Abstract
We introduce a novel LSTM architecture, parameterized LSTM (p-LSTM) which utilizes parameterized Elliott (p-Elliott) activation at the gates. The advantages of parameterization is evident in better generalization ability of the network to predict blood glucose levels of patients from a real, vetted data set. The parameter of the Elliott activation is learned from the backpropagation steps of the LSTM which reaps the benefits of learning flexible patterns from data using all features and causal features, as the parameter values change in training phase of p-LSTM. The learning of the parameter is also facilitated by fixed point methods on p-Elliott. This leads to better fit and adds explainability in prediction (due to causal features) to the blood glucose fluctuation patterns over time. The coupling of LSTM architecture with p-Elliott leads to superior prediction of glucose levels. It also provides an excellent technique to fit highly nonlinear temporal data, in comparison to the performance of state-of-the-art methods.
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
Arpit, D., Kanuparthi, B., Kerg, G., Ke, N.R., Mitliagkas, I., Bengio, Y.: h-detach: Modifying the lstm gradient towards better optimization (2018). https://doi.org/10.48550/ARXIV.1810.03023, https://arxiv.org/abs/1810.03023
Borle, N.C., Ryan, E.A., Greiner, R.: The challenge of predicting blood glucose concentration changes in patients with type i diabetes. Health Informatics J. 27(1), 1460458220977584 (2021) , https://doi.org/10.1177/1460458220977584, pMID: 33504254
Du, M.: Improving lstm neural networks for better short-term wind power predictions. In: 2019 IEEE 2nd International Conference on Renewable Energy and Power Engineering (REPE), pp. 105–109 (2019). https://doi.org/10.1109/REPE48501.2019.9025143
Farzad, A., Mashayekhi, H., Hassanpour, H.: A comparative performance analysis of different activation functions in LSTM networks for classification. Neural Comput. Appl. 31(7), 2507–2521 (2017). https://doi.org/10.1007/s00521-017-3210-6
Ganatra, V., Swain, A., Saha, S., Mathur, A.: p-LSTM (June 2022). https://github.com/Vaibhav-Ganatra/p-LSTM
Gould, P.G., Koehler, A.B., Ord, J.K., Snyder, R.D., Hyndman, R.J., Vahid-Araghi, F.: Forecasting time series with multiple seasonal patterns. European J. Operational Res. 191(1), 207–222 (2008). https://doi.org/10.1016/j.ejor.2007.08.024, https://www.sciencedirect.com/science/article/pii/S0377221707008740
Granger, C.W.J.: Investigating causal relations by econometric models and cross-spectral methods. Econometrica 37(3), 424–438 (1969). https://www.jstor.org/stable/1912791
Hamdi, T., et al.: Artificial neural network for blood glucose level prediction. In: 2017 International Conference on Smart, Monitored and Controlled Cities (SM2C), pp. 91–95 (2017). https://doi.org/10.1109/SM2C.2017.8071825
Jensen, M.H., Christensen, T.F., Tarnow, L., Seto, E., Dencker Johansen, M., Hejlesen, O.K.: Real-time hypoglycemia detection from continuous glucose monitoring data of subjects with type 1 diabetes. Diabetes Technol. Therapeutics 15(7), 538–543 (2013). https://doi.org/10.1089/dia.2013.0069, https://doi.org/10.1089/dia.2013.0069, pMID: 23631608
Marling, C., Bunescu, R.: The ohiot1dm dataset for blood glucose level prediction: Update 2020. In: CEUR Workshop Proceedings, vol. 2675, pp. 71–74 (09 2020)
Marling, C., Wiley, M., Bunescu, R., Shubrook, J., Schwartz, F.: Emerging applications for intelligent diabetes management. AI Magazine 33(2), 67 (2012). https://doi.org/10.1609/aimag.v33i2.2410, https://ojs.aaai.org/index.php/aimagazine/article/view/2410
Martinsson, J., Schliep, A., Eliasson, B., Mogren, O.: Blood glucose prediction with variance estimation using recurrent neural networks. J. Heal. Informatics Res. 4(1), 1–18 (2020). https://doi.org/10.1007/s41666-019-00059-y, https://doi.org/10.1007/s41666-019-00059-y
Mhaskar, H.N., Pereverzyev, S.V., van der Walt, M.D.: A deep learning approach to diabetic blood glucose prediction. Front. Appli. Mathem. Stat. 3 (2017). https://doi.org/10.3389/fams.2017.00014,https://www.frontiersin.org/article/10.3389/fams.2017.00014
Pappada, S., et al.: Neural network-based real-time prediction of glucose in patients with insulin-dependent diabetes. Diabetes Technol. Therapeutics 13, 135–41 (2011). https://doi.org/10.1089/dia.2010.0104
Rana, M., Uddin, M.M., Hoque, M.M.: Effects of activation functions and optimizers on stock price prediction using lstm recurrent networks. In: Proceedings of the 2019 3rd International Conference on Computer Science and Artificial Intelligence, CSAI 2019, pp. 354–358. Association for Computing Machinery, New York (2019). https://doi.org/10.1145/3374587.3374622,https://doi.org/10.1145/3374587.3374622
Saha, S., Nagaraj, N., Mathur, A., Yedida, R., H R, S.: Evolution of novel activation functions in neural network training for astronomy data: habitability classification of exoplanets. Euro. Phys. J. Special Topics 229(16), 2629–2738 (2020). https://doi.org/10.1140/epjst/e2020-000098-9
Shahid, S., Hussain, S., Khan, W.A.: Predicting continuous blood glucose level using deep learning. In: Proceedings of the 14th IEEE/ACM International Conference on Utility and Cloud Computing Companion, UCC 2021, Association for Computing Machinery, New York (2021). https://doi.org/10.1145/3492323.3495598,https://doi.org/10.1145/3492323.3495598
Vicente, R., Wibral, M., Lindner, M., Pipa, G.: Transfer entropy-a model-free measure of effective connectivity for the neurosciences. J. Computat. Neurosci. 30, 45–67 (2011). https://doi.org/10.1007/s10827-010-0262-3
Xu, H., et al.: Modified lstm with memory layer for power grid signal classification. In: 2020 IEEE 4th Conference on Energy Internet and Energy System Integration (EI2), pp. 3693–3697 (2020). https://doi.org/10.1109/EI250167.2020.9347143
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Swain, A., Ganatra, V., Saha, S., Mathur, A., Phadke, R. (2023). P-LSTM: A Novel LSTM Architecture for Glucose Level Prediction Problem. In: Tanveer, M., Agarwal, S., Ozawa, S., Ekbal, A., Jatowt, A. (eds) Neural Information Processing. ICONIP 2022. Communications in Computer and Information Science, vol 1794. Springer, Singapore. https://doi.org/10.1007/978-981-99-1648-1_31
Download citation
DOI: https://doi.org/10.1007/978-981-99-1648-1_31
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1647-4
Online ISBN: 978-981-99-1648-1
eBook Packages: Computer ScienceComputer Science (R0)