Large-Scale Deep Learning Framework on FPGA for Fingerprint-Based Indoor Localization
Localization Based Service (LBS) has become as one of the most important applications in modern daily life. Positioning technologies for outdoor environments are relatively mature because of the wide coverage of satellite navigating systems such as the Global Positioning System (GPS). In contrast, indoor localization remains a great challenge due to the uctuated radio propagation environment. In addition to the high requirement of accuracy, an indoor localization system should also be low cost, low power consumption, and ubiquitous availability in mobile devices. To this end, ngerprint-based indoor localization schemes have served as an effective methodology to satisfy those requirements and have attracted more and more research attentions. In this paper, we present a scalable Deep Neural Network (DNN) architecture with Denoising Auto-encoder for Fingerprint-based Indoor Localization (called ``SDNNLoc'') based-on FPGA implementation. First, a scalable stacked denoising auto-encoder is introduced to extract features from the ngerprint database for robustness and accuracy. Then, a generic parameterized DNN accelerator generat- ing & optimization framework is proposed for FPGA implementation. In addition, we also demonstrate a WiFi-based ngerprinting indoor localization system for a crowdsensed university campus scenario. The experimental results show that the proposed DNN framework and its FPGA implementation are feasible for efcient and accurate indoor localization with good performance and high scalability.
Indoor localization, deep learning, deep neural networks, DNN, FPGA acceleration.