WGAN ile bebek emme vakum basıncının simülasyonu

Year 2024, Volume: 3 Issue: 2, 78 - 86

Fatih Furkan Arslan , Önder Dinçel

https://doi.org/10.70700/bjea.1581791

Abstract

Bu çalışmada, bebeklerin emme vakum basınçlarının Wasserstein Generative Adversarial Network (WGAN) modeli ile çoğaltılarak bebek emme vakumlarının benzetiminin yapılması amaçlanmıştır. Bebeklerin beslenme davranışlarını fizyolojisini anlamak için emme fizyolojisini kavramak oldukça önemlidir. Beslenme fizyolojisinin en önemli unsurlarından bir tanesi bebek emme vakumudur. Bu bağlamda, WGAN modelinin ile üretilen bebek emme vakum basıncı başarıyla taklit edilmiştir. Çalışmada kullanılan WGAN modelinin en doğru benzetimi yapabilmesi için veri ön işleme yapılmış ve hiperparametre optimizasyonu yapılmıştır.
Sonuç olarak, gerçek verilerle üretilen veriler arasındaki düşük RMSE ve yüksek R2 değeri modelin başarılı çalıştığını göstermektedir. Bu yöntem ile bebeklerin emme davranışlarının daha iyi anlaşılması ve bebek beslenmesi alanındaki sorunların çözülmesine katkı sağlaması açısından umut vadetmektedir. Gelecekte, modelin daha geniş verilerle desteklenmesi ve bebek emme fizyolojisinin diğer unsurları olan yutma ve solunum gibi unsurlarında ele alınmasıyla bebek emme benzetim daha başarılı bir şekilde yapılabilecektir. Bu tür bir benzetim ile bebek beslenmesi ve anne sütü sağımı alanlarında yeni uygulamalara zemin hazırlayacaktır.

Keywords

Bebek Emme Vakumu, WGAN, Benzetim, Emme Fizyolojisi

Simulation of infant suction vacuum pressure using WGAN

Abstract

In this study, it is aimed to simulate infant suction vacuums by replicating infant suction vacuum pressures with the Wasserstein Generative Adversarial Network (WGAN) model. To understand the physiology of infants' feeding behavior, it is very important to understand the physiology of sucking. One of the most important elements of feeding physiology is the infant suction vacuum. In this context, the infant suction vacuum pressure produced by the WGAN model was successfully simulated. Data preprocessing and hyperparameter optimization were performed to ensure the most accurate simulation of the WGAN model used in the study.
As a result, the low RMSE and high R2 value between the real data and the generated data show that the model works successfully. This method is promising in terms of better understanding the sucking behavior of infants and contributing to solving problems in the field of infant feeding. In the future, infant sucking simulation will be more successful if the model is supported with larger data and other elements of infant sucking physiology such as swallowing and respiration are considered. This kind of simulation will pave the way for new applications in the fields of infant feeding and breastfeeding.

Keywords

Infant Sucking Vacuum, WGAN, Simulation, Sucking Physiology

References

• M. Martell, G. Martínez, M. González, and J. L. D. Rosselló, “Suction patterns in preterm infants,” J Perinat Med, vol. 21, no. 5, pp. 363–369, 1993, doi: https://doi.org/10.1515/jpme.1993.21.5.363.
• A. M. Cannon, V. S. Sakalidis, C. T. Lai, S. L. Perrella, and D. T. Geddes, “Vacuum characteristics of the sucking cycle and relationships with milk removal from the breast in term infants,” Early Hum Dev, vol. 96, pp. 1–6, 2016, doi: https://doi.org/10.1016/j.earlhumdev.2016.02.003.
• C. Prieto, H. Cardenas, A. Salvatierra, C. Boza, C. Montes, and H. Croxatto, “Sucking pressure and its relationship to milk transfer during breastfeeding in humans,” Bioscientifica Ltd, vol. 108, no. 1, pp. 69–74, Nov. 1996, doi: https://doi.org/10.1530/jrf.0.1080069.
• D. T. Geddes, J. C. Kent, L. R. Mitoulas, and P. E. Hartmann, “Tongue movement and intra-oral vacuum in breastfeeding infants,” Early Hum Dev, vol. 84, no. 7, pp. 471–477, 2008, doi: https://doi.org/10.1016/j.earlhumdev.2007.12.008.
• D. T. Geddes and V. S. Sakalidis, “Breastfeeding: how do they do it? Infant sucking, swallowing and breathing,” Infant, vol. 11, no. 5, pp. 146–150, 2015.
• J. S. McGowan, R. R. Marsh, S. M. Fowler, S. E. Levy, and V. A. Stallings, “DEVELOPMENTAL PATTERNS OF NORMAL NUTRITIVE SUCKING IN INFANTS,” Dev Med Child Neurol, vol. 33, no. 10, pp. 891–897, 1991, doi: https://doi.org/10.1111/j.1469-8749.1991.tb14798.x.
• L. Chen, R. F. Lucas, and B. Feng, “A Novel System to Measure Infants’ Nutritive Sucking During Breastfeeding: the Breastfeeding Diagnostic Device (BDD),” IEEE J Transl Eng Health Med, vol. 6, pp. 1–8, 2018, doi:10.1109/JTEHM.2018.2838139.
• D. T. Geddes, K. Chooi, K. Nancarrow, A. R. Hepworth, H. Gardner, and K. Simmer, “Characterisation of sucking dynamics of breastfeeding preterm infants: a cross sectional study,” BMC Pregnancy Childbirth, vol. 17, no. 1, Nov. 2017, doi: https://doi.org/10.1186/s12884-017-1574-3.
• S. Akbarzadeh et al., “Evaluation of Apgar Scores and Non-Nutritive Sucking Skills in Infants Using a Novel Sensitized Non-Nutritive Sucking System,” 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 4282–4285, 2020, doi: 10.1109/EMBC44109.2020.9176146.
• A. J. Sameroff, “An apparatus for recording sucking and controlling feeding in the first days of life,” Psychon Sci, vol. 2, no. 1, pp. 355–356, 1965.
• P. Truong, E. Walsh, V. P. Scott, T. Coleman, G. Tilvawala, and J. Friend, “Non-Nutritive Suckling System for Real-Time Characterization of Intraoral Vacuum Profile in Full Term Neonates,” IEEE J Transl Eng Health Med, vol. 11, pp. 107–115, 2023, doi: 10.1109/JTEHM.2022.3231788.
• V. S. Sakalidis et al., “Ultrasound Imaging of Infant Sucking Dynamics during the Establishment of Lactation,” Journal of Human Lactation, vol. 29, no. 2, pp. 205–213, 2013, doi: 10.1177/0890334412452933.
• L. Jiang and F. Hassanipour, “Bio-Inspired Breastfeeding Simulator (BIBS): A Tool for Studying the Infant Feeding Mechanism,” IEEE Trans Biomed Eng, vol. 67, no. 11, pp. 3242–3252, 2020, doi: 10.1109/TBME.2020.2980545.
• I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. C. Courville, “Improved Training of Wasserstein GANs,” in Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, Eds., Curran Associates, Inc., 2017. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2017/file/892c3b1c6dccd52936e27cbd0ff683d6-Paper.pdf
• M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein Generative Adversarial Networks,” in Proceedings of the 34th International Conference on Machine Learning, D. Precup and Y. W. Teh, Eds., in Proceedings of Machine Learning Research, vol. 70. PMLR, Nov. 2017, pp. 214–223. [Online]. Available: https://proceedings.mlr.press/v70/arjovsky17a.html
• S. Brahmbhatt, Practical OpenCV, no. 2. Apress, 2013.
• I. Goodfellow et al., “Generative adversarial networks,” Commun ACM, vol. 63, no. 11, pp. 139–144, 2020. J. Xu, Z. Li, B. Du, M. Zhang, and J. Liu, “Reluplex made more practical: Leaky ReLU,” in 2020 IEEE Symposium on Computers and Communications (ISCC), 2020, pp. 1–7. doi: 10.1109/ISCC50000.2020.9219587.
• M. M. Lau and K. Hann Lim, “Review of Adaptive Activation Function in Deep Neural Network,” in 2018 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), 2018, pp. 686–690. doi: 10.1109/IECBES.2018.8626714.
• P. Baldi and P. J. Sadowski, “Understanding Dropout,” in Advances in Neural Information Processing Systems, C. J. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K. Q. Weinberger, Eds., Curran Associates, Inc., 2013. [Online].Available:https://proceedings.neurips.cc/paper_files/paper/2013/file/71f6278d140af599e06ad9bf1ba03cb0-Paper.pdf
• A. D. Rasamoelina, F. Adjailia, and P. Sinčák, “A Review of Activation Function for Artificial Neural Network,” in 2020 IEEE 18th World Symposium on Applied Machine Intelligence and Informatics (SAMI), 2020, pp. 281–286. doi: 10.1109/SAMI48414.2020.9108717.