[25]	ZHANG J, LI P, ZHANG H, et al. Investigation on the relationship between population density and satellite image features：a deep learning based approach[J]. Journal of Geodesy and Geoinformation Science, 2022, 5(4): 50-58.
[26]	WANG M, YAN Z, FENG Y, et al. Multi-task learning of semantic segmentation and height estimation for multi-modal remote sensing images[J]. Journal of Geodesy and Geoinformation Science, 2023, 6(4): 27-39.
[27]	WRIGHT L G, ONODERA T, STEIN M M, et al. Deep physical neural networks trained with backpropagation[J]. Nature, 2022, 601: 549-555.
[28]	HENDERI H. Comparison of Min-Max normalization and Z-Score normalization in the K-nearest neighbor (KNN) algorithm to test the accuracy of types of breast cancer[J]. International Journal of Informatics and Information Systems, 2021, 4(1): 13-20.
[29]	王嵘冰, 徐红艳, 李波, 等. BP神经网络隐含层节点数确定方法研究[J]. 计算机技术与发展, 2018, 28(4): 31-35.
	WANG Rongbing, XU Hongyan, LI Bo, et al. Research on method of determining hidden layer nodes in BP neural network[J]. Computer Technology and Development, 2018, 28(4): 31-35.
[30]	沈花玉, 王兆霞, 高成耀, 等. BP神经网络隐含层单元数的确定[J]. 天津理工大学学报, 2008, 24(5): 13-15.
	SHEN Huayu, WANG Zhaoxia, GAO Chengyao, et al. Determining the number of BP neural network hidden layer units[J]. Journal of Tianjin University of Technology, 2008, 24(5): 13-15.
[31]	CUI Xuerong, YANG Jin, LI Juan, et al. Improved genetic algorithm to optimize the Wi-Fi indoor positioning based on artificial neural network[J]. IEEE Access, 2020, 8: 74914-74921.
[32]	费扬. 基于BP神经网络的室内定位指纹算法研究[D]. 昆明: 昆明理工大学, 2018.
	FEI Yang. Research on indoor location fingerprint algorithm based on BP neural network[D]. Kunming: Kunming University of Science and Technology, 2018.

n的取值	ME	STD	RMSE
n=2.0	3.908	3.114	4.997
n=2.4	3.561	2.643	4.435
n=2.8	4.310	2.157	4.820
n=3.2	5.399	2.553	5.972
n=3.6	6.595	3.671	7.548
n=4.0	8.227	4.412	9.335

算法	ME	STD	RMSE	Max	Mid
PLM	1.572	1.564	2.218	6.860	1.005
BP	1.168	1.005	1.541	3.932	0.710
GA－BP	0.998	0.784	1.269	3.133	0.841
GWO－BP	0.803	0.684	1.054	3.000	0.660

算法	ME	STD	RMSE	Max	Mid
PLM	1.250	1.637	2.059	5.600	0.504
BP	0.968	1.211	1.551	4.032	0.468
GA－BP	0.818	0.879	1.201	4.125	0.426
GWO－BP	0.609	0.568	0.833	2.758	0.478