Hybrid Building/Floor Classification and Location Coordinates Regression Using A Single-Input and Multi-Output Deep Neural Network for Large-Scale Indoor Localization Based on Wi-Fi Fingerprinting
This work addresses indoor localization for users in large-scale environments, representing an incremental improvement over prior methods.
The paper tackles indoor localization by proposing a hybrid building/floor classification and location coordinates regression using a single-input multi-output deep neural network, achieving improved floor detection rates and reduced mean positioning errors compared to existing schemes.
In this paper, we propose hybrid building/floor classification and floor-level two-dimensional location coordinates regression using a single-input and multi-output (SIMO) deep neural network (DNN) for large-scale indoor localization based on Wi-Fi fingerprinting. The proposed scheme exploits the different nature of the estimation of building/floor and floor-level location coordinates and uses a different estimation framework for each task with a dedicated output and hidden layers enabled by SIMO DNN architecture. We carry out preliminary evaluation of the performance of the hybrid floor classification and floor-level two-dimensional location coordinates regression using new Wi-Fi crowdsourced fingerprinting datasets provided by Tampere University of Technology (TUT), Finland, covering a single building with five floors. Experimental results demonstrate that the proposed SIMO-DNN-based hybrid classification/regression scheme outperforms existing schemes in terms of both floor detection rate and mean positioning errors.