A Framework for Active Indoor Positioning in WiFi Networks with Dense Deployment PROJECT TITLE : A Framework for Proactive Indoor Positioning in Densely Deployed WiFi Networks ABSTRACT: For the purpose of network-based indoor positioning utilizing radio signal strength (RSS) measurements of WiFi access points, a framework has been developed. This framework incorporates channel modeling, position estimation, and error analysis methods (APs). In order to build an accurate channel model with RSS measurements that are heavily impacted by propagation attenuations, multipath reflections, and shadowing effects, a novel sparse Bayesian learning algorithm was developed to model the radio power map (RPM) in indoor space. This was done in order to facilitate the construction of an accurate channel model. A two-stage positioning method is developed further, and it is based on the RPM model that was proposed earlier. In the first stage of coarse positioning, the location of the target is determined up to the scale of an individual room or indoor area. After that, the RPMs of the given indoor space are utilized in the second stage of the fine positioning process. This is done so that a Bayesian estimator can determine the location of the target within the given space. When compared to the Bayesian Cramer-Rao lower bound, the mean squared positioning errors are found to be accurate. Extensive experiments have shown that the proposed RPM-based approach has an average positioning error of 1.98 meters, which is an improvement of 22 percent over the most advanced RSS-based indoor positioning methods. Most importantly, the modeling and positioning method that has been proposed is able to effectively exploit the spatial relationship present in the RSS samples, which helps to improve positioning accuracy. Did you like this research project? To get this research project Guidelines, Training and Code... Click Here facebook twitter google+ linkedin stumble pinterest Using Multiple Semantic Matrices and Sensors, a Deep Learning Model for Unseen Locomotion Mode Identification Comparing Clustering and Optimization Rules in Wi-Fi Fingerprinting in a Comprehensive and Reliable Way