Ultra-Local Model Control of Parkinson's Patients Based on Machine Learning

Document Type : Original research papers


1 Department of Electrical and Biomedical Engineering, University College of Rouzbahan, Sari, Iran.

2 Department of Sport Biomechanics and Technology, Sport Sciences Research Institute, Tehran, Iran.


Parkinson’s disease (PD) is one of the most privileged neurodegenerative, which has had an upward trend in recent decades. The most important complications of PD are tremor, rigidity, and slow movement. A surgery method namely Deep brain stimulation (DBS) plays a vital role in the treatment of advanced Parkinson’s patients. In the past decades, stimulating one nucleus of basal ganglia including Globus pallidus internal (GPi) or Subthalamic nucleus (STN) without any feedback (open-loop manner) has had a common strategy, which leads to several different side-effects like muscle tonic and forgetfulness. In the present paper, two nuclei of BG are stimulated in a closed-loop structure (feedback signal) to reduce the entrance electric field intensity to the brain, and in addition to shrinking hand tremor in Parkinson’s patients. For this purpose, an ultra-local model (ULM) control based on a deep deterministic policy gradient (DDPG) is designed to stimulate the STN and a conventional feedback controller is considered for stimulating GPi. In this method, the coefficients of the ULM are adaptively assumed as the control objective parameters, which are designed by the critic and actor neural networks (NNs) of DDPG. To demonstrate the effectiveness and suitability of the suggested approach is compared to state-of-the-art strategies such as ULM, SMC, and PI controllers.


Main Subjects

1.         Ringe D, Petsko GA. Q&A: What are pharmacological chaperones and why are they interesting? Journal of biology. 2009;8(9):80.
2.         Santillán M, Hernández-Pérez R, Delgado-Lezama R. A numeric study of the noise-induced tremor in a mathematical model of the stretch reflex. Journal of theoretical biology. 2003;222(1):99-115.
3.         Kubben N, Misteli T. Shared molecular and cellular mechanisms of premature ageing and ageing-associated diseases. Nature Reviews Molecular Cell Biology. 2017;18(10):595.
4.         Rouhollahi K, Andani ME, Karbassi SM, Izadi I. Design of robust adaptive controller and feedback error learning for rehabilitation in Parkinson's disease: a simulation study. IET systems biology. 2017;11(1):19-29.
5.         Gallego JA, Rocon E, Roa JO, Moreno JC, Pons JL. Real-time estimation of pathological tremor parameters from gyroscope data. Sensors. 2010;10(3):2129-49.
6.         Di Pino G, Formica D, Melgari J-M, Taffoni F, Salomone G, di Biase L, et al., editors. Neurophysiological bases of tremors and accelerometric parameters analysis2012: IEEE.
7.         Milanov I. Electromyographic differentiation of tremors. Clinical Neurophysiology. 2001;112(9):1626-32.
8.         Blumrosen G, Uziel M, Rubinsky B, Porrat D, editors. Tremor acquisition system based on UWB Wireless Sensor Network2010: IEEE.
9.         Haeri M, Sarbaz Y, Gharibzadeh S. Modeling the Parkinson's tremor and its treatments. Journal of theoretical biology. 2005;236(3):311-22.
10.       Limousin P, Krack P, Pollak P, Benazzouz A, Ardouin C, Hoffmann D, et al. Electrical stimulation of the subthalamic nucleus in advanced Parkinson's disease. New England Journal of Medicine. 1998;339(16):1105-11.
11.       Gorzelic P, Schiff SJ, Sinha A. Model-based rational feedback controller design for closed-loop deep brain stimulation of Parkinson's disease. Journal of neural engineering. 2013;10(2):026016.
12.       Klostermann F, Vesper J, Curio G. Identification of target areas for deep brain stimulation in human basal ganglia substructures based on median nerve sensory evoked potential criteria. Journal of Neurology, Neurosurgery & Psychiatry. 2003;74(8):1031-5.
13.       Mehanna R, Lai EC. Deep brain stimulation in Parkinson’s disease. Translational neurodegeneration. 2013;2(1):22.
14.       Rouhollahi K, Andani ME, Izadi I, Karbassi SM. Controllability and observability analysis of basal ganglia model and feedback linearisation control. IET Systems Biology. 2017;11(5):144-54.
15.       Rouhollahi K, Andani ME, Karbassi SM, Izadi I. Designing a robust backstepping controller for rehabilitation in Parkinson's disease: a simulation study. IET systems biology. 2016;10(4):136-46.
16.       Rouhollahi K, Andani ME, Marnanii JA, Karbassi SM. Rehabilitation of the Parkinson's tremor by using robust adaptive sliding mode controller: a simulation study. IET Systems Biology. 2019;13(2):92-9.
17.       Gheisarnejad M, Faraji B, Esfahani Z, Khooban M-H. A Close loop multi-area brain stimulation control for Parkinson’s Patients Rehabilitation. IEEE Sensors Journal. 2019;20(4):2205-13.
18.       Thabet H, Ayadi M, Rotella F. Towards an ultra-local model control of two-tank-system. International Journal of Dynamics and Control. 2016;4(1):59-66.
19.       Agee JT, Kizir S, Bingul Z. Intelligent proportional-integral (iPI) control of a single link flexible joint manipulator. Journal of Vibration and Control. 2015;21(11):2273-88.
20.       Chen P, He Z, Chen C, Xu J. Control strategy of speed servo systems based on deep reinforcement learning. Algorithms. 2018;11(5):65.
21.       Grover S, Bhartia S, Yadav A, Seeja KR. Predicting severity of Parkinson’s disease using deep learning. Procedia computer science. 2018;132:1788-94.
22.       Qian L, Wu Y, Jiang F, Yu N, Lu W, Lin B. NOMA assisted Multi-task Multi-access Mobile Edge Computing via Deep Reinforcement Learning for Industrial Internet of Things. IEEE Transactions on Industrial Informatics. 2020.
23.       Wu Y, Tan H, Peng J, Zhang H, He H. Deep reinforcement learning of energy management with continuous control strategy and traffic information for a series-parallel plug-in hybrid electric bus. Applied Energy. 2019;247:454-66.
24.       Hasanvand S, Rafiei M, Gheisarnejad M, Khooban M-H. Reliable Power Scheduling of an Emission-Free Ship: Multi-Objective Deep Reinforcement Learning. IEEE Transactions on Transportation Electrification. 2020.
25.       Zhang M, Zhang Y, Gao Z, He X. An Improved DDPG and Its Application Based on the Double-Layer BP Neural Network. IEEE Access. 2020;8:177734-44.
26.       Kwon D, Jeon J, Park S, Kim J, Cho S. Multi-Agent DDPG-based Deep Learning for Smart Ocean Federated Learning IoT Networks. IEEE Internet of Things Journal. 2020.
27.       Kandel ER, Schwartz JH, Jessell TM, Department of B, Molecular Biophysics Thomas J, Siegelbaum S, et al. Principles of neural science: McGraw-hill New York; 2000.
28.       Gheisarnejad M, Boudjadar J, Khooban M-H. A new adaptive type-II fuzzy-based deep reinforcement learning control: fuel cell air-feed sensors control. IEEE Sensors Journal. 2019;19(20):9081-9.
29.       Khooban MH, Gheisarnejad M. A Novel Deep Reinforcement Learning Controller Based Type-II Fuzzy System: Frequency Regulation in Microgrids. IEEE Transactions on Emerging Topics in Computational Intelligence. 2020.
30.       Faraji B, Esfahani Z, Rouhollahi K, Khezri D. Optimal Canceling of the Physiological Tremor for Rehabilitation in Parkinson’s disease. Journal of Exercise Science and Medicine. 2019;11(2):-.
31.       Faraji B, Gheisarnejad M, Esfahani Z, Khooban M-H. Smart Sensor Control for Rehabilitation in Parkinson's Patients. IEEE Transactions on Emerging Topics in Computational Intelligence. 2021.