| SPECIAL TOPIC — Biophysical circuits: Modeling & applications in neuroscience |
Prev
Next
|
|
|
Optimized PID neural network closed-loop control for basal ganglia network in Parkinson’s disease |
| Hengxi Zhang(张恒熙)1,2, Honghui Zhang(张红慧)1,2,†, Shuang Liu(柳爽)3, and Lin Du(都琳)1,2 |
1 School of Mathematics and Statistics, Northwestern Polytechnical University, Xi'an 710129, China;
2 MIIT Key Laboratory of Dynamics and Control of Complex Systems, Xi'an 710129, China;
3 Shanghai Engineering Research Center of Physical Vapor Deposition (PVD) Superhard Coating and Equipment, Shanghai Institute of Technology, Shanghai 201418, China |
|
|
|
|
Abstract Conventional open-loop deep brain stimulation (DBS) systems with fixed parameters fail to accommodate inter-individual pathological differences in Parkinson’s disease (PD) management while potentially inducing adverse effects and causing excessive energy consumption. In this paper, we present an adaptive closed-loop framework integrating a Yogi-optimized proportional-integral-derivative neural network (Yogi-PIDNN) controller. The Yogi-augmented gradient adaptation mechanism accelerates the convergence of general PIDNN controllers in high-dimensional nonlinear control systems while reducing control energy usage. In addition, a system identification method establishes input-output dynamics for pre-training stimulation waveforms, bypassing real-time parameter-tuning constraints and thereby enhancing closed-loop adaptability. Finally, a theoretical analysis based on Lyapunov stability criteria establishes a sufficient condition for closed-loop stability within the identified model. Computational validations demonstrate that our approach restores thalamic relay reliability while reducing energy consumption by (81.0 ±0.7)% across multi-frequency tests. This study advances adaptive neuromodulation by synergizing data-driven pre-training with stability-guaranteed real-time control, offering a novel framework for energy-efficient and personalized Parkinson’s therapy.
|
Received: 11 July 2025
Revised: 29 September 2025
Accepted manuscript online: 30 September 2025
|
|
PACS:
|
07.05.Mh
|
(Neural networks, fuzzy logic, artificial intelligence)
|
| |
87.19.lj
|
(Neuronal network dynamics)
|
| |
87.19.lr
|
(Control theory and feedback)
|
| |
87.85.dq
|
(Neural networks)
|
|
| Fund: This project was supported by the National Natural Science Foundation of China (Grant Nos. 12372064 and 12172291) and the Youth and Middle-Aged Science and Technology Development Program of Shanghai Institute of Technology (Grant No. ZQ2024-10). |
Corresponding Authors:
Honghui Zhang
E-mail: haozhucy@nwpu.edu.cn
|
Cite this article:
Hengxi Zhang(张恒熙), Honghui Zhang(张红慧), Shuang Liu(柳爽), and Lin Du(都琳) Optimized PID neural network closed-loop control for basal ganglia network in Parkinson’s disease 2025 Chin. Phys. B 34 120701
|
[1] Benabid A L 2003 Curr. Opin. Neurobiol. 13 696
[2] Okun M S 2012 N. Engl. J. Med. 367 1529
[3] Hariz M and Blomstedt P 2022 J. Intern. Med. 292 764
[4] Limousin P and Foltynie T 2019 Nat. Rev. Neurol. 15 234
[5] Lozano A M, Lipsman N, Bergman H, et al. 2019 Nat. Rev. Neurol. 15 148
[6] Guidetti M, Marceglia S, Loh A, Harmsen I E, Meoni S, Foffani G, Lozano A M, Moro E, Volkmann J and Priori A 2021 Brain Stimul. 14 1238
[7] Bouthour W, Mégevand P, Donoghue J, Lüscher C, Birbaumer N and Krack P 2019 Nat. Rev. Neurol. 15 343
[8] Krauss J K, Lipsman N, Aziz T, Boutet A, Brown P, Chang JW, Davidson B, Grill W M, Hariz M I and Horn A 2021 Nat. Rev. Neurol. 17 75
[9] Rosa M, Arlotti M, Ardolino G, Cogiamanian F, Marceglia S, Di Fonzo A, Cortese F, Rampini P M and Priori A 2015 Mov. Disord. 30 1003
[10] Gorzelic P, Schiff S and Sinha A 2013 J. Neural Eng. 10 026016
[11] Chen L, Jiang W, Bin D, et al. 2016 IEEE Trans. Neural Syst. Rehabil. Eng. 24 1109
[12] Coronel-Escamilla A, Gomez-Aguilar J F, Stamova I and Santamaria F 2020 Chaos Solitons Fractals 140 110149
[13] Liu C, Zhao G, Meng Z, et al. 2021 Cogn. Neurodyn. 15 1157
[14] Fleming J E, Dunn E and Lowery M M 2020 Front. Neurosci. 14 166
[15] Shu H and Pi Y 2000 Comput. Chem. Eng. 24 859
[16] Zeng G Q, Xie X Q, ChenMR andWeng J 2019 Swarm Evol. Comput. 44 320
[17] Ding J, WuMand XiaoM2022 IEEE Trans. Neural Netw. Learn. Syst. 35 8715
[18] Psaltis D, Sideris A and Yamamura A A 1988 IEEE Control Syst. Mag. 8 17
[19] Yang H and Liu J 2018 IEEECAA J. Autom. Sin. 5 457
[20] Liu Y J, Zeng Q, Tong S, Chen C P and Liu L 2019 IEEE Trans. Ind. Electron. 66 9458
[21] Liu Y J, Zhao W, Liu L, Li D, Tong S and Chen C P 2021 IEEE Trans. Neural Netw. Learn. Syst. 34 2732
[22] Khan S, Khan F, Sikander Q U A, Alam M M and Su’Ud M M 2021 IEEE Access 9 136929
[23] Liu C, Zhao G, Wang J, Wu H, Li H, Fietkiewicz C and Loparo K A 2020 IEEE Access 8 161067
[24] Wang K, Wang J, Zhu Y, Li H, Liu C, Fietkiewicz C and Loparo K A 2022 Biomed. Signal Process. Control 77 103776
[25] Zaheer M, Reddi S, Sachan D, Kale S and Kumar S 2018 Adv. Neural Inf. Process. Syst. 31
[26] Kingma D P 2014 arXiv:1412.6980
[27] Abdulkadirov R, Lyakhov P, Bergerman M and Reznikov D 2024 Chaos Solitons Fractals 179 114432
[28] Chang Z, Zhang Y and Chen W 2019 Energy 187 115804
[29] Böttcher L, Antulov-Fantulin N and Asikis T 2022 Nat. Commun. 13 333
[30] So R Q, Kent A R and Grill W M 2012 J. Comput. Neurosci. 32 499
[31] Terman D, Rubin J E, Yew A and Wilson C 2002 J. Neurosci. 22 2963
[32] Rubin J E and Terman D 2004 J. Comput. Neurosci. 16 211
[33] Liu C, Wang J, Li H, Lu M, Deng B, Yu H, Wei X, Fietkiewicz C and Loparo K A 2016 IEEE Trans. Neural Netw. Learn. Syst. 28 371
[34] Schiff S J 2010 Philos. Trans. R. Soc. A 368 2269
[35] Lu M, Wei X, Che Y, Wang J and Loparo K A 2019 IEEE Trans. Neural Syst. Rehabil. Eng. 28 339
[36] Feng X J, Shea-Brown E, Greenwald B, Kosut R and Rabitz H 2007 J. Comput. Neurosci. 23 265
[37] Lin N, Chi R and Huang B 2020 Appl. Math. Model. 81 787
[38] Glorot X and Bengio Y 2010 Proc. 13th Int. Conf. Artif. Intell. Stat. (JMLR Workshop and Conference Proceedings) pp. 249–256
[39] Birdno M J and Grill W M 2008 Neurotherapeutics 5 14
[40] Zhao T, Faustino B L, Jagatheesaperumal S K, Rolim F d P S and de Albuquerque V H C 2025 Expert Syst. Appl. 267 126154
[41] Holgado A J N, Terry J R and Bogacz R 2010 J. Neurosci. 30 12340
[42] Liu C, Wang J, Yu H, Deng B, Wei X, Li H, Loparo K A and Fietkiewicz C 2015 Commun. Nonlinear Sci. Numer. Simul. 28 10
[43] Yu Y, Wang X, Wang Q and Wang Q 2020 Appl. Math. Mech. 41 1747
[44] Kumaravelu K, Brocker D T and GrillWM 2016 J. Comput. Neurosci. 40 207
[45] Yu Y and Wang Q 2019 Nonlinear Dyn. 98 1065 |
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|
