Optimization and Evaluation of Multidetector Deep Neural Network for High-Accuracy Wi-Fi Fingerprint Positioning

Abstract

To fulfill the need for high-accuracy indoor positioning in many location-based services (LBSs) and the emerging Internet of Things (IoT) applications, in this article, we propose a novel scene-analysis positioning solution of the multidetector deep neural network (DNN) architecture, with preprocessing steps, model optimization techniques, and variance estimation methods. During the offline site-surveying phase in our approach, fingerprint databases are created by purposely built robotic surveying devices traversing the target site to gather perceivable Wi-Fi and other signals including to create spatial positioning models for further use in the online positioning phase. The intricate nonlinear relationship between fingerprints and spatial positions are thus resolved by the multidetector DNN in our approach. Hyperparameter analyses were conducted to further optimize our proposed multidetector model in terms of complexity, achieving at least 6.7 times of parameter complexity reduction while retaining < 1% degradation of 0.9-m (3 ft) positioning accuracy level.