A time series based sequence prediction algorithm to detect activi -ties of daily living in smart home

M. Marufuzzaman, Md. Mamun Ibne Reaz, M. A M Ali, L. F. Rahman

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Objectives: The goal of smart homes is to create an intelligent environment adapting the inhabitants need and assisting the person who needs special care and safety in their daily life. This can be reached by collecting the ADL (activities of daily living) data and further analysis within existing computing elements. In this research, a very recent algorithm named sequence prediction via enhanced episode discovery (SPEED) is modified and in order to improve accuracy time component is included. Methods: The modified SPEED or M-SPEED is a sequence prediction algorithm, which modified the previous SPEED algorithm by using time duration of appliance’s ON-OFF states to decide the next state. M-SPEED discovered periodic episodes of inhabitant behavior, trained it with learned episodes, and made decisions based on the obtained knowledge. Results: The results showed that M-SPEED achieves 96.8% prediction accuracy, which is better than other time prediction algorithms like PUBS, ALZ with temporal rules and the previous SPEED. Conclusions: Since human behavior shows natural temporal patterns, duration times can be used to predict future events more accurately. This inhabitant activity prediction system will certainly improve the smart homes by ensuring safety and better care for elderly and handicapped people.

Original languageEnglish
Pages (from-to)262-270
Number of pages9
JournalMethods of Information in Medicine
Volume54
Issue number3
DOIs
Publication statusPublished - 2015

Fingerprint

Safety
Disabled Persons
Activities of Daily Living
Research

Keywords

  • ADL
  • M-speed
  • Machine learning
  • Sequence prediction
  • Smart home

ASJC Scopus subject areas

  • Health Informatics
  • Health Information Management
  • Advanced and Specialised Nursing

Cite this

A time series based sequence prediction algorithm to detect activi -ties of daily living in smart home. / Marufuzzaman, M.; Ibne Reaz, Md. Mamun; Ali, M. A M; Rahman, L. F.

In: Methods of Information in Medicine, Vol. 54, No. 3, 2015, p. 262-270.

Research output: Contribution to journalArticle

@article{8f489e1b51cf4e82ab56485eae5f271e,
title = "A time series based sequence prediction algorithm to detect activi -ties of daily living in smart home",
abstract = "Objectives: The goal of smart homes is to create an intelligent environment adapting the inhabitants need and assisting the person who needs special care and safety in their daily life. This can be reached by collecting the ADL (activities of daily living) data and further analysis within existing computing elements. In this research, a very recent algorithm named sequence prediction via enhanced episode discovery (SPEED) is modified and in order to improve accuracy time component is included. Methods: The modified SPEED or M-SPEED is a sequence prediction algorithm, which modified the previous SPEED algorithm by using time duration of appliance’s ON-OFF states to decide the next state. M-SPEED discovered periodic episodes of inhabitant behavior, trained it with learned episodes, and made decisions based on the obtained knowledge. Results: The results showed that M-SPEED achieves 96.8{\%} prediction accuracy, which is better than other time prediction algorithms like PUBS, ALZ with temporal rules and the previous SPEED. Conclusions: Since human behavior shows natural temporal patterns, duration times can be used to predict future events more accurately. This inhabitant activity prediction system will certainly improve the smart homes by ensuring safety and better care for elderly and handicapped people.",
keywords = "ADL, M-speed, Machine learning, Sequence prediction, Smart home",
author = "M. Marufuzzaman and {Ibne Reaz}, {Md. Mamun} and Ali, {M. A M} and Rahman, {L. F.}",
year = "2015",
doi = "10.3414/ME14-01-0061",
language = "English",
volume = "54",
pages = "262--270",
journal = "Methods of Information in Medicine",
issn = "0026-1270",
publisher = "Schattauer GmbH",
number = "3",

}

TY - JOUR

T1 - A time series based sequence prediction algorithm to detect activi -ties of daily living in smart home

AU - Marufuzzaman, M.

AU - Ibne Reaz, Md. Mamun

AU - Ali, M. A M

AU - Rahman, L. F.

PY - 2015

Y1 - 2015

N2 - Objectives: The goal of smart homes is to create an intelligent environment adapting the inhabitants need and assisting the person who needs special care and safety in their daily life. This can be reached by collecting the ADL (activities of daily living) data and further analysis within existing computing elements. In this research, a very recent algorithm named sequence prediction via enhanced episode discovery (SPEED) is modified and in order to improve accuracy time component is included. Methods: The modified SPEED or M-SPEED is a sequence prediction algorithm, which modified the previous SPEED algorithm by using time duration of appliance’s ON-OFF states to decide the next state. M-SPEED discovered periodic episodes of inhabitant behavior, trained it with learned episodes, and made decisions based on the obtained knowledge. Results: The results showed that M-SPEED achieves 96.8% prediction accuracy, which is better than other time prediction algorithms like PUBS, ALZ with temporal rules and the previous SPEED. Conclusions: Since human behavior shows natural temporal patterns, duration times can be used to predict future events more accurately. This inhabitant activity prediction system will certainly improve the smart homes by ensuring safety and better care for elderly and handicapped people.

AB - Objectives: The goal of smart homes is to create an intelligent environment adapting the inhabitants need and assisting the person who needs special care and safety in their daily life. This can be reached by collecting the ADL (activities of daily living) data and further analysis within existing computing elements. In this research, a very recent algorithm named sequence prediction via enhanced episode discovery (SPEED) is modified and in order to improve accuracy time component is included. Methods: The modified SPEED or M-SPEED is a sequence prediction algorithm, which modified the previous SPEED algorithm by using time duration of appliance’s ON-OFF states to decide the next state. M-SPEED discovered periodic episodes of inhabitant behavior, trained it with learned episodes, and made decisions based on the obtained knowledge. Results: The results showed that M-SPEED achieves 96.8% prediction accuracy, which is better than other time prediction algorithms like PUBS, ALZ with temporal rules and the previous SPEED. Conclusions: Since human behavior shows natural temporal patterns, duration times can be used to predict future events more accurately. This inhabitant activity prediction system will certainly improve the smart homes by ensuring safety and better care for elderly and handicapped people.

KW - ADL

KW - M-speed

KW - Machine learning

KW - Sequence prediction

KW - Smart home

UR - http://www.scopus.com/inward/record.url?scp=84930848916&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84930848916&partnerID=8YFLogxK

U2 - 10.3414/ME14-01-0061

DO - 10.3414/ME14-01-0061

M3 - Article

C2 - 25604028

AN - SCOPUS:84930848916

VL - 54

SP - 262

EP - 270

JO - Methods of Information in Medicine

JF - Methods of Information in Medicine

SN - 0026-1270

IS - 3

ER -