Implementation of Wearable Devices and Indoor Positioning System for a Smart Hospital Environment

Abstract

This study attempts to develop a Wi-Fi signal based indoor positioning system (IPS) for implementation of a smart hospital. The proposed system is composed of an arduino platform, a RedBearLab CC3200 WiFi Mini module, Li-ion battery, speaker, OLED display, cloud server, and portable client devices. In the client end, the home-made wristbands are designed to receive the strength of Received Signal Strength Index (RSSI) signals, and the corresponding Media Access Controllers (MACs) are then sent to the cloud server via UDP/IP protocol. In the server end, the computation for the extracted RSSI is automatically performed by using the trilateration and fingerprinting. Because the Wi-Fi based RSSI is within a certain variation, the extracted valuable information is then analyzed by introducing the fuzzy logic and genetic algorithm to improve the robustness of the IPS in this study. Further, some restrictions consisting of movement speed and the wall separation, are considered to suppress unreasonable positions and minimize the measuring errors. Preliminary results indicate that the proposed method achieves the error distances about 2 meters and the miss-location for room identification is nearly zero. So, the developed wearable module has some advantages such as robustness, low-power consumption and high-efficiency for providing at least four days.