Detecting Human Movement by Differential Air Pressure Sensing in HVAC System Ductwork: An Exploration in Infrastructure Mediated Sensing

@inproceedings{Patel2009DetectingHM,
  title={Detecting Human Movement by Differential Air Pressure Sensing in HVAC System Ductwork: An Exploration in Infrastructure Mediated Sensing},
  author={Shwetak N. Patel and Matthew S. Reynolds and Gregory D. Abowd},
  booktitle={International Conference on Pervasive Computing},
  year={2009},
  url={https://api.semanticscholar.org/CorpusID:619878}
}
Preliminary results show the system can classify unique transition events with up to 75-80% accuracy, and is one member of an important new class of human activity monitoring approaches based on what is called infrastructure mediated sensing, or "home bus snooping."
View via Publisher
cs.washington.edu
135 Citations
Highly Influential Citations
4
Background Citations
66
Methods Citations
21
Results Citations
2

135 Citations

Monitoring building door events using barometer sensor in smartphones

It is shown that barometer sensors found in latest smartphones can directly detect the building door open/close events anywhere inside an insulated building, and the sudden pressure change observed by barometers is sufficient to detect events even in presence of user mobility.

HydroSense: infrastructure-mediated single-point sensing of whole-home water activity

HydSense is presented, a low-cost and easily-installed single-point sensor of pressure within a home's water infrastructure that supports both identification of activity at individual water fixtures within aHome as well as estimation of the amount of water being used at each fixture.

An opportunistic activity-sensing approach to save energy in office buildings

This work recognised office worker activities that are relevant for energy-related control of appliances and building systems using sensors that are commonly installed in new or refurbished office buildings using sensors based on the EnOcean platform and plug-in power meters.

Recognizing water-based activities in the home through infrastructure-mediated sensing

This work is the first to employ infrastructure-mediated sensing for inferring high-level human activities in a home setting and uses a vector space model learning approach as the basis of an activity recognition system for the home.

Detecting Door Events Using a Smartphone via Active Sound Sensing

The proposed method is capable of recognizing walking activities of a person related to door events in the environment, which are necessary information for applications such as HVAC control that require information about both door events and human presence.

A WiFi-based Home Security System

A Wi Fi based security system that uses commodity WiFi devices, which most modern households already have, to perform the three primary tasks of typical home security systems, detected intrusions with over 95% accuracy and identified the exact door/window that moved with just 4.5% average error.

Detecting Room-to-Room Movement by Passive Infrared Sensors in Home Environments

The problem of simultaneous tracking, which exploits the synergy between location and movement to provide the information necessary for intelligent home appliance control, is discussed and an approach that uses information gathered using only passive infrared sensors commonly found in lighting control systems is proposed.

DOSE: Detecting user-driven operating states of electronic devices from a single sensing point

DOSE is introduced, a significant advancement for inferring operating states of electronic devices from a single sensing point in a home and employs domain knowledge of the device's circuitry for semi-supervised model training to avoid tedious labeling process.

Capacitive indoor positioning and contact sensing for activity recognition in smart homes

This paper presents a single privacy-preserving method to measure user position and activity which can easily be adapted to measure the subject's height and posture as well and shows that a standing person can be positioned to within either 7 or 11-cm accuracy at a 90% confidence level.

A Nonintrusive and Single-Point Infrastructure-Mediated Sensing Approach for Water-Use Activity Recognition

A single-point infrastructure-mediated sensing technique is proposed for water-use activity recognition using a single 3-axis accelerometer sensor attached to the surface of the main water pipe in the house to detect and collect the vibration signals of themain water pipe.
...

45 References

Sensing from the basement: a feasibility study of unobtrusive and low-cost home activity recognition

A new approach that "reaches into the home" via the existing infrastructure by deploying a small number of low-cost sensors at critical locations in a home's water distribution infrastructure, which can infer activities in the home based on water usage patterns.

At the Flick of a Switch: Detecting and Classifying Unique Electrical Events on the Residential Power Line (Nominated for the Best Paper Award)

This work uses machine learning techniques to recognize electrically noisy events such as turning on or off a particular light switch, a television set, or an electric stove and indicates that the system can learn and classify various electrical events with accuracies ranging from 85-90%.

Activity recognition in the home setting using simple and ubiquitous sensors

Results show that it is possible to recognize activities of interest to medical professionals such as toileting, bathing, and grooming with detection accuracies ranging from 25% to 89% depending on the evaluation criteria used, and a new algorithm for recognizing activities that extends the naive Bayes classifier to incorporate low-order temporal relationships was created.

Activity Recognition in the Home Using Simple and Ubiquitous Sensors

Preliminary results on a small dataset show that it is possible to recognize activities of interest to medical professionals such as toileting, bathing, and grooming with detection accuracies ranging from 25% to 89% depending on the evaluation criteria used.

The Design of a Portable Kit of Wireless Sensors for Naturalistic Data Collection

This paper describes how the MITes kit is being used for acquisition of data in non-laboratory settings where real-time multi-modal sensor information is acquired simultaneously from several sensors worn on the body and up to several hundred sensors distributed in an environment.

Using Sound Source Localization in a Home Environment

This paper examines the feasibility of sound source localization (SSL) in a home environment, and explores its potential to support inference of communication activity between people, and provides a quantitative assessment of the accuracy and precision of the system.

Simultaneous Tracking and Activity Recognition (STAR) Using Many Anonymous, Binary Sensors

The simultaneous tracking and activity recognition (STAR) problem is introduced, which exploits the synergy between location and activity to provide the information necessary for automatic health monitoring.

Toward Scalable Activity Recognition for Sensor Networks

Sensor networks hold the promise of truly intelligent buildings: buildings that adapt to the behavior of their occupants to improve productivity, efficiency, safety, and security. To be practical,…

UbiComp 2007: Ubiquitous Computing, 9th International Conference, UbiComp 2007, Innsbruck, Austria, September 16-19, 2007, Proceedings

This book discusses Ubicomp, a Statistical Reasoning System for Medication Prompting, and Sensor Networks or Smart Artifacts?

Bathroom Activity Monitoring Based on Sound

An automated bathroom activity monitoring system based on acoustics designed to recognize and classify major activities occurring within a bathroom based on sound contributes towards increased understanding of personal hygiene behavioral problems that significantly affect both informal care-giving and clinical care of dementia patients.