| PEDESTRIAN DEAD RECKONING USING SMARTPHONES SENSORS: AN EFFICIENT INDOOR POSITIONING SYSTEM IN COMPLEX BUILDINGS OF SMART CITIES |
| Paper ID : 1355-SMPR |
| Authors: |
|
Esmaiel Saadatzadeh *1, Rahim Ali Abaspour2, Alireza chehreghan3 1Department of surveying and Geomatics Engineering, College of Engineering, University of Tehran,Tehran, Iran 2School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran, Iran. 3Mining Engineering Faculty, Sahand University of Technology, Tabriz, Iran. |
| Abstract: |
| This paper proposes a method of indoor positioning using the Pedestrian Dead Reckoning method based on smartphone sensors and the recognition of the state of phone holding. In the first phase, we classify and evaluate the samples based on the properties feature vectors from sensor data with three classification algorithms, Decision Tree (DT), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) smartphone holding mode. From the perspective of the classification algorithm, the Decision Tree algorithm has the best performance in terms of processing time and classification. In the second phase, the step detection process, the step length estimation, and the estimation of the direction of the user's movement for each step are taken to determine the position of the user. We also use the Map Matching algorithm by the building plan to correct false positions. Finally, the final accuracy obtained from normal-speed walking was obtained for three different paths of circle, rectangle, and square, equal to 1.8 m, 2.1 m and 1.9 m, respectively. |
| Keywords: |
| Smart buildings, Indoor positioning, Pedestrian dead reckoning, Smartphone sensors, Holding mode, Smartphone, Map matching |
| Status : Conditional Accept (Poster) |
