Fine Tuning CNN Pre-trained Model Based on Thermal Imaging for Obesity Early Detection

Hendrik Leo; Fitri Arnia; Khairul Munadi

doi:10.17529/jre.v18i1.25100

Fine Tuning CNN Pre-trained Model Based on Thermal Imaging for Obesity Early Detection

Hendrik Leo, Fitri Arnia, Khairul Munadi

Abstract

Obesity is a complex disease that causes serious impact health, such as diabetes mellitus, cardiovascular disease, cancer, and stroke. An early obesity diagnosis/ detection method is required to prevent the increasing number of obese people. This study aims to: (i) fine-tune the pre-trained Convolutional Neural Network (CNN) models to build an early detection of obesity and (ii) evaluate the model performance in terms of classifying performance, computation speed, and learning performance. The thermal images acquisition procedure was conducted with 18 normal subjects and 15 obese subjects to build a thermal images dataset of obesity. Pre-trained CNN models: VGG19, MobileNet, ResNet152V, and DenseNet201 were modified and trained using the acquired dataset as the input. The training results show that the DenseNet201 model outperformed other models regarding classifying accuracy: 83.33 % and learning performances. At the same time, the MobileNet model outperformed other models in terms of computation speed with training elapsed time: 12 seconds/epoch. The proposed DenseNet201 model was suitable for implementation as an early screening system of obesity for health workers or physicians. Meanwhile, the proposed MobileNet model was suitable for mobile applications' early detection/diagnosis of obesity.

Keywords

Obesity; Deep Learning; Transfer Learning; Pre-trained CNN; Thermal Imaging

Full Text:

PDF

References

Y. C. Chooi, C. Ding, and F. Magkos, “The epidemiology of obesity,” Metabolism., vol. 92, pp. 6–10, 2019, doi: 10.1016/j.metabol.2018.09.005.

J. Berglund, “The future of fat: As obesity grows to epidemic proportions, researchers are trying to halt the trend,” IEEE Pulse, vol. 9, no. 5, pp. 8–11, 2018.

WHO, “World Health Statistics Monitoring Health For The SDGs,” 2021.

K. Jindal, N. Baliyan, and P. S. Rana, Obesity prediction using ensemble machine learning approaches, vol. 708. Springer Singapore, 2018.

T. M. Dugan, S. Mukhopadhyay, A. Carroll, and S. Downs, “Machine learning techniques for prediction of early childhood obesity,” Appl. Clin. Inform., vol. 6, no. 3, pp. 506–520, 2015, doi: 10.4338/ACI-2015-03-RA-0036.

S. A. Thamrin, D. S. Arsyad, H. Kuswanto, A. Lawi, and S. Nasir, “Predicting Obesity in Adults Using Machine Learning Techniques: An Analysis of Indonesian Basic Health Research 2018,” Front. Nutr., vol. 8, no. June, pp. 1–15, 2021, doi: 10.3389/fnut.2021.669155.

K. W. DeGregory et al., “A review of machine learning in obesity,” Obes. Rev., vol. 19, no. 5, pp. 668–685, 2018, doi: 10.1111/obr.12667.

X. Pang, C. B. Forrest, F. Le-Scherban, and A. J. Masino, “Understanding early childhood obesity via interpretation of machine learning model predictions,” Proc. - 18th IEEE Int. Conf. Mach. Learn. Appl. ICMLA 2019, pp. 1438–1443, 2019, doi: 10.1109/ICMLA.2019.00235.

M. E. Symonds and H. Budge, “How promising is thermal imaging in the quest to combat obesity?,” Imaging Med., vol. 4, no. 6, pp. 589–591, 2012.

S. Brasil, A. C. Renck, F. de Meneck, M. L. Brioschi, E. F. Costa, and M. J. Teixeira, “A systematic review on the role of infrared thermography in the Brown adipose tissue assessment,” Rev. Endocr. Metab. Disord., vol. 21, no. 1, pp. 37–44, 2020, doi: 10.1007/s11154-020-09539-8.

R. Rashmi and U. Snekhalatha, “Thermal imaging method in the evaluation of obesity in various body regions–A preliminary study,” IOP Conf. Ser. Mater. Sci. Eng., vol. 912, p. 062022, 2020.

H. Leo, K. Saddami, R. Roslidar, M. Oktiana, F. Arnia, and K. Munadi, “A Study of Parameters Required for a Thermogram Dataset in Obesity Detection : A Systematic Review,” 2021, no. Dl, doi: https://doi.org/10.1109/COSITE52651.2021.9649552.

R. Rashmi, S. Umapathy, and P. T. Krishnan, “Thermal imaging method to evaluate childhood obesity based on machine learning techniques,” Int. J. Imaging Syst. Technol., no. March, pp. 1–17, 2021.

U. Snekhalatha, K. Palani Thanaraj, and K. Sangamithrai, “Obesity Detection in Thermal Imaging Using Convolution Neural Network: A Comparison with Machine Learning Models,” in Proceedings of the International e-Conference on Intelligent Systems and Signal Processing, 2022, pp. 583–592.

X. Yin, W. Chen, X. Wu, and H. Yue, “Fine-tuning and visualization of convolutional neural networks,” Proc. 2017 12th IEEE Conf. Ind. Electron. Appl. ICIEA 2017, vol. 2018-Febru, pp. 1310–1315, 2018, doi: 10.1109/ICIEA.2017.8283041.

R. Roslidar, K. Saddami, F. Arnia, M. Syukri, and K. Munadi, “A study of fine-tuning CNN models based on thermal imaging for breast cancer classification,” Proc. Cybern. 2019 - 2019 IEEE Int. Conf. Cybern. Comput. Intell. Towar. a Smart Human-Centered Cyber World, pp. 77–81, 2019.

Y. Lecun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015, doi: 10.1038/nature14539.

A. C. Ian Goodfellow, Yoshua Bengio, Deep learning. MIT Press, 2016.

K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc., pp. 1–14, 2015.

A. G. Howard et al., “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” 2017, [Online]. Available: http://arxiv.org/abs/1704.04861.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2016-Decem, pp. 770–778, 2016, doi: 10.1109/CVPR.2016.90.

G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 2261–2269, 2017, doi: 10.1109/CVPR.2017.243.

A. Elhassouny and F. Smarandache, “Trends in deep convolutional neural Networks architectures: A review,” Proc. 2019 Int. Conf. Comput. Sci. Renew. Energies, ICCSRE 2019, no. 1, pp. 1–8, 2019, doi: 10.1109/ICCSRE.2019.8807741.

DOI: https://doi.org/10.17529/jre.v18i1.25100

Article Metrics

Abstract view : 0 times
PDF - 0 times

Refbacks

There are currently no refbacks.

View My Stats

Jurnal Rekayasa Elektrika (JRE) is published under license of Creative Commons Attribution-ShareAlike 4.0 International License.