Multi-Layer Perceptron Decomposition Architecture for Mobile IoT Indoor Positioning
Conference paper > Full Text
Authors: Erdem Cakan, Aral Sahin, Mert Nakip, Volkan Rodoplu
2021 IEEE 7th World Forum on Internet of Things (WF-IoT), , , International, Full Text, pp 253-257
DOI: 10.1109/wf-iot51360.2021.9595282
Summary
We develop a Multi-Layer Perceptron (MLP) Decomposition architecture for mobile Internet Things (IoT) indoor positioning. We demonstrate the performance of our architecture on an indoor system that utilizes ultra-wideband (UWB) positioning. Our architecture outperforms the following benchmark processing techniques on the same data: MLP, Linear Regression, Ridge Regression, Support Vector Regression, and the Least Squares Method for indoor positioning. The results show that our architecture can significantly advance the positioning accuracy of indoor positioning systems and enable indoor applications such as navigation, proximity marketing, asset tracking, collision avoidance, and social distancing.