Archive | 2021
A Deep Neural Network Based on Stacked Auto-encoder and Dataset Stratification in Indoor Location
Abstract
Indoor location has become the core part in the large-scale locationaware services, especially in the extendable/scalable applications. Fingerprint location by using the signal strength indicator (RSSI) of the received WiFi signal has the advantages of full coverage and strong expansibility. It also has the disadvantages of requiring data calibration and lacking samples under the dynamic environment. This paper describes a deep neural network method used for indoor positioning (DNNIP) based on stacked auto-encoder and data stratification. The experimental results show that this DNNIP has better classification accuracy than the machine learning algorithms that are based on UJIIndoorLoc dataset.