Amir Abolfazl Suratgar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Amir Abolfazl Suratgar has a total of 89 co-authors. Here are the top co-authors by number of shared publications:
- Mohammad Bagher Menhaj
Department of Electrical Engineering, Amirkabir University of Technology, Tehran, Iran
14 shared publications Mohammad Bagher Menhaj
6 shared publications- Ehsan Ranjbar
MEMS Dynamics and Control Research Group, Industrial Control Lab, Department of Electrical Engineering, Amirkabir University of Technology, Tehran, Iran
5 shared publications - Heidar Ali Talebi
Department of Electrical Engineering, Amirkabir University of Technology, Tehran, Iran
5 shared publications - Mohsen Zamani
School of Electrical Engineering and Computing, University of Newcastle, Callaghan, NSW, Australia
5 shared publications Amir Adibzadeh
Electrical Engineering Department, Amirkabir University of Technology, Tehran, Iran
4 shared publications
Latest Publications
- Open Access
- 21 August 2026
- Published by Elsevier in SSRN Electronic Journal
Data-Driven Multi-Objective Optimization for Dynamic Combined Economic Emission Dispatch (CEED): Application of the OCA and Benchmarking of Metaheuristic Algorithms
This paper employs the Olympic Champion Algorithm (OCA), a novel metaheuristic inspired by the transformation of an ordinary individual into an elite Olympic athlete, to solve the Combined Economic Emission Dispatch (CEED) problem. Enhancing power system performance while reducing environmental impacts is a strategic priority in sustainable energy operations. The CEED problem, central to this objective, directly influences both economic efficiency and ecological responsibility. Even slight improvements in solution quality can result in significant operational cost saving. Given the complexity, non-convexity, and high-dimensional nature of the CEED problem—especially in the presence of constraints such as Prohibited Operating Zones (POZ) and Valve Point Loading (VPL)—metaheuristic algorithms have emerged as effective and scalable approaches. We evaluate the performance of OCA on CEED by benchmarking it against 23 state-of-the-art and widely cited optimization algorithms. Simulation results show that OCA consistently outperforms its counterparts across various evaluation metrics, confirming its robustness and superior optimization capabilities for dynamic CEED problems. The proposed method effectively addresses common CEED constraints, demonstrating strong convergence behavior and high solution accuracy.
- 21 August 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessData-Driven Multi-Objective Optimization for Dynamic Combined Economic Emission Dispatch (CEED): Application of the OCA and Benchmarking of Metaheuristic Algorithms
This paper employs the Olympic Champion Algorithm (OCA), a novel metaheuristic inspired by the transformation of an ordinary individual into an elite Olympic athlete, to solve the Combined Economic Emission Dispatch (CEED) problem. Enhancing power system performance while reducing environmental impacts is a strategic priority in sustainable energy operations. The CEED problem, central to this objective, directly influences both economic efficiency and ecological responsibility. Even slight improvements in solution quality can result in significant operational cost saving. Given the complexity, non-convexity, and high-dimensional nature of the CEED problem—especially in the presence of constraints such as Prohibited Operating Zones (POZ) and Valve Point Loading (VPL)—metaheuristic algorithms have emerged as effective and scalable approaches. We evaluate the performance of OCA on CEED by benchmarking it against 23 state-of-the-art and widely cited optimization algorithms. Simulation results show that OCA consistently outperforms its counterparts across various evaluation metrics, confirming its robustness and superior optimization capabilities for dynamic CEED problems. The proposed method effectively addresses common CEED constraints, demonstrating strong convergence behavior and high solution accuracy.
- Open Access
- 7 July 2026
- Published by Elsevier in SSRN Electronic Journal
Bus-Level Distributed Optimization for Multi-Period Multi-Objective AC Optimal Power Flow(MPMO-ACOPF) with Energy Storage System (ESS) Dynamics
In recent years, extensive research has been conducted on power system op-timization, especially with new tools such as energy storage systems (ESS),flexible distributed generation (FDG), and many other emerging tools. Thecurrent study mainly focuses on the effective utilization of ESS. We presenta novel formulation of the Multi-Period Multi-Objective AC Optimal PowerFlow (MPMO-ACOPF) problem that effectively incorporates the energystorage system (ESS) state of charge (SOC) dynamics. The inherently non-convex nature of the problem is addressed using a distributed optimizationbased on the saddle-point theorem approach. We reformulate the MPMO-ACOPF problem as a Gradient Dynamical System (GDS) by deriving theLagrangian function. Certain conditions exist in which the equilibrium pointof the proposed GDS corresponds to a saddle point of the Lagrangian, ensur-ing that the GDS converges to this point, representing a Karush-Kuhn-Tucker(KKT) solution. Consequently, the duality gap will be equal to zero. Theproposed method is validated through simulations on modified IEEE 14-, 30-,and 57-bus systems under time-varying load conditions.
- 7 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessBus-Level Distributed Optimization for Multi-Period Multi-Objective AC Optimal Power Flow(MPMO-ACOPF) with Energy Storage System (ESS) Dynamics
In recent years, extensive research has been conducted on power system op-timization, especially with new tools such as energy storage systems (ESS),flexible distributed generation (FDG), and many other emerging tools. Thecurrent study mainly focuses on the effective utilization of ESS. We presenta novel formulation of the Multi-Period Multi-Objective AC Optimal PowerFlow (MPMO-ACOPF) problem that effectively incorporates the energystorage system (ESS) state of charge (SOC) dynamics. The inherently non-convex nature of the problem is addressed using a distributed optimizationbased on the saddle-point theorem approach. We reformulate the MPMO-ACOPF problem as a Gradient Dynamical System (GDS) by deriving theLagrangian function. Certain conditions exist in which the equilibrium pointof the proposed GDS corresponds to a saddle point of the Lagrangian, ensur-ing that the GDS converges to this point, representing a Karush-Kuhn-Tucker(KKT) solution. Consequently, the duality gap will be equal to zero. Theproposed method is validated through simulations on modified IEEE 14-, 30-,and 57-bus systems under time-varying load conditions.
- Open Access
- 18 September 2025
- Published by Springer Nature in Research Square
Olympic Champion Algorithm (OCA): A new human-inspired metaheuristic algorithm for solving optimization problems
The complexity and computational demands of many optimization challenges have led to the rise and advancement of metaheuristic algorithms. These methods offer intelligent approaches for optimization, utilizing a structured and iterative process to search the solution space effectively. In this paper, we introduce a novel metaheuristic approach known as the Olympic Champion Algorithm (OCA), inspired by human behavior. The fundamental idea behind OCA is inspired by the structured process of transforming an ordinary human into an Olympic champion athlete. This inspiration is drawn from the structure of talent discovery, Coaching and Training, Local Competitions, Global Ambitions and Olympic quota, Social Support, Close Competitions, Resilience and Persistence and Intelligent Analysis of Opponents in Finals employed to choose the champion of each iteration. The implementation stages of OCA are modeled mathematically in three phases: population generation and exploration, exploitation, and description. "The performance of the proposed OCA was evaluated on 140 challenging benchmark functions and 15 well-known engineering design problems. The convergence curves and statistical data were compared with 22 highly cited optimization algorithms. Statistical validation was carried out using the Wilcoxon and Friedman tests. The results demonstrate that the OCA is one of the most powerful and effective metaheuristic optimization algorithms for various problems and applications, highlighting its distinctiveness. The article clearly presents the OCA algorithm, which uses a novel and effective solution update formula to achieve impressive results, and emphasizes its potential to advance future metaheuristic algorithms.
- 18 September 2025
- Published by Springer Nature in Research Square
Open AccessOlympic Champion Algorithm (OCA): A new human-inspired metaheuristic algorithm for solving optimization problems
The complexity and computational demands of many optimization challenges have led to the rise and advancement of metaheuristic algorithms. These methods offer intelligent approaches for optimization, utilizing a structured and iterative process to search the solution space effectively. In this paper, we introduce a novel metaheuristic approach known as the Olympic Champion Algorithm (OCA), inspired by human behavior. The fundamental idea behind OCA is inspired by the structured process of transforming an ordinary human into an Olympic champion athlete. This inspiration is drawn from the structure of talent discovery, Coaching and Training, Local Competitions, Global Ambitions and Olympic quota, Social Support, Close Competitions, Resilience and Persistence and Intelligent Analysis of Opponents in Finals employed to choose the champion of each iteration. The implementation stages of OCA are modeled mathematically in three phases: population generation and exploration, exploitation, and description. "The performance of the proposed OCA was evaluated on 140 challenging benchmark functions and 15 well-known engineering design problems. The convergence curves and statistical data were compared with 22 highly cited optimization algorithms. Statistical validation was carried out using the Wilcoxon and Friedman tests. The results demonstrate that the OCA is one of the most powerful and effective metaheuristic optimization algorithms for various problems and applications, highlighting its distinctiveness. The article clearly presents the OCA algorithm, which uses a novel and effective solution update formula to achieve impressive results, and emphasizes its potential to advance future metaheuristic algorithms.
- 30 August 2025
- Published by Elsevier in Measurement
- Vol. 257
Detection of driver maneuvers using a modular, low-cost sensor device
- 30 August 2025
- Published by Elsevier in Measurement
- Vol. 257
Detection of driver maneuvers using a modular, low-cost sensor device
- Open Access
Probing Multimodal Fusion in the Brain: The Dominance of Audiovisual Streams in Naturalistic Encoding
Predicting brain activity in response to naturalistic, multimodal stimuli is a key challenge in computational neuroscience. While encoding models are becoming more powerful, their ability to generalize to truly novel contexts remains a critical, often untested, question. In this work, we developed brain encoding models using state-of-the-art visual (X-CLIP) and auditory (Whisper) feature extractors and rigorously evaluated them on both in-distribution (ID) and diverse out-of-distribution (OOD) data. Our results reveal a fundamental trade-off between model complexity and generalization: a higher-capacity attention-based model excelled on ID data, but a simpler linear model was more robust, outperforming a competitive baseline by 18\% on the OOD set. Intriguingly, we found that linguistic features did not improve predictive accuracy, suggesting that for familiar languages, neural encoding may be dominated by the continuous visual and auditory streams over redundant textual information. Spatially, our approach showed marked performance gains in the auditory cortex, underscoring the benefit of high-fidelity speech representations. Collectively, our findings demonstrate that rigorous OOD testing is essential for building robust neuro-AI models and provides nuanced insights into how model architecture, stimulus characteristics, and sensory hierarchies shape the neural encoding of our rich, multimodal world.
Open AccessProbing Multimodal Fusion in the Brain: The Dominance of Audiovisual Streams in Naturalistic Encoding
Predicting brain activity in response to naturalistic, multimodal stimuli is a key challenge in computational neuroscience. While encoding models are becoming more powerful, their ability to generalize to truly novel contexts remains a critical, often untested, question. In this work, we developed brain encoding models using state-of-the-art visual (X-CLIP) and auditory (Whisper) feature extractors and rigorously evaluated them on both in-distribution (ID) and diverse out-of-distribution (OOD) data. Our results reveal a fundamental trade-off between model complexity and generalization: a higher-capacity attention-based model excelled on ID data, but a simpler linear model was more robust, outperforming a competitive baseline by 18\% on the OOD set. Intriguingly, we found that linguistic features did not improve predictive accuracy, suggesting that for familiar languages, neural encoding may be dominated by the continuous visual and auditory streams over redundant textual information. Spatially, our approach showed marked performance gains in the auditory cortex, underscoring the benefit of high-fidelity speech representations. Collectively, our findings demonstrate that rigorous OOD testing is essential for building robust neuro-AI models and provides nuanced insights into how model architecture, stimulus characteristics, and sensory hierarchies shape the neural encoding of our rich, multimodal world.
- Open Access
- 19 February 2025
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 21 (2) , e1012822
Compression-enabled interpretability of voxelwise encoding models
Voxelwise encoding models based on convolutional neural networks (CNNs) are widely used as predictive models of brain activity evoked by natural movies. Despite their superior predictive performance, the huge number of parameters in CNN-based models have made them difficult to interpret. Here, we investigate whether model compression can build more interpretable and more stable CNN-based voxelwise models while maintaining accuracy. We used multiple compression techniques to prune less important CNN filters and connections, a receptive field compression method to select receptive fields with optimal center and size, and principal component analysis to reduce dimensionality. We demonstrate that the model compression improves the accuracy of identifying visual stimuli in a hold-out test set. Additionally, compressed models offer a more stable interpretation of voxelwise pattern selectivity than uncompressed models. Finally, the receptive field-compressed models reveal that the optimal model-based population receptive fields become larger and more centralized along the ventral visual pathway. Overall, our findings support using model compression to build more interpretable voxelwise models.
- 19 February 2025
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 21 (2) , e1012822
Open AccessCompression-enabled interpretability of voxelwise encoding models
Voxelwise encoding models based on convolutional neural networks (CNNs) are widely used as predictive models of brain activity evoked by natural movies. Despite their superior predictive performance, the huge number of parameters in CNN-based models have made them difficult to interpret. Here, we investigate whether model compression can build more interpretable and more stable CNN-based voxelwise models while maintaining accuracy. We used multiple compression techniques to prune less important CNN filters and connections, a receptive field compression method to select receptive fields with optimal center and size, and principal component analysis to reduce dimensionality. We demonstrate that the model compression improves the accuracy of identifying visual stimuli in a hold-out test set. Additionally, compressed models offer a more stable interpretation of voxelwise pattern selectivity than uncompressed models. Finally, the receptive field-compressed models reveal that the optimal model-based population receptive fields become larger and more centralized along the ventral visual pathway. Overall, our findings support using model compression to build more interpretable voxelwise models.
- 6 October 2024
- Published by Springer Nature in Journal of Optimization Theory and Applications
- Vol. 203 (1) , 1054-1082
Data-Driven Distributed Optimal Control Using Neighbourhood Optimization for Nonlinear Interconnected Systems
- 6 October 2024
- Published by Springer Nature in Journal of Optimization Theory and Applications
- Vol. 203 (1) , 1054-1082
Data-Driven Distributed Optimal Control Using Neighbourhood Optimization for Nonlinear Interconnected Systems
- Open Access
Enhancing Human Action Recognition and Violence Detection Through Deep Learning Audiovisual Fusion
This paper proposes a hybrid fusion-based deep learning approach based on two different modalities, audio and video, to improve human activity recognition and violence detection in public places. To take advantage of audiovisual fusion, late fusion, intermediate fusion, and hybrid fusion-based deep learning (HFBDL) are used and compared. Since the objective is to detect and recognize human violence in public places, Real-life violence situation (RLVS) dataset is expanded and used. Simulating results of HFBDL show 96.67\% accuracy on validation data, which is more accurate than the other state-of-the-art methods on this dataset. To showcase our model's ability in real-world scenarios, another dataset of 54 sounded videos of both violent and non-violent situations was recorded. The model could successfully detect 52 out of 54 videos correctly. The proposed method shows a promising performance on real scenarios. Thus, it can be used for human action recognition and violence detection in public places for security purposes.
Open AccessEnhancing Human Action Recognition and Violence Detection Through Deep Learning Audiovisual Fusion
This paper proposes a hybrid fusion-based deep learning approach based on two different modalities, audio and video, to improve human activity recognition and violence detection in public places. To take advantage of audiovisual fusion, late fusion, intermediate fusion, and hybrid fusion-based deep learning (HFBDL) are used and compared. Since the objective is to detect and recognize human violence in public places, Real-life violence situation (RLVS) dataset is expanded and used. Simulating results of HFBDL show 96.67\% accuracy on validation data, which is more accurate than the other state-of-the-art methods on this dataset. To showcase our model's ability in real-world scenarios, another dataset of 54 sounded videos of both violent and non-violent situations was recorded. The model could successfully detect 52 out of 54 videos correctly. The proposed method shows a promising performance on real scenarios. Thus, it can be used for human action recognition and violence detection in public places for security purposes.
- Open Access
- 26 July 2024
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 21 (4) , 046027
Structurally-constrained encoding framework using a multi-voxel reduced-rank latent model for human natural vision
Objective. Voxel-wise visual encoding models based on convolutional neural networks (CNNs) have emerged as one of the prominent predictive tools of human brain activity via functional magnetic resonance imaging signals. While CNN-based models imitate the hierarchical structure of the human visual cortex to generate explainable features in response to natural visual stimuli, there is still a need for a brain-inspired model to predict brain responses accurately based on biomedical data. Approach. To bridge this gap, we propose a response prediction module called the Structurally Constrained Multi-Output (SCMO) module to include homologous correlations that arise between a group of voxels in a cortical region and predict more accurate responses. Main results. This module employs all the responses across a visual area to predict individual voxel-wise BOLD responses and therefore accounts for the population activity and collective behavior of voxels. Such a module can determine the relationships within each visual region by creating a structure matrix that represents the underlying voxel-to-voxel interactions. Moreover, since each response module in visual encoding tasks relies on the image features, we conducted experiments using two different feature extraction modules to assess the predictive performance of our proposed module. Specifically, we employed a recurrent CNN that integrates both feedforward and recurrent interactions, as well as the popular AlexNet model that utilizes feedforward connections. Significance. We demonstrate that the proposed framework provides a reliable predictive ability to generate brain responses across multiple areas, outperforming benchmark models in terms of stability and coherency of features.
- 26 July 2024
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 21 (4) , 046027
Open AccessStructurally-constrained encoding framework using a multi-voxel reduced-rank latent model for human natural vision
Objective. Voxel-wise visual encoding models based on convolutional neural networks (CNNs) have emerged as one of the prominent predictive tools of human brain activity via functional magnetic resonance imaging signals. While CNN-based models imitate the hierarchical structure of the human visual cortex to generate explainable features in response to natural visual stimuli, there is still a need for a brain-inspired model to predict brain responses accurately based on biomedical data. Approach. To bridge this gap, we propose a response prediction module called the Structurally Constrained Multi-Output (SCMO) module to include homologous correlations that arise between a group of voxels in a cortical region and predict more accurate responses. Main results. This module employs all the responses across a visual area to predict individual voxel-wise BOLD responses and therefore accounts for the population activity and collective behavior of voxels. Such a module can determine the relationships within each visual region by creating a structure matrix that represents the underlying voxel-to-voxel interactions. Moreover, since each response module in visual encoding tasks relies on the image features, we conducted experiments using two different feature extraction modules to assess the predictive performance of our proposed module. Specifically, we employed a recurrent CNN that integrates both feedforward and recurrent interactions, as well as the popular AlexNet model that utilizes feedforward connections. Significance. We demonstrate that the proposed framework provides a reliable predictive ability to generate brain responses across multiple areas, outperforming benchmark models in terms of stability and coherency of features.
- 1 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Systems Journal
- Vol. 18 (3) , 1570-1580
Heterogeneous Unknown Multiagent Systems of Different Relative Degrees: A Distributed Optimal Coordination Design
This study delves into the distributed optimal coordination (DOC) problem, where a network comprises agents with different relative degrees. Each agent is equipped with a private cost function. The goal is to steer these agents towards minimizing the global cost function, which aggregates their individual costs. Existing literature often leans on known agent dynamics, which may not faithfully represent real-world scenarios. To bridge this gap, we delve into the DOC problem within a network of linear time-invariant (LTI) agents, where the system matrices remain entirely unknown. Our proposed solution introduces a novel distributed two-layer control policy: the top layer endeavors to find the minimizer and generates tailored reference signals for each agent, while the bottom layer equips each agent with an adaptive controller to track these references. Key assumptions include strongly convex private cost functions with local Lipschitz gradients. Under these conditions, our control policy guarantees asymptotic consensus on the global minimizer within the network. Moreover, the control policy operates fully distributedly, relying solely on private and neighbor information for execution. Theoretical insights are substantiated through simulations, encompassing both numerical and practical examples involving speed control of a multimotor network, thereby affirming the efficacy of our approach in practical settings.
- 1 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Systems Journal
- Vol. 18 (3) , 1570-1580
Heterogeneous Unknown Multiagent Systems of Different Relative Degrees: A Distributed Optimal Coordination Design
This study delves into the distributed optimal coordination (DOC) problem, where a network comprises agents with different relative degrees. Each agent is equipped with a private cost function. The goal is to steer these agents towards minimizing the global cost function, which aggregates their individual costs. Existing literature often leans on known agent dynamics, which may not faithfully represent real-world scenarios. To bridge this gap, we delve into the DOC problem within a network of linear time-invariant (LTI) agents, where the system matrices remain entirely unknown. Our proposed solution introduces a novel distributed two-layer control policy: the top layer endeavors to find the minimizer and generates tailored reference signals for each agent, while the bottom layer equips each agent with an adaptive controller to track these references. Key assumptions include strongly convex private cost functions with local Lipschitz gradients. Under these conditions, our control policy guarantees asymptotic consensus on the global minimizer within the network. Moreover, the control policy operates fully distributedly, relying solely on private and neighbor information for execution. Theoretical insights are substantiated through simulations, encompassing both numerical and practical examples involving speed control of a multimotor network, thereby affirming the efficacy of our approach in practical settings.