Design of Robust Evolving Cloud-Based Controller for Type 1 Diabetic Patients Using n-Beats Algorithm

Kalaimani, Subasri Chellamuthu; Jeyakumar, Vijay

doi:10.1590/1678-4324-2024230857

Acessibilidade / Reportar erro

Brasil

Brazilian Archives of Biology and Technology

Español English

Brasil

Español English

sumário « anterior atual seguinte »

Sumário

Article - Engineering, Technology and Techniques • Braz. arch. biol. technol. 67 • 2024 • https://doi.org/10.1590/1678-4324-2024230857 copy

Design of Robust Evolving Cloud-Based Controller for Type 1 Diabetic Patients Using n-Beats Algorithm

Authorship SCIMAGO INSTITUTIONS RANKINGS

Abstract

Designing and analyzing adaptive controllers to control blood glucose levels by giving insulin in the Lehman-Based Diabetic Patient Model (LBDPM) while considering diverse stochastic environments in gaining popularity is challenging task. RECCo, a notable recent innovation that implements the concept of the ANYA fuzzy rule-based system, is an online adaptive type controller that is used in this study for the application of diabetes. The simulation results show that the suggested controller is used in the model to track standard blood glucose values even in the presence of some unexpected external disturbances. The primary concern in the field of type 1 diabetes is achieving higher accuracy using a deep learning algorithm with data obtained from simulated patient models. To achieve better accuracy, validation of the model is performed using the N-BEATS algorithm. By utilizing an online parameter estimation technique, the RPME is integrated to improve the performance of the adaptive model predictive controller. The system identification technique is used to attain a transfer function that is designed further for implementation of the controller. The experimental validation of the proposed N-BEATS algorithm method is compared with other conventional machine learning algorithms. The proposed controller method attains excellent blood glucose set point tracking and the proposed algorithms give accuracy rates of 97.4% and 96% for the data obtained. It outperforms other state-of-the-art methods with an increase in the accuracy percentage compared with other Benchmark Pima Indian Diabetes Datasets (PIDD).

Keywords:
Adaptive Model Predictive Control (AMPC); Glucose-Insulin (GI); Lehman Based Diabetic Patient Model (LBDPM); Neural Network (NN); Neural Basis Expansion Analysis for Interpretable Time Series (N-BEATS)

HIGHLIGHTS

RECCo is an online adaptive type controller, represents a notable recent innovation in the field of diabetes management.

RPME is an online parameter estimation technique into the Adaptive Model Predictive Controller based on real-time data, making it more adaptive to changes in the patient's condition.

The proposed N-BEATS algorithm is used for model validation. Comparing the performance of this algorithm with other conventional machine learning algorithms adds novelty to the study's approach.

Authors	Diabetes Type	Controller Types	Merits / Demerits
(Bahremand et al., 2019) [¹⁰10 Bahremand S, Ko HS, Balouchzadeh R, Felix Lee H, Park S, Kwon G. Neural network-based model predictive control for type 1 diabetic rats on artificial pancreas system. Med Biol Eng Comput. 2019 Jan;57(1):177-91. https://doi.org/10.1007/s11517-018-1872-6. https://doi.org/10.1007/s11517-018-1872-... ]	Type-1	Neural Network based Model Predictive Controller (MPC)	The practical implementation is very difficult using NN-based MPC.
(Colmegna, Bianchi, & Sánchez-Peña, 2020) [¹¹11 Colmegna PH, Bianchi FD, Sánchez-Peña RS. Automatic glucose control during meals and exercise in type 1 diabetes: Proof-of-concept in silicon tests using a switched LPV approach. IEEE Control Syst. Lett. 2020; 5(5): 1489-94. https://doi.org/10.1109/LCSYS.2020.3041211. https://doi.org/10.1109/LCSYS.2020.30412... ]	Type-1	Switched Linear Parameter Varying (SLPV) Controller	Different meal scenarios were tested under various condition which overcomes risk of hypo and hyperglycemia.
(Alfian et al., 2020) [¹²12 Alfian G, Syafrudin M, Anshari M, Benes F, Atmaji FTD, Fahrurrozi I, et al. Blood glucose prediction model for type 1 diabetes based on artificial neural network with time-domain features. J. Appl. Biomed. 2020;40(4):1586-99. http://dx.doi.org/10.1016/j.bbe.2020.10.004 http://dx.doi.org/10.1016/j.bbe.2020.10.... ]	Type-1	Artificial Neural Network (ANN)	The future blood glucose values can be predicted which provides alert in critical cases.
(Khaqan, Nauman, Shuja, Khurshaid, & Kim, 2022) [¹³13 Khaqan A, Nauman A, Shuja S, Khurshaid T, Kim KC. An Intelligent Model-Based Effective Approach for Glycemic Control in Type-1 Diabetes. Sens. 2022; 22(20): 7773. https://doi.org/10.3390/s22207773 https://doi.org/10.3390/s22207773... ]	Type-1	Sliding Mode Controller (SMC)	The brief comparison between (PID & LQR) and Nonlinear method SMC provides good efficiency.
(Belmon & Auxillia, 2020) [¹⁴14 Belmon AP, Auxillia J. An adaptive technique based blood glucose control in type-1 diabetes Mellitus patients. Int. J. Numer. Method. Biomed. Eng. 2020; 36(8): e3371. https://doi.org/10.1002/cnm.3371 https://doi.org/10.1002/cnm.3371... ]	Type-1	Grasshopper Optimization Algorithm (GOA) based Proportional Integral Derivative (PID)	Compared to conventional controllers GOA based PID provides good results with best accuracy.

Authors	Diabetes Type	Classification methods	Merits / Demerits
Sun, Jankovic, Bally, & Mougiakakou, 2018 [¹⁵15 Parameswari A, Vinoth Kumar K. Gopinath S. Thermal analysis of Alzheimer's disease prediction using Random Forest Classification Model. Mater. Today Proc. 2022; 66.https://doi.org/10.1016/j.matpr.2022.04.357 https://doi.org/10.1016/j.matpr.2022.04.... ]	Type-1	Bidirectional LSTM (Bi-LSTM)	In this method future values can be predicted which satisfy the evaluation criteria.
De Bois, El Yacoubi, & Ammi, 2019 [¹⁶16 De Bois M, El Yacoubi M, Ammi M. Study of short-term personalized glucose predictive models on type-1 diabetic children. IJCNN. 2019; http://dx.doi.org/10.1109/IJCNN.2019.8852399 http://dx.doi.org/10.1109/IJCNN.2019.885... ]	Type-1	Long Short Term Memory (LSTM)	Performs well when compared to other state of art methods.
Li, Yeh, Chen, & Chung, 2019 [¹⁷17 Yang H, Chen Z, Huang J, Li S. AWD-stacking: An enhanced ensemble learning model for predicting glucose levels. PLoS One. 2024 Feb 14;19(2):e0291594. https://doi.org/10.1371%2Fjournal.pone.0291594. https://doi.org/10.1371%2Fjournal.pone.0... ]	Type-1	Deep Convolution Neural Networks (DCNNs)	Based on the computer assisted method used in Diabetic Retinopathy applications.
Freiburghaus, Rizzotti, & Albertetti, 2020 [¹⁸18 Khadem H, Nemat H, Elliott J, Benaissa M. Blood Glucose Level Time Series Forecasting: Nested Deep Ensemble Learning Lag Fusion. Bioengineering (Basel). 2023 Apr 19;10(4):487. https://doi.org/10.3390%2Fbioengineering10040487. https://doi.org/10.3390%2Fbioengineering... ]	Type-1	Multi layer Convolution Recurrent Neural Network (CRNN)	This method provides data driven technique which provides long term health support during complications.
Alazwari et al., 2022 [¹⁹19 Alazwari A, Abdollahian M, Tafakori L, Johnstone A, Alshumrani RA, Alhelal, MT, et al. Predicting age at onset of type 1 diabetes in children using regression, artificial neural network and Random Forest: A case study in Saudi Arabia. PLoS One. 2022;17(2): e0264118. https://doi.org/10.1371/journal.pone.0264118 https://doi.org/10.1371/journal.pone.026... ]	Type-1	Random forests (RF) and Relief feature evaluation algorithms	It provides knowledge about how the future weights get integrated.

Parameters considered in simulation	Symbol	Values	Unit
Constant rate of Insulin Elimination	$K_{ea}$	6.3	$h^{- 1}$
$I_{p}$ Insulin action delay rate	K_1a	0.025	$h^{- 1}$
$I_{a}$ Insulin action delay rate	$K_{2 a}$	1.550	$h^{- 1}$
Reference value of plasma insulin	$I_{basal}$	1.0	$mU / dl$
Constant rate of glucose by Gut	$K_{gabsa}$	1.000	$h^{- 1}$
Rate of Gastric emptying system	${Vmax}_{gea}$	360.0	$mg / min$
Distribution of Insulin volume in whole body weight	$V_{Ia}$	1.42 * 80	$dl$
Distribution of insulin volume in whole bodyweight	$V_{Ga}$	2.21 * 80	$dl$
For reaching ${Vmax}_{gea}$ , rise time	${Tasc}_{gea}$	30	$min$
From ${Vmax}_{gea}$ to 0 falling time	${Tdes}_{gea}$	30	$min$
Creatinine Clearance Rate	$CCR$	1.0	$dl / min$
Renal Threshold Glucose Value	$RTG$	162	$mg / dl$

Error Covariance matrix value				Estimated state values	True state values	Measurement states
30.84	0	14.52	0	14.33	16.07	20.1	6.994
0	30.83	0	14.5	5.068	0
14.52	0	17.87	0	0.8892	30
0	14.5	0	17.86	0.9774

Name of Controller	Peak Overshoot Time (min)	Settling Time (min)	Meal intake (gm)	Insulin Dose (mU/L)	Noise (%)
Proportional Integral Derivative (PID)	800 min	650 min	60	59.6	10
Adaptive Model Predictive Controller (AMPC)	20 min	120 min	60	59.2	5
RECCo (Proposed method controller)	Minimzed Justified in graph (Figure 12)	50 min	60	59	1

Process Parameters	Values	Evolving Parameters	Values	Adaptation Parameters	Values
$u_{\min}$	0	$γ_{\max}$	0.93	G_sign	_{± 1}
$u_{\max}$	100	$k_{a d d 1}$	1	α_pa,α_Ia, α_Da,α_Ra	0.1
$y_{\min}$	20	$n_{a d d 1}$	20
$y_{\max}$	70	C	0
T_S (SamplingRate)	2	$C_{\max}$	20
$τ$ (Time Constant)	40	$γ_{\max}$	0.93

Algorithms Used	Precision	Recall	F1-Score	Mean Square Error	Accuracy	Training Accuracy	Testing Accuracy
N-BEATS	0.969	0.966	0.973	0.152	97.4%	0.974	0.971
XGB	0.929	0.924	0.921	0.346	93%	0.91	0.92
SVM	0.919	0.915	0.912	0.469	91%	0.86	0.91
Decision Tree	0.921	0.927	0.922	0.217	92%	0.81	0.90
KNN	0.898	0.863	0.869	0.521	89%	0.93	0.92
Reinforcement Learning	0.964	0.867	0.878	0.174	96.1%	0.87	0.89

Instituto de Tecnologia do Paraná - Tecpar Rua Prof. Algacyr Munhoz Mader, 3775 - CIC, 81350-010 Curitiba PR Brazil, Tel.: +55 41 3316-3052/3054, Fax: +55 41 3346-2872 - Curitiba - PR - Brazil
E-mail: babt@tecpar.br

Acompanhe os números deste periódico no seu leitor de RSS

[1] *Correspondence: subasribme@outlook.com; (S.C.K.)

Normalized Relative Density	$λ_{a k 1}^{i}$ = $γ_{a k 1}^{i}$ / $Σ_{j = 1}^{c} γ_{a k 1}^{i}$ i=1,2,3..C where $γ_{a k 1}^{i}$ - local density of i^th cloud
Local Density	$γ_{a k 1}^{i}$ =1/ 1+ ǁǁ $x_{a k 1}$ - $μ_{a k 1}^{i}$ ǁǁ² + $σ_{a k 1}^{i}$ - ǁǁ $μ_{a k 1}^{i}$ ǁǁ²
Mean Value	$μ_{a k 1}^{i}$ = (( $M^{i}$ - 1/ $M^{i}$ ) $μ_{k - 1}^{i}$ + 1/ $M^{i}$ _* ( $x_{a k 1}$ [ $M^{i}$ = No of data points]
Mean Square Length	$σ_{a k 1}^{i}$ = (( $M^{i}$ - 1/ $M^{i}$ ) $σ_{k - 1}^{i}$ + 1/ $M^{i}$ ǁǁ $x_{a k 1}$ ǁǁ² [ Initial condition $M^{i}$ = 1], mean value $μ_{1}^{i}$ = $x_{1}$ , $σ_{1}^{i}$ = ǁǁ $x_{1}$ ǁǁ²

(i) Dead zone in adaptation law (function to switch off algorithm when value of tracking error is lower that threshold value)	$Δ {\bar{θ}}_{k}^{i} = {\begin{matrix} Δ θ_{k}^{i}, Δ ε_{a k 1} Δ \geq d_{d e a d} \\ 0, Δ ε_{a k 1} Δ < d_{d e a d} \end{matrix}}$ i=1,….c (25)
(ii) Parameter projection (it is converged to get optimal parameters values)	$θ_{k}^{i}$ = ${\begin{matrix} θ_{k - 1}^{i} + Δ θ_{k}^{i}, \underline{θ} \leq θ_{k - 1}^{i} + Δ θ_{k}^{i} \leq \bar{θ} \\ \underline{θ}, θ_{k - 1}^{i} + Δ θ_{k}^{i} < \underline{θ} \\ \bar{θ}, θ_{k - 1}^{i} + Δ θ_{k}^{i} > \bar{θ} \end{matrix}}$ i=1,….c (26)
(iii) Leakage in adaptation law ( $σ$ _- modification)	$θ_{k}^{i}$ = (1- $σ$ _L) $θ_{k - 1}^{i}$ + $Δ θ_{k}^{i}$ i=1,….c (27)
(iv) Interruption of adaptation law	$Δ {\bar{θ}}_{k}^{i} = {\begin{matrix} Δ θ_{k}^{i}, u_{\min} < u (k) < u_{\max} \\ 0, o t h e r w i s e \end{matrix}}$ i=1,….c (28)