Situation awareness in a smart home environment

Shu Yun Lee, Fuchun Lin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

17 Scopus citations

Abstract

Situation awareness is a must for a smart home to exhibit its smartness. Normally, this is accomplished by accurately detecting the activities of a home user and then responding to the need of the user accordingly. This research utilizes a single wearable device equipped with an accelerometer and a gyroscope to detect eight potential activities in the living room of a smart home environment. First, the models of activities are constructed based on training data generated from the wearable device. Then, when a user performs the activity, the newly generated data would be compared with the established models to identify the type of current activity. Our method of model construction and activity detection is based on Decision Tree and Hidden Markov Model (HMM) with the assistance of location data derived from Beacons. The unique advantage of our method lies in its low cost as only one wearable device and a couple of beacons are required for achieving the desired situation awareness.

Original languageEnglish
Title of host publication2016 IEEE 3rd World Forum on Internet of Things, WF-IoT 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages678-683
Number of pages6
ISBN (Electronic)9781509041305
DOIs
StatePublished - 2016
Event3rd IEEE World Forum on Internet of Things, WF-IoT 2016 - Reston, United States
Duration: 12 Dec 201614 Dec 2016

Publication series

Name2016 IEEE 3rd World Forum on Internet of Things, WF-IoT 2016

Conference

Conference3rd IEEE World Forum on Internet of Things, WF-IoT 2016
Country/TerritoryUnited States
CityReston
Period12/12/1614/12/16

Keywords

  • Decision Tree
  • Hidden Markov Model
  • Internet of Things
  • Wearable Device

Fingerprint

Dive into the research topics of 'Situation awareness in a smart home environment'. Together they form a unique fingerprint.

Cite this