Showing papers by "Neal Patwari published in 2015"

Fingerprint-Based Device-Free Localization Performance in Changing Environments

Abstract: Device-free localization (DFL) systems locate a person in an environment by measuring the changes in received signals on links in a wireless network. A fingerprint-based DFL method collects a training database of measurement fingerprints and uses a machine learning classifier to determine a person's location from a new fingerprint. However, as the environment changes over time due to furniture or other objects being moved, the fingerprints diverge from those in the database. This paper addresses, for DFL methods that use received signal strength as measurements, the degradation caused as a result of environmental changes. We perform experiments to quantify how changes in an environment affect accuracy, through a repetitive process of randomly moving an item in a residential home and then conducting a localization experiment, and then repeating. We quantify the degradation and consider ways to be more robust to environmental change. We find that the localization error rate doubles, on average, for every six random changes in the environment. We find that the random forests classifier has the lowest error rate among four tested. We present a correlation method for selecting channels, which decreases the localization error rate from 4.8% to 1.6%.

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

Abstract: Device-free localization systems, such as variance-based radio tomographic imaging (VRTI), use received signal strength (RSS) variations caused by human motion in a static wireless network to locate and track people in the area of the network, even through walls. However, intrinsic motion, such as branches moving in the wind or rotating or vibrating machinery, also causes RSS variations which degrade the performance of a localization system. In this paper, we propose a new estimator, least squares variance-based radio tomography (LSVRT), which reduces the impact of the variations caused by intrinsic motion. We compare the novel method to subspace variance-based radio tomography (SubVRT) and VRTI. SubVRT also reduces intrinsic noise compared to VRTI, but LSVRT achieves better localization accuracy and does not require manually tuning additional parameters compared to VRTI. We also propose and test an online calibration method so that LSVRT and SubVRT do not require “empty-area” calibration and thus can be used in emergency situations. Experimental results from five data sets collected during three experimental deployments show that both estimators, using online calibration, can reduce localization root mean squared error by more than 40 percent compared to VRTI. In addition, the Kalman filter tracking results from both estimators have 97th percentile error of 1.3 m, a 60 percent reduction compared to VRTI.

dRTI: directional radio tomographic imaging

Abstract: Radio tomographic imaging (RTI) enables device free localisation of people and objects in many challenging environments and situations. Its basic principle is to detect the changes in the statistics of radio signals due to the radio link obstruction by people or objects. However, the localisation accuracy of RTI suffers from complicated multipath propagation behaviours in radio links. We propose to use inexpensive and energy efficient electronically switched directional (ESD) antennas to improve the quality of radio link behaviour observations, and therefore, the localisation accuracy of RTI. We implement a directional RTI (dRTI) system to understand how directional antennas can be used to improve RTI localisation accuracy. We also study the impact of the choice of antenna directions on the localisation accuracy of dRTI and propose methods to effectively choose informative antenna directions to improve localisation accuracy while reducing overhead. Furthermore, we analyse radio link obstruction performance in both theory and simulation, as well as false positives and false negatives of the obstruction measurements to show the superiority of the directional communication for RTI. We evaluate the performance of dRTI in diverse indoor environments and show that dRTI significantly outperforms the existing RTI localisation methods based on omni-directional antennas.

Competitive Live Evaluations of Activity-Recognition Systems

Abstract: Ensuring the validity and usability of activity recognition approaches requires agreement on a set of standard evaluation methods. Due to the diversity of the sensors and other hardware employed, however, designing, implementing, and accepting standard tests is a difficult task. This article presents an initiative to evaluate activity recognition systems: a living-lab evaluation established through the annual Evaluating Ambient Assisted Living Systems through Competitive Benchmarking--Activity Recognition (EvAAL-AR) competition. In the EvAAL-AR, each team brings its own activity-recognition system; all systems are evaluated live on the same activity scenario performed by an actor. The evaluation criteria attempt to capture practical usability: recognition accuracy, user acceptance, recognition delay, installation complexity, and interoperability with ambient assisted living systems. Here, the authors discuss the competition and the competing systems, focusing on the system that achieved the best recognition accuracy, and the system that was evaluated as the best overall. The authors also discuss lessons learned from the competition and ideas for future development of the competition and of the activity recognition field in general.

You're crossing the line: Localizing border crossings using wireless RF links

Abstract: Detecting and localizing a person crossing a line segment, i.e., border, is valuable information in security systems and human context awareness. To that end, we propose a border crossing localization system that uses the changes in measured received signal strength (RSS) on links between transceivers deployed linearly along the border. Any single link has a low signal-to-noise ratio because its RSS also varies due to environmental change, (e.g., branches swaying in wind), and sometimes does not change significantly when a person crosses it. The redundant, overlapping nature of the links between many possible pairs of nodes in the network provides an opportunity to mitigate errors. We propose new classifiers to use the redundancy to estimate where a person crosses the border. Specifically, the solution of these classifiers indicates which pair of neighboring nodes the person crosses between. We demonstrate that in many cases, these classifiers provide more robust border crossing localization compared to a classifier that excludes these noisy, redundant measurements.

Through-Wall Person Localization Using Transceivers in Motion.

Abstract: We develop novel methods for device-free localization (DFL) using transceivers in motion. Such localization technologies are useful in various cross-layer applications/protocols including those that are related to security situations where it is important to know the presence and position of an unauthorized person; in monitoring the daily activities of elderly or special needs individuals; or in emergency situations when police or firefighters can use the locations of people inside of a building in order to save lives. We propose that transceivers mounted on autonomous vehicles could be both quickly deployed and kept moving to ``sweep'' an area for changes in the channel that would indicate the location of moving people and objects. The challenge is that changes to channel measurements are introduced both by changes in the environment and from motion of the transceivers. In this paper, we demonstrate a method to detect human movement despite transceiver motion using ultra-wideband impulse radar (UWB-IR) transceivers. The measurements reliably detect a person's presence on a link line despite small-scale fading. We explore via multiple experiments the ability of mobile UWB-IR transceivers, moving outside of the walls of a room, to measure many lines crossing through the room and accurately locate a person inside within 0.25 m average error.

RUBreathing: non-contact real time respiratory rate monitoring system

Abstract: The respiration rate of a person provides critical information about their well-being. Conventionally, contact sensing is used for breathing monitoring; however, it is expensive, uncomfortable, and immobile. In-home non-contact breathing monitoring is now possible via Doppler radar and motion capture video sensors, yet these technologies are limited in mobility, among other limitations. When monitoring a patient who is free to move around his or her home, it is dificult to scale current non-contact sensors to cover the large area. Our RUBreathing sensor system uses RF received signal strength (RSS) in a network to estimate breathing rate in real-time with high accuracy over a wide area. In this demonstration, we show the sensor continuously estimating a patient's respiration rate from non-contact RSS measurements between wireless devices.

Detecting and localizing border crossings using RF links

Abstract: Detecting and localizing a person crossing a line segment, i.e., border, is valuable information in security and data analytic applications. To that end, we use the received signal strength (RSS) measured on RF links between nodes deployed linearly along a border as a border crossing detection and localization system. RSS measurements from any single RF link are noisy and prone to variations due to environmental changes (e.g. branches moving in wind). The redundant overlapping nature of the links between pairs of nodes in our proposed system provides an opportunity to mitigate these issues. We propose a hidden Markov model (HMM) which models the RSS on network links as a function of the neighboring nodes between which a person crosses. We demonstrate that the forward-backward solution to this HMM provides a robust and real time border crossing detection and localization system.