LASSO-Based Identification of Sparse Autoregressive Exogenous Input Model Coefficients
Application to Automated AMBU-Bag Resuscitator System
DOI:
https://doi.org/10.3991/ijoe.v22i10.61627Keywords:
ARX model, LASSO regression, model identification, sparse estimation, AMBU-bag resuscitator, respiratory mechanicsAbstract
Accurate system identification is important role in the development of reliable control approaches for automated respiratory devices. Nonetheless, conventional identification approaches suffer from overfitting and sensitivity to noise. Therefore, in this paper, a novel sparse autoregressive exogenous input identification scheme based on the least absolute shrinkage and selection operator is proposed for the automated AMBU-bag resuscitator (AABR). Specifically, it incorporates decoupled regularization terms for autoregressive and input-related components, as well as enables robust parameter estimation without requiring normalization of input data. The grey wolf optimizer (GWO) is used to optimize regularization parameters by minimizing prediction errors on validation datasets. The experimental data were obtained from a real AABR system with three excitation signals: cosine, parabolic, and ramp, corresponding to smooth periodic, second-order polynomial, and linear profiles, respectively. The smooth periodic profile dataset was used for training, while the others were employed for validation. As a result, the proposed model achieved consistent prediction accuracy, with the root mean square errors (RMSEs) of 0.177893, 0.195727, and 0.150998. Conversely, the conventional recursive least squares (RLS) method exhibited severe overfitting, with RMSE increasing from 0.009821 to 11.436522.
References
[1] I. R. Drennan, M. R. Neth, and B. K. Walsh, “Advancements in Ventilation During Cardiac Resuscitation,” Crit. Care Clin., vol. 42, no. 1, pp. 131–147, Jan. 2026, doi: 10.1016/j.ccc.2025.08.007.
[2] C. T. Truong, K. H. Huynh, V. T. Duong, H. H. Nguyen, L. A. Pham, and T. T. Nguyen, “Model-free volume and pressure cycled control of automatic bag valve mask ventilator,” AIMS Bioeng., vol. 8, no. 3, pp. 192–207, 2021, doi: 10.3934/bioeng.2021017.
[3] K. Iyengar, S. Bahl, Raju Vaishya, and A. Vaish, “Design of an Advanced PID Control-based Portable Ventilator Prototype for Enhanced Respiratory Support,” Recent Advances in Electrical and Electronic Engineering, vol. 19, no. 4, pp. 499–501, Jan. 2026, doi: 10.1016/j.dsx.2020.04.048.
[4] S. Saisukirtha, M. Omprakash, S. Shane Steffy, and S. Dilip Kumar, “Smart Ventilation Bag with Adjustable Oxygen Range and Automated Pressure Regulation,” 3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025, pp. 1014–1019, 2025, doi: 10.1109/IDCIOT64235.2025.10914958.
[5] C. T. Truong, K. H. Huynh, V. T. Duong, H. H. Nguyen, L. A. Pham, and T. T. Nguyen, “Linear Regression Model and Least Square Method for Experimental Identification of AMBU Bag in Simple Ventilator,” International Journal of Intelligent Unmanned Systems, Aug. 2022, doi: 10.1108/IJIUS-07-2021-0072.
[6] C. T. Truong, T. D. Phan, M. H. Nguyen, V. T. Duong, H. H. Nguyen, and T. T. Nguyen, “Ensemble Bidirectional Long Short-Term Memory Network Identification for Nonlinear Autoregressive Exogenous Model: Application to Dual Double-Acting Piston Pump,” IEEE Access, vol. 13, pp. 174445–174461, 2025, doi: 10.1109/ACCESS.2025.3612891.
[7] M. A. Khan, D. E. Ze. Baig, H. Ali, and F. R. Albogamy, “Optimized System Identification (SI) of Brushless DC (BLDC) motor using Data-Driven Modeling Methods,” Scientific Reports 2025 15:1, vol. 15, no. 1, pp. 8497-, Mar. 2025, doi: 10.1038/s41598-025-93444-0.
[8] C. T. Truong, T. D. Phan, V. T. Duong, H. H. Nguyen, and T. T. Nguyen, “Model Identification of Ventilation Air Pump Utilizing Ridge-Momentum Regression and Grid-Based Structure Optimization,” Mathematical Biosciences and Engineering, vol. 22, no. 8, pp. 2020–2038, 2025, doi: 10.3934/mbe.2025074.
[9] N. Arridu, M. Lippi, M. Franceschelli, and A. Gasparri, “On Ensemble Learning Models for Autoencoder-Based Identification of Nonlinear Dynamical Systems,” IEEE Access, vol. 13, pp. 169071–169082, 2025, doi: 10.1109/ACCESS.2025.3611914.
[10] N. Xu and F. Ding, “Recursive estimation algorithms based on the least squares and their convergence for a class of time-varying systems,” Nonlinear Dynamics 2023 111:19, vol. 111, no. 19, pp. 18191–18213, Aug. 2023, doi: 10.1007/s11071-023-08816-w.
[11] K. Gajula, L. K. Marepalli, X. Yao, and L. Herrera, “Recursive Least Squares and Adaptive Kalman Filter-Based State and Parameter Estimation for Series Arc Fault Detection on DC Microgrids,” IEEE J. Emerg. Sel. Top. Power Electron., vol. 10, no. 4, pp. 4715–4724, Aug. 2022, doi: 10.1109/JESTPE.2021.3135409.
[12] A. Dong, A. Starr, Y. Zhao, A. Dong, A. Starr, and Y. Zhao, “End-to-end Identification of Autoregressive with Exogenous Input (ARX) Models Using Neural Networks,” Machine Intelligence Research 2025 22:1, vol. 22, no. 1, pp. 117–130, Jan. 2025, doi: 10.1007/s11633-024-1523-3.
[13] X. Chen and J. Li, “Multi-Sensor Recursive EM Algorithm for Robust Identification of ARX Models,” Sensors (Basel), vol. 25, no. 22, Nov. 2025, doi: 10.3390/s25227060.
[14] R. Tibshirani, “Regression Shrinkage and Selection Via the Lasso,” J. R. Stat. Soc. Series B Stat. Methodol., vol. 58, no. 1, pp. 267–288, Jan. 1996, doi: 10.1111/j.2517-6161.1996.tb02080.x.
[15] H. Zhou, C. Ibrahim, W. X. Zheng, and W. Pan, “Sparse Bayesian deep learning for dynamic system identification,” Automatica, vol. 144, no. 6, p. 110489, Oct. 2022, doi: 10.1016/j.automatica.2022.110489.
[16] N. V. N. Sowjanya and M. Palanivelan, “Study of Sparse Optimization for System Identification and Machine Learning,” Algorithms in Advanced Artificial Intelligence, pp. 731–737, Mar. 2025, doi: 10.1201/9781003641537-111.
[17] J. Gillariose, J. Joseph, and C. Chesneau, “Lasso and Ridge regression: a comprehensive review of applications and developments in machine learning,” International Journal of Data Science and Analytics 2025 21:1, vol. 21, no. 1, pp. 7-, Nov. 2025, doi: 10.1007/s41060-025-00957-y.
[18] J. Singh, J. K. Sandhu, and Y. Kumar, “Metaheuristic-based hyperparameter optimization for multi-disease detection and diagnosis in machine learning,” Service Oriented Computing and Applications 2024 18:2, vol. 18, no. 2, pp. 163–182, Jan. 2024, doi: 10.1007/s11761-023-00382-8.
[19] Y. Liu, A. As’arry, M. K. Hassan, A. A. Hairuddin, and H. Mohamad, “Review of the grey wolf optimization algorithm: variants and applications,” Neural Computing and Applications 2023 36:6, vol. 36, no. 6, pp. 2713–2735, Nov. 2023, doi: 10.1007/s00521-023-09202-8.
[20] V. H. S. Pham and V. K. Nguyen, “A study on optimization of HVAC system in buildings using gray wolf optimizer (GWO) and artificial neural network (ANN),” Asian Journal of Civil Engineering 2023 24:8, vol. 24, no. 8, pp. 3743–3757, Jun. 2023, doi: 10.1007/s42107-023-00747-6.
[21] J. Friedman, T. Hastie, and R. Tibshirani, “Regularization Paths for Generalized Linear Models via Coordinate Descent,” J. Stat. Softw., vol. 22, no. 1, pp. 1–22, Feb. 2010, doi: 10.18637/jss.v033.i01.
[22] C. T. Truong, T. D. Phan, V. T. Duong, H. H. Nguyen, and T. T. Nguyen, “L1 Adaptive Control for a Low-Cost Bag-Valve-Mask Ventilator in Volume-Controlled Continuous Mandatory Ventilation Mode: Design, Simulation and Experiment,” Eur. J. Control, p. 101409, 2025, doi: 10.1016/j.ejcon.2025.101409.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Trung Dat Phan, Cong Toai Truong, Huy Hung Nguyen, Tan Tien Nguyen, Van Tu Duong
This work is licensed under a Creative Commons Attribution 4.0 International License.
