Abstract
The performance of an Artificial Neural Network (ANN)-based algorithm is subject to the way the feature data is extracted. This is a common issue when applying the ANN to indoor fingerprinting-based localization where the signal is unstable. To date, there is not adequate feature extraction method that can significantly mitigate the influence of the receiver signal strength indicator (RSSI) variation that degrades the performance of the ANN-based indoor fingerprinting algorithm. In this work, a wavelet scattering transform is used to extract reliable features that are stable to small deformation and rotation invariant. The extracted features are used by a deep neural network (DNN) model to predict the location. The zeroth and the first layer of decomposition coefficients were used as features data by concatenating different scattering path coefficients. The proposed algorithm has been validated on real measurements and has achieved good performance. The experimentation results demonstrate that the proposed feature extraction method is stable to the RSSI variation.
Highlights
Indoor location-based services such as tracking, patient monitoring, navigation, and localization are relevant for today’s society and smart cities [1,2]
Approaches based on the receiver signal strength (RSS) measurement such as fingerprinting algorithms have attracted a lot of attention
All datasets used in this paper are Wi-Fi receiver signal strength indicator (RSSI) datasets
Summary
Indoor location-based services such as tracking, patient monitoring, navigation, and localization are relevant for today’s society and smart cities [1,2]. The GPS system is generally inefficient in indoor and some outdoor environments due to the signal attenuation and weakened or unavailable signal respectively To support such services and overcome the limitations of the GPS system, several approaches have been investigated. In the online phase, when a new RSSI data is collected in the same area, the location of that measured RSSI is estimated by finding the closest match between the current measured RSSI data and those in the radio map. The main advantage of RSS-based localization methods is that they do not require a specific network infrastructure or hardware to effectively operate. These days, smartphones have built-in RSSI measurement functionalities that can accurately measure the RSSIs of most available radio networks such as Wi-Fi and Bluetooth
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
