Seyyed Ali Zendehbad
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Seyyed Ali Zendehbad has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Elias Mazrooei Rad
Biomedical Engineering Department, Khavaran Institute of Higher Education, Mashhad, Iran
3 shared publications Zahra Sedaghat
2 shared publicationsAbdollah PourMottaghi
1 shared publicationAlireza Zarei
Department of Engineering, Faculty of Biomedical Engineering, Apadana Institute of Higher Education, Shiraz, Iran
1 shared publicationAthena Sharifi Razavi
1 shared publicationAthena Sharifi-Razavi
1 shared publication
Latest Publications
- Open Access
- 11 January 2026
- Published by Institution of Engineering and Technology (IET) in IET Signal Processing
- Vol. 2026 (1)
Revolutionizing Fetal QRS Complex Detection: A Cutting‐Edge Algorithm Employing New Adaptive Filters and Peak Thresholds
Purpose: This study proposes an innovative algorithm based on the morphological parameters of noninvasive fetal electrocardiography (NI‐FECG) for the comprehensive analysis of all electrocardiography (ECG) signal components, including the P wave, PR interval, QRS complex, ST segment, T wave, U wave, and QT interval. Accurate identification of these components is critical for a holistic evaluation of fetal heart health. While the QRS complex is crucial for detecting arrhythmias and guiding clinical interventions, a complete diagnostic evaluation requires analyzing all waveform components. The computational efficiency and robustness of the proposed algorithm make it highly suitable for real‐time clinical applications, distinguishing it from conventional methods. Materials and Methods: The proposed method utilizes a dataset of 55 multichannel abdominal NI‐FECG recordings collected between gestational weeks 21 and 40. This method focuses on enhancing detection accuracy across various ECG signal components by incorporating adaptive filtering techniques and dynamic peak thresholding to minimize noise interference and improve signal clarity. The study provides a detailed evaluation of the variability in QRS morphology and the influence of arrhythmias on the ECG waveform. Results: Experimental results demonstrate the proposed algorithm’s robustness, achieving an average detection error of 1.78% and a standard deviation of 0.46% across all participants for all ECG components, with specific emphasis on the QRS complex. Additionally, the computational complexity is significantly reduced compared to existing approaches, ensuring feasibility for real‐time deployment in clinical settings. Conclusion: This study presents a groundbreaking algorithm for fetal ECG analysis using NI‐FECG signals, yielding a high precision for the detection of all morphological features, such as the PR, RR, ST, and QT intervals. The holistic approach ensures a more reliable assessment of fetal heart health. With a swift 0.22‐s execution time, the algorithm is practical for real‐time applications. Our findings highlight the significance of tailored biological signal processing over generic artificial intelligence (AI)‐based models in enhancing accuracy and noise resilience in fetal ECG analysis. Further research is needed to optimize performance in diverse clinical scenarios. Integration of this approach into routine clinical practice could significantly improve fetal cardiovascular health monitoring and overall pregnancy outcomes.
- 11 January 2026
- Published by Institution of Engineering and Technology (IET) in IET Signal Processing
- Vol. 2026 (1)
Open AccessRevolutionizing Fetal QRS Complex Detection: A Cutting‐Edge Algorithm Employing New Adaptive Filters and Peak Thresholds
Purpose: This study proposes an innovative algorithm based on the morphological parameters of noninvasive fetal electrocardiography (NI‐FECG) for the comprehensive analysis of all electrocardiography (ECG) signal components, including the P wave, PR interval, QRS complex, ST segment, T wave, U wave, and QT interval. Accurate identification of these components is critical for a holistic evaluation of fetal heart health. While the QRS complex is crucial for detecting arrhythmias and guiding clinical interventions, a complete diagnostic evaluation requires analyzing all waveform components. The computational efficiency and robustness of the proposed algorithm make it highly suitable for real‐time clinical applications, distinguishing it from conventional methods. Materials and Methods: The proposed method utilizes a dataset of 55 multichannel abdominal NI‐FECG recordings collected between gestational weeks 21 and 40. This method focuses on enhancing detection accuracy across various ECG signal components by incorporating adaptive filtering techniques and dynamic peak thresholding to minimize noise interference and improve signal clarity. The study provides a detailed evaluation of the variability in QRS morphology and the influence of arrhythmias on the ECG waveform. Results: Experimental results demonstrate the proposed algorithm’s robustness, achieving an average detection error of 1.78% and a standard deviation of 0.46% across all participants for all ECG components, with specific emphasis on the QRS complex. Additionally, the computational complexity is significantly reduced compared to existing approaches, ensuring feasibility for real‐time deployment in clinical settings. Conclusion: This study presents a groundbreaking algorithm for fetal ECG analysis using NI‐FECG signals, yielding a high precision for the detection of all morphological features, such as the PR, RR, ST, and QT intervals. The holistic approach ensures a more reliable assessment of fetal heart health. With a swift 0.22‐s execution time, the algorithm is practical for real‐time applications. Our findings highlight the significance of tailored biological signal processing over generic artificial intelligence (AI)‐based models in enhancing accuracy and noise resilience in fetal ECG analysis. Further research is needed to optimize performance in diverse clinical scenarios. Integration of this approach into routine clinical practice could significantly improve fetal cardiovascular health monitoring and overall pregnancy outcomes.
- Open Access
- 22 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 34 (15344320) , 372-381
Real-Time Model-Free Adaptive Dual Control in Closed-Loop Deep Brain Stimulation: A Path to Individualized Parkinson’s Treatment
Deep brain stimulation (DBS) is an advanced clinical treatment for suppressing tremors in Parkinsonian patients. However, traditional open-loop DBS systems remain unable to adapt to patient-specific neural dynamics, often leading to suboptimal results. To address these limitations, this paper proposes a novel closed-loop DBS scheme based on a data-driven model-free adaptive control (MFAC) strategy, designed to effectively suppress pathological tremors hindering overstimulation and providing less power consumption. Using the basal ganglia (BG) system dynamics which is assumed to be completely unknown, the proposed method overcomes the incomplete regional contraction mapping or inaccurate neural dynamics representations, making it a viable option for patient-specific adaptation. The online control strategy continuously adjusts based on real-time data, using an unknown BG model that is merely employed to generate input-output data for simultaneous regulation of the subthalamic nucleus (STN) and globus pallidus internus (GPi) regions. Three linearization techniques (compact-form, partial-form, and full-form dynamic linearization) are utilized to enhance performance and suppress pathological tremor and bring much flexibility to controller design. Performance metrics, including Integral Absolute Error (IAE), Integral Time Absolute Error (ITAE), and Integral Time Squared Error (ITSE), demonstrate a detailed comparison to check the tracking accuracy and tremor suppression based on the error signal. The controller’s robustness against inter- and intra-patient variations is evaluated through Monte-Carlo (MC) simulations, providing a reliable in-vitro alternative to real-world clinical trials. In addition, a Hardware-In-the-Loop (HIL) setup has been devised using an Arduino microcontroller to validate the proposed individualized closed-loop DBS performance in a more realistic environment, validating the adaptation, and accounting for noise and time delay in real-world clinical situations. The findings indicate that the proposed novel adaptive deep brain stimulator can significantly improve the quality of life for Parkinsonian patients by effectively suppressing the disease-related tremors.
- 22 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 34 (15344320) , 372-381
Open AccessReal-Time Model-Free Adaptive Dual Control in Closed-Loop Deep Brain Stimulation: A Path to Individualized Parkinson’s Treatment
Deep brain stimulation (DBS) is an advanced clinical treatment for suppressing tremors in Parkinsonian patients. However, traditional open-loop DBS systems remain unable to adapt to patient-specific neural dynamics, often leading to suboptimal results. To address these limitations, this paper proposes a novel closed-loop DBS scheme based on a data-driven model-free adaptive control (MFAC) strategy, designed to effectively suppress pathological tremors hindering overstimulation and providing less power consumption. Using the basal ganglia (BG) system dynamics which is assumed to be completely unknown, the proposed method overcomes the incomplete regional contraction mapping or inaccurate neural dynamics representations, making it a viable option for patient-specific adaptation. The online control strategy continuously adjusts based on real-time data, using an unknown BG model that is merely employed to generate input-output data for simultaneous regulation of the subthalamic nucleus (STN) and globus pallidus internus (GPi) regions. Three linearization techniques (compact-form, partial-form, and full-form dynamic linearization) are utilized to enhance performance and suppress pathological tremor and bring much flexibility to controller design. Performance metrics, including Integral Absolute Error (IAE), Integral Time Absolute Error (ITAE), and Integral Time Squared Error (ITSE), demonstrate a detailed comparison to check the tracking accuracy and tremor suppression based on the error signal. The controller’s robustness against inter- and intra-patient variations is evaluated through Monte-Carlo (MC) simulations, providing a reliable in-vitro alternative to real-world clinical trials. In addition, a Hardware-In-the-Loop (HIL) setup has been devised using an Arduino microcontroller to validate the proposed individualized closed-loop DBS performance in a more realistic environment, validating the adaptation, and accounting for noise and time delay in real-world clinical situations. The findings indicate that the proposed novel adaptive deep brain stimulator can significantly improve the quality of life for Parkinsonian patients by effectively suppressing the disease-related tremors.
- Open Access
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Signal Processing
- Vol. 2025 (1)
GSVMD: A High‐Performance Method for Denoising Surface‐Electromyography Signals With Generalized Successive Variational Mode Decomposition
Surface electromyography (sEMG) has been used for decades to diagnose movement and neuromuscular disorders; however, sEMG signals are noisy and interfered with, and the nonstationary, nonlinear nature of sEMG signals complicates their use for diagnostic purposes. However, existing denoising methods often sacrifice the original signal, thereby losing practical physiological details, which makes them clinically less applicable. To overcome these challenges, we introduce generalized successive variational mode decomposition (GSVMD), an advanced denoising technique that preserves signal integrity over all frequencies. GSVMD decouples Successive variational mode decomposition (SVMD) for adaptive signal decomposition, Soft interval thresholding (SIT) for focused noise reduction, and attention mechanisms to focus on clinically relevant signal components. GVSMD was evaluated using 4‐channel sEMG data from 12 healthy participants and 24 stroke patients, demonstrating superior performance compared to traditional methods, with a significant increase in SNR and R 2 values. Its robustness was confirmed by statistical validation ( p < 0.001, p < 0.05). Taken together, these findings highlight GSVMD’s potential for real‐time clinical diagnostics and its potential application in a wide range of patient groups and conditions.
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Signal Processing
- Vol. 2025 (1)
Open AccessGSVMD: A High‐Performance Method for Denoising Surface‐Electromyography Signals With Generalized Successive Variational Mode Decomposition
Surface electromyography (sEMG) has been used for decades to diagnose movement and neuromuscular disorders; however, sEMG signals are noisy and interfered with, and the nonstationary, nonlinear nature of sEMG signals complicates their use for diagnostic purposes. However, existing denoising methods often sacrifice the original signal, thereby losing practical physiological details, which makes them clinically less applicable. To overcome these challenges, we introduce generalized successive variational mode decomposition (GSVMD), an advanced denoising technique that preserves signal integrity over all frequencies. GSVMD decouples Successive variational mode decomposition (SVMD) for adaptive signal decomposition, Soft interval thresholding (SIT) for focused noise reduction, and attention mechanisms to focus on clinically relevant signal components. GVSMD was evaluated using 4‐channel sEMG data from 12 healthy participants and 24 stroke patients, demonstrating superior performance compared to traditional methods, with a significant increase in SNR and R 2 values. Its robustness was confirmed by statistical validation ( p < 0.001, p < 0.05). Taken together, these findings highlight GSVMD’s potential for real‐time clinical diagnostics and its potential application in a wide range of patient groups and conditions.
- Open Access
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in Healthcare Technology Letters
- Vol. 12 (1)
Trustworthy AI in Telehealth: Navigating Challenges, Ethical Considerations, and Future Opportunities for Equitable Healthcare Delivery
Trustworthy artificial intelligence (TAI) will transform telehealth by providing safe, transparent, and ethically compliant systems that enhance clinician decision‐making and patient relationships. This systematic review examines how TAI and large language models (LLMs), including large language model meta ai (LLaMA), can be integrated into telehealth systems, their role in optimizing e‐consultation workflows, and their capacity to support personalized care through data collected by wearable biosensors and biological microelectromechanical systems (BioMEMS). These devices monitor physiological and behavioral data, such as heart rate, blood pressure, and emotional state. TAI enables effective diagnostics and targeted treatment by combining various information sources, including biosensor readings, patient history, and cognitive data. Firmware integrity plays a crucial role in ensuring security, reliability, and continuous data encryption. This review analyses 135 papers (October 2020‐March 2025) from databases like IEEE Xplore, PubMed, and Scopus to demonstrate TAI's potential to enhance resource use and patient engagement. However, widespread adoption depends on overcoming technical challenges, improving firmware reliability, strengthening data security, and addressing ethical concerns. This review offers valuable guidance for engineers, system architects, and healthcare providers to create a sensitive and effective telehealth ecosystem.
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in Healthcare Technology Letters
- Vol. 12 (1)
Open AccessTrustworthy AI in Telehealth: Navigating Challenges, Ethical Considerations, and Future Opportunities for Equitable Healthcare Delivery
Trustworthy artificial intelligence (TAI) will transform telehealth by providing safe, transparent, and ethically compliant systems that enhance clinician decision‐making and patient relationships. This systematic review examines how TAI and large language models (LLMs), including large language model meta ai (LLaMA), can be integrated into telehealth systems, their role in optimizing e‐consultation workflows, and their capacity to support personalized care through data collected by wearable biosensors and biological microelectromechanical systems (BioMEMS). These devices monitor physiological and behavioral data, such as heart rate, blood pressure, and emotional state. TAI enables effective diagnostics and targeted treatment by combining various information sources, including biosensor readings, patient history, and cognitive data. Firmware integrity plays a crucial role in ensuring security, reliability, and continuous data encryption. This review analyses 135 papers (October 2020‐March 2025) from databases like IEEE Xplore, PubMed, and Scopus to demonstrate TAI's potential to enhance resource use and patient engagement. However, widespread adoption depends on overcoming technical challenges, improving firmware reliability, strengthening data security, and addressing ethical concerns. This review offers valuable guidance for engineers, system architects, and healthcare providers to create a sensitive and effective telehealth ecosystem.
- Open Access
- 1 January 2025
- Published by Wiley in Prostate Cancer
- Vol. 2025 (1) , 2019841
Providing a Prostate Cancer Detection and Prevention Method With Developed Deep Learning Approach
Introduction: Prostate cancer is the second most common cancer among men worldwide. This cancer has become extremely noticeable due to the increase of prostate cancer in Iranian men in recent years due to the lack of marriage and sexual intercourse, as well as the abuse of hormones in sports without any standards. Methods: The histopathology images from a treatment center to diagnose prostate cancer are used with the help of deep learning methods, considering the two characteristics of Tile and Grad‐CAM. The approach of this research is to present a prostate cancer diagnosis model to achieve proper performance from histopathology images with the help of a developed deep learning method based on the manifold model. Results: Similarly, in addition to the diagnosis of prostate cancer, a study on the methods of preventing this disease was investigated in literature reviews, and finally, after simulation, prostate cancer presentation factors were determined. Conclusions: The simulation results indicated that the proposed method has a performance advantage over the other state‐of‐the‐art methods, and the accuracy of this method is up to 97.41%.
- 1 January 2025
- Published by Wiley in Prostate Cancer
- Vol. 2025 (1) , 2019841
Open AccessProviding a Prostate Cancer Detection and Prevention Method With Developed Deep Learning Approach
Introduction: Prostate cancer is the second most common cancer among men worldwide. This cancer has become extremely noticeable due to the increase of prostate cancer in Iranian men in recent years due to the lack of marriage and sexual intercourse, as well as the abuse of hormones in sports without any standards. Methods: The histopathology images from a treatment center to diagnose prostate cancer are used with the help of deep learning methods, considering the two characteristics of Tile and Grad‐CAM. The approach of this research is to present a prostate cancer diagnosis model to achieve proper performance from histopathology images with the help of a developed deep learning method based on the manifold model. Results: Similarly, in addition to the diagnosis of prostate cancer, a study on the methods of preventing this disease was investigated in literature reviews, and finally, after simulation, prostate cancer presentation factors were determined. Conclusions: The simulation results indicated that the proposed method has a performance advantage over the other state‐of‐the‐art methods, and the accuracy of this method is up to 97.41%.