Design and assessment of the data analysis process for a wrist-worn smart object to detect atomic activities in the smart home

Qin Ni, I Cleland, CD Nugent, Ana Belén García Hernando, Ivan Pau de la Cruz

Research output: Contribution to journalArticle

Abstract

The ability to accurately identify the different activities of daily living (ADLs) is considered as one of the basis to foster new technological solutions inside the smart home. Current ADL recognition proposals, still however, struggle to accurately and robustly identify the range of different activities that can be performed at home, namely static, dynamic and transient activities, and the high variety of technologies and data analysis possibilities to classify the information gathered by the sensors. In this paper, we describe the methodological approach that we have followed for the processing, analysis and classification of data obtained by a simple and non-intrusive smart object with the objective to detect atomic (i.e. non-divisible) activities inside the smart home. The smart object consists of a wrist-worn 3D accelerometer, which presents as its advantages its customizability and usability. We have performed a set of systematic experiments involving ten people and have followed the steps from data gathering to the comparison of different classification techniques, to find out that it is possible to select a complete succession of data processing steps in order to detect, with high accuracy, a set of atomic activities of daily life with the selected smart object, which performs well with different independent datasets besides ours.
LanguageEnglish
Pages57-70
Number of pages14
JournalPervasive and Mobile Computing
Volume56
Early online date3 Apr 2019
DOIs
Publication statusPublished - 1 May 2019

Fingerprint

Smart Objects
Smart Home
Data analysis
Accelerometers
Sensors
Processing
Experiments
Accelerometer
Usability
Design
High Accuracy
Classify
Sensor
Range of data

Keywords

  • Activity recognition
  • Class imbalance
  • Ensemble classification
  • Smart home
  • Smart object

Cite this

@article{a653407859b14651ba06f07a514b29f4,
title = "Design and assessment of the data analysis process for a wrist-worn smart object to detect atomic activities in the smart home",
abstract = "The ability to accurately identify the different activities of daily living (ADLs) is considered as one of the basis to foster new technological solutions inside the smart home. Current ADL recognition proposals, still however, struggle to accurately and robustly identify the range of different activities that can be performed at home, namely static, dynamic and transient activities, and the high variety of technologies and data analysis possibilities to classify the information gathered by the sensors. In this paper, we describe the methodological approach that we have followed for the processing, analysis and classification of data obtained by a simple and non-intrusive smart object with the objective to detect atomic (i.e. non-divisible) activities inside the smart home. The smart object consists of a wrist-worn 3D accelerometer, which presents as its advantages its customizability and usability. We have performed a set of systematic experiments involving ten people and have followed the steps from data gathering to the comparison of different classification techniques, to find out that it is possible to select a complete succession of data processing steps in order to detect, with high accuracy, a set of atomic activities of daily life with the selected smart object, which performs well with different independent datasets besides ours.",
keywords = "Activity recognition, Class imbalance, Ensemble classification, Smart home, Smart object",
author = "Qin Ni and I Cleland and CD Nugent and {Garc{\'i}a Hernando}, {Ana Bel{\'e}n} and {Pau de la Cruz}, Ivan",
year = "2019",
month = "5",
day = "1",
doi = "10.1016/j.pmcj.2019.03.006",
language = "English",
volume = "56",
pages = "57--70",

}

Design and assessment of the data analysis process for a wrist-worn smart object to detect atomic activities in the smart home. / Ni, Qin; Cleland, I; Nugent, CD; García Hernando, Ana Belén; Pau de la Cruz, Ivan.

Vol. 56, 01.05.2019, p. 57-70.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Design and assessment of the data analysis process for a wrist-worn smart object to detect atomic activities in the smart home

AU - Ni, Qin

AU - Cleland, I

AU - Nugent, CD

AU - García Hernando, Ana Belén

AU - Pau de la Cruz, Ivan

PY - 2019/5/1

Y1 - 2019/5/1

N2 - The ability to accurately identify the different activities of daily living (ADLs) is considered as one of the basis to foster new technological solutions inside the smart home. Current ADL recognition proposals, still however, struggle to accurately and robustly identify the range of different activities that can be performed at home, namely static, dynamic and transient activities, and the high variety of technologies and data analysis possibilities to classify the information gathered by the sensors. In this paper, we describe the methodological approach that we have followed for the processing, analysis and classification of data obtained by a simple and non-intrusive smart object with the objective to detect atomic (i.e. non-divisible) activities inside the smart home. The smart object consists of a wrist-worn 3D accelerometer, which presents as its advantages its customizability and usability. We have performed a set of systematic experiments involving ten people and have followed the steps from data gathering to the comparison of different classification techniques, to find out that it is possible to select a complete succession of data processing steps in order to detect, with high accuracy, a set of atomic activities of daily life with the selected smart object, which performs well with different independent datasets besides ours.

AB - The ability to accurately identify the different activities of daily living (ADLs) is considered as one of the basis to foster new technological solutions inside the smart home. Current ADL recognition proposals, still however, struggle to accurately and robustly identify the range of different activities that can be performed at home, namely static, dynamic and transient activities, and the high variety of technologies and data analysis possibilities to classify the information gathered by the sensors. In this paper, we describe the methodological approach that we have followed for the processing, analysis and classification of data obtained by a simple and non-intrusive smart object with the objective to detect atomic (i.e. non-divisible) activities inside the smart home. The smart object consists of a wrist-worn 3D accelerometer, which presents as its advantages its customizability and usability. We have performed a set of systematic experiments involving ten people and have followed the steps from data gathering to the comparison of different classification techniques, to find out that it is possible to select a complete succession of data processing steps in order to detect, with high accuracy, a set of atomic activities of daily life with the selected smart object, which performs well with different independent datasets besides ours.

KW - Activity recognition

KW - Class imbalance

KW - Ensemble classification

KW - Smart home

KW - Smart object

UR - http://www.scopus.com/inward/record.url?scp=85064257445&partnerID=8YFLogxK

U2 - 10.1016/j.pmcj.2019.03.006

DO - 10.1016/j.pmcj.2019.03.006

M3 - Article

VL - 56

SP - 57

EP - 70

ER -