Abstract
Diabetes is a chronic disease that seriously endangers human health, which should be early detection, early diagnosis and early treatment by establishing prediction model. With the help of disease auxiliary diagnosis based on machine learning, the process of early diagnosis could be more reliable. Then, the patients have more chances of early treatment. Deep learning technology can take advantage of its own powerful feature learning ability to the application of disease auxiliary diagnosis, and has gained good results. This paper proposes a diabetes prediction model based on Deep Belief Network (DBN). The model is established by using Pima Indians Diabetes data set, combined with cross-validation, setting DBN structure and adjusting DBN network parameters. The experimental results show that the accuracy of the model is as high as 77.60% and the performance is good.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
IDF Diabetes Atlas Eighth Edition poster Homepage. http://diabetesatlas.org/resources/2017-atlas.html. Accessed 24 Sept 2018
Liu, X., Jia, H., Li, A., et al.: Common methods and standards for screening and diagnosing diabetes mellitus. Med. Recapitul. 11(12), 1104–1106 (2005)
Pérez-GandÃa, C., Facchinetti, A., Sparacino, G., et al.: Artificial neural network algorithm for online glucose prediction from continuous glucose monitoring. Diabetes Technol. Therap. 12(1), 81–88 (2010)
Gao, W., Wang, S., Wang, Z., et al.: Study on the application of artificial neural network in analysing the risk factors of diabetes mellitus. Chin. J. Epidemiol. 25(8), 715–718 (2004)
Zhu, M., Wu, Y.: Research on image processing based on deep network. Electron. Technol. Softw. Eng. (5), 101–102 (2014)
Li, H., Li, X., Ramanathan, M., et al.: Identifying informative risk factors and predicting bone disease progression via deep belief networks. Methods 69(3), 257–265 (2014)
Chen, D., Zhou, D., Le, J.: Thyroid nodule benign and malignant prediction based on deep learning. Softw. Algorithms 36(12), 13–15 (2017)
Lim, K., Lee, B.M., Kang, U., et al.: An optimized DBN-based coronary heart disease risk prediction. Int. J. Comput. Commun. Control 13(4), 492–502 (2018)
Hinton, G.E., Osindero, S., The, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)
Wang, Z., Li, Y., Feng, X., et al.: Personalized information recommendation based on deep belief network. Computer Engineering 42(10), 201–206 (2016)
Wang, F., Li, Q.: Research on face recognition algorithm based on improved deep belief networks. J. Lanzhou Jiaotong Univ. 35(1), 42–48 (2016)
Yang, X.: Study of early warning for cerebrovascular risk based on deep beliefs networks. Beijing Jiaotong University (2016)
Sun, Z., Xue, L., Xu, Y., et al.: Overview of deep learning. Appl. Res. Comput. 29(8), 2806–2810 (2012)
Yang, X.H., Zhong, N.Y.: Forecasting of hospital outpatient based on deep belief network. Comput. Sci. 43(11A), 26–30 (2016)
Hu, J., Zhang, G.: K-fold cross-validation based selected ensemble classification algorithm. Bull. Sci. Technol. 29(12), 115–117 (2013)
Gao, Q., Ma, Y.-M.: Research and application of the level of the deep belief network (DBN). Sci. Technol. Eng. 16(23), 234–238 (2016)
Liao, Q., Zhang, J.: Optimization of DBN network structure based on information entropy. Inf. Commun. 1, 44–48 (2018)
Ma, L.: Analyzing risk factors for multi-diseases with decision tree, logistic regression and improved neural network. Software 12, 58–65 (2014)
Eggermont, J., Kok, J.N., Kosters, W.A., et al.: Genetic programming for data classification: partitioning the search space. In: ACM Symposium on Applied Computing, pp. 1001–1005 (2004)
Karthikeyani, V., Begum, I.P., Tajudin, K., et al.: Comparative of data mining classification algorithm (CDMCA) in diabetes disease prediction. Int. J. Comput. Appl. 60(12), 26–31 (2012)
Karthikeyani, D.V., Begum, I.P.: Comparison a performance of data mining algorithms (CPDMA) in prediction of diabetes disease. Int. J. Comput. Sci. Eng. 5(3), 205 (2013)
Bozkurt, M.R., Yurtay, N., Yilmaz, Z., et al.: Comparison of different methods for determining diabetes. Turk. J. Electr. Eng. Comput. Sci. 22(4), 1044–1055 (2015)
Iyer, A., Jeyalatha, S., Sumbaly, R.: Diagnosis of diabetes using classification mining techniques. Int. J. Data Min. Knowl. Manage. Process 5(1), 1–14 (2015)
Acknowledgements
This research is supported by the Harbin Science and Technology Bureau outstanding subject leader fund project (2017RAXXJ055), the Nature Science Foundation of Heilongjiang Province (F2018020) and the Humanities and social sciences research projects of the Ministry of Education (18YJAZH128).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Zhao, Z., Liu, Y., Sun, H., Han, X., Wang, R. (2019). Research on Diabetes Aided Diagnosis Model Based on Deep Belief Network. In: Jia, M., Guo, Q., Meng, W. (eds) Wireless and Satellite Systems. WiSATS 2019. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 281. Springer, Cham. https://doi.org/10.1007/978-3-030-19156-6_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-19156-6_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-19155-9
Online ISBN: 978-3-030-19156-6
eBook Packages: Computer ScienceComputer Science (R0)