2012
DOI: 10.1109/tsmca.2011.2173568
|View full text |Cite
|
Sign up to set email alerts
|

SPEED: An Inhabitant Activity Prediction Algorithm for Smart Homes

Abstract: This paper proposes an algorithm, called sequence prediction via enhanced episode discovery (SPEED), to predict inhabitant activity in smart homes. SPEED is a variant of the sequence prediction algorithm. It works with the episodes of smart home events that have been extracted based on the ON-OFF states of home appliances. An episode is a set of sequential user activities that periodically occur in smart homes. The extracted episodes are processed and arranged in a finite-order Markov model. A method based on … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
64
0

Year Published

2015
2015
2021
2021

Publication Types

Select...
5
4

Relationship

0
9

Authors

Journals

citations
Cited by 85 publications
(64 citation statements)
references
References 11 publications
0
64
0
Order By: Relevance
“…The majority have focused on the single-user environment, particularly AAL and ADL routines. The research in [27] addressed a Markov model-based method derived from prediction by partial matching (PPM) that selects the most probable future activity. Because of the limitations based on simple sensor data, this method was modified to improve the accuracy by adding a time component [22]; however, the resulting study was limited because it considered only one specific situation: one person in one room.…”
Section: Related Workmentioning
confidence: 99%
“…The majority have focused on the single-user environment, particularly AAL and ADL routines. The research in [27] addressed a Markov model-based method derived from prediction by partial matching (PPM) that selects the most probable future activity. Because of the limitations based on simple sensor data, this method was modified to improve the accuracy by adding a time component [22]; however, the resulting study was limited because it considered only one specific situation: one person in one room.…”
Section: Related Workmentioning
confidence: 99%
“…Some recent works involve using variable-order Markov models for predicting the behavior of drivers in vehicular networks, such as in the work from Xue et al [26]; predicting the future location of mobile users, as in the work from Katsaros & Manolopoulos [15] or applying Markov-based models to the prediction of the inhabitants' activity in smart ubiquitous homes, as proposed by Kang et al [14] or Alam et al [1]. Also, an attempt to build a domainindependent predictor of user intention based on Markov model and considering fixed attributes from users is described by Antwarg et al [2].…”
Section: State Of the Artmentioning
confidence: 99%
“…Many works have also addressed the prediction of what an inhabitant will do in the near future, in order to enable planning and scheduling of services ahead of time [4,15], for instance, to implement energy-efficient control of appliances [16,17]. Typically, activity recognition solutions rely on static sensors placed throughout an environment [15,[18][19][20][21], but more recently frameworks have been produced to recognize human activities with limited guarantees about placement, nature and run-time availability of sensors, including static and wearable ones [22,23]. However, the strict computational and energy constraints imposed by WSN-based environments have constituted a major obstacle to translating the full potential benefits of these results in robotic ecologies.…”
Section: Learningmentioning
confidence: 99%
“…We have extended the test-bed with one Turtlebot 14 mobile robot and a IEEE802.15.46 compliant wireless sensor network. We employ motes based on the original open-source TelosB platform 15 . In addition, the user wears a bracelet carrying a mote providing radio signal strength (RSS) data.…”
Section: The Homelab Test-bedmentioning
confidence: 99%