Education, Science, Technology, Innovation and Life
Open Access
Sign In

Research on Wi-Fi Indoor Positioning Technology based on Deep Neural Network

Download as PDF

DOI: 10.23977/cii2019.84

Author(s)

Yahui Zhang

Corresponding Author

Yahui Zhang

ABSTRACT

Various research works have been proposed for Wi-Fi based indoor positioning, such as K-Nearest Neighbor Algorithm (KNN), Weighted K-nearest Neighbor Algorithm (WKNN), and Bayesian Algorithm, but these algorithms have different complexity due to indoor environment. In order to make the indoor positioning more precise, this paper designs a Wi-Fi indoor positioning technology based on deep neural network. The value of RSSI obtained is preprocessed to adapt to the neural network, and then the system further trains the value of RSSI according to the actual position to obtain a more accurate indoor positioning model. Through the test, the positioning algorithm in the paper has higher positioning accuracy and better stability.

KEYWORDS

Deep Neural Network (DNN), indoor positioning, Received Signal Strength (RSSI), offline training stage

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.