One of the key points in any localization proposal for indoor environments is to determine in a precise way whether a device is inside or outside a particular building. That preliminary step of binary classification is required, for example, in order to send sensor readings to a location-based service. In this paper, we present a binary classifier, based on the well-known machine learning meta-algorithm AdaBoost, which makes use of the received Wi-Fi signals in order to infer the indoor/outdoor condition. The simple, so-called, weak learners, which lie at the heart of every AdaBoost implementation, are based in our case in simple RSSI magnitude comparisons between signal observations. Our solution requires only a coarse-grained training stage to produce two sets of samples (indoor and outdoor) that will be used to calculate the final model composed by several of these extremely simple weak learners. The resulting model is therefore really compact and efficient, which provides scalability to calculate in a fast way whether a device is inside or outside a particular building. In addition, we propose a slight modification of the base AdaBoost meta-algorithm to minimize the negative effect of unpredicted AP failures or changes in the network infrastructure, which will result in a moderate impact on the classification error under those circumstances. In order to verify empirically our proposal, we conducted several tests and we compared our results with those obtained using other well-known classification techniques. Our experiments made use of several devices in two different buildings and show that the resulting performance, a mean error rate around 2.5%, is satisfying. We also depict some applications of our system for several scenarios.

This paper introduces an LBS multisensor system that acquires data from different sensors available in commodity smart phones to provide accurate location estimations. Our approach is based on the use of visual structure from motion techniques to run off-line 3D reconstructions of the environment from the correspondences among the SIFT descriptors of the training images. We present several solutions to reduce the deployment cost, in terms of time, and to minimize the interference degree within the environment, but also pursuing a good balance between accuracy and performance. To determine the position of the smartphones, we first obtain a coarse-grained estimation based on WiFi signals, digital compasses, and built-in accelerometers, making use of fingerprinting methods, probabilistic techniques, and motion estimators. Then, using images captured by the camera, we perform a matching process to determine correspondences between 2D pixels and model 3D points, but only analyzing a subset of the 3D model delimited by the coarse-grained estimation. We implement a resection process providing high localization accuracy when the camera has been previously calibrated, that is, we know intrinsic parameters like focal length, but it is also accurate if an auto-calibration process is required. Furthermore, our experimental tests show promising results, since we are able to provide high accuracy with an average error down to 15 cm in less than 0.5 seconds of response time, making this proposal suitable for applications combining location-services and augmented reality.

Indoor positioning methods based on fingerprinting and radio signals rely on the quality of the radio map. For example, for room-level classification purposes, it is required that the signal observations related to each room exhibit significant differences in their RSSI values. However, it is difficult to verify and visualize that separability since radio maps are constituted by multi-dimensional observations whose dimension is directly related to the number of access points or monitors being employed for localization purposes. In this paper, we propose a refinement cycle for passive indoor positioning systems, which is based on dimensionality reduction techniques, to evaluate the quality of a radio map. By means of these techniques and our own data representation, we have defined two different visualization methods to obtain graphical information about the quality of a particular radio map in terms of overlapping areas and outliers. That information will be useful to determine whether new monitors are required or some existing ones should be moved. We have performed an exhaustive experimental analysis based on a variety of different scenarios, some deployed by our own research group and others corresponding to a well-known existing dataset widely analyzed by the community, in order to validate our proposal. As we will show, among the different combinations of data representation methods and dimensionality reduction techniques that we discuss, we have found that there are some specific configurations that are more useful in order to perform the refinement process.

A proposed identity management framework provides privacy protection, by means of virtual identities, and cross-layer single sign-on for users who subscribe to multiple service and identity providers.