On the use of decision tree for posture recognition

Nooritawati Md Tahir, Aini Hussain, Salina Abdul Samad, Hafizah Hussin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

The aim of this study is to evaluate the effectiveness of decision tree as classifier for recognition of four main human postures (standing, sitting, bending and lying) since decision trees are well known for their success for prediction, recognition and classification task in data mining problems. Firstly, the eigenfeatures of these postures are optimized via Principal Component Analysis rules of thumb specifically the KG-rule, Cumulative Variance and the Scree Test. Next, these eigenfeatures are statistically analyzed prior to classification. In doing so, the most relevant eigenfeatures that we termed as eigenpostures can be ascertained. Further, we employed decision tree as classifier for posture recognition. Initial results of the experiments are encouraging which suggested that our method can efficiently be applied for posture classification using DT.

Original languageEnglish
Title of host publicationISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation
Pages209-214
Number of pages6
DOIs
Publication statusPublished - 2010
EventUKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation, ISMS 2010 - Liverpool
Duration: 27 Jan 201029 Jan 2010

Other

OtherUKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation, ISMS 2010
CityLiverpool
Period27/1/1029/1/10

Fingerprint

Decision trees
Decision tree
Classifiers
Classifier
Principal component analysis
Principal Component Analysis
Data mining
Data Mining
Evaluate
Prediction
Experiment
Experiments

Keywords

  • ANOVA
  • Decision Tree
  • Posture Recognition
  • Principal Component Analysis

ASJC Scopus subject areas

  • Computer Science(all)
  • Theoretical Computer Science

Cite this

Tahir, N. M., Hussain, A., Abdul Samad, S., & Hussin, H. (2010). On the use of decision tree for posture recognition. In ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation (pp. 209-214). [5416092] https://doi.org/10.1109/ISMS.2010.47

On the use of decision tree for posture recognition. / Tahir, Nooritawati Md; Hussain, Aini; Abdul Samad, Salina; Hussin, Hafizah.

ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation. 2010. p. 209-214 5416092.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tahir, NM, Hussain, A, Abdul Samad, S & Hussin, H 2010, On the use of decision tree for posture recognition. in ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation., 5416092, pp. 209-214, UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation, ISMS 2010, Liverpool, 27/1/10. https://doi.org/10.1109/ISMS.2010.47
Tahir NM, Hussain A, Abdul Samad S, Hussin H. On the use of decision tree for posture recognition. In ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation. 2010. p. 209-214. 5416092 https://doi.org/10.1109/ISMS.2010.47
Tahir, Nooritawati Md ; Hussain, Aini ; Abdul Samad, Salina ; Hussin, Hafizah. / On the use of decision tree for posture recognition. ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation. 2010. pp. 209-214
@inproceedings{bea29567aed84d01b35a57c70ee64280,
title = "On the use of decision tree for posture recognition",
abstract = "The aim of this study is to evaluate the effectiveness of decision tree as classifier for recognition of four main human postures (standing, sitting, bending and lying) since decision trees are well known for their success for prediction, recognition and classification task in data mining problems. Firstly, the eigenfeatures of these postures are optimized via Principal Component Analysis rules of thumb specifically the KG-rule, Cumulative Variance and the Scree Test. Next, these eigenfeatures are statistically analyzed prior to classification. In doing so, the most relevant eigenfeatures that we termed as eigenpostures can be ascertained. Further, we employed decision tree as classifier for posture recognition. Initial results of the experiments are encouraging which suggested that our method can efficiently be applied for posture classification using DT.",
keywords = "ANOVA, Decision Tree, Posture Recognition, Principal Component Analysis",
author = "Tahir, {Nooritawati Md} and Aini Hussain and {Abdul Samad}, Salina and Hafizah Hussin",
year = "2010",
doi = "10.1109/ISMS.2010.47",
language = "English",
isbn = "9780769539737",
pages = "209--214",
booktitle = "ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation",

}

TY - GEN

T1 - On the use of decision tree for posture recognition

AU - Tahir, Nooritawati Md

AU - Hussain, Aini

AU - Abdul Samad, Salina

AU - Hussin, Hafizah

PY - 2010

Y1 - 2010

N2 - The aim of this study is to evaluate the effectiveness of decision tree as classifier for recognition of four main human postures (standing, sitting, bending and lying) since decision trees are well known for their success for prediction, recognition and classification task in data mining problems. Firstly, the eigenfeatures of these postures are optimized via Principal Component Analysis rules of thumb specifically the KG-rule, Cumulative Variance and the Scree Test. Next, these eigenfeatures are statistically analyzed prior to classification. In doing so, the most relevant eigenfeatures that we termed as eigenpostures can be ascertained. Further, we employed decision tree as classifier for posture recognition. Initial results of the experiments are encouraging which suggested that our method can efficiently be applied for posture classification using DT.

AB - The aim of this study is to evaluate the effectiveness of decision tree as classifier for recognition of four main human postures (standing, sitting, bending and lying) since decision trees are well known for their success for prediction, recognition and classification task in data mining problems. Firstly, the eigenfeatures of these postures are optimized via Principal Component Analysis rules of thumb specifically the KG-rule, Cumulative Variance and the Scree Test. Next, these eigenfeatures are statistically analyzed prior to classification. In doing so, the most relevant eigenfeatures that we termed as eigenpostures can be ascertained. Further, we employed decision tree as classifier for posture recognition. Initial results of the experiments are encouraging which suggested that our method can efficiently be applied for posture classification using DT.

KW - ANOVA

KW - Decision Tree

KW - Posture Recognition

KW - Principal Component Analysis

UR - http://www.scopus.com/inward/record.url?scp=77950928836&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77950928836&partnerID=8YFLogxK

U2 - 10.1109/ISMS.2010.47

DO - 10.1109/ISMS.2010.47

M3 - Conference contribution

SN - 9780769539737

SP - 209

EP - 214

BT - ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation

ER -