Mohammed M. Alammar
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
Mohammed M. Alammar has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Miguel López-Benítez
University of Liverpool
4 shared publications - Hamada Esmaiel
King Khalid University
3 shared publications - Abdulrahman Al Ayidh
King Khalid University
2 shared publications - Mourad Yessef
LIMAS Laboratory, Faculty of Sciences Dhar El Mahraz, Sidi Mohamed Ben Abdellah University, Fes, Morocco
2 shared publications Muneer Parayangat
Electrical Engineering Department, College of Engineering, King Khalid University, Abha, Saudi Arabia
2 shared publications- Zakaria Mohamed Salem Elbarbary
Department of Electrical Engineering, College of Engineering, King Khalid University, KSA, Abha, Saudi Arabia
2 shared publications
Latest Publications
- Open Access
- 2 November 2026
- Published by MDPI AG in Electronics
- Vol. 15 (21) , 5085
Lyapunov-Based Cross-Layer Transmission Control for Finite-Blocklength URLLC Systems with Deadline-Constrained Queues
Ultra-Reliable Low-Latency Communication (URLLC) systems require extremely reliable packet delivery under stringent latency constraints, particularly in mission-critical wireless applications such as industrial automation, autonomous transportation, and intelligent control systems. In such systems, communication reliability is jointly influenced by finite-blocklength decoding behavior, stochastic wireless channel variations, queue evolution, and packet deadline violations. This paper develops a Lyapunov-based cross-layer transmission control framework for finite-blocklength URLLC systems with deadline-constrained queues and stochastic traffic arrivals. The proposed method jointly models short-packet communication reliability, queue dynamics, packet expiration, and adaptive transmission parameter selection within a unified mathematical formulation. An end-to-end (E2E) reliability metric incorporating both physical-layer (PHY) decoding failures and queue-induced deadline violations is introduced. In order to satisfy long-term reliability and power constraints while preserving queue stability, virtual queues are constructed and integrated into a Lyapunov drift-plus-penalty optimization framework. Based on the proposed formulation, an online transmission control algorithm is developed for adaptive selection of transmission blocklength, coding rate, and transmit power according to instantaneous queue and wireless channel conditions. Unlike reinforcement-learning-based methods, the proposed framework does not require offline training or prior statistical knowledge of traffic and channel distributions. The analysis establishes bounded real-queue occupancy under capped admissions and deadline expiration, and shows that mean-rate stability of the virtual queues implies the corresponding surrogate-risk and power constraints. Classical Lyapunov scaling is discussed as a conditional benchmark rather than an established optimality guarantee for the implemented urgency-weighted controller. Simulation results show that the proposed framework reduces time-average transmit power by approximately 33.0% relative to Adaptive-FBL, 42.3% relative to EC-FBL, 46.7% relative to the simplified Lyapunov baseline, and 71.6% relative to fixed transmission, while maintaining packet-level reliability, delay, and queueing performance close to the adaptive benchmarks. Simulation results show that the proposed approach achieves a favorable balance between reliability, latency, and energy consumption across different traffic conditions.
- 2 November 2026
- Published by MDPI AG in Electronics
- Vol. 15 (21) , 5085
Open AccessLyapunov-Based Cross-Layer Transmission Control for Finite-Blocklength URLLC Systems with Deadline-Constrained Queues
Ultra-Reliable Low-Latency Communication (URLLC) systems require extremely reliable packet delivery under stringent latency constraints, particularly in mission-critical wireless applications such as industrial automation, autonomous transportation, and intelligent control systems. In such systems, communication reliability is jointly influenced by finite-blocklength decoding behavior, stochastic wireless channel variations, queue evolution, and packet deadline violations. This paper develops a Lyapunov-based cross-layer transmission control framework for finite-blocklength URLLC systems with deadline-constrained queues and stochastic traffic arrivals. The proposed method jointly models short-packet communication reliability, queue dynamics, packet expiration, and adaptive transmission parameter selection within a unified mathematical formulation. An end-to-end (E2E) reliability metric incorporating both physical-layer (PHY) decoding failures and queue-induced deadline violations is introduced. In order to satisfy long-term reliability and power constraints while preserving queue stability, virtual queues are constructed and integrated into a Lyapunov drift-plus-penalty optimization framework. Based on the proposed formulation, an online transmission control algorithm is developed for adaptive selection of transmission blocklength, coding rate, and transmit power according to instantaneous queue and wireless channel conditions. Unlike reinforcement-learning-based methods, the proposed framework does not require offline training or prior statistical knowledge of traffic and channel distributions. The analysis establishes bounded real-queue occupancy under capped admissions and deadline expiration, and shows that mean-rate stability of the virtual queues implies the corresponding surrogate-risk and power constraints. Classical Lyapunov scaling is discussed as a conditional benchmark rather than an established optimality guarantee for the implemented urgency-weighted controller. Simulation results show that the proposed framework reduces time-average transmit power by approximately 33.0% relative to Adaptive-FBL, 42.3% relative to EC-FBL, 46.7% relative to the simplified Lyapunov baseline, and 71.6% relative to fixed transmission, while maintaining packet-level reliability, delay, and queueing performance close to the adaptive benchmarks. Simulation results show that the proposed approach achieves a favorable balance between reliability, latency, and energy consumption across different traffic conditions.
- 22 October 2026
- Published by Springer Nature in Journal of the Brazilian Society of Mechanical Sciences and Engineering
- Vol. 48 (12) , 872
Enhancing the operational performance of an induction motor through a modified super-twisting algorithm
- 22 October 2026
- Published by Springer Nature in Journal of the Brazilian Society of Mechanical Sciences and Engineering
- Vol. 48 (12) , 872
Enhancing the operational performance of an induction motor through a modified super-twisting algorithm
- 29 May 2026
- Published by Wiley in Microwave and Optical Technology Letters
- Vol. 68 (6) , e70629
Graphene‐Au‐Cu‐MXene Multilayer Metamaterial Plasmonic Biosensor With Machine Learning‐Assisted Optimization for Label‐Free THz Detection of Waterborne Bacterial Pathogens
Detection of waterborne bacterial pathogens such as Escherichia coli , Salmonella typhimurium , and Vibrio cholerae requires methods that operate with high sensitivity and can be deployed outside laboratory settings. This study describes a multilayer metamaterial plasmonic biosensor operating in the terahertz frequency range for label‐free refractive index sensing. The device uses a 4 × 4 periodic array of vertically stacked resonant nanostructures on a silicon substrate. The structure combines a gold Y‐shaped nanoresonator, a copper circular cavity, a MXene square‐ring resonator, and a graphene circular disc. This configuration supports strong field confinement, electrical tunability through graphene, and reduced reliance on noble metals.Finite element simulations in COMSOL Multiphysics quantify the dependence of absorption on incidence angle, graphene chemical potential, and resonator geometry. The optimized configuration uses a copper circular resonator diameter of 5500 nm, a MXene square‐ring outer dimension of 2000 nm, and a gold Y‐resonator arm width of 600 nm. Within a refractive index range of n = 1.33 to n = 1.3921, the device achieves a peak sensitivity of 0.751 THz/RIU and a figure of merit of 1.140 RIU −1 . The frequency response shows a linear relation with refractive index, with R 2 = 0.93337 across the evaluated material configurations. A regression‐based surrogate model trained on the simulation dataset predicts device response with R 2 above 0.9992 and mean absolute percentage error below 0.2%. This model reduces the need for repeated full‐wave simulations during design iterations. The results support the use of the proposed structure for label‐free THz sensing of waterborne pathogens over relevant refractive index ranges.
- 29 May 2026
- Published by Wiley in Microwave and Optical Technology Letters
- Vol. 68 (6) , e70629
Graphene‐Au‐Cu‐MXene Multilayer Metamaterial Plasmonic Biosensor With Machine Learning‐Assisted Optimization for Label‐Free THz Detection of Waterborne Bacterial Pathogens
Detection of waterborne bacterial pathogens such as Escherichia coli , Salmonella typhimurium , and Vibrio cholerae requires methods that operate with high sensitivity and can be deployed outside laboratory settings. This study describes a multilayer metamaterial plasmonic biosensor operating in the terahertz frequency range for label‐free refractive index sensing. The device uses a 4 × 4 periodic array of vertically stacked resonant nanostructures on a silicon substrate. The structure combines a gold Y‐shaped nanoresonator, a copper circular cavity, a MXene square‐ring resonator, and a graphene circular disc. This configuration supports strong field confinement, electrical tunability through graphene, and reduced reliance on noble metals.Finite element simulations in COMSOL Multiphysics quantify the dependence of absorption on incidence angle, graphene chemical potential, and resonator geometry. The optimized configuration uses a copper circular resonator diameter of 5500 nm, a MXene square‐ring outer dimension of 2000 nm, and a gold Y‐resonator arm width of 600 nm. Within a refractive index range of n = 1.33 to n = 1.3921, the device achieves a peak sensitivity of 0.751 THz/RIU and a figure of merit of 1.140 RIU −1 . The frequency response shows a linear relation with refractive index, with R 2 = 0.93337 across the evaluated material configurations. A regression‐based surrogate model trained on the simulation dataset predicts device response with R 2 above 0.9992 and mean absolute percentage error below 0.2%. This model reduces the need for repeated full‐wave simulations during design iterations. The results support the use of the proposed structure for label‐free THz sensing of waterborne pathogens over relevant refractive index ranges.
- Open Access
- 22 May 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Performance evaluation of DF-based cooperative DCSK for next-generation wireless networks
Differential chaos shift keying (DCSK) is a non-coherent modulation technique that has attracted attention for communication over fading channels. This paper investigates the performance of a cooperative DCSK system employing decode-and-forward (DF) relaying over Rayleigh and Nakagami- m fading environments. Analytical expressions are developed for outage probability and average-capacity evaluation, while the bit error performance is examined through an analytical treatment supported by Monte Carlo simulation. The analysis shows that the Nakagami- m fading parameter has a clear impact on system performance, where less severe fading leads to improved reliability. The results also indicate that the relay-destination link plays an important role in the cooperative gain achieved by the considered system. The contribution of the paper is presented within the scope of the adopted two-user DF cooperative DCSK model and the corresponding analytical assumptions. Therefore, the reported findings should be interpreted as an analytical and numerical characterization of the studied framework under the specified channel conditions.
- 22 May 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessPerformance evaluation of DF-based cooperative DCSK for next-generation wireless networks
Differential chaos shift keying (DCSK) is a non-coherent modulation technique that has attracted attention for communication over fading channels. This paper investigates the performance of a cooperative DCSK system employing decode-and-forward (DF) relaying over Rayleigh and Nakagami- m fading environments. Analytical expressions are developed for outage probability and average-capacity evaluation, while the bit error performance is examined through an analytical treatment supported by Monte Carlo simulation. The analysis shows that the Nakagami- m fading parameter has a clear impact on system performance, where less severe fading leads to improved reliability. The results also indicate that the relay-destination link plays an important role in the cooperative gain achieved by the considered system. The contribution of the paper is presented within the scope of the adopted two-user DF cooperative DCSK model and the corresponding analytical assumptions. Therefore, the reported findings should be interpreted as an analytical and numerical characterization of the studied framework under the specified channel conditions.
- Open Access
- 18 May 2026
- Published by Wiley in Energy Science & Engineering
- Vol. 14 (8) , 3741-3773
Real‐Time Incremental Learning Artificial Neural Networks Maximum Power Point Tracking With Raspberry Pi‐Based Meteorological Data Acquisition
This paper presents a new maximum power point tracking (MPPT) method for photovoltaic (PV) systems based on artificial neural networks (ANNs) models integrated with incremental learning and the capability of real‐time acquiring meteorological conditions by using a Raspberry Pi. The approach uses hourly irradiance and temperature values obtained from the NASA POWER API to dynamically re‐train the ANN model according to weather conditions. Simulation results using MATLAB/Simulink reveal that the proposed system exhibits high precision and robust performance over a range of irradiance (200–1000 W/m 2 ). The system achieved an average PV conversion efficiency of 99.52% and load‐side efficiency of 98.50%, outperforming several conventional and intelligent MPPT techniques reported in the literature. Performance quantification results in an MSE of 0.0024 and an R 2 value of 0.9987, revealing the excellent regression accuracy for the Vmp. Apart from the accuracy, the system exhibits a low response time and good power tracking under various operating circumstances.
- 18 May 2026
- Published by Wiley in Energy Science & Engineering
- Vol. 14 (8) , 3741-3773
Open AccessReal‐Time Incremental Learning Artificial Neural Networks Maximum Power Point Tracking With Raspberry Pi‐Based Meteorological Data Acquisition
This paper presents a new maximum power point tracking (MPPT) method for photovoltaic (PV) systems based on artificial neural networks (ANNs) models integrated with incremental learning and the capability of real‐time acquiring meteorological conditions by using a Raspberry Pi. The approach uses hourly irradiance and temperature values obtained from the NASA POWER API to dynamically re‐train the ANN model according to weather conditions. Simulation results using MATLAB/Simulink reveal that the proposed system exhibits high precision and robust performance over a range of irradiance (200–1000 W/m 2 ). The system achieved an average PV conversion efficiency of 99.52% and load‐side efficiency of 98.50%, outperforming several conventional and intelligent MPPT techniques reported in the literature. Performance quantification results in an MSE of 0.0024 and an R 2 value of 0.9987, revealing the excellent regression accuracy for the Vmp. Apart from the accuracy, the system exhibits a low response time and good power tracking under various operating circumstances.
- Open Access
- 10 April 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (8) , 3752
A Sustainable Multi-Objective Framework for Green Neural Architecture Optimization Using Grey Wolf Optimizer
The rising computational demands of deep learning models have intensified concerns regarding their energy consumption and environmental impact, motivating the development of Green Artificial Intelligence (Green AI) approaches. This paper proposes a multi-objective Green AI optimization framework based on the Grey Wolf Optimizer (GWO) to design efficient multilayer perceptron (MLP) architectures. Unlike conventional strategies that focus solely on maximizing accuracy, the proposed method jointly optimizes validation accuracy, training time, number of trainable parameters, and estimated floating-point operations (FLOPs). Evaluated on the Fashion-MNIST dataset and compared against a baseline MLP and Random Search, the GWO-based approach achieves competitive predictive performance while drastically reducing model size, computational complexity, and training time. Pareto front analysis confirms that GWO consistently identifies non-dominated architectures that offer superior trade-offs between accuracy and efficiency. Additional equal-accuracy evaluations demonstrate improved convergence efficiency and stability despite reduced model complexity. The results provide empirical evidence, within the MLP design setting considered in this study, that bio-inspired multi-objective optimization can support Green AI by identifying more compact and efficient architectures with competitive predictive performance.
- 10 April 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (8) , 3752
Open AccessA Sustainable Multi-Objective Framework for Green Neural Architecture Optimization Using Grey Wolf Optimizer
The rising computational demands of deep learning models have intensified concerns regarding their energy consumption and environmental impact, motivating the development of Green Artificial Intelligence (Green AI) approaches. This paper proposes a multi-objective Green AI optimization framework based on the Grey Wolf Optimizer (GWO) to design efficient multilayer perceptron (MLP) architectures. Unlike conventional strategies that focus solely on maximizing accuracy, the proposed method jointly optimizes validation accuracy, training time, number of trainable parameters, and estimated floating-point operations (FLOPs). Evaluated on the Fashion-MNIST dataset and compared against a baseline MLP and Random Search, the GWO-based approach achieves competitive predictive performance while drastically reducing model size, computational complexity, and training time. Pareto front analysis confirms that GWO consistently identifies non-dominated architectures that offer superior trade-offs between accuracy and efficiency. Additional equal-accuracy evaluations demonstrate improved convergence efficiency and stability despite reduced model complexity. The results provide empirical evidence, within the MLP design setting considered in this study, that bio-inspired multi-objective optimization can support Green AI by identifying more compact and efficient architectures with competitive predictive performance.
- Open Access
- 19 March 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Explainable AI (XAI) for transparent resource allocation in public safety communications networks
Public Safety Networks (PSNs) play a crucial role in enabling efficient communication and coordination among first responders and emergency management agencies during critical situations such as natural disasters, terrorist attacks, and public health crises. These networks must facilitate timely and reliable data transmission to ensure informed decision-making in dynamic and high-pressure environments. However, effective resource allocation within PSNs is a challenging task due to fluctuating demands, limited bandwidth, and the need for real-time adaptability. Traditional AI-based allocation models, while capable of optimizing resource distribution, often function as black-box systems, offering little transparency into the decision-making process. The lack of explainability in these models raises concerns among stakeholders, as opaque AI-driven decisions may result in inefficiencies, biases, or unintended disparities in resource allocation. To address these challenges, this study presents an XAI-driven framework for resource allocation that integrates SHAP (Shapley Additive Explanations) and LIME (Local Interpretable Model-Agnostic Explanations) to enhance both global and local interpretability. By leveraging these techniques, the proposed model improves transparency, ensures fairness, and provides interpretable justifications for allocation decisions. Furthermore, Bayesian uncertainty modeling is incorporated to enhance decision reliability, particularly in rapidly evolving emergency scenarios. Experimental evaluations demonstrate that the framework optimizes resource distribution while maintaining explainability, fostering trust among emergency responders, policymakers, and stakeholders. By bridging the gap between AI-driven optimization and human interpretability, this research contributes to the advancement of equitable, accountable, and transparent decision-making processes in PSNs, ultimately improving emergency response efficiency and public safety outcomes.
- 19 March 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessExplainable AI (XAI) for transparent resource allocation in public safety communications networks
Public Safety Networks (PSNs) play a crucial role in enabling efficient communication and coordination among first responders and emergency management agencies during critical situations such as natural disasters, terrorist attacks, and public health crises. These networks must facilitate timely and reliable data transmission to ensure informed decision-making in dynamic and high-pressure environments. However, effective resource allocation within PSNs is a challenging task due to fluctuating demands, limited bandwidth, and the need for real-time adaptability. Traditional AI-based allocation models, while capable of optimizing resource distribution, often function as black-box systems, offering little transparency into the decision-making process. The lack of explainability in these models raises concerns among stakeholders, as opaque AI-driven decisions may result in inefficiencies, biases, or unintended disparities in resource allocation. To address these challenges, this study presents an XAI-driven framework for resource allocation that integrates SHAP (Shapley Additive Explanations) and LIME (Local Interpretable Model-Agnostic Explanations) to enhance both global and local interpretability. By leveraging these techniques, the proposed model improves transparency, ensures fairness, and provides interpretable justifications for allocation decisions. Furthermore, Bayesian uncertainty modeling is incorporated to enhance decision reliability, particularly in rapidly evolving emergency scenarios. Experimental evaluations demonstrate that the framework optimizes resource distribution while maintaining explainability, fostering trust among emergency responders, policymakers, and stakeholders. By bridging the gap between AI-driven optimization and human interpretability, this research contributes to the advancement of equitable, accountable, and transparent decision-making processes in PSNs, ultimately improving emergency response efficiency and public safety outcomes.
- 19 February 2026
- Published by Taylor & Francis in IETE Technical Review
- Vol. 43 (3) , 339-353
Time Reversal NOMA for Underwater X-Transform TDS-IM-OFDM-SS Communication Systems
1. Underwater acoustic (UWA) communication has attracted significant attention owing to its expanding range of scientific, industrial, and naval uses. Among the diverse technologies for underwater ...
- 19 February 2026
- Published by Taylor & Francis in IETE Technical Review
- Vol. 43 (3) , 339-353
Time Reversal NOMA for Underwater X-Transform TDS-IM-OFDM-SS Communication Systems
1. Underwater acoustic (UWA) communication has attracted significant attention owing to its expanding range of scientific, industrial, and naval uses. Among the diverse technologies for underwater ...
- Open Access
- 1 January 2026
- Published by Institution of Engineering and Technology (IET) in IET Communications
- Vol. 20 (1)
Reinforcement Learning for Robust Modulation Classification in Non‐Orthogonal Multiple Access (NOMA) Systems
This paper presents a reinforcement learning (RL)‐based framework for optimising modulation classification, power allocation, and resource management in NOMA systems. The primary objective is to leverage machine learning techniques, particularly deep reinforcement learning (DRL) and Q‐learning, to enhance spectral efficiency, minimise interference, and improve signal detection accuracy. The algorithm has been implemented incorporating key components such as state representation, temporal difference learning, experience replay, policy optimisation, and generalised advantage estimation (GAE). The results demonstrate the evolution of Q‐values, policy gradients, proximal policy optimisation (PPO) loss, and the temporal difference (TD) error, providing insights into the agent's learning process and convergence behaviour. The findings highlight the effectiveness of reinforcement learning in dynamic wireless environments, offering adaptive, data‐driven solutions for NOMA systems where traditional optimisation methods struggle. By analysing the stability and efficiency of the proposed approach, this study underscores the potential of RL to enhance modulation classification and resource allocation, paving the way for next‐generation intelligent communication networks. Furthermore, the results reveal that integrating softmax policy selection and prioritised experience replay significantly improves the agent's learning efficiency, ensuring faster convergence and better decision‐making under varying channel conditions. These insights establish a strong foundation for future research on RL‐driven autonomous communication networks, enabling robust and intelligent resource management in 5G and beyond wireless systems.
- 1 January 2026
- Published by Institution of Engineering and Technology (IET) in IET Communications
- Vol. 20 (1)
Open AccessReinforcement Learning for Robust Modulation Classification in Non‐Orthogonal Multiple Access (NOMA) Systems
This paper presents a reinforcement learning (RL)‐based framework for optimising modulation classification, power allocation, and resource management in NOMA systems. The primary objective is to leverage machine learning techniques, particularly deep reinforcement learning (DRL) and Q‐learning, to enhance spectral efficiency, minimise interference, and improve signal detection accuracy. The algorithm has been implemented incorporating key components such as state representation, temporal difference learning, experience replay, policy optimisation, and generalised advantage estimation (GAE). The results demonstrate the evolution of Q‐values, policy gradients, proximal policy optimisation (PPO) loss, and the temporal difference (TD) error, providing insights into the agent's learning process and convergence behaviour. The findings highlight the effectiveness of reinforcement learning in dynamic wireless environments, offering adaptive, data‐driven solutions for NOMA systems where traditional optimisation methods struggle. By analysing the stability and efficiency of the proposed approach, this study underscores the potential of RL to enhance modulation classification and resource allocation, paving the way for next‐generation intelligent communication networks. Furthermore, the results reveal that integrating softmax policy selection and prioritised experience replay significantly improves the agent's learning efficiency, ensuring faster convergence and better decision‐making under varying channel conditions. These insights establish a strong foundation for future research on RL‐driven autonomous communication networks, enabling robust and intelligent resource management in 5G and beyond wireless systems.
- Open Access
- 7 November 2025
- Published by Springer Nature in Research Square
Beat-by-Beat ECG Monitoring from PPG Using Spatio-Temporal Information with WaveNet
The synthesis of the Electrocardiogram (ECG) from the Photoplethysmogram (PPG) is a hot research topic in the last decade. Also, PPG can be measured using PPG sensor connected with fingertips or even measured from RGB signals. The successful reconstruction of the ECG waveform from a PPG signal promises to enable continuous, comfortable, and diagnostically rich cardiac monitoring outside of traditional clinical settings. The main limitations of the current ECG reconstruction techniques are the use of invalid training datasets, unsuitable networks, and/or insufficient information. Therefore, in this paper, we propose to emphasize the cleanness of the datasets including spatial and temporal information with adapted WaveNet as an efficient network which is deep neural network model for generating raw audio waveforms. The adaptation includes the use of the network for regression rather than audio generation. Also, the architecture of the network is optimized for signal-to-signal regression. Two scenarios are designed and tested in this paper, namely, beat-to-beat regression fixed number of beats (three beats is tested) to beat. The effect of using the time interval information is evaluated as well, The experimental results demonstrated that using fixed number of beats is better than using single beat and better that using signal to signal ECG estimation. Also, it confirmed that the time interval information is essential for ECG monitoring. The proposed system can achieve a Pearson‘s correlation coefficient (r), Fréchet distance (FD), root mean square error (RMSE), percentage root mean square difference (PRD), mean absolute error (MAE) and standard deviation (SD) of 0.9831, 0.1174, 0.0373, 12.3207, 0.0262 and 0.0371, respectively which outperforms the existing state-of-the-arts ECG reconstruction algorithms. This research uses both of spatial and temporal information in beat-to-beat ECG reconstruction.
- 7 November 2025
- Published by Springer Nature in Research Square
Open AccessBeat-by-Beat ECG Monitoring from PPG Using Spatio-Temporal Information with WaveNet
The synthesis of the Electrocardiogram (ECG) from the Photoplethysmogram (PPG) is a hot research topic in the last decade. Also, PPG can be measured using PPG sensor connected with fingertips or even measured from RGB signals. The successful reconstruction of the ECG waveform from a PPG signal promises to enable continuous, comfortable, and diagnostically rich cardiac monitoring outside of traditional clinical settings. The main limitations of the current ECG reconstruction techniques are the use of invalid training datasets, unsuitable networks, and/or insufficient information. Therefore, in this paper, we propose to emphasize the cleanness of the datasets including spatial and temporal information with adapted WaveNet as an efficient network which is deep neural network model for generating raw audio waveforms. The adaptation includes the use of the network for regression rather than audio generation. Also, the architecture of the network is optimized for signal-to-signal regression. Two scenarios are designed and tested in this paper, namely, beat-to-beat regression fixed number of beats (three beats is tested) to beat. The effect of using the time interval information is evaluated as well, The experimental results demonstrated that using fixed number of beats is better than using single beat and better that using signal to signal ECG estimation. Also, it confirmed that the time interval information is essential for ECG monitoring. The proposed system can achieve a Pearson‘s correlation coefficient (r), Fréchet distance (FD), root mean square error (RMSE), percentage root mean square difference (PRD), mean absolute error (MAE) and standard deviation (SD) of 0.9831, 0.1174, 0.0373, 12.3207, 0.0262 and 0.0371, respectively which outperforms the existing state-of-the-arts ECG reconstruction algorithms. This research uses both of spatial and temporal information in beat-to-beat ECG reconstruction.