Temporal modeling of human activity in smart homes

Muhammad Raisul Alam, Md. Mamun Ibne Reaz, Mohd Alauddin Mohd Ali, Salina Abdul Samad

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Recognition of human activity is a potential challenge to design an effective smart home. The paper proposed a novel algorithm to recognize activities of daily living (ADL) of the resident. It provides analysis and mathematical modeling of temporal intervals of the event. The opposite entity states are used to extract the pattern of event sequence. Each extracted episode represents a distinct task of the resident. Result shows that, the algorithm can successfully identify 135 unique tasks of different lengths with temporal characteristics. The analysis confirms that temporal pattern follows normal distribution which can be modeled by Gaussian function.

Original languageEnglish
Pages (from-to)118-121
Number of pages4
JournalInformacije MIDEM
Volume41
Issue number2
Publication statusPublished - 2011

Fingerprint

Normal distribution

Keywords

  • Activities of daily living (ADL)
  • Pattern recognition
  • Smart home
  • Temporal modeling

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials

Cite this

Temporal modeling of human activity in smart homes. / Alam, Muhammad Raisul; Ibne Reaz, Md. Mamun; Ali, Mohd Alauddin Mohd; Abdul Samad, Salina.

In: Informacije MIDEM, Vol. 41, No. 2, 2011, p. 118-121.

Research output: Contribution to journalArticle

Alam, Muhammad Raisul ; Ibne Reaz, Md. Mamun ; Ali, Mohd Alauddin Mohd ; Abdul Samad, Salina. / Temporal modeling of human activity in smart homes. In: Informacije MIDEM. 2011 ; Vol. 41, No. 2. pp. 118-121.
@article{5f5537a223c84269ba2508ba6845cde5,
title = "Temporal modeling of human activity in smart homes",
abstract = "Recognition of human activity is a potential challenge to design an effective smart home. The paper proposed a novel algorithm to recognize activities of daily living (ADL) of the resident. It provides analysis and mathematical modeling of temporal intervals of the event. The opposite entity states are used to extract the pattern of event sequence. Each extracted episode represents a distinct task of the resident. Result shows that, the algorithm can successfully identify 135 unique tasks of different lengths with temporal characteristics. The analysis confirms that temporal pattern follows normal distribution which can be modeled by Gaussian function.",
keywords = "Activities of daily living (ADL), Pattern recognition, Smart home, Temporal modeling",
author = "Alam, {Muhammad Raisul} and {Ibne Reaz}, {Md. Mamun} and Ali, {Mohd Alauddin Mohd} and {Abdul Samad}, Salina",
year = "2011",
language = "English",
volume = "41",
pages = "118--121",
journal = "Informacije MIDEM",
issn = "0352-9045",
publisher = "Society for Microelectronics, Electric Components and Materials",
number = "2",

}

TY - JOUR

T1 - Temporal modeling of human activity in smart homes

AU - Alam, Muhammad Raisul

AU - Ibne Reaz, Md. Mamun

AU - Ali, Mohd Alauddin Mohd

AU - Abdul Samad, Salina

PY - 2011

Y1 - 2011

N2 - Recognition of human activity is a potential challenge to design an effective smart home. The paper proposed a novel algorithm to recognize activities of daily living (ADL) of the resident. It provides analysis and mathematical modeling of temporal intervals of the event. The opposite entity states are used to extract the pattern of event sequence. Each extracted episode represents a distinct task of the resident. Result shows that, the algorithm can successfully identify 135 unique tasks of different lengths with temporal characteristics. The analysis confirms that temporal pattern follows normal distribution which can be modeled by Gaussian function.

AB - Recognition of human activity is a potential challenge to design an effective smart home. The paper proposed a novel algorithm to recognize activities of daily living (ADL) of the resident. It provides analysis and mathematical modeling of temporal intervals of the event. The opposite entity states are used to extract the pattern of event sequence. Each extracted episode represents a distinct task of the resident. Result shows that, the algorithm can successfully identify 135 unique tasks of different lengths with temporal characteristics. The analysis confirms that temporal pattern follows normal distribution which can be modeled by Gaussian function.

KW - Activities of daily living (ADL)

KW - Pattern recognition

KW - Smart home

KW - Temporal modeling

UR - http://www.scopus.com/inward/record.url?scp=80054985569&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80054985569&partnerID=8YFLogxK

M3 - Article

VL - 41

SP - 118

EP - 121

JO - Informacije MIDEM

JF - Informacije MIDEM

SN - 0352-9045

IS - 2

ER -