A regression model-based method for indoor positioning with compound location fingerprints
作者机构:Hewlett-Packard JapanLtdTokyoJapan Graduate School of EngineeringChiba UniversityChibaJapan
出 版 物:《Geo-Spatial Information Science》 (地球空间信息科学学报(英文))
年 卷 期:2019年第22卷第2期
页 面:107-113,I0003页
核心收录:
学科分类:0303[法学-社会学] 0709[理学-地质学] 0809[工学-电子科学与技术(可授工学、理学学位)] 08[工学] 0708[理学-地球物理学] 0705[理学-地理学] 0813[工学-建筑学] 0833[工学-城乡规划学] 0812[工学-计算机科学与技术(可授工学、理学学位)]
主 题:Indoor positioning integrated estimation radio fingerprinting dead reckoning machine learning non-linear regression
摘 要:This paper proposed and evaluated an estimation method for indoor *** method combines location fingerprinting and dead reckoning differently from the conventional *** uses compound location fingerprints,which are composed of radio fingerprints at multiple points of time,that is,at multiple positions,and displacements between them estimated by dead *** avoid errors accumulated from dead reckoning,the method uses short-range dead *** method was evaluated using 16 Bluetooth beacons installed in a student room with the dimensions of 11×5 m with furniture *** Received Signal Strength Indicator(RSSI)values of the beacons were collected at 30 measuring points,which were points at the intersections on a 1×1 m grid with no obstacles.A compound location fingerprint is composed of RSSI vectors at two points and a displacement vector between *** Forests(RF)was used to build regression models to estimate positions from location *** root mean square error of position estimation was 0.87 m using 16 Bluetooth *** error is lower than that received with a single-point baseline model,where a feature vector is composed of only RSSI values at one *** results suggest that the proposed method is effective for indoor positioning.