Sehraneh Ghaemi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sehraneh Ghaemi has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Mohammad Ali Badamchizadeh
Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran
21 shared publications - Amir Rikhtehgar Ghiasi
Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran
5 shared publications - Reza Behinfaraz
Faculty of Electrical and Computer Engineering, Urmia University, Urmia 57561-51818, Iran
5 shared publications - Ardashir Mohammadzadeh
Faculty of Engineering, Department of Electrical and Electronics Engineering Sakarya University Sakarya Turkiye
4 shared publications - Alessandro Del Vecchio
Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität erlangen-Nürnberg, Erlangen, Germany
3 shared publications - Amir Arslan Haghrah
Faculty of Electrical and Computer Engineering University of Tabriz Tabriz Iran
3 shared publications
Latest Publications
- Open Access
- 28 October 2026
- Published by Elsevier in Decision Analytics Journal
- Vol. 21
A Hybrid Fuzzy Clustering and Neuro-Fuzzy Analytics Framework for Chronic Kidney Disease Decision Support
- 28 October 2026
- Published by Elsevier in Decision Analytics Journal
- Vol. 21
Open AccessA Hybrid Fuzzy Clustering and Neuro-Fuzzy Analytics Framework for Chronic Kidney Disease Decision Support
- Open Access
- 13 October 2026
- Published by Elsevier in Results in Control and Optimization
- Vol. 25
Deep reinforcement learning-based robust control of an H-bridge RLC inverter under chaotic dynamics
- 13 October 2026
- Published by Elsevier in Results in Control and Optimization
- Vol. 25
Open AccessDeep reinforcement learning-based robust control of an H-bridge RLC inverter under chaotic dynamics
- 21 July 2026
- Published by Springer Nature in International Journal of Dynamics and Control
- Vol. 14 (8) , 292
Neural Network-Based Adaptive Sliding Mode Leader-Following Consensus with Unknown External Disturbances and Output Constraints
- 21 July 2026
- Published by Springer Nature in International Journal of Dynamics and Control
- Vol. 14 (8) , 292
Neural Network-Based Adaptive Sliding Mode Leader-Following Consensus with Unknown External Disturbances and Output Constraints
- Open Access
- 12 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 79400-79410
Simultaneous Control of Human Hand Joint Positions and Grip Force via HD-sEMG and Deep Learning
In myoelectric control, simultaneous control of multiple degrees of freedom can be challenging due to the dexterity of the human hand. Numerous studies have focused on hand functionality, however, they only focused on a few degrees of freedom. In this paper, a 3DCNN-MLP model is proposed that uses high-density sEMG signals to estimate 20 hand joint positions and grip force simultaneously. The deep learning model maps the muscle activity to the hand kinematics and kinetics. The proposed models’ performance is also evaluated in estimating grip forces with real-time resolution. This paper investigated three individual dynamic hand movements (2pinch, 3pinch, and fist closing and opening) while applying forces in 10% and 30% of the maximum voluntary contraction (MVC). The results demonstrated high accuracy in estimating kinetics and kinematics. The average Euclidean distance across all joints and subjects was 11.01 ± 2.22 mm and the normalized root mean square error for offline and real-time force estimation were found to be 2.17 ± 0.79 %MVC and 5.10 ± 1.81 %MVC respectively. The results demonstrated that by leveraging high-density sEMG and deep learning, it is possible to estimate human hand dynamics (kinematics and kinetics), which is a step toward developing more accurate systems for controlling prosthetic devices and assistive technologies.
- 12 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 79400-79410
Open AccessSimultaneous Control of Human Hand Joint Positions and Grip Force via HD-sEMG and Deep Learning
In myoelectric control, simultaneous control of multiple degrees of freedom can be challenging due to the dexterity of the human hand. Numerous studies have focused on hand functionality, however, they only focused on a few degrees of freedom. In this paper, a 3DCNN-MLP model is proposed that uses high-density sEMG signals to estimate 20 hand joint positions and grip force simultaneously. The deep learning model maps the muscle activity to the hand kinematics and kinetics. The proposed models’ performance is also evaluated in estimating grip forces with real-time resolution. This paper investigated three individual dynamic hand movements (2pinch, 3pinch, and fist closing and opening) while applying forces in 10% and 30% of the maximum voluntary contraction (MVC). The results demonstrated high accuracy in estimating kinetics and kinematics. The average Euclidean distance across all joints and subjects was 11.01 ± 2.22 mm and the normalized root mean square error for offline and real-time force estimation were found to be 2.17 ± 0.79 %MVC and 5.10 ± 1.81 %MVC respectively. The results demonstrated that by leveraging high-density sEMG and deep learning, it is possible to estimate human hand dynamics (kinematics and kinetics), which is a step toward developing more accurate systems for controlling prosthetic devices and assistive technologies.
- Open Access
- 14 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 11704-11719
Modeling and Solving Multi-Objective Path Planning Problem for Cooperative Cable-Suspended Load Transportation Considering the Time Variable Risk
Cooperative load transportation has the potential to revolutionize the urban logistics industry and can also be utilized in rescue operations following natural disasters. Utilizing cooperative cable-suspended load transportation in such applications involves addressing three problems: static path planning, dynamic path planning, and control. In this article, we aim to tackle the first problem, i.e., static path planning, which is largely separate from the other two tasks. In this regard, we propose a model for the offline path planning of the cooperative cable-suspended load transportation system, including practical constraints. Using the proposed model, we can limit parameters such as the speed and acceleration of UAVs, flight altitude, task completion time, and safety distances between UAVs and obstacles, while minimizing the path length and risk. In addition, we propose an improved hybrid fuzzy particle swarm optimization (PSO) and whale optimization algorithm (WOA) to solve the introduced path planning problem efficiently. Furthermore, a chaotic mutation operator prevents premature convergence in the PSO algorithm. To demonstrate the efficiency of the proposed model and algorithm, three case studies inspired by a fire incident in a forest park have been conducted, and the results have been compared with those of seven other well-known algorithms.
- 14 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 11704-11719
Open AccessModeling and Solving Multi-Objective Path Planning Problem for Cooperative Cable-Suspended Load Transportation Considering the Time Variable Risk
Cooperative load transportation has the potential to revolutionize the urban logistics industry and can also be utilized in rescue operations following natural disasters. Utilizing cooperative cable-suspended load transportation in such applications involves addressing three problems: static path planning, dynamic path planning, and control. In this article, we aim to tackle the first problem, i.e., static path planning, which is largely separate from the other two tasks. In this regard, we propose a model for the offline path planning of the cooperative cable-suspended load transportation system, including practical constraints. Using the proposed model, we can limit parameters such as the speed and acceleration of UAVs, flight altitude, task completion time, and safety distances between UAVs and obstacles, while minimizing the path length and risk. In addition, we propose an improved hybrid fuzzy particle swarm optimization (PSO) and whale optimization algorithm (WOA) to solve the introduced path planning problem efficiently. Furthermore, a chaotic mutation operator prevents premature convergence in the PSO algorithm. To demonstrate the efficiency of the proposed model and algorithm, three case studies inspired by a fire incident in a forest park have been conducted, and the results have been compared with those of seven other well-known algorithms.
- Open Access
Simultaneous Control of Human Hand Joint Positions and Grip Force via HD-EMG and Deep Learning
In myoelectric control, simultaneous control of multiple degrees of freedom can be challenging due to the dexterity of the human hand. Numerous studies have focused on hand functionality, however, they only focused on a few degrees of freedom. In this paper, a 3DCNN-MLP model is proposed that uses high-density sEMG signals to estimate 20 hand joint positions and grip force simultaneously. The deep learning model maps the muscle activity to the hand kinematics and kinetics. The proposed models' performance is also evaluated in estimating grip forces with real-time resolution. This paper investigated three individual dynamic hand movements (2pinch, 3pinch, and fist closing and opening) while applying forces in 10% and 30% of the maximum voluntary contraction (MVC). The results demonstrated significant accuracy in estimating kinetics and kinematics. The average Euclidean distance across all joints and subjects was 11.01 $\pm$ 2.22 mm and the mean absolute error for offline and real-time force estimation were found to be 0.8 $\pm$ 0.33 N and 2.09 $\pm$ 0.9 N respectively. The results demonstrate that by leveraging high-density sEMG and deep learning, it is possible to estimate human hand dynamics (kinematics and kinetics), which is a step forward to practical prosthetic hands.Open AccessSimultaneous Control of Human Hand Joint Positions and Grip Force via HD-EMG and Deep Learning
In myoelectric control, simultaneous control of multiple degrees of freedom can be challenging due to the dexterity of the human hand. Numerous studies have focused on hand functionality, however, they only focused on a few degrees of freedom. In this paper, a 3DCNN-MLP model is proposed that uses high-density sEMG signals to estimate 20 hand joint positions and grip force simultaneously. The deep learning model maps the muscle activity to the hand kinematics and kinetics. The proposed models' performance is also evaluated in estimating grip forces with real-time resolution. This paper investigated three individual dynamic hand movements (2pinch, 3pinch, and fist closing and opening) while applying forces in 10% and 30% of the maximum voluntary contraction (MVC). The results demonstrated significant accuracy in estimating kinetics and kinematics. The average Euclidean distance across all joints and subjects was 11.01 $\pm$ 2.22 mm and the mean absolute error for offline and real-time force estimation were found to be 0.8 $\pm$ 0.33 N and 2.09 $\pm$ 0.9 N respectively. The results demonstrate that by leveraging high-density sEMG and deep learning, it is possible to estimate human hand dynamics (kinematics and kinetics), which is a step forward to practical prosthetic hands. - 22 July 2024
- Published by SAGE Publications in Journal of Vibration and Control
- Vol. 31 (13-14) , 2651-2675
A new distributed robust H ∞ control strategy for a class of uncertain interconnected large-scale time-delay systems subject to actuator saturation and disturbance
In the realm of large-scale systems, the complexity of controller design has long been exacerbated by the proliferation of decision variables and inherent conservatism. This study introduces a novel approach to address these challenges, presenting a new distributed robust controller design methodology tailored for large-scale systems grappling with disturbances, uncertainties, and actuator saturations. The primary objectives include reducing conservatism, minimizing decision variables, and significantly curtailing computation time. To surmount these hurdles, the research leverages descriptive and reciprocally convex methods, formulating the design procedure using linear matrix inequalities. This enables the adjustment of uncertain parameters and robust disturbance rejection, thereby ensuring stability in large-scale systems. Additionally, a feedback control law is proposed to accommodate saturation constraints and ensure the closed-loop system’s stability. Notably, the effectiveness of the proposed control scheme is demonstrated through the evaluation of a full-car active suspension system, which is partitioned into interconnected subsystems to a large-scale system. Comparative analyses underscore the superior performance and technical advancements offered by the proposed methodology over existing approaches.
- 22 July 2024
- Published by SAGE Publications in Journal of Vibration and Control
- Vol. 31 (13-14) , 2651-2675
A new distributed robust H ∞ control strategy for a class of uncertain interconnected large-scale time-delay systems subject to actuator saturation and disturbance
In the realm of large-scale systems, the complexity of controller design has long been exacerbated by the proliferation of decision variables and inherent conservatism. This study introduces a novel approach to address these challenges, presenting a new distributed robust controller design methodology tailored for large-scale systems grappling with disturbances, uncertainties, and actuator saturations. The primary objectives include reducing conservatism, minimizing decision variables, and significantly curtailing computation time. To surmount these hurdles, the research leverages descriptive and reciprocally convex methods, formulating the design procedure using linear matrix inequalities. This enables the adjustment of uncertain parameters and robust disturbance rejection, thereby ensuring stability in large-scale systems. Additionally, a feedback control law is proposed to accommodate saturation constraints and ensure the closed-loop system’s stability. Notably, the effectiveness of the proposed control scheme is demonstrated through the evaluation of a full-car active suspension system, which is partitioned into interconnected subsystems to a large-scale system. Comparative analyses underscore the superior performance and technical advancements offered by the proposed methodology over existing approaches.
- Open Access
- 18 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 41421-41435
Designing of a PSO-Based Adaptive SMC With a Multilevel Inverter for MPPT of PV Systems Under Rapidly Changing Weather Conditions
This study discusses the widespread problem of chattering phenomena and high frequency oscillations in sliding mode controllers (SMCs) used for maximum power point (MPP) tracking (MPPT) in photovoltaic (PV) systems. Moreover, this study introduces an adaptive sliding mode controller (ASMC) made just for PV panels with MPPT capability to address these problems. The main goal of the control method is to make PV systems more reliable and effective by precisely tracking the MPP, even when the weather quickly changes. This strategy demonstrates superior static and dynamic responsiveness compared with traditional methods. The particle swarm optimization (PSO) algorithm is employed to determine the best gains for the SMC method, specifically for controlling the variable step of the standard perturb and observe (P&O) algorithm. This algorithm used in the study with a Soltech 1STH-250-WH module is linked to a boost DC-DC converter. The aforementioned converter provided power to a resistive load, which was then controlled by a voltage regulator. Subsequently, the research highlights the utilization of a new voltage source inverter: a 9-level diode clamp inverter (DCI) employed to mitigate harmonics, hence enhancing power quality through the reduction of its components and generating a sinusoidal AC voltage that has multiple uses.
- 18 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 41421-41435
Open AccessDesigning of a PSO-Based Adaptive SMC With a Multilevel Inverter for MPPT of PV Systems Under Rapidly Changing Weather Conditions
This study discusses the widespread problem of chattering phenomena and high frequency oscillations in sliding mode controllers (SMCs) used for maximum power point (MPP) tracking (MPPT) in photovoltaic (PV) systems. Moreover, this study introduces an adaptive sliding mode controller (ASMC) made just for PV panels with MPPT capability to address these problems. The main goal of the control method is to make PV systems more reliable and effective by precisely tracking the MPP, even when the weather quickly changes. This strategy demonstrates superior static and dynamic responsiveness compared with traditional methods. The particle swarm optimization (PSO) algorithm is employed to determine the best gains for the SMC method, specifically for controlling the variable step of the standard perturb and observe (P&O) algorithm. This algorithm used in the study with a Soltech 1STH-250-WH module is linked to a boost DC-DC converter. The aforementioned converter provided power to a resistive load, which was then controlled by a voltage regulator. Subsequently, the research highlights the utilization of a new voltage source inverter: a 9-level diode clamp inverter (DCI) employed to mitigate harmonics, hence enhancing power quality through the reduction of its components and generating a sinusoidal AC voltage that has multiple uses.
- 5 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (10) , 5708-5717
Simultaneous Estimation of Digit Tip Forces and Hand Postures in a Simulated Real-Life Condition With High-Density Electromyography and Deep Learning
In myoelectric control, continuous estimation of multiple degrees of freedom has an important role. Most studies have focused on estimating discrete postures or forces of the human hand but for a practical prosthetic system, both should be considered. In daily life activities, hand postures vary for grasping different objects and the amount of force exerted on each fingertip depends on the shape and weight of the object. This study aims to investigate the feasibility of continuous estimation of multiple degrees of freedom. We proposed a reach and grasp framework to study both absolute fingertip forces and hand movement types using deep learning techniques applied to high-density surface electromyography (HD-sEMG). Four daily life grasp types were examined and absolute fingertip forces were simultaneously estimated while grasping various objects, along with the grasp types. We showed that combining a 3-dimensional Convolutional Neural Network (3DCNN) with a Long Short-term Memory (LSTM) can reliably and continuously estimate the digit tip forces and classify different hand postures in human individuals. The mean absolute error (MAE) and Pearson correlation coefficient (PCC) results of the force estimation problem across all fingers and subjects were 0.46 ± 0.23 and 0.90 ± 0.03% respectively and for the classification problem, they were 0.04 ± 0.01 and 0.97 ± 0.02%. The results demonstrated that both absolute digit tip forces and hand postures can be successfully estimated through deep learning and HD-sEMG.
- 5 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (10) , 5708-5717
Simultaneous Estimation of Digit Tip Forces and Hand Postures in a Simulated Real-Life Condition With High-Density Electromyography and Deep Learning
In myoelectric control, continuous estimation of multiple degrees of freedom has an important role. Most studies have focused on estimating discrete postures or forces of the human hand but for a practical prosthetic system, both should be considered. In daily life activities, hand postures vary for grasping different objects and the amount of force exerted on each fingertip depends on the shape and weight of the object. This study aims to investigate the feasibility of continuous estimation of multiple degrees of freedom. We proposed a reach and grasp framework to study both absolute fingertip forces and hand movement types using deep learning techniques applied to high-density surface electromyography (HD-sEMG). Four daily life grasp types were examined and absolute fingertip forces were simultaneously estimated while grasping various objects, along with the grasp types. We showed that combining a 3-dimensional Convolutional Neural Network (3DCNN) with a Long Short-term Memory (LSTM) can reliably and continuously estimate the digit tip forces and classify different hand postures in human individuals. The mean absolute error (MAE) and Pearson correlation coefficient (PCC) results of the force estimation problem across all fingers and subjects were 0.46 ± 0.23 and 0.90 ± 0.03% respectively and for the classification problem, they were 0.04 ± 0.01 and 0.97 ± 0.02%. The results demonstrated that both absolute digit tip forces and hand postures can be successfully estimated through deep learning and HD-sEMG.