Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Statistics for Spatial Data.

Wireless indoor positioning systems have become very popular in recent years. These systems have been successfully used in many applications such as asset tracking and inventory management. This paper provides an overview of the existing wireless indoor positioning solutions and attempts to classify different techniques and systems. Three typical location estimation schemes of triangulation, scene analysis, and proximity are analyzed. We also discuss location fingerprinting in detail since it is used in most current system or solutions. We then examine a set of properties by which location systems are evaluated, and apply this evaluation method to survey a number of existing systems. Comprehensive performance comparisons including accuracy, precision, complexity, scalability, robustness, and cost are presented.

Survey of Wireless Indoor Positioning Techniques and Systems

Accurate and low-cost sensor localization is a critical requirement for the deployment of wireless sensor networks in a wide variety of applications. In cooperative localization, sensors work together in a peer-to-peer manner to make measurements and then forms a map of the network. Various application requirements influence the design of sensor localization systems. In this article, the authors describe the measurement-based statistical models useful to describe time-of-arrival (TOA), angle-of-arrival (AOA), and received-signal-strength (RSS) measurements in wireless sensor networks. Wideband and ultra-wideband (UWB) measurements, and RF and acoustic media are also discussed. Using the models, the authors have shown the calculation of a Cramer-Rao bound (CRB) on the location estimation precision possible for a given set of measurements. The article briefly surveys a large and growing body of sensor localization algorithms. This article is intended to emphasize the basic statistical signal processing background necessary to understand the state-of-the-art and to make progress in the new and largely open areas of sensor network localization research.

Locating the nodes: cooperative localization in wireless sensor networks

With digital equipment becoming increasingly networked, either on wired or wireless networks, for personal and professional use alike, distributed software systems have become a crucial element in information and communications technologies. The study of these systems forms the core of the ARLES' work, which is specifically concerned with defining new system software architectures, based on the use of emerging networking technologies. In this context, we concentrate on the study of distributed systems which bring to life the vision of ubiquitous computing systems, also known as ambient intelligence.

반도체 공정 overview

Human motion in the vicinity of a wireless link causes variations in the link received signal strength (RSS). Device-free localization (DFL) systems, such as variance-based radio tomographic imaging (VRTI), use these RSS variations in a static wireless network to detect, locate and track people in the area of the network, even through walls. However, intrinsic motion, such as branches moving in the wind and rotating or vibrating machinery, also causes RSS variations which degrade the performance of a DFL system. In this paper, we propose and evaluate two estimators to reduce the impact of the variations caused by intrinsic motion. One estimator uses subspace decomposition, and the other estimator uses a least squares formulation. Experimental results show that both estimators reduce localization root mean squared error by about 40% compared to VRTI. In addition, the Kalman filter tracking results from both estimators have 97% of errors less than 1.3 m, more than 60% improvement compared to tracking results from VRTI.

Robust Estimators for Variance-Based Device-Free Localization and Tracking

We propose an approach where wireless devices, interested in establishing a secret key, sample the channel impulse response (CIR) space in a physical area to collect and combine uncorrelated CIR measurements to generate the secret key. We study the impact of mobility patterns in obtaining uncorrelated measurements. Using extensive measurements in both indoor and outdoor settings, we find that (i) when movement step size is larger than one foot the measured CIRs are mostly uncorrelated, and (ii) more diffusion in the mobility results in less correlation in the measured CIRs. We develop efficient mechanisms to encode CIRs and reconcile the differences in the bits extracted between the two devices. Our results show that our scheme generates very high entropy secret bits and that too at a high bit rate. The secret bits, that we generate using our approach, also pass the 8 randomness tests of the NIST test suite.

/pdf/mobility-assisted-secret-key-generation-using-wireless-link-4pr6ubo9eh.pdf

Mobility Assisted Secret Key Generation Using Wireless Link Signatures

The number of people aged 65 and over continues to rapidly increase, leading to a greater need for technologies to assist in caring for an aging population. Among these technologies are fall detection systems, since falling is a major concern for the elderly. In this paper we present a method of detecting falls using radio tomographic imaging. A two-level array of RF sensor nodes is deployed around the perimeter of a room, and the shadowing losses in the signals relayed between sensors is used to detect a person's horizontal and vertical position. Training data is used to provide a relationship between the attenutation measured as a function of height and a person's pose, which is then used in a hidden Markov model. During system operation, a forward algorithm estimates the most likely current state at each time. If the time between a standing pose and a lying down pose is too short, the system detects a fall. Using a collected experimental test set, we show that the system can distinguish falls from controlled lying down actions (e.g., sitting on the floor) with 100% reliability and no false alarms.

/pdf/fall-detection-using-rf-sensor-networks-3gplfiiue4.pdf

Fall detection using RF sensor networks

Radio tomographic imaging systems use received signal strength measurements between static wireless sensors to image the changes in the radio propagation environment in the area of the sensors, which can be used to localize a person causing the change. To date, spatial models used for such systems are set a priori and do not change. Imaging and tracking performance suffers because of the mismatch between the model and the measurements. Collecting labeled training data requires intensive effort, and the data degrade quickly as the environment changes. This paper provides a means for a radio tomographic imaging system to bootstrap to improve its spatial models using unlabeled data, iteratively improving itself over time. A collection of tracking filters are presented to improve the accuracy of image and coordinate estimates. This paper presents an online method to use these estimates to instantaneously update spatial model parameters. Further, a smoothing method is presented to fine-tune the model with a given finite latency. The development efforts are evaluated using simulations and validated with real-world experiments conducted in three different environments. With respect to another state-of-the-art radio tomographic imaging system, the results suggest that the presented system increases the median tracking accuracy by twofold in the most challenging environment and by threefold when the model parameters are trained using the smoothing method.

ARTI: An Adaptive Radio Tomographic Imaging System

A system for inferring a set of characteristics and method for inferring an electronic rendering (170) of an environment (110) comprises a plurality of devices (341 and 345) and a processing device. Each wireless device is capable of determining a distance between a neighboring wireless device. Moreover, each device is capable of performing at least one of the following: determining an environmental attribute of the environment, and determining a location of an object in the environment. The processing device gathers information determined from the plurality of devices and infers the set of characteristics electronic rendering of the environment based on the information gathered.

Neal Patwari

Papers

Robust Estimators for Variance-Based Device-Free Localization and Tracking

Mobility Assisted Secret Key Generation Using Wireless Link Signatures

Fall detection using RF sensor networks

ARTI: An Adaptive Radio Tomographic Imaging System

System and method for inferring an electronic rendering of an environment