A Lightweight Hierarchical Activity Recognition Framework Using Smartphone Sensors

Manhyung Han, Jae Bang, CD Nugent, Sally McClean, Sungyoung Lee

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Activity recognition for the purposes of recognizing a user’s intentions using multimodal sensors is becoming a widely researched topic largely based on the prevalence of the smartphone. Previous studies have reported the difficulty in recognizing life-logs by only using a smartphone due to the challenges with activity modeling and real-time recognition. In addition, recognizing life-logs is difficult due to the absence of an established framework which enables the use of different sources of sensor data. In this paper, we propose a smartphone-based Hierarchical Activity Recognition Framework which extends the Naïve Bayes approach for the processing of activity modeling and real-time activity recognition. The proposed algorithm demonstrates higher accuracy than the Naïve Bayes approach and also enables the recognition of a user’s activities within a mobile environment. The proposed algorithm has the ability to classify fifteen activities with an average classification accuracy of 92.96%.
LanguageEnglish
Pages16181
JournalSensors
Volume14
Issue number9
DOIs
Publication statusPublished - 2014

Fingerprint

Smartphones
sensors
Sensors
Aptitude
Information Storage and Retrieval
Processing
Smartphone
Recognition (Psychology)

Cite this

Han, Manhyung ; Bang, Jae ; Nugent, CD ; McClean, Sally ; Lee, Sungyoung. / A Lightweight Hierarchical Activity Recognition Framework Using Smartphone Sensors. In: Sensors. 2014 ; Vol. 14, No. 9. pp. 16181.
@article{21eaf29544e74df7a03fe8cc3f5aff1f,
title = "A Lightweight Hierarchical Activity Recognition Framework Using Smartphone Sensors",
abstract = "Activity recognition for the purposes of recognizing a user’s intentions using multimodal sensors is becoming a widely researched topic largely based on the prevalence of the smartphone. Previous studies have reported the difficulty in recognizing life-logs by only using a smartphone due to the challenges with activity modeling and real-time recognition. In addition, recognizing life-logs is difficult due to the absence of an established framework which enables the use of different sources of sensor data. In this paper, we propose a smartphone-based Hierarchical Activity Recognition Framework which extends the Na{\"i}ve Bayes approach for the processing of activity modeling and real-time activity recognition. The proposed algorithm demonstrates higher accuracy than the Na{\"i}ve Bayes approach and also enables the recognition of a user’s activities within a mobile environment. The proposed algorithm has the ability to classify fifteen activities with an average classification accuracy of 92.96{\%}.",
author = "Manhyung Han and Jae Bang and CD Nugent and Sally McClean and Sungyoung Lee",
year = "2014",
doi = "10.3390/s140916181",
language = "English",
volume = "14",
pages = "16181",
journal = "Sensors",
issn = "1424-8220",
publisher = "MDPI",
number = "9",

}

A Lightweight Hierarchical Activity Recognition Framework Using Smartphone Sensors. / Han, Manhyung; Bang, Jae; Nugent, CD; McClean, Sally; Lee, Sungyoung.

In: Sensors, Vol. 14, No. 9, 2014, p. 16181.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Lightweight Hierarchical Activity Recognition Framework Using Smartphone Sensors

AU - Han, Manhyung

AU - Bang, Jae

AU - Nugent, CD

AU - McClean, Sally

AU - Lee, Sungyoung

PY - 2014

Y1 - 2014

N2 - Activity recognition for the purposes of recognizing a user’s intentions using multimodal sensors is becoming a widely researched topic largely based on the prevalence of the smartphone. Previous studies have reported the difficulty in recognizing life-logs by only using a smartphone due to the challenges with activity modeling and real-time recognition. In addition, recognizing life-logs is difficult due to the absence of an established framework which enables the use of different sources of sensor data. In this paper, we propose a smartphone-based Hierarchical Activity Recognition Framework which extends the Naïve Bayes approach for the processing of activity modeling and real-time activity recognition. The proposed algorithm demonstrates higher accuracy than the Naïve Bayes approach and also enables the recognition of a user’s activities within a mobile environment. The proposed algorithm has the ability to classify fifteen activities with an average classification accuracy of 92.96%.

AB - Activity recognition for the purposes of recognizing a user’s intentions using multimodal sensors is becoming a widely researched topic largely based on the prevalence of the smartphone. Previous studies have reported the difficulty in recognizing life-logs by only using a smartphone due to the challenges with activity modeling and real-time recognition. In addition, recognizing life-logs is difficult due to the absence of an established framework which enables the use of different sources of sensor data. In this paper, we propose a smartphone-based Hierarchical Activity Recognition Framework which extends the Naïve Bayes approach for the processing of activity modeling and real-time activity recognition. The proposed algorithm demonstrates higher accuracy than the Naïve Bayes approach and also enables the recognition of a user’s activities within a mobile environment. The proposed algorithm has the ability to classify fifteen activities with an average classification accuracy of 92.96%.

U2 - 10.3390/s140916181

DO - 10.3390/s140916181

M3 - Article

VL - 14

SP - 16181

JO - Sensors

T2 - Sensors

JF - Sensors

SN - 1424-8220

IS - 9

ER -