Abstract
Maximal Oxygen Uptake (VO2max) is the most siginificant indicator for cardiorespiratory fitness.
In this study, Support Vector Machines (SVM) based prediction models have been developed to predict
the VO2max of 185 healty subjects to which a submaximal treadmill exercise test has been applied. To
form the VO2max regression equation, a dataset including 185 test subjects have been utilized. Using
10-fold cross validation on the dataset, standard error of estimates (SEE’s) and multiple correlation
coefficients (R’s) of the models have been calculated. For comparison purposes, VO2max prediction
models using Multiple Linear Regression (MLR) and Multilayer Perceptron (MLP) have been also
developed. In conclusion, it is observed that SVM-based VO2max prediction models yield lower SEE’s
than the ones obtained by using MLR-based and MLP-based predicton models.
References
- Dalleck L. C., Kravitz L., Robergs R. A. (2006): “Development of a Submaximal Test to Predict Elliptical Cross-Trainer VO2max”, National Strenght and Conditioning Association, Cilt 20, No. 2, s.278-283.
- Friedrichs F., Igel C. (2005): “Evolutionary Tuning of Multiple SVM Parameters”, Neurocomputing, Cilt 64, s.107–117.
- George J. D., Paul S. L., Hyde A., Bradshaw D. I., Vehrs P. R., Hager R. L. (2009): “Prediction of Maximum Oxygen Uptake Using Both Exercise and Non-Exercise Data”, Measurement in Physical Education and Exercise Science, Cilt 13, No. 1, s.1–12.
- Hsu C. W., Chang C. C., Lin C. J. (2003): “A Practical Guide to Support Vector Classification”, http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf.
- Kale G., Akay, M. F., Aktürk E., Tunçdemir A. E. (2013): “Yapay Sinir Ağları Kullanılarak Egzersiz ve Egzersize Dayalı Olmayan Verilerden VO2max tahmini”, 21. Sinyal İşleme ve İletişim Uygulamaları Kurultayı, SİU2013, 24-26 Nisan 2013, KKTC.
- Larsen G. E., George J. D., Alexander J. L., Fellingham G. W., Aldana S. G., Parcell A. C., (2002): Prediction of Maximum Oxygen Consumption from Walking, Jogging, or Running”, Research Quarterly for Exercise and Sport, Cilt 71, No. 1, s.66–72.
- McComb J. J. R., Roh D., Williams J. S. (2006): “Explanatory Variance in Maximal Oxygen Uptake”, Journal of Sports Science and Medicine, Cilt 5, No. 2, s.296–303.
- Nielson E. D. (2009): “Predicting VO2max in College-Aged Participants Using Cycle Ergometry and Nonexercise Measures”, Department of Exercise Sciences Brigham Young University, Master of Science, December.
- Vehrs P. R., George J. D., Fellingham G. W., Plowman S. A., Dustman-Allen K. (2007): “Submaximal Treadmill Exercise Test to Predict VO2max in Fit Adults”, Measurement in Physical Education and Exercise Science, Cilt 11, No. 2, s.61–72.
- William L., Wilkins (2000): “ACSM’s Guideline for Exercise Testing and Prescription (6th ed.).”, American College of Sports Medicine, Philadelphia
DESTEK VEKTÖR MAKINELERI KULLANILARAK SUBMAKSIMAL VERILERDEN MAKSIMUM OKSIJEN TÜKETIMININ TAHMIN EDILMESI
Abstract
Maksimum oksijen tüketimi (VO2max), kardiyo respiratuar uygunluğu belirleyen en önemli
bileşendir. Bu çalışmada, submaksimal koşu bandı egzersizi uygulanan sağlıklı yetişkinlerin
VO2max’ını tahmin etmek için Destek Vektör Makinesi (DVM) tabanlı modeller geliştirilmiştir.
VO2max regresyon denklemini oluşturabilmek için 185 denek içeren veri kümesi kullanılmıştır. 10 katlı
çapraz doğrulama kullanılarak, modellerin standart tahmin hatası (STH) ve çoklu korelasyon katsayısı
(KK) hesaplanmıştır. Karşılaştırma yapabilmek amacı ile Çoklu Doğrusal Regresyon (ÇDR) yöntemi
ve Çok Katmanlı Algılayıcı (ÇKA) kullanılarak VO2max tahmin modelleri de geliştirilmiştir. Sonuç
olarak, DVM tabanlı modellere ait STH değerlerinin ÇDR ve ÇKA tabanlı modellerin STH
değerlerinden daha düşük olduğu gözlemlenmiştir.
References
- Dalleck L. C., Kravitz L., Robergs R. A. (2006): “Development of a Submaximal Test to Predict Elliptical Cross-Trainer VO2max”, National Strenght and Conditioning Association, Cilt 20, No. 2, s.278-283.
- Friedrichs F., Igel C. (2005): “Evolutionary Tuning of Multiple SVM Parameters”, Neurocomputing, Cilt 64, s.107–117.
- George J. D., Paul S. L., Hyde A., Bradshaw D. I., Vehrs P. R., Hager R. L. (2009): “Prediction of Maximum Oxygen Uptake Using Both Exercise and Non-Exercise Data”, Measurement in Physical Education and Exercise Science, Cilt 13, No. 1, s.1–12.
- Hsu C. W., Chang C. C., Lin C. J. (2003): “A Practical Guide to Support Vector Classification”, http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf.
- Kale G., Akay, M. F., Aktürk E., Tunçdemir A. E. (2013): “Yapay Sinir Ağları Kullanılarak Egzersiz ve Egzersize Dayalı Olmayan Verilerden VO2max tahmini”, 21. Sinyal İşleme ve İletişim Uygulamaları Kurultayı, SİU2013, 24-26 Nisan 2013, KKTC.
- Larsen G. E., George J. D., Alexander J. L., Fellingham G. W., Aldana S. G., Parcell A. C., (2002): Prediction of Maximum Oxygen Consumption from Walking, Jogging, or Running”, Research Quarterly for Exercise and Sport, Cilt 71, No. 1, s.66–72.
- McComb J. J. R., Roh D., Williams J. S. (2006): “Explanatory Variance in Maximal Oxygen Uptake”, Journal of Sports Science and Medicine, Cilt 5, No. 2, s.296–303.
- Nielson E. D. (2009): “Predicting VO2max in College-Aged Participants Using Cycle Ergometry and Nonexercise Measures”, Department of Exercise Sciences Brigham Young University, Master of Science, December.
- Vehrs P. R., George J. D., Fellingham G. W., Plowman S. A., Dustman-Allen K. (2007): “Submaximal Treadmill Exercise Test to Predict VO2max in Fit Adults”, Measurement in Physical Education and Exercise Science, Cilt 11, No. 2, s.61–72.
- William L., Wilkins (2000): “ACSM’s Guideline for Exercise Testing and Prescription (6th ed.).”, American College of Sports Medicine, Philadelphia
Details
| Other ID | JA97KR89AU |
|---|---|
| Journal Section | Research Article |
| Authors | |
| Publication Date | September 1, 2014 |
| Published in Issue | Year 2014 Volume: 16 Issue: 48 |
Cite
Dokuz Eylül Üniversitesi, Mühendislik Fakültesi Dekanlığı Tınaztepe Yerleşkesi, Adatepe Mah. Doğuş Cad. No: 207-I / 35390 Buca-İZMİR.