Türkiye'de Cinsiyete göre Obezite Öncesi Yüzdelik Dağılımının Yapay Sinir Ağı ve Zaman Serileri ile Tahmini

Year 2024, Volume: 14 Issue: 3, 1340 - 1359, 15.09.2024

Halil Çolak , Emre Çolak

https://doi.org/10.31466/kfbd.1456340

Abstract

Obezite, artan aşırı kilolu birey oranları nedeniyle Türkiye'de önemli bir halk sağlığı sorunu teşkil etmektedir. Ancak bu sorun, sağlıklı beslenme alışkanlıklarının teşvik edilmesi, düzenli fiziksel aktivitenin desteklenmesi ve toplumsal farkındalığın artırılması gibi önlemlerle etkili bir şekilde ele alınabilir. Bu hedefe ulaşmak kolektif bir çaba ve ortak bir vizyon gerektirecektir. Obezite için alınacak tedbirlerin etkin olabilmesi açısından, obezite öncesi dönemin bilinmesi büyük önem taşımaktadır. Makine öğrenmesinin avantajlarından bir tanesi de geleceği tahmin etmesidir. Yapılan bu çalışmada Türkiye’de cinsiyete göre obezite öncesi yüzdelik dağılım tahminleri yapılmış ve 2023 ile 2030 yılları arasındaki veriler tahmin edilmiştir. Bunun için Levenberg-Marquardt (LM) algoritması, Bayesian Regularization (BR) algoritması, ARIMA model ve Holt-Winters (HW) yöntemi kullanılmıştır. Çıkan sonuçlara göre Türkiye’de cinsiye göre obezite öncesi yüzdelik dağılımın 2030 yılında kadınlarda LM’e göre %32,79 değerinde erkeklerde ise ARIMA modelin %42,73 değerinde olacağı tahminlendi.

Keywords

Obezite öncesi, Levenberg-Marquardt, Bayesian Regularization, ARIMA, Holt-Winters

Estimation of Prevalence Distribution of Pre-obesity by Gender in Türkiye Using Artificial Neural Networks and Time Series Analysis

Abstract

Obesity is an important public health problem in Türkiye due to the increasing proportion of overweight individuals. However, this problem can be effectively addressed through measures such as promoting healthy eating habits, supporting regular physical activity, and raising public awareness. Achieving this goal will require a collective effort and a common vision. For the measures to be taken for obesity to be effective, it is of great importance to know the pre-obesity period. One of the advantages of machine learning is that it predicts the future. In this study, the pre-obesity percentage distribution of obesity in Türkiye by gender was estimated and the data between 2023 and 2030 were estimated. For this purpose, the Levenberg-Marquardt (LM) algorithm, Bayesian Regularisation (BR) algorithm, ARIMA model, and Holt-Winters (HW) method were used. According to the results, the pre-obesity percentage distribution by gender in Türkiye in 2030 was estimated to be 32.79% for women according to LM, and 42.73% for men according to the ARIMA model.

Keywords

Pre-obesity, Levenberg-Marquardt, Bayesian Regularization, ARIMA, Holt-Winters

References

• al-Swaidani, A. M., & al-Hajeh, T. (2023). Estimation of GPA at Undergraduate Level using MLR and ANN at Arab International University During the Syrian Crisis: A Case Study. Open Education Studies, 5(1), 20220197.
• Baer, D. J., Dalton, M., Blundell, J., Finlayson, G., & Hu, F. B. (2023). Nuts, energy balance and body weight. Nutrients, 15(5), 1162.
• Benli, M., Acar, Y., & Bas, S. (2024). Testing obesity Kuznets curve for Türkiye. Obesity Medicine, 100537.
• Burden, F., & Winkler, D. (2009). Bayesian regularization of neural networks. Artificial neural networks: methods and applications, 23-42.
• Busebee, B., Ghusn, W., Cifuentes, L., & Acosta, A. (2023). Obesity: A review of pathophysiology and classification. Paper presented at the Mayo Clinic Proceedings.
• Celik, Y., Guney, S., & Dengiz, B. (2021). Obesity level estimation based on machine learning methods and artificial neural networks. Paper presented at the 2021 44th International Conference on Telecommunications and Signal Processing (TSP).
• Conejo, A. J., Plazas, M. A., Espinola, R., & Molina, A. B. (2005). Day-ahead electricity price forecasting using the wavelet transform and ARIMA models. IEEE transactions on power systems, 20(2), 1035-1042.
• Çolak, H., Kale, R., & Cihan, H. (2003). Yoğunlaştırılmış Yürüyüş ve Jogging Programının Yüksek Dansiteli Lipoproteinler (HDL) ve Düşük Dansiteli Lİipoproteinler (LDL) Üzerine Olan Etkisi. Spormetre Beden Eğitimi ve Spor Bilimleri Dergisi, 1(1), 69-76.
• Çolak, H., & Şenol, H. Türkiye’nin Lisanslı Sporcu Sayısının Yapay Sinir Ağları ile 2030 Yılına Kadar Tahmini: Spor Bilimleri Alanında Akademik Değerlendirmeler-7 (2023).
• da Costa, N. L., de Lima, M. D., & Barbosa, R. (2021). Evaluation of feature selection methods based on artificial neural network weights. Expert Systems with Applications, 168, 114312.
• Danacı, Ç., Derya, A., & Tuncer, S. A. (2023). Komşuluk Bileşen Analizi Tabanlı Makine Öğrenimi Yöntemleri ile Obezite Seviyelerinin Tahmini. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 35(2), 433-442.
• Eisbach, S., Mai, O., & Hertel, G. (2024). Combining theoretical modelling and machine learning approaches: The case of teamwork effects on individual effort expenditure. New Ideas in Psychology, 73, 101077.
• Elagizi, A., Kachur, S., Carbone, S., Lavie, C. J., & Blair, S. N. (2020). A review of obesity, physical activity, and cardiovascular disease. Current obesity reports, 9, 571-581.
• Henriques, I., & Sadorsky, P. (2023). Forecasting rare earth stock prices with machine learning. Resources Policy, 86, 104248.
• Jani, D., Mishra, M., & Sahoo, P. K. (2017). Application of artificial neural network for predicting performance of solid desiccant cooling systems–A review. Renewable and Sustainable Energy Reviews, 80, 352-366.
• Janssen, I., Katzmarzyk, P. T., Srinivasan, S. R., Chen, W., Malina, R. M., Bouchard, C., & Berenson, G. S. (2005). Combined influence of body mass index and waist circumference on coronary artery disease risk factors among children and adolescents. Pediatrics, 115(6), 1623-1630.
• Jiang, L.-y., Tian, J., Yang, Y.-n., Jia, S.-h., & Shu, Q. (2024). Acupuncture for obesity and related diseases: insight for regulating neural circuit. Journal of Integrative Medicine.
• Krejić, N., Malaspina, G., & Swaenen, L. (2023). A split Levenberg-Marquardt method for large-scale sparse problems. Computational Optimization and Applications, 85(1), 147-179.
• Li, S., & Li, R. (2017). Comparison of forecasting energy consumption in Shandong, China Using the ARIMA model, GM model, and ARIMA-GM model. Sustainability, 9(7), 1181.
• Marcos, F. L., & Plangklang, B. (2024). A high accurate user-friendly energy audit platform of a university building using ANN Bayesian regularization and Levenberg-Marquardt algorithm. Energy Reports, 11, 2220-2235.
• Martínez, J. (2024). Levenberg-marquardt revisited and parameter tuning of river regression models. Computational and Applied Mathematics, 43(1), 14.
• Ozcan, İ., Tasar, B., Tatar, A. B., & Yakut, O. (2019). Destek vektör makinasi algoritması ile kalp hastalıklarının tahmini. Computer Science, 4(2), 74-79.
• Pauchet-Traversat, A.-F., Berrebi, S., Brugère, S., Cancel, A., Communal, D., Constantin, A., . . . Gauthier, C. (2023). Surpoids et obésité de l’adulte: 14 messages clés pour améliorer les pratiques: Overweight and obesity in adults: 14 key messages to improve practices. Nutrition Clinique et Métabolisme, 37(2), 2S58-52S61.
• Pekkurnaz, D. (2023). Causal effect of obesity on the probability of employment in women in Turkey. Economics & Human Biology, 51, 101301.
• Pleños, M. (2022). Time series forecasting using holt-winters exponential smoothing: Application to abaca fiber data. Zeszyty Naukowe SGGW w Warszawie-Problemy Rolnictwa Światowego, 22(2), 17-29.
• Pomponi, J., Scardapane, S., & Uncini, A. (2021). Bayesian neural networks with maximum mean discrepancy regularization. Neurocomputing, 453, 428-437.
• Rashidi, M. H., Keshavarz, S., Pazari, P., Safahieh, N., & Samimi, A. (2022). Modeling the accuracy of traffic crash prediction models. IATSS research, 46(3), 345-352.
• Ross, R., & Bradshaw, A. J. (2009). The future of obesity reduction: beyond weight loss. Nature Reviews Endocrinology, 5(6), 319-325.
• Rumbe, G., Hamasha, M., & Al Mashaqbeh, S. (2024). A comparison of Holts-Winter and Artificial Neural Network approach in forecasting: A case study for tent manufacturing industry. Results in Engineering, 21, 101899.
• Salih, S. O., Bezenchek, A., Moramarco, S., De Iuliis, M., Stanev, D., Fanti, I., . . . Gialloreti, L. E. (2022). Forecasting causes of death in Northern Iraq using neural network. Journal of Statistical Theory and Applications, 21(2), 58-77.
• Sarwar, S., Aziz, G., & Tiwari, A. K. (2023). Implication of machine learning techniques to forecast the electricity price and carbon emission: Evidence from a hot region. Geoscience Frontiers, 101647.
• Sözmen, K., Unal, B., Capewell, S., Critchley, J., & O’Flaherty, M. (2015). Estimating diabetes prevalence in Turkey in 2025 with and without possible interventions to reduce obesity and smoking prevalence, using a modelling approach. International journal of public health, 60, 13-21.
• Şenol, H. (2021). Methane yield prediction of ultrasonic pretreated sewage sludge by means of an artificial neural network. Energy, 215, 119173.
• Şenol, H., Çakır, İ. T., Bianco, F., & Görgün, E. (2024). Improved methane production from ultrasonically-pretreated secondary sedimentation tank sludge and new model proposal: Time series (ARIMA). Bioresource technology, 391, 129866.
• Şenol, H., Dereli, M. A., & Özbilgin, F. (2021). Investigation of the distribution of bovine manure-based biomethane potential using an artificial neural network in Turkey to 2030. Renewable and Sustainable Energy Reviews, 149, 111338.
• Tarmanini, C., Sarma, N., Gezegin, C., & Ozgonenel, O. (2023). Short term load forecasting based on ARIMA and ANN approaches. Energy Reports, 9, 550-557.
• Türkiye İstatistik Kurumu (TÜİK) (2024). Retrieved from www.tuik.gov.tr
• Wang, W., He, N., Chen, M., & Jia, P. (2024). Freight Rate Index Forecasting with Prophet Model based on Multi-dimensional Significant Events. Expert Systems with Applications, 123451.
• Wei, C., Liu, L., Liu, R., Dai, W., Cui, W., & Li, D. (2022). Association between the phytochemical index and overweight/obesity: a meta-analysis. Nutrients, 14(7), 1429.
• World Health Organization Obesity and Overweight. (2011). Retrieved from https://www.who.int/
• Zhang, G., Patuwo, B. E., & Hu, M. Y. (1998). Forecasting with artificial neural networks:: The state of the art. International journal of forecasting, 14(1), 35-62.