Localization of User in an Indoor Environment Using Machine Learning Classification Models

There is a wide range of applications like detecting the position of people in intelligent home systems, locating persons in specific areas, finding the number of people using an internet access point, etc. for our present investigation. Here, based on Wi-Fi signal values we are discovering users in an indoor location. In this paper, we are using the Wi-Fi signal strength obtained on the mobile devices of various people through different routers present in an office like the place and using this data to build an effective model to predict the user’s location based on that. The signal strength values collected from routers are associated with the person's position and that association can be considered as a grouping problem. We have used five classification models, "logistic regression, k-nearest neighbor, support vector machine, kernel support vector machine, and naïve bayes" to obtain a model that results in better prediction of the classifier.