An Exercise Prescription Formulating Scheme Based on a Two-Layer Classifier
碩士 === 國立中興大學 === 資訊科學與工程學系所 === 100 === An exercise prescription is a professionally designed exercise plan for improving one‘s health according to the results of his health-related physical fitness (HRPF) tests. The exercise prescription is usually categorized into five levels by experts. Traditio...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2012
|
Online Access: | http://ndltd.ncl.edu.tw/handle/18827555940192988003 |
id |
ndltd-TW-100NCHU5394036 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-100NCHU53940362016-10-23T04:11:28Z http://ndltd.ncl.edu.tw/handle/18827555940192988003 An Exercise Prescription Formulating Scheme Based on a Two-Layer Classifier 雙層分類器為基礎的體適能運動處方產生器 Chia-Chi Liu 劉佳琪 碩士 國立中興大學 資訊科學與工程學系所 100 An exercise prescription is a professionally designed exercise plan for improving one‘s health according to the results of his health-related physical fitness (HRPF) tests. The exercise prescription is usually categorized into five levels by experts. Traditionally, an exercise prescription is formulated by manually checking the norm-referenced chart of HRPF. However, it is time consuming, and a highly specialized and experienced expert on health-related physical fitness testing is needed to formulate this prescription. To solve above problems, it is necessary to develope an automatic exercise prescription formulating scheme for categorizing the measured data of HRPF tests and then assign the best appopriate exercise prescription for each class. In this study, a two-layer classifier, integrating the techniques of K-means clustering algorithm and genetic algorithm, is proposed to classify the measured data of HRPF tests into classes and provide the best appropriate exercise prescription for each class. When the data variance within one class is very large, the centroid of the class cannot effectively represent each datum in the class. The two-layer classifier therefore partitions each class into several clusters (subclasses) and then classifies the measured data of HRPF tests into clusters. In this study, a genetic algorithm is provided to determine the number of clusters, which each class should be separated into, and the best suitable values of the parameters used in the two-layer classifier. The experimental results demonstrate that the two-layer classifier can effectively and efficiently classify the measured data of HRPF tests and design a most suitable exercise plan. Cardiovascular fitness in HRPF is one of the most important factor for health. Hence, in this study, the T-test statistics is used to evaluate the impact of exercise on cardiorespiratory fitness. Shyr-Shen Yu 喻石生 2012 學位論文 ; thesis 39 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立中興大學 === 資訊科學與工程學系所 === 100 === An exercise prescription is a professionally designed exercise plan for improving one‘s health according to the results of his health-related physical fitness (HRPF) tests. The exercise prescription is usually categorized into five levels by experts. Traditionally, an exercise prescription is formulated by manually checking the norm-referenced chart of HRPF. However, it is time consuming, and a highly specialized and experienced expert on health-related physical fitness testing is needed to formulate this prescription. To solve above problems, it is necessary to develope an automatic exercise prescription formulating scheme for categorizing the measured data of HRPF tests and then assign the best appopriate exercise prescription for each class. In this study, a two-layer classifier, integrating the techniques of K-means clustering algorithm and genetic algorithm, is proposed to classify the measured data of HRPF tests into classes and provide the best appropriate exercise prescription for each class. When the data variance within one class is very large, the centroid of the class cannot effectively represent each datum in the class. The two-layer classifier therefore partitions each class into several clusters (subclasses) and then classifies the measured data of HRPF tests into clusters. In this study, a genetic algorithm is provided to determine the number of clusters, which each class should be separated into, and the best suitable values of the parameters used in the two-layer classifier. The experimental results demonstrate that the two-layer classifier can effectively and efficiently classify the measured data of HRPF tests and design a most suitable exercise plan. Cardiovascular fitness in HRPF is one of the most important factor for health. Hence, in this study, the T-test statistics is used to evaluate the impact of exercise on cardiorespiratory fitness.
|
author2 |
Shyr-Shen Yu |
author_facet |
Shyr-Shen Yu Chia-Chi Liu 劉佳琪 |
author |
Chia-Chi Liu 劉佳琪 |
spellingShingle |
Chia-Chi Liu 劉佳琪 An Exercise Prescription Formulating Scheme Based on a Two-Layer Classifier |
author_sort |
Chia-Chi Liu |
title |
An Exercise Prescription Formulating Scheme Based on a Two-Layer Classifier |
title_short |
An Exercise Prescription Formulating Scheme Based on a Two-Layer Classifier |
title_full |
An Exercise Prescription Formulating Scheme Based on a Two-Layer Classifier |
title_fullStr |
An Exercise Prescription Formulating Scheme Based on a Two-Layer Classifier |
title_full_unstemmed |
An Exercise Prescription Formulating Scheme Based on a Two-Layer Classifier |
title_sort |
exercise prescription formulating scheme based on a two-layer classifier |
publishDate |
2012 |
url |
http://ndltd.ncl.edu.tw/handle/18827555940192988003 |
work_keys_str_mv |
AT chiachiliu anexerciseprescriptionformulatingschemebasedonatwolayerclassifier AT liújiāqí anexerciseprescriptionformulatingschemebasedonatwolayerclassifier AT chiachiliu shuāngcéngfēnlèiqìwèijīchǔdetǐshìnéngyùndòngchùfāngchǎnshēngqì AT liújiāqí shuāngcéngfēnlèiqìwèijīchǔdetǐshìnéngyùndòngchùfāngchǎnshēngqì AT chiachiliu exerciseprescriptionformulatingschemebasedonatwolayerclassifier AT liújiāqí exerciseprescriptionformulatingschemebasedonatwolayerclassifier |
_version_ |
1718388560445308928 |