Sensor data mining on the kinematical characteristics of the competitive swimming

Yuji Ohgi, Koichi Kaneda, Akira Takakura

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

5 Citations (Scopus)

Abstract

The purpose of this study was to propose a new methodology for the automatic identification and the classification of the swimmers kinematical information during interval training of competitive swimming. Forty-five college swimmers attached the newly developed chest band sensor unit, which has a triple-axes accelerometer inside, and then performed a controlled interval training set with four stroke styles. The authors identified swimmer's states, such as the swimming/rest phases and the start, turn and goal touch events by using the trunk longitudinal acceleration (Ay). With the inductive inference based on the experimental results and the deductive inference based on the empirical rule on the interval training brought the estimation of the swimming time. For the classification of the swimming strokes, using the extracted swimming phase acceleration, the mean, variance and skewness of each bout were calculated. The authors compared different data mining algorithms for the stroke style classification with these descriptive statistics, such as mean, variance, skewness on the each axial acceleration as the independent variables and stroke styles as the depending variable. The accuracy of the stroke style classification by both the multi-layered neural network (NN) and the C4.5 decision tree were 91.1%.

Original languageEnglish
Title of host publicationProcedia Engineering
PublisherElsevier Ltd
Pages829-834
Number of pages6
Volume72
DOIs
Publication statusPublished - 2014
Event2014 10th Conference of the International Sports Engineering Association, ISEA 2014 - Sheffield, United Kingdom
Duration: 2014 Jul 142014 Jul 17

Other

Other2014 10th Conference of the International Sports Engineering Association, ISEA 2014
CountryUnited Kingdom
CitySheffield
Period14/7/1414/7/17

Fingerprint

Data mining
Sensors
Decision trees
Accelerometers
Swimming
Statistics
Neural networks

Keywords

  • Accelerometer
  • Classification
  • Competitive swimming
  • Data mining
  • Decision tree
  • Neural network

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Ohgi, Y., Kaneda, K., & Takakura, A. (2014). Sensor data mining on the kinematical characteristics of the competitive swimming. In Procedia Engineering (Vol. 72, pp. 829-834). Elsevier Ltd. https://doi.org/10.1016/j.proeng.2014.06.036

Sensor data mining on the kinematical characteristics of the competitive swimming. / Ohgi, Yuji; Kaneda, Koichi; Takakura, Akira.

Procedia Engineering. Vol. 72 Elsevier Ltd, 2014. p. 829-834.

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

Ohgi, Y, Kaneda, K & Takakura, A 2014, Sensor data mining on the kinematical characteristics of the competitive swimming. in Procedia Engineering. vol. 72, Elsevier Ltd, pp. 829-834, 2014 10th Conference of the International Sports Engineering Association, ISEA 2014, Sheffield, United Kingdom, 14/7/14. https://doi.org/10.1016/j.proeng.2014.06.036
Ohgi Y, Kaneda K, Takakura A. Sensor data mining on the kinematical characteristics of the competitive swimming. In Procedia Engineering. Vol. 72. Elsevier Ltd. 2014. p. 829-834 https://doi.org/10.1016/j.proeng.2014.06.036
Ohgi, Yuji ; Kaneda, Koichi ; Takakura, Akira. / Sensor data mining on the kinematical characteristics of the competitive swimming. Procedia Engineering. Vol. 72 Elsevier Ltd, 2014. pp. 829-834
@inproceedings{3849e602202946a6a3bc840df1d22b11,
title = "Sensor data mining on the kinematical characteristics of the competitive swimming",
abstract = "The purpose of this study was to propose a new methodology for the automatic identification and the classification of the swimmers kinematical information during interval training of competitive swimming. Forty-five college swimmers attached the newly developed chest band sensor unit, which has a triple-axes accelerometer inside, and then performed a controlled interval training set with four stroke styles. The authors identified swimmer's states, such as the swimming/rest phases and the start, turn and goal touch events by using the trunk longitudinal acceleration (Ay). With the inductive inference based on the experimental results and the deductive inference based on the empirical rule on the interval training brought the estimation of the swimming time. For the classification of the swimming strokes, using the extracted swimming phase acceleration, the mean, variance and skewness of each bout were calculated. The authors compared different data mining algorithms for the stroke style classification with these descriptive statistics, such as mean, variance, skewness on the each axial acceleration as the independent variables and stroke styles as the depending variable. The accuracy of the stroke style classification by both the multi-layered neural network (NN) and the C4.5 decision tree were 91.1{\%}.",
keywords = "Accelerometer, Classification, Competitive swimming, Data mining, Decision tree, Neural network",
author = "Yuji Ohgi and Koichi Kaneda and Akira Takakura",
year = "2014",
doi = "10.1016/j.proeng.2014.06.036",
language = "English",
volume = "72",
pages = "829--834",
booktitle = "Procedia Engineering",
publisher = "Elsevier Ltd",

}

TY - GEN

T1 - Sensor data mining on the kinematical characteristics of the competitive swimming

AU - Ohgi, Yuji

AU - Kaneda, Koichi

AU - Takakura, Akira

PY - 2014

Y1 - 2014

N2 - The purpose of this study was to propose a new methodology for the automatic identification and the classification of the swimmers kinematical information during interval training of competitive swimming. Forty-five college swimmers attached the newly developed chest band sensor unit, which has a triple-axes accelerometer inside, and then performed a controlled interval training set with four stroke styles. The authors identified swimmer's states, such as the swimming/rest phases and the start, turn and goal touch events by using the trunk longitudinal acceleration (Ay). With the inductive inference based on the experimental results and the deductive inference based on the empirical rule on the interval training brought the estimation of the swimming time. For the classification of the swimming strokes, using the extracted swimming phase acceleration, the mean, variance and skewness of each bout were calculated. The authors compared different data mining algorithms for the stroke style classification with these descriptive statistics, such as mean, variance, skewness on the each axial acceleration as the independent variables and stroke styles as the depending variable. The accuracy of the stroke style classification by both the multi-layered neural network (NN) and the C4.5 decision tree were 91.1%.

AB - The purpose of this study was to propose a new methodology for the automatic identification and the classification of the swimmers kinematical information during interval training of competitive swimming. Forty-five college swimmers attached the newly developed chest band sensor unit, which has a triple-axes accelerometer inside, and then performed a controlled interval training set with four stroke styles. The authors identified swimmer's states, such as the swimming/rest phases and the start, turn and goal touch events by using the trunk longitudinal acceleration (Ay). With the inductive inference based on the experimental results and the deductive inference based on the empirical rule on the interval training brought the estimation of the swimming time. For the classification of the swimming strokes, using the extracted swimming phase acceleration, the mean, variance and skewness of each bout were calculated. The authors compared different data mining algorithms for the stroke style classification with these descriptive statistics, such as mean, variance, skewness on the each axial acceleration as the independent variables and stroke styles as the depending variable. The accuracy of the stroke style classification by both the multi-layered neural network (NN) and the C4.5 decision tree were 91.1%.

KW - Accelerometer

KW - Classification

KW - Competitive swimming

KW - Data mining

KW - Decision tree

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=84903771580&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903771580&partnerID=8YFLogxK

U2 - 10.1016/j.proeng.2014.06.036

DO - 10.1016/j.proeng.2014.06.036

M3 - Conference contribution

VL - 72

SP - 829

EP - 834

BT - Procedia Engineering

PB - Elsevier Ltd

ER -