Open Access Open Access  Restricted Access Subscription Access

Diabetes Detection through Web Application and Personal Home Training System

Srinivas Mishra, Aruna Tripathy

Abstract


Physical activity is frequently advised as the initial preventive and control intervention by healthcare professionals. Food, medication, and exercise are all vital. Over 366 million people will have diabetes worldwide, according to the International Diabetes Prevention and Control Federation. The only country with more than 50 million type II diabetes is India, and as long as these alarming figures continue to rise, they will put pressure on economies all around the world [1]. As a result, researchers and medical professionals from all over the world are collaborating to develop and offer recommendations for preventing and treating this devastating illness. In Japan, Sato conducted a thorough investigation into the benefits of prescribing exercise to people with diabetes. The research recommends that people avoid spending extended periods of time sitting and moving about every 30 minutes [2]. According to Kirwan et al., regular exercise is essential for the treatment and prevention of type 2 diabetes. They especially examined the metabolic effects of diabetes medication and diabetic patients' tissues. The findings suggests that people should stand up and move around every 30 minutes as opposed to sitting down for extended periods of time [2]. According to Kirwan et al., regular exercise is essential for the treatment and prevention of type 2 diabetes. They carefully looked at the effect of metabolism on diabetic individuals' tissues and we present Blaze Pose, a convolutional neural network architecture that is lightweight for predicting human pose on mobile devices and built for real-time inference. On a Pixel 2 phone, the network generates 32 body key points for a single person during inference at a rate of more than 30 frames per second. This makes it particularly suitable for real-time use cases like fitness tracking and sign language recognition. Our main contributions are a novel body posture monitoring technique and a compact body pose estimation neural network that uses heat maps and regression to obtain key point coordinates.


Full Text:

PDF PDF

References


Bazarevsky, V., Grishchenko, I., Raveendran, K., Zhu, T., Zhang, F., & Grundmann, M. (2020). Blazepose: On-device real-time body pose tracking. arXiv preprint arXiv:2006.10204.

Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., ... & Zitnick, C. L. (2014, September). Microsoft coco: Common objects in context. In European conference on computer vision (pp. 740-755). Springer, Cham.

Kreiss, S., Bertoni, L., & Alahi, A. (2019). Pifpaf: Composite fields for human pose estimation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 11977-11986).

Newell, A., Yang, K., & Deng, J. (2016, October). Stacked hourglass networks for human pose estimation. In European conference on computer vision (pp. 483-499). Springer, Cham.

Butt, U. M., Letchmunan, S., Ali, M., Hassan, F. H., Baqir, A., & Sherazi, H. H. R. (2021). Machine learning based diabetes classification and prediction for healthcare applications. Journal of healthcare engineering, 2021.

Kartynnik, Y., Ablavatski, A., Grishchenko, I., & Grundmann, M. (2019). Real-time facial surface geometry from monocular video on mobile GPUs. arXiv preprint arXiv:1907.06724.

Bazarevsky, V., Kartynnik, Y., Vakunov, A., Raveendran, K., & Grundmann, M. (2019). Blazeface: Sub-millisecond neural face detection on mobile gpus. arXiv preprint arXiv:1907.05047.

Cao, Z., Simon, T., Wei, S. E., & Sheikh, Y. (2017). Realtime multi-person 2d pose estimation using part affinity fields. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7291-7299).

Moreno-Ibarra, M. A., Villuendas-Rey, Y., Lytras, M. D., Yáñez-Márquez, C., & Salgado-Ramírez, J. C. (2021). Classification of diseases using machine learning algorithms: A comparative study. Mathematics, 9(15), 1817.

Fahmy, H. I., Develekos, G., & Douligeris, C. (1997). Application of neural networks and machine learning in network design. IEEE Journal on Selected Areas in Communications, 15(2), 226-237.


Refbacks

  • There are currently no refbacks.