Wireless access points (APs) divide a plane into small areas where their coverage ranges overlap. A mobile device can be located within a particular small overlapped area based on the unique set of APs covering the device. We formally define an optimal AP deployment problem for both coverage and area localization. Our objective is to deploy a minimum number of APs that provide full communication coverage while achieving the ability to locate a mobile device within a certain area no larger than a given accuracy parameter. We propose a set of optimal solutions and approximations to this problem under the diamond pattern, a deployment pattern that has been shown to achieve optimal coverage in most cases. We conduct extensive numerical evaluation as well as real experiments to validate our proposed solutions.

Effective location distinction can help to detect the replication attack towards wireless stations. Instantaneous signal strength information can be used to identify different location information for one certain station. However, most of the previous solutions are under an assumption of a static network. In this paper, we propose a simple centroid based classification model to effectively classify the packets sent by masqueraders among all the packets received based on the aggregate signal strength vectors of packets from multiple access points. The simulation results indicate that the self-location recognition accuracies of our method for static and moving stations achieve 95% and 90%, respectively. Moreover, our method is shown to be very effective in attacker detection, in which attacker locations detection accuracy surpasses 80% even if the attacked targets are moving.

Particle filters have been applied with great success to various state estimation problems in robotics. However, particle filters often require extensive parameter tweaking in order to work well in practice. This is based on two observations. First, particle filters typically rely on independence assumptions such as "the beams in a laser scan are independent given the robot's location in a map". Second, even when the noise parameters of the dynamical system are perfectly known, the sample-based approximation can result in poor filter performance. In this paper we introduce CRF-filters, a novel variant of particle filtering for sequential state estimation. CRF-filters are based on conditional random fields, which are discriminative models that can handle arbitrary dependencies between observations. We show how to learn the parameters of CRF-filters based on labeled training data. Experiments using a robot equipped with a laser range-finder demonstrate that our technique is able to learn parameters of the robot's motion and sensor models that result in good localization performance, without the need of additional parameter tweaking.

Learning patterns of human behavior from sensor data is extremely important for high-level activity inference. We show how to extract and label a person's activities and significant places from traces of GPS data. In contrast to existing techniques, our approach simultaneously detects and classifies the significant locations of a person and takes the highlevel context into account. Our system uses relational Markov networks to represent the hierarchical activity model that encodes the complex relations among GPS readings, activities and significant places. We apply FFT-based message passing to perform efficient summation over large numbers of nodes in the networks. We present experiments that show significant improvements over existing techniques.

Tracking the activity of people in indoor environments has gained considerable attention in the robotics community over the last years. Most of the existing approaches are based on sensors, which allow to accurately determining the locations of people but do not provide means to distinguish between different persons. In this paper we propose a novel approach to tracking moving objects and their identity using noisy, sparse information collected by id-sensors such as infrared and ultrasound badge systems. The key idea of our approach is to use particle filters to estimate the locations of people on the Voronoi graph of the environment. By restricting particles to a graph, we make use of the inherent structure of indoor environments. The approach has two key advantages. First, it is by far more efficient and robust than unconstrained particle filters. Second, the Voronoi graph provides a natural discretization of human motion, which allows us to apply unsupervised learning techniques to derive typical motion patterns of the people in the environment. Experiments using a robot to collect ground-truth data indicate the superior performance of Voronoi tracking. Furthermore, we demonstrate that EM-based learning of behavior patterns increases the tracking performance and provides valuable information for high-level behavior recognition.