The profile-based approach is known to be advantageous when it comes to inferring positions of mobile wireless devices in complex indoor environments. The past decade has seen a significant body of work that explores different implementations of this approach, with varying degrees of success. Here, the authors cast the profile-based approach in a probabilistic framework. Launching from the theoretical basis that this framework provides, they provide a suite of carefully designed methods that make use of sophisticated computations in pursuit of high localization accuracy with low hardware investment and moderate set-up cost. More specifically, they use full distributional information on signal measurements at a set of discrete locations, termed landmarks.