Ali Foroutannia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Ali Foroutannia has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Mahdieh Ghasemi
Neural Engineering Laboratory, Department of Biomedical Engineering, University of Neyshabur, Neyshabur, Iran
6 shared publications - Masoud Mohammadian
Faculty of Science and Technology, University of Canberra, Canberra, ACT 2617, Australia
3 shared publications - Sajad Jafari
Department of Biomedical Engineering, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran
2 shared publications - Abbas Babajani-Feremi
Department of Neurology, University of Florida, Gainesville, FL, USA (Ahmadi B, Babajani-Feremi A)
1 shared publication - Afshin Shoeibi
Data Science and Computational Intelligence Institute, University of Granada, Spain
1 shared publication - Alireza Mirzajani
Inland Waters Aquaculture Research Center
1 shared publication
Latest Publications
- Open Access
Adaptive Control of Lower-Limb Assistive Exoskeleton for Rehabilitation Using Deep Reinforcement Learning
Lower-limb rehabilitation exoskeletons have the potential to improve gait recovery after stroke by providing intensive and repetitive training. However, conventional control strategies often rely on fixed control parameters and exhibit limited adaptability to patient-specific characteristics, sensor noise, and dynamic uncertainties. This paper proposes an adaptive control framework that combines deep reinforcement learning (RL) with model-based impedance control for personalised lower-limb exoskeleton assistance. Patient-specific biological parameters are incorporated into the simulation environment and reward formulation to improve adaptability and robustness. Three state-of-the-art deep RL algorithms, Deep Deterministic Policy Gradient (DDPG), Twin Delayed Deep Deterministic Policy Gradient (TD3), and Soft Actor-Critic (SAC), are evaluated in a continuous control environment under varying signal-to-noise ratio (SNR) conditions ranging from 5 dB to noise-free conditions. Results demonstrate that TD3 achieves the most stable learning performance, obtaining a mean reward of −354.24 under noise-free conditions, while DDPG provides the highest joint-angle tracking accuracy with an RMSE of 0.0369 rad. SAC exhibits superior robustness in noisy environments, achieving the highest learning ratio of 0.51 at 5 dB SNR. Furthermore, the proposed personalised framework reduces tracking errors by up to 27% compared with non-personalised baseline approaches. The findings indicate that integrating patient-specific information with RL-based adaptive control can significantly enhance robustness, tracking performance, and personalisation in exoskeleton-assisted gait rehabilitation, providing a promising direction for future intelligent rehabilitation systems.
Open AccessAdaptive Control of Lower-Limb Assistive Exoskeleton for Rehabilitation Using Deep Reinforcement Learning
Lower-limb rehabilitation exoskeletons have the potential to improve gait recovery after stroke by providing intensive and repetitive training. However, conventional control strategies often rely on fixed control parameters and exhibit limited adaptability to patient-specific characteristics, sensor noise, and dynamic uncertainties. This paper proposes an adaptive control framework that combines deep reinforcement learning (RL) with model-based impedance control for personalised lower-limb exoskeleton assistance. Patient-specific biological parameters are incorporated into the simulation environment and reward formulation to improve adaptability and robustness. Three state-of-the-art deep RL algorithms, Deep Deterministic Policy Gradient (DDPG), Twin Delayed Deep Deterministic Policy Gradient (TD3), and Soft Actor-Critic (SAC), are evaluated in a continuous control environment under varying signal-to-noise ratio (SNR) conditions ranging from 5 dB to noise-free conditions. Results demonstrate that TD3 achieves the most stable learning performance, obtaining a mean reward of −354.24 under noise-free conditions, while DDPG provides the highest joint-angle tracking accuracy with an RMSE of 0.0369 rad. SAC exhibits superior robustness in noisy environments, achieving the highest learning ratio of 0.51 at 5 dB SNR. Furthermore, the proposed personalised framework reduces tracking errors by up to 27% compared with non-personalised baseline approaches. The findings indicate that integrating patient-specific information with RL-based adaptive control can significantly enhance robustness, tracking performance, and personalisation in exoskeleton-assisted gait rehabilitation, providing a promising direction for future intelligent rehabilitation systems.
- Open Access
- 11 February 2026
- Published by Elsevier in Information Sciences
- Vol. 741
Advancing autonomous driving systems: A 3-dimensional U-Net framework for object detection via fusion of camera and LiDAR sensors
- 11 February 2026
- Published by Elsevier in Information Sciences
- Vol. 741
Open AccessAdvancing autonomous driving systems: A 3-dimensional U-Net framework for object detection via fusion of camera and LiDAR sensors
- 17 October 2025
- Published by Elsevier in Robotics and Autonomous Systems
- Vol. 195
A comprehensive survey of lower limb assistive exoskeleton robots: Models, dynamics, mechanics, and control
- 17 October 2025
- Published by Elsevier in Robotics and Autonomous Systems
- Vol. 195
A comprehensive survey of lower limb assistive exoskeleton robots: Models, dynamics, mechanics, and control
- 26 March 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Bifurcation and Chaos
- Vol. 35 (06)
Investigating the Relationship Between Tumor Cells, Healthy Tissue, and an Active Immune System in a Mathematical Model of Cancer Cell Growth
Analyzing tumor growth dynamics improves treatment strategies for cancer. Many models have been proposed to analyze cancer development dynamics, which do not always exhibit chaotic behavior. This research aims to create and examine a unique dynamical cancer model that exhibits chaotic behavior for certain parameters. Introducing chaos into the model allows for the exploration of irregular tumor growth patterns and the identification of critical thresholds that can influence treatment outcomes. The model is examined, and each system parameter’s impact on the model’s dynamics is evaluated. The analysis of the bifurcation and Lyapunov diagrams demonstrates chaos in three populations of tumor, healthy, and immune system cells. By suppressing the immunological response, the cancer cell gains control of the chaotic attractor and establishes a stable state. This might lower the cancer condition by altering the appropriate parameter range assisting in tumor treatment.
- 26 March 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Bifurcation and Chaos
- Vol. 35 (06)
Investigating the Relationship Between Tumor Cells, Healthy Tissue, and an Active Immune System in a Mathematical Model of Cancer Cell Growth
Analyzing tumor growth dynamics improves treatment strategies for cancer. Many models have been proposed to analyze cancer development dynamics, which do not always exhibit chaotic behavior. This research aims to create and examine a unique dynamical cancer model that exhibits chaotic behavior for certain parameters. Introducing chaos into the model allows for the exploration of irregular tumor growth patterns and the identification of critical thresholds that can influence treatment outcomes. The model is examined, and each system parameter’s impact on the model’s dynamics is evaluated. The analysis of the bifurcation and Lyapunov diagrams demonstrates chaos in three populations of tumor, healthy, and immune system cells. By suppressing the immunological response, the cancer cell gains control of the chaotic attractor and establishes a stable state. This might lower the cancer condition by altering the appropriate parameter range assisting in tumor treatment.
- Open Access
- 8 September 2024
- Published by MDPI AG in Biomimetics
- Vol. 9 (9) , 543
Dynamic Effects Analysis in Fractional Memristor-Based Rulkov Neuron Model
Mathematical models such as Fitzhugh–Nagoma and Hodgkin–Huxley models have been used to understand complex nervous systems. Still, due to their complexity, these models have made it challenging to analyze neural function. The discrete Rulkov model allows the analysis of neural function to facilitate the investigation of neuronal dynamics or others. This paper introduces a fractional memristor Rulkov neuron model and analyzes its dynamic effects, investigating how to improve neuron models by combining discrete memristors and fractional derivatives. These improvements include the more accurate generation of heritable properties compared to full-order models, the treatment of dynamic firing activity at multiple time scales for a single neuron, and the better performance of firing frequency responses in fractional designs compared to integer models. Initially, we combined a Rulkov neuron model with a memristor and evaluated all system parameters using bifurcation diagrams and the 0–1 chaos test. Subsequently, we applied a discrete fractional-order approach to the Rulkov memristor map. We investigated the impact of all parameters and the fractional order on the model and observed that the system exhibited various behaviors, including tonic firing, periodic firing, and chaotic firing. We also found that the more I tend towards the correct order, the more chaotic modes in the range of parameters. Following this, we coupled the proposed model with a similar one and assessed how the fractional order influences synchronization. Our results demonstrated that the fractional order significantly improves synchronization. The results of this research emphasize that the combination of memristor and discrete neurons provides an effective tool for modeling and estimating biophysical effects in neurons and artificial neural networks.
- 8 September 2024
- Published by MDPI AG in Biomimetics
- Vol. 9 (9) , 543
Open AccessDynamic Effects Analysis in Fractional Memristor-Based Rulkov Neuron Model
Mathematical models such as Fitzhugh–Nagoma and Hodgkin–Huxley models have been used to understand complex nervous systems. Still, due to their complexity, these models have made it challenging to analyze neural function. The discrete Rulkov model allows the analysis of neural function to facilitate the investigation of neuronal dynamics or others. This paper introduces a fractional memristor Rulkov neuron model and analyzes its dynamic effects, investigating how to improve neuron models by combining discrete memristors and fractional derivatives. These improvements include the more accurate generation of heritable properties compared to full-order models, the treatment of dynamic firing activity at multiple time scales for a single neuron, and the better performance of firing frequency responses in fractional designs compared to integer models. Initially, we combined a Rulkov neuron model with a memristor and evaluated all system parameters using bifurcation diagrams and the 0–1 chaos test. Subsequently, we applied a discrete fractional-order approach to the Rulkov memristor map. We investigated the impact of all parameters and the fractional order on the model and observed that the system exhibited various behaviors, including tonic firing, periodic firing, and chaotic firing. We also found that the more I tend towards the correct order, the more chaotic modes in the range of parameters. Following this, we coupled the proposed model with a similar one and assessed how the fractional order influences synchronization. Our results demonstrated that the fractional order significantly improves synchronization. The results of this research emphasize that the combination of memristor and discrete neurons provides an effective tool for modeling and estimating biophysical effects in neurons and artificial neural networks.
- 1 April 2024
- Published by SAGE Publications in Brain Connectivity
- Vol. 14 (3) , 189-197
Characterizing the Visual Cortex Function in Cognitive Task-Induced Mental Load: An Functional Magnetic Resonance Imaging Study
Introduction: The mental load caused by simultaneous multitasks can affect visual information processing and reduce its ability. This study investigated the effect of mental load caused by cognitive tasks simultaneously with visual task on the number of active voxels in the visual cortex. Methods: This study recruited 22 individuals with a mean age of 24.72±5.47 years. 3 Tesla functional MRI (fMRI) was used to examine the functions of visual cortex and amygdala region during three different task conditions: visual task alone, visual task with an auditory n-back task, and visual task with an arithmetic task. The visual stimuli consisted of Gabor patches with a contrast of 55% at spatial frequencies of 0.25, 4, and 9 cycles per degree (cpd). These were presented in three trials of eight blocks with a stimulation time of 12 and a rest time of 14 milliseconds. Results: Activated brain voxels in the primary, secondary, and associated visual cortex areas were reduced in response to the mental load imposed by the n-back and arithmetic task. This reduction was greater for spatial frequency of 0.25 cpd in n-back task condition and for spatial frequency of 9 cpd in the arithmetic task condition. Also, the amygdala was stimulated in 2-back task and arithmetic task conditions. Conclusion: This study revealed a decline in the number of activated voxels of the visual cortex due to the mental load caused by simultaneous cognitive tasks, confirming the findings of previous psychophysical studies.
- 1 April 2024
- Published by SAGE Publications in Brain Connectivity
- Vol. 14 (3) , 189-197
Characterizing the Visual Cortex Function in Cognitive Task-Induced Mental Load: An Functional Magnetic Resonance Imaging Study
Introduction: The mental load caused by simultaneous multitasks can affect visual information processing and reduce its ability. This study investigated the effect of mental load caused by cognitive tasks simultaneously with visual task on the number of active voxels in the visual cortex. Methods: This study recruited 22 individuals with a mean age of 24.72±5.47 years. 3 Tesla functional MRI (fMRI) was used to examine the functions of visual cortex and amygdala region during three different task conditions: visual task alone, visual task with an auditory n-back task, and visual task with an arithmetic task. The visual stimuli consisted of Gabor patches with a contrast of 55% at spatial frequencies of 0.25, 4, and 9 cycles per degree (cpd). These were presented in three trials of eight blocks with a stimulation time of 12 and a rest time of 14 milliseconds. Results: Activated brain voxels in the primary, secondary, and associated visual cortex areas were reduced in response to the mental load imposed by the n-back and arithmetic task. This reduction was greater for spatial frequency of 0.25 cpd in n-back task condition and for spatial frequency of 9 cpd in the arithmetic task condition. Also, the amygdala was stimulated in 2-back task and arithmetic task conditions. Conclusion: This study revealed a decline in the number of activated voxels of the visual cortex due to the mental load caused by simultaneous cognitive tasks, confirming the findings of previous psychophysical studies.
- 4 February 2023
- Published by Springer Nature in Nonlinear Dynamics
- Vol. 111 (9) , 8713-8736
Predicting cortical oscillations with bidirectional LSTM network: a simulation study
- 4 February 2023
- Published by Springer Nature in Nonlinear Dynamics
- Vol. 111 (9) , 8713-8736
Predicting cortical oscillations with bidirectional LSTM network: a simulation study
- 17 October 2022
- Published by Elsevier in Journal of Theoretical Biology
- Vol. 556, 111311
A PID controller for synchronization between master-slave neurons in fractional-order of neocortical network model
- 17 October 2022
- Published by Elsevier in Journal of Theoretical Biology
- Vol. 556, 111311
A PID controller for synchronization between master-slave neurons in fractional-order of neocortical network model
- 15 July 2021
- Published by Elsevier in Journal of Theoretical Biology
- Vol. 528, 110837
Chaos in memory function of sleep: A nonlinear dynamical analysis in thalamocortical study
- 15 July 2021
- Published by Elsevier in Journal of Theoretical Biology
- Vol. 528, 110837
Chaos in memory function of sleep: A nonlinear dynamical analysis in thalamocortical study