Smartphone Indoor Localizations using Semi-Supervised Learning for Smart Offices
Abstract
Accurate and reliable smartphone indoor localization is fundamental for indoor location-based services (LBS). Smart environments, such as smart offices, interconnect office facilities, indoor wireless sensor and actuator networks (WSANs), smartphones, and human to provide comfortable user experiences. To smoothly integrate the localization algorithms with WSAN infrastructures, a combination of both hardware and software components is required. In this work, we present a system for creating indoor location-aware smart office environments using wireless sensor and actuator networks. Our system includes a smartphone indoor localization module, a WSAN responsible for environmental monitoring and actuator activation, and a gateway that interconnects WSAN, indoor localization module with smartphone users. To reduce the efforts of data collection, we have designed a semi-supervised learning-based indoor localization mechanism, which uses only a small amount of labeled data and a big amount of unlabeled data. The system is based on data fusion of Wi-Fi RSSI and smartphone onboard IMU readings. We implemented a system prototype and performed intensive experiments in indoor office environments to evaluate the system performance. The system could accurately locate real-time positions of occupants, which could trigger the retrieval of environmental measurements and activate the office appliances automatically (e.g. turn on/off lights) based on the estimated locations and correlated environmental sensor information.
Date Issued
2017-09
Publication Type
Working Paper
Language(s)
en
Author(s)
Additional Credits
Journal
IEEE Transactions
Access(Rights)
metadata.only