Öz
Bazal Metabolizma Hızı (BMH) günlük harcanan ve alınması gereken enerji hakkında bilinmesi gereken en önemli unsurlardan biridir. Literatürde genellikle kalorimetreler ve birtakım denklemler tarafından tespit edilmektedir. Bu çalışmada BMH tahmini için elektrokardiyografi (ECG) sinyalleri ile yapay zekâ tabanlı bir model oluşturulmuştur. Öncelikle bireylerden toplanan ECG sinyalleri gürültülerden temizlenip filtrelenmiştir. Daha sonra özellik çıkartılıp özellik seçme algoritmaları yardımıyla azaltılmıştır. Elde kalan özelliklerle yapay zekâ algoritmaları sayesinde BMH tahmininde bulunulmuştur. Erkekler için R = 0.91, kadınlar için R = 0.99 değerlerine sahip modeller oluşturulmuştur. Performans değerlendirme kriterleri de göz önüne alınarak en iyi model kadınlar için de erkekler için de Linear Regression modeli seçilmiştir. Tüm bu sonuçlara bakıldığında günlük hayatta BMH tahmini için önerilen modelin kullanılabileceği belirlenmiştir.
Anahtar Kelimeler
Yapay Zekâ Bazal Metabolizma Hızı Elektrokardiyografi Sinyali
Destekleyen Kurum
Sakarya Üniversitesi
Proje Numarası
2019-5-19-244
Teşekkür
Bu çalışma Sakarya Üniversitesi Bilimsel Araştırma Projeleri Komisyonu Tarafından Desteklenmiştir. Proje Numarası: 2019-5-19-244.
Kaynakça
- Akay, Ebru Çağlayan. 2018. “Ekonometride Yeni Bir Ufuk: Büyük Veri ve Makine Öğrenmesi.” Social Sciences Research Journal 7(2): 41–53.
- Arslan, Perihan. 1984. “BAZAL METABOLİZMA HIZININ SAPTANMASINDA KULLANILAN YÖNTEMLERİN KIYASLANMASI VE BAZAL METABOLİZMA ENERJİSİNİN VÜCUDUN YAĞSIZ DOKU KÜTLESİ İLE İLİŞKİSİ ÜZERİNDE BİR ARAŞTIRMA.” Beslenme ve Diyet Dergisi.
- Ferrannini, Eleuterio. 1988. “The Theoretical Bases of Indirect Calorimetry: A Review.” Metabolism 37(3): 287–301.
- Flancbaum, Louis et al. 1999. “Comparison of Indirect Calorimetry, the Fick Method, and Prediction Equations in Estimating the Energy Requirements of Critically Ill Patients.” The American Journal of Clinical Nutrition 69(3): 461–66. https://academic.oup.com/ajcn/article/69/3/461/4694179 (January 30, 2021).
- Forman, George. 2003. 3 Journal of Machine Learning Research An Extensive Empirical Study of Feature Selection Metrics for Text Classification.
- LIU, HSIU YING, YI FA LU, and WEI JAO CHEN. 1995. “Predictive Equations for Basal Metabolic Rate in Chinese Adults. A Cross-Validation Study.” Journal of the American Dietetic Association 95(12): 1403–8.
- Müller, B., S. Merk, U. Bürgi, and P. Diem. 2001. “Berechnung Des Grundumsatzes Bei Schwerer Und Morbider Adipositas.” Praxis 90(45): 1955–63. https://europepmc.org/article/med/11817239 (January 30, 2021).
- Nur Göz, Ayşe et al. 2017. EKG İŞARETLERİ YARDIMIYLA BİR OTOMATİK ARİTMİ DEDEKTÖRÜ. Fatih Sultan Mehmet Vakıf Üniversitesi Biyomedikal Elektronik Tasarım, Uygulama ve Araştırma Merkezi. http://acikerisim.fsm.edu.tr:8080/xmlui/handle/11352/2491 (January 30, 2021).
- Speakman, John R., Elzbieta Król, and Maria S. Johnson. 2004. “The Functional Significance of Individual Variation in Basal Metabolic Rate.” In Physiological and Biochemical Zoology, The University of Chicago Press , 900–915. https://www.journals.uchicago.edu/doi/abs/10.1086/427059 (January 30, 2021).
- Tverskaya, Rozalia, Russell Rising, Debra Brown, and Fima Lifshitz. 1998. “Comparison of Several Equations and Derivation of a New Equation for Calculating Basal Metabolic Rate in Obese Children.” Journal of the American College of Nutrition 17(4): 333–36. https://pubmed.ncbi.nlm.nih.gov/9710841/ (January 30, 2021).
- Wang, Wenjian, and Zongben Xu. 2004. “A Heuristic Training for Support Vector Regression.” Neurocomputing 61(1–4): 259–75.
Gender-Based Artificial Intelligence Based Detection of Basal Metabolic Rate by Electrocardiography Signal
Öz
Basal Metabolic Rate (BMR) is one of the most important factors that should be known about the energy consumed and taken daily. It is usually determined by calorimeters and some equations in the literature. In this study, an artificial intelligence-based model was created with electrocardiography (ECG) signals for BMR prediction. First of all, ECG signals collected from individuals are cleaned from noise and filtered. Later, the feature was removed and reduced with the help of feature selection algorithms. BMR predictions have been made with the remaining features thanks to artificial intelligence algorithms. Models with R = 0.91 for men and R = 0.99 for women were created. Considering the performance evaluation criteria, the Linear Regression model was chosen as the best model for both women and men. Considering all these results, it was determined that the proposed model could be used for BMR estimation in daily life.
Anahtar Kelimeler
Artificial Intelligence Basal Metabolic Rate Electrocardiography Signal
Proje Numarası
2019-5-19-244
Kaynakça
- Akay, Ebru Çağlayan. 2018. “Ekonometride Yeni Bir Ufuk: Büyük Veri ve Makine Öğrenmesi.” Social Sciences Research Journal 7(2): 41–53.
- Arslan, Perihan. 1984. “BAZAL METABOLİZMA HIZININ SAPTANMASINDA KULLANILAN YÖNTEMLERİN KIYASLANMASI VE BAZAL METABOLİZMA ENERJİSİNİN VÜCUDUN YAĞSIZ DOKU KÜTLESİ İLE İLİŞKİSİ ÜZERİNDE BİR ARAŞTIRMA.” Beslenme ve Diyet Dergisi.
- Ferrannini, Eleuterio. 1988. “The Theoretical Bases of Indirect Calorimetry: A Review.” Metabolism 37(3): 287–301.
- Flancbaum, Louis et al. 1999. “Comparison of Indirect Calorimetry, the Fick Method, and Prediction Equations in Estimating the Energy Requirements of Critically Ill Patients.” The American Journal of Clinical Nutrition 69(3): 461–66. https://academic.oup.com/ajcn/article/69/3/461/4694179 (January 30, 2021).
- Forman, George. 2003. 3 Journal of Machine Learning Research An Extensive Empirical Study of Feature Selection Metrics for Text Classification.
- LIU, HSIU YING, YI FA LU, and WEI JAO CHEN. 1995. “Predictive Equations for Basal Metabolic Rate in Chinese Adults. A Cross-Validation Study.” Journal of the American Dietetic Association 95(12): 1403–8.
- Müller, B., S. Merk, U. Bürgi, and P. Diem. 2001. “Berechnung Des Grundumsatzes Bei Schwerer Und Morbider Adipositas.” Praxis 90(45): 1955–63. https://europepmc.org/article/med/11817239 (January 30, 2021).
- Nur Göz, Ayşe et al. 2017. EKG İŞARETLERİ YARDIMIYLA BİR OTOMATİK ARİTMİ DEDEKTÖRÜ. Fatih Sultan Mehmet Vakıf Üniversitesi Biyomedikal Elektronik Tasarım, Uygulama ve Araştırma Merkezi. http://acikerisim.fsm.edu.tr:8080/xmlui/handle/11352/2491 (January 30, 2021).
- Speakman, John R., Elzbieta Król, and Maria S. Johnson. 2004. “The Functional Significance of Individual Variation in Basal Metabolic Rate.” In Physiological and Biochemical Zoology, The University of Chicago Press , 900–915. https://www.journals.uchicago.edu/doi/abs/10.1086/427059 (January 30, 2021).
- Tverskaya, Rozalia, Russell Rising, Debra Brown, and Fima Lifshitz. 1998. “Comparison of Several Equations and Derivation of a New Equation for Calculating Basal Metabolic Rate in Obese Children.” Journal of the American College of Nutrition 17(4): 333–36. https://pubmed.ncbi.nlm.nih.gov/9710841/ (January 30, 2021).
- Wang, Wenjian, and Zongben Xu. 2004. “A Heuristic Training for Support Vector Regression.” Neurocomputing 61(1–4): 259–75.
Ayrıntılar
| Birincil Dil | Türkçe |
|---|---|
| Konular | Yapay Zeka |
| Bölüm | Araştırma Makalesi |
| Yazarlar | |
| Proje Numarası | 2019-5-19-244 |
| Yayımlanma Tarihi | 23 Eylül 2021 |
| Gönderilme Tarihi | 3 Nisan 2021 |
| Yayımlandığı Sayı | Yıl 2021 Cilt: 4 Sayı: 2 |
Kaynak Göster
Zeki Sistemler Teori ve Uygulamaları Dergisi