Localization with WLAN on smartphones in hospitals

With the rise of location based services (LBS), indoor and outdoor localization using RF based network has been popular in recent years. Since the outdoor location determination is dominated by global positioning system (GPS), the outdoor part of localization is not included in our discussion. Here we propose a novel indoor localization method deploying WiFi access points (APs) called cluster k-NN algorithm, which does not cost extra money for infrastructures and still offers decent accuracy comparing to other indoor localization techniques. According to the offline simulation, the complexity of cluster k-NN is lower, while the accuracy is up to 98.67%. As a result, the complexity and the calculation are greatly decreased, while the accuracy is still maintained. We have also made the application including our algorithm and data on Android based smart phones with intuitive user interface and quick access to change parameters, in order to briefly demonstrate our result to determine the location of users in real time. Online positioning was tested under cluster k-NN with the optimal parameters obtained through offline simulation. The tested environment was the LaRC laboratory on the fourth floor in the TSMC building in National Tsing Hua University (NTHU). With the background dimension in 227.59 m², the average error rate of our algorithm is 4.75%, and the average error distance is 3.728m, which is a satisfactory result. Compared to other designs, the accuracy of our algorithm does not differ much. However, the complexity is at least a third less. With such accuracy and portability, precise position of every patient is sent to the cloud server and computed real-time, which enables doctors to be fully informed, with the reduced energy consumption and longer time the devices can stand by.