User in the Loop: Adaptive Smart Homes Exploiting User Feedback—State of the Art and Future Directions
Due to the decrease of sensor and actuator prices and their ease of installation, smart homes and smart environments are more and more exploited in automation and health applications. In these applications, activity recognition has an important place. This article presents a general architecture tha...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2016-06-01
|
Series: | Information |
Subjects: | |
Online Access: | http://www.mdpi.com/2078-2489/7/2/35 |
id |
doaj-5f1f273c5f6c4ec18a538cd5f5632d5a |
---|---|
record_format |
Article |
spelling |
doaj-5f1f273c5f6c4ec18a538cd5f5632d5a2020-11-24T22:37:21ZengMDPI AGInformation2078-24892016-06-01723510.3390/info7020035info7020035User in the Loop: Adaptive Smart Homes Exploiting User Feedback—State of the Art and Future DirectionsAbir B. Karami0Anthony Fleury1Jacques Boonaert2Stéphane Lecoeuche3University of Lille, F-59000 Lille and Mines Douai, URIA, F-90508 Douai, FranceUniversity of Lille, F-59000 Lille and Mines Douai, URIA, F-90508 Douai, FranceUniversity of Lille, F-59000 Lille and Mines Douai, URIA, F-90508 Douai, FranceUniversity of Lille, F-59000 Lille and Mines Douai, URIA, F-90508 Douai, FranceDue to the decrease of sensor and actuator prices and their ease of installation, smart homes and smart environments are more and more exploited in automation and health applications. In these applications, activity recognition has an important place. This article presents a general architecture that is responsible for adapting automation for the different users of the smart home while recognizing their activities. For that, semi-supervised learning algorithms and Markov-based models are used to determine the preferences of the user considering a combination of: (1) observations of the data that have been acquired since the start of the experiment and (2) feedback of the users on decisions that have been taken by the automation. We present preliminarily simulated experimental results regarding the determination of preferences for a user.http://www.mdpi.com/2078-2489/7/2/35smart homesuser-centered decision makingMarkov decision process |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Abir B. Karami Anthony Fleury Jacques Boonaert Stéphane Lecoeuche |
spellingShingle |
Abir B. Karami Anthony Fleury Jacques Boonaert Stéphane Lecoeuche User in the Loop: Adaptive Smart Homes Exploiting User Feedback—State of the Art and Future Directions Information smart homes user-centered decision making Markov decision process |
author_facet |
Abir B. Karami Anthony Fleury Jacques Boonaert Stéphane Lecoeuche |
author_sort |
Abir B. Karami |
title |
User in the Loop: Adaptive Smart Homes Exploiting User Feedback—State of the Art and Future Directions |
title_short |
User in the Loop: Adaptive Smart Homes Exploiting User Feedback—State of the Art and Future Directions |
title_full |
User in the Loop: Adaptive Smart Homes Exploiting User Feedback—State of the Art and Future Directions |
title_fullStr |
User in the Loop: Adaptive Smart Homes Exploiting User Feedback—State of the Art and Future Directions |
title_full_unstemmed |
User in the Loop: Adaptive Smart Homes Exploiting User Feedback—State of the Art and Future Directions |
title_sort |
user in the loop: adaptive smart homes exploiting user feedback—state of the art and future directions |
publisher |
MDPI AG |
series |
Information |
issn |
2078-2489 |
publishDate |
2016-06-01 |
description |
Due to the decrease of sensor and actuator prices and their ease of installation, smart homes and smart environments are more and more exploited in automation and health applications. In these applications, activity recognition has an important place. This article presents a general architecture that is responsible for adapting automation for the different users of the smart home while recognizing their activities. For that, semi-supervised learning algorithms and Markov-based models are used to determine the preferences of the user considering a combination of: (1) observations of the data that have been acquired since the start of the experiment and (2) feedback of the users on decisions that have been taken by the automation. We present preliminarily simulated experimental results regarding the determination of preferences for a user. |
topic |
smart homes user-centered decision making Markov decision process |
url |
http://www.mdpi.com/2078-2489/7/2/35 |
work_keys_str_mv |
AT abirbkarami userintheloopadaptivesmarthomesexploitinguserfeedbackstateoftheartandfuturedirections AT anthonyfleury userintheloopadaptivesmarthomesexploitinguserfeedbackstateoftheartandfuturedirections AT jacquesboonaert userintheloopadaptivesmarthomesexploitinguserfeedbackstateoftheartandfuturedirections AT stephanelecoeuche userintheloopadaptivesmarthomesexploitinguserfeedbackstateoftheartandfuturedirections |
_version_ |
1725717348602609664 |