Dorothy Curtis

Implications of device diversity for organic localization

Many indoor localization methods are based on the association of 802.11 wireless RF signals from wireless access points (WAPs) with location labels. An “organic” RF positioning system relies on regular users, not dedicated surveyors, to build the map of RF fingerprints to location labels. However, signal variation due to device heterogeneity may degrade localization performance. We analyze the diversity of those signal characteristics pertinent to indoor localization — signal strength and AP detection — as measured by a variety of 802.11 devices. We first analyze signal strength diversity, and show that pairwise linear transformation alone does not solve the problem. We propose kernel estimation with a wide kernel width to reduce the difference in probability estimates. We also investigate diversity in access point detection. We demonstrate that localization performance may degrade significantly when AP detection rate is used as a feature for localization, and correlate the loss of performance to a device dissimilarity measure captured by Kullback-Leibler divergence. Based on this analysis, we show that using only signal strength, without incorporating negative evidence, achieves good localization performance when devices are heterogeneous.

SMART—An Integrated Wireless System for Monitoring Unattended Patients

Monitoring vital signs and locations of certain classes of ambulatory patients can be useful in overcrowded emergency departments and at disaster scenes, both on-site and during transportation. To be useful, such monitoring needs to be portable and low cost, and have minimal adverse impact on emergency personnel, e.g., by not raising an excessive number of alarms. The SMART (Scalable Medical Alert Response Technology) system integrates wireless patient monitoring (ECG, SpO(2)), geo-positioning, signal processing, targeted alerting, and a wireless interface for caregivers. A prototype implementation of SMART was piloted in the waiting area of an emergency department and evaluated with 145 post-triage patients. System deployment aspects were also evaluated during a small-scale disaster-drill exercise.

Online pose classification and walking speed estimation using handheld devices

We describe and evaluate two methods for device pose classification and walking speed estimation that generalize well to new users, compared to previous work. These machine learning based methods are designed for the general case of a person holding a mobile device in an unknown location and require only a single low-cost, low-power sensor: a triaxial accelerometer. We evaluate our methods in straight-path indoor walking experiments as well as in natural indoor walking settings. Experiments with 14 human participants to test user generalization show that our pose classifier correctly selects among four device poses with 94% accuracy compared to 82% for previous work, and our walking speed estimates are within 12-15% (straight/indoor walk) of ground truth compared to 17-22% for previous work. Implementation on a mobile phone demonstrates that both methods can run efficiently online.

Physiological signal monitoring in the waiting areas of an emergency room

The Scalable Medical Alert and Response Technology (SMART) System was developed to monitor physiological signals from patients in the waiting areas of an emergency department. The system monitors the SpO2 (oxygenation level in the blood), ECG (electrical activity of the heart) and the location of multiple patients wirelessly. It was deployed at the Brigham and Womens Hospital in Boston, MA, between June, 2006, and December, 2007. This paper describes the overall architecture, the sensors used, challenges in deploying this technology in a hospital and the degree of patient acceptance. Some sections of this article are based on an article first published in the Journal of the American Medical Informatics Association (J Am Med Inform Assn: 2008; 1) [7].

Mole: A scalable, user-generated WiFi positioning engine

We describe the design, implementation, and evaluation of Mole, a mobile organic localization engine. Unlike previous work on crowd-sourced WiFi positioning, Mole uses a hierarchical name space. By not relying on a map and by being more strict than uninterpreted names for places, Mole aims for a more flexible and scalable point in the design space of localization systems. Mole employs several new techniques, including a new statistical positioning algorithm to differentiate between neighboring places, a motion detector to reduce update lag, and a scalable “cloud”-based fingerprint distribution system. Moles localization algorithm, called Maximum Overlap (MAO), accounts for temporal variations in a places fingerprint in a principled manner. It also allows for aggregation of fingerprints from many users and is compact enough for on-device storage. We show through end-to-end experiments in two deployments that MAO is significantly more accurate than state-of-the-art Bayesian-based localizers. We also show that non-experts can use Mole to quickly survey a building, enabling room-grained location-based services for themselves and others.

Molé: a scalable, user-generated WiFi positioning engine

We describe the design, implementation, and evaluation of Molé, a mobile organic localization engine. Unlike previous work on crowd-sourced WiFi positioning, Mole uses a hierarchical name space. By not relying on a map and by being more strict than uninterpreted names for places, Molé aims for a more flexible and scalable point in the design space of localization systems. Molé employs several new techniques, including a new statistical positioning algorithm to differentiate between neighboring places, a motion detector to reduce update lag, and a scalable “cloud”-based fingerprint distribution system. Molés localization algorithm, called Maximum Overlap (MAO), accounts for temporal variations in a places fingerprint in a principled manner. It also allows for aggregation of fingerprints from many users and is compact enough for on-device storage. We show through end-to-end experiments in two deployments that MAO is significantly more accurate than state-of-the-art Bayesian-based localizers. We also show that non-experts can use Molé to quickly survey a building, enabling room-grained location-based services for themselves and others.

An approach to disconnected operation in an object-oriented database

With the advent of mobile computers, new challenges arise for software designers. The paper focuses on disconnected operation: making mobile computers work well on shared data whether the network is available or not. Initially the shared data is cached on the mobile computer. Modifications and additions to this cached data will be reconciled with the shared data when the mobile computer is reconnected to the network. Conflict resolution will be used to reconcile conflicting changes. We examine these issues by adding support for disconnected operation to Thor an object-oriented database.

Audio-Visual Tools for Computer-Assisted Diagnosis of Cardiac Disorders

The process of interpreting heart sounds is restricted by human auditory limitations. Shortcomings such as insensitivity to frequency changes, slow responses to rapidly occurring changes in acoustic signals and an inability to discriminate the presence of soft pathological sounds are the source of inaccuracies and persist even with experience. This restricts both the practice and teaching of auscultation. In this paper we propose and evaluate a suite of presentation tools for computer-assisted auscultation. We explore the use of digital signal processing techniques to slow down heart sounds while preserving frequency content, differential enhancement across frequency scales to amplify pathological disease signatures, visualization of the signal to measure changes in signal energy across time and presentation of a representative prototypical signal for the patient

Monitoring technology for wheelchair users with advanced multiple sclerosis

This paper presents a non-invasive assistive device for people with advanced Multiple Sclerosis (MS) who use electric power wheelchairs (EPW). The proposed system can acquire respiration and heart activity from ballistocardiogram (BCG), seat and back pressure distribution, wheelchair tilt angle and ambient temperature and relative humidity. The sensors collect information related to the main issues of MS patients: fatigue, heat sensitivity and low mobility. Preliminary results show the signals as the wheelchair is moving, stopped and tilting. The system is able to capture sufficient relevant information to provide suggestions and alarms in a future stage. The system will be tested at The Boston Home, a specialized residence for adults with advanced MS.

Improving sparse organic WiFi localization with inertial sensors

Personal location discovery and navigation within buildings has become an important research topic in the last years. One method to determine ones current position based on mobile-devices is to compare the set of available WiFi access points (APs), i.e. the fingerprint of a given space, to a previously collected database. In this context, this paper addresses the inherent problem of such systems that this fingerprint database needs to be established beforehand. Thus, situations can occur where a building is only partially represented in the database and localization can only be provided in a subset of the spaces of the building. This problem occurs especially in crowd-sourcing (organic) approaches where users consecutively contribute location-binds. In these situations an additional system is needed to provide localization. We present a first study on the fusion of pedestrian dead reckoning (PDR) from inertial sensors with position estimates from a WiFi localization system. We outline a possible design of particle filter and analyze its behavior on experimental data. We conclude that the outlined method can help to improve WiFi localization and is especially useful within crowd-sourcing environments.