Papers by Siamak Pedrammehr
Electronics, 2024
The integration of machine learning (ML) with image and signal processing has revolutionized vari... more The integration of machine learning (ML) with image and signal processing has revolutionized various fields by enhancing researchers' ability to analyse and interpret complex data. ML algorithms can extract meaningful features from signals and images, improve classification accuracy, and enable advanced functionalities such as real-time processing and automated decision-making. This synergy between ML and image/signal processing has broad applications, including medical diagnostics, remote sensing, security, and multimedia. This Special Issue highlights innovative research and addresses ongoing challenges in this field, with a particular focus on signal and image processing, signal reconstruction, image quantization, and advanced medical imaging applications. It serves as a platform for researchers to share their cutting-edge research, insights, and experiences, fostering collaboration and advancing the field. This Special Issue's scope includes a wide range of topics related to the machine learning applications in image and signal processing.
https://www.mdpi.com/journal/electronics/special_issues/E78O481SR2
In the realm of Industry 5.0, where human capabilities harmonize with cutting-edge technologies, ... more In the realm of Industry 5.0, where human capabilities harmonize with cutting-edge technologies, fostering collaborative relationships between humans and machines is paramount to elevate innovation, productivity, and sustainability in industrial processes. This research explores the indispensable role of Complex Systems Integration (CSI) within the dynamic landscape of Industry 5.0, marked by the convergence of cyber-physical systems, artificial intelligence (AI), and the Internet of Things (IoT). Acknowledging a significant gap in existing research, which has hitherto overlooked the profound influence of increasingly complex systems and their integration on the genesis of industrial revolutions, particularly within the context of Industry 5.0, our article addresses this knowledge gap. The integration of complex systems serves as a catalyst, significantly contributing to the advancement of Industry 5.0 goals. As Industry 5.0 unfolds, our research underscores the transformative potential of a synergistic fusion encompassing AI, Industrial IoT (IIoT), and robotics. This, distinct from the compartmentalized strategy of Industry 4.0, underscores the evolving dynamics of technological integration. The study concludes by positioning CSI not merely as a technological enabler but as a driving force propelling Industry 5.0 towards its overarching goals. By establishing a robust technological foundation, our research asserts that CSI shapes the trajectory of technological advancement and positively influences goals of Industry 5.0.
This paper introduces a Schönflies parallel mechanism that incorporates a unique rotational capab... more This paper introduces a Schönflies parallel mechanism that incorporates a unique rotational capability around the horizontal axis. The main contributions of this study lie in the analytical solutions for the kinematics and singularity analysis of this specific mechanism. The mechanism's inverse kinematics encompasses velocity, position, and acceleration. To achieve this, we employ the efficient algebraic framework of screw theory. Additionally, we conduct a comprehensive investigation of the mechanism's workspace, considering both geometrical and singularity constraints. By utilizing MATLAB programming, we perform a rigorous workspace analysis, plotting the boundaries that account for physical and kinematic limitations. Furthermore, we evaluate the workspace and analyze the kinematics using the SolidWorks environment. The comparison between the results obtained from the CAD and analytical models confirms the mechanism's reliability and accuracy. Our findings showcase the exceptional flexibility and singularity-free workspace of the proposed mechanism, making it a highly suitable and dependable choice for various industrial applications. Over all, this paper presents an innovative and promising solution that enables precise motion, offering potential benefits across multiple industrial fields. Additionally, the validation of the analytical method through comparison with SolidWorks simulation enhances the credibility of the findings. This research not only benefits the understanding of the 3T1R mechanism but also offers a dependable, validated method for future research in modeling and simulating various manipulators.
Technological advancements have facilitated the development of innovative wearable electrocardiog... more Technological advancements have facilitated the development of innovative wearable electrocardiography (ECG) patches suitable for remote patient monitoring. However, there is a current lack of comprehensive understanding regarding the user experience (UX) associated with these devices which is crucial to ensure their widespread acceptance. This research aims to present a design for a wireless ECG patch (WEP) that focuses on user experience features, making it easy to operate and integrate into daily routines. Initially, we surveyed 50 participants to discern the pertinent criteria for the user experience (UX) design of commercial ECG patches. Our approach integrated existing research findings and incorporated technical considerations mandated by project stakeholders. Subsequently, an expert panel comprising a designer, technical experts, and a physician selected the optimal design concept. Following the development of the prototype, it underwent a 48-hour user experience investigation, which involved a questionnaire and an overview assessment. A significant majority of participants reported that the device was comfortable to wear and easy to use. Additionally, the study participants expressed satisfaction and indicated a keen interest in utilizing the device in the future. These results affirm that the newly designed WEP is a reliable, comfortable, and user-friendly device for remote patient monitoring, hinting at the potential for such devices to enhance patient care and improve overall health outcomes through further development and adoption.
Deleted Journal, Apr 29, 2024
Axioms, Jan 10, 2024
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
Seminars in Ophthalmology, Dec 12, 2023
Multiple sclerosis (MS) is a complex autoimmune disease characterized by inflammatory processes, ... more Multiple sclerosis (MS) is a complex autoimmune disease characterized by inflammatory processes, demyelination, neurodegeneration, and axonal damage within the central nervous system (CNS). Retinal imaging, particularly Optical coherence tomography (OCT), has emerged as a crucial tool for investigating MS-related retinal injury. The integration of artificial intelligence(AI) has shown promise in enhancing OCT analysis for MS. Researchers are actively utilizing AI algorithms to accurately detect and classify MS-related abnormalities, leading to improved efficiency in diagnosis, monitoring, and personalized treatment planning. The prognostic value of AI in predicting MS disease progression has garnered substantial attention. Machine learning (ML) and deep learning (DL) algorithms can analyze longitudinal OCT data to forecast the course of the disease, providing critical information for personalized treatment planning and improved patient outcomes. Early detection of high-risk patients allows for targeted interventions to mitigate disability progression effectively. As such, AI-driven approaches yielded remarkable abilities in classifying distinct MS subtypes based on retinal features, aiding in disease characterization and guiding tailored therapeutic strategies. Additionally, these algorithms have enhanced the accuracy and efficiency of OCT image segmentation, streamlined diagnostic processes, and reduced human error. This study reviews the current research studies on the integration of AI,including ML and DL algorithms, with OCT in the context of MS. It examines the advancements, challenges, potential prospects, and ethical concerns of AI-powered techniques in enhancing MS diagnosis, monitoring disease progression, revolutionizing patient care, the development of patient screening tools, and supported clinical decision-making based on OCT images.
Lecture notes in computer science, 2024
Despite the absence of a standardized clinical definition, morning stress is widely recognized as... more Despite the absence of a standardized clinical definition, morning stress is widely recognized as the stress experienced upon waking. Given its established link to various diseases prevalent in modern society, the accurate measurement and effective management of stress are paramount for maintaining optimal health. In this study, we present a novel approach leveraging the sophisticated capabilities of smartphones to extract photoplethysmography (PPG) signals for immediate detection of morning stress. Data from 61 participants were meticulously collected and processed to extract PPG signals, subsequently employing 11 carefully selected features for stress detection. Through the utilization of the Support Vector Machine (SVM) for classification, we scrutinized the accuracy of our method against established benchmarks. Notably, by integrating the False Discovery Rate (FDR) formula and employing the Particle Swarm Optimization (PSO) algorithm, we achieved a significant enhancement in the classification rate, elevating it from 96% to an impressive 100%. These compelling results underscore the efficacy of our proposed methodology and illuminate the promising potential of smartphone-based morning stress detection as a viable tool for proactive health management.
Electronics (Impact Factor: 2.6, CiteScore: 5.3, ISSN 2079-9292), 2024
Dear Colleagues,
The integration of machine learning (ML) with image and signal processing has r... more Dear Colleagues,
The integration of machine learning (ML) with image and signal processing has revolutionized various fields by enhancing researchers’ ability to analyse and interpret complex data. ML algorithms can extract meaningful features from signals and images, improve classification accuracy, and enable advanced functionalities such as real-time processing and automated decision-making. This synergy between ML and image/signal processing has broad applications, including medical diagnostics, remote sensing, security, and multimedia.
This Special Issue highlights innovative research and addresses ongoing challenges in this field, with a particular focus on signal and image processing, signal reconstruction, image quantization, and advanced medical imaging applications. It serves as a platform for researchers to share their cutting-edge research, insights, and experiences, fostering collaboration and advancing the field.
This Special Issue’s scope includes a wide range of topics related to the machine learning applications in image and signal processing. Topics of interest include, but are not limited to, the following:
Pre-trained models for imaging diagnosis;
Image segmentation, quantization, classification and dimensionality reduction;
Pattern recognition;
Molecular imaging and nuclear medicine;
X-ray, CT-scan, MRI, NMR, FMRI, and ultrasonography analysis;
Machine learning applications in OCT, OCTA, and other ophthalmology imaging
Biometric recognition systems;
Integration of machine learning in imaging devices, imaging sequences, and imaging-guided intervention;
Anomaly detection, signal denoising, and signal classification;
Signal filtering and reconstruction.
Dr. Siamak Pedrammehr
Guest Editor
Frontiers in Human Neuroscience, 2024
We extend a sincere and warm invitation to researchers to submit their high-quality and innovativ... more We extend a sincere and warm invitation to researchers to submit their high-quality and innovative research papers for consideration. We seek contributions that can inspire advances in the field of Artificial Intelligence Advancements in Neural Signal Processing and Neurotechnology. This topic will be published under Frontiers in Human Neuroscience (Impact Factor: 2.4, CiteScore: 4.7). Please note that the submission deadline for this topic has been extended to February 1st, 2025.
https://www.frontiersin.org/research-topics/61562/artificial-intelligence-advancements-in-neural-signal-processing-and-neurotechnology
The motion cueing (MC) is used to generate suitable motion signals for a motion simulator user th... more The motion cueing (MC) is used to generate suitable motion signals for a motion simulator user that has a limited working envelope. As model predictive control (MPC) is able to keep the platform within the physical constraints, this category of MC is recently introduced to reproduce the precise motion cues. However, the accuracy of MPC is subject to the use of appropriate weighting parameters. While a genetic algorithm (GA) is useful for tuning the weighting parameters, the results can vary for every test scenario. In addition, the speed of convergence is slow, and it has lots of parameters that should be determined properly. The aim of this article is the employment of a particle swarm optimization to determine the optimal weighting parameters of the MPCMC and contrast it with the Genetic Algorithm (GA) tuning based method. The cost function is dependent on the motion sensation error, input signals and additional motion indexes of the simulator. The usefulness of the proposed model is evaluated in simulated environments, and better accuracy and repeatability results as compared with those from the GA tuning method are produced. The results prove that PSO has better efficacy in extracting the true global optimal solution which has led the better MC performance compared with the GA but with remarkably better computational efficacy.
Technological advancements have facilitated the development of innovative wearable electrocardiog... more Technological advancements have facilitated the development of innovative wearable electrocardiography (ECG) patches suitable for remote patient monitoring. However, there is a current lack of comprehensive understanding regarding the user experience (UX) associated with these devices which is crucial to ensure their widespread acceptance. This research aims to present a design for a wireless ECG patch (WEP) that focuses on user experience features, making it easy to operate and integrate into daily routines. Initially, we surveyed 50 participants to discern the pertinent criteria for the user experience (UX) design of commercial ECG patches. Our approach integrated existing research findings and incorporated technical considerations mandated by project stakeholders. Subsequently, an expert panel comprising a designer, technical experts, and a physician selected the optimal design concept. Following the development of the prototype, it underwent a 48-hour user experience investigation, which involved a questionnaire and an overview assessment. A significant majority of participants reported that the device was comfortable to wear and easy to use. Additionally, the study participants expressed satisfaction and indicated a keen interest in utilizing the device in the future. These results affirm that the newly designed WEP is a reliable, comfortable, and user-friendly device for remote patient monitoring, hinting at the potential for such devices to enhance patient care and improve overall health outcomes through further development and adoption.
In the realm of Industry 5.0, where human capabilities harmonize with cutting-edge technologies, ... more In the realm of Industry 5.0, where human capabilities harmonize with cutting-edge technologies, fostering collaborative relationships between humans and machines is paramount to elevate innovation, productivity, and sustainability in industrial processes. This research explores the indispensable role of Complex Systems Integration (CSI) within the dynamic landscape of Industry 5.0, marked by the convergence of cyber-physical systems, artificial intelligence (AI), and the Internet of Things (IoT). Acknowledging a significant gap in existing research, which has hitherto overlooked the profound influence of increasingly complex systems and their integration on the genesis of industrial revolutions, particularly within the context of Industry 5.0, our article addresses this knowledge gap. The integration of complex systems serves as a catalyst, significantly contributing to the advancement of Industry 5.0 goals. As Industry 5.0 unfolds, our research underscores the transformative potential of a synergistic fusion encompassing AI, Industrial IoT (IIoT), and robotics. This, distinct from the compartmentalized strategy of Industry 4.0, underscores the evolving dynamics of technological integration. The study concludes by positioning CSI not merely as a technological enabler but as a driving force propelling Industry 5.0 towards its overarching goals. By establishing a robust technological foundation, our research asserts that CSI shapes the trajectory of technological advancement and positively influences goals of Industry 5.0.
This paper introduces a Schönflies parallel mechanism that incorporates a unique rotational capab... more This paper introduces a Schönflies parallel mechanism that incorporates a unique rotational capability around the horizontal axis. The main contributions of this study lie in the analytical solutions for the kinematics and singularity analysis of this specific mechanism. The mechanism's inverse kinematics encompasses velocity, position, and acceleration. To achieve this, we employ the efficient algebraic framework of screw theory. Additionally, we conduct a comprehensive investigation of the mechanism's workspace, considering both geometrical and singularity constraints. By utilizing MATLAB programming, we perform a rigorous workspace analysis, plotting the boundaries that account for physical and kinematic limitations. Furthermore, we evaluate the workspace and analyze the kinematics using the SolidWorks environment. The comparison between the results obtained from the CAD and analytical models confirms the mechanism's reliability and accuracy. Our findings showcase the exceptional flexibility and singularity-free workspace of the proposed mechanism, making it a highly suitable and dependable choice for various industrial applications. Over all, this paper presents an innovative and promising solution that enables precise motion, offering potential benefits across multiple industrial fields. Additionally, the validation of the analytical method through comparison with SolidWorks simulation enhances the credibility of the findings. This research not only benefits the understanding of the 3T1R mechanism but also offers a dependable, validated method for future research in modeling and simulating various manipulators.
Nowadays, the use of electromagnetic waves in medical applications has become common, and hyperth... more Nowadays, the use of electromagnetic waves in medical applications has become common, and hyperthermia is one of the popular areas. Nonetheless, designing effective antennas for electromagnetic hyperthermia poses a key challenge. In designing of hyperthermia antennas for medical applications, factors such as appropriate resonant frequencies and appropriate antenna sizes are important. Another critical aspect in the design of useful and usable hyperthermia antenna is the heat on the target body area, since a proper depth setting for heating is normally neglected. In this paper, using the Particle Swarm Optimization (PSO) algorithm, we focus on the heat on the target area when designing a hyperthermia antenna that operates at the frequency of 432 MHz. The antenna is analyzed using the finite difference time domain method, while the PSO fitness function is selected in such a way as to maintain the optimal frequency characteristics of the antenna, along with optimization of its heating performance. A series of simulation studies in MATLAB and the associated laboratory results confirm accuracy of the designed antenna. With minimal influence on healthy tissues, the temperature of approximately 42 degrees Celsius is achieved steadily after about 12 min from the start of heating in the target area, where the tumor is located. We observe minor differences between simulation and laboratory results, owing to not being able to use living tissue in the laboratory and lack of precision in the construction of antenna with optimized parameters. Article Highlights • An antenna structure intended for hyperthermia applications is designed with optimized parameters. • The PSO optimization enhanced both the antenna's frequency characteristics and its heating performance. • A steady, precise heating of 42o C in the target area is achieved with the least possible heating in non-target parts.
Multiple sclerosis (MS) is a complex autoimmune disease characterized by inflammatory processes, ... more Multiple sclerosis (MS) is a complex autoimmune disease characterized by inflammatory processes, demyelination, neurodegeneration, and axonal damage within the central nervous system (CNS). Retinal imaging, particularly Optical coherence tomography (OCT), has emerged as a crucial tool for investigating MS-related retinal injury. The integration of artificial intelligence(AI) has shown promise in enhancing OCT analysis for MS. Researchers are actively utilizing AI algorithms to accurately detect and classify MS-related abnormalities, leading to improved efficiency in diagnosis, monitoring, and personalized treatment planning. The prognostic value of AI in predicting MS disease progression has garnered substantial attention. Machine learning (ML) and deep learning (DL) algorithms can analyze longitudinal OCT data to forecast the course of the disease, providing critical information for personalized treatment planning and improved patient outcomes. Early detection of high-risk patients allows for targeted interventions to mitigate disability progression effectively. As such, AI-driven approaches yielded remarkable abilities in classifying distinct MS subtypes based on retinal features, aiding in disease characterization and guiding tailored therapeutic strategies. Additionally, these algorithms have enhanced the accuracy and efficiency of OCT image segmentation, streamlined diagnostic processes, and reduced human error. This study reviews the current research studies on the integration of AI,including ML and DL algorithms, with OCT in the context of MS. It examines the advancements, challenges, potential prospects, and ethical concerns of AI-powered techniques in enhancing MS diagnosis, monitoring disease progression, revolutionizing patient care, the development of patient screening tools, and supported clinical decision-making based on OCT images.
The development of machine learning technology and its algorithms has led to a significant breakt... more The development of machine learning technology and its algorithms has led to a significant breakthrough in the medical field. The ability to diagnose and predict diseases with high accuracy has been achieved with the help of machine learning. This capability is particularly useful in creating systems that can automatically analyze medical test data without the need for a doctor's presence. This paper focuses on designing a system for analyzing data obtained from spectrophotometric analysis to diagnose heart diseases. Different classification methods such as K Nearest Neighbor, Parzen, Bayesian, Multilayer Perceptron, and RBF have been used in this research. It also suggests unbalanced, non-normalized, and whitened data as pre-processing methods. In addition, Genetic algorithm has been used to optimize hyperparameters. Experimental reports and results show that KNN, Parzen, One-layer perceptron and Two-layer perceptron classifiers have an accuracy of 75.64%, 80.67%, 84.74%, and 71.66%, respectively. And the RBF neural network and the Bayesian method with whitened data and optimized parameters have higher accuracy than other methods and can detect the subject's health or disease with 100% accuracy and analysis providing the expert audience with a detailed description of the methods used to diagnose heart diseases.
In this paper, vibrational properties of carbon nanocones with different lengths and apex angles ... more In this paper, vibrational properties of carbon nanocones with different lengths and apex angles in various boundary conditions are studied. The results are presented in two categories: natural frequencies and the corresponding mode shapes. The molecular mechanics based finite element method is the approach applied to investigate the desired behaviors of the mentioned nanostructures. The results propose that with increasing lengths and apex angles, all of the natural frequencies decrease. Furthermore, there are some similarities between the successive frequency values and their corresponding mode shapes.
Modelling and simulation of the bridge response during vehicle crossing is of the utmost importan... more Modelling and simulation of the bridge response during vehicle crossing is of the utmost importance in bridge design. In previous works some studies have been conducted on this issue, but parametric statistical investigations and reliability analysis of the bridge response are not studied in the reported literature. In this research, after modelling the bridge-vehicle system, the uncertainties of the vehicles is produced using Gaussian probability distribution function and the statistical parameters of the response is extracted by Monte-Carlo simulation. The results, which are based on the confidence intervals and the variance of the statistical parameters, are obtained to study the effects of uncertainties on the dynamic response of the bridge. In addition, the probabilities of failure are calculated to illustrate a quantitative measure for the simulated statistical results. The most effective parameters on the uncertainty of the bridge response are also presented in this paper.
Uploads
Papers by Siamak Pedrammehr
https://www.mdpi.com/journal/electronics/special_issues/E78O481SR2
The integration of machine learning (ML) with image and signal processing has revolutionized various fields by enhancing researchers’ ability to analyse and interpret complex data. ML algorithms can extract meaningful features from signals and images, improve classification accuracy, and enable advanced functionalities such as real-time processing and automated decision-making. This synergy between ML and image/signal processing has broad applications, including medical diagnostics, remote sensing, security, and multimedia.
This Special Issue highlights innovative research and addresses ongoing challenges in this field, with a particular focus on signal and image processing, signal reconstruction, image quantization, and advanced medical imaging applications. It serves as a platform for researchers to share their cutting-edge research, insights, and experiences, fostering collaboration and advancing the field.
This Special Issue’s scope includes a wide range of topics related to the machine learning applications in image and signal processing. Topics of interest include, but are not limited to, the following:
Pre-trained models for imaging diagnosis;
Image segmentation, quantization, classification and dimensionality reduction;
Pattern recognition;
Molecular imaging and nuclear medicine;
X-ray, CT-scan, MRI, NMR, FMRI, and ultrasonography analysis;
Machine learning applications in OCT, OCTA, and other ophthalmology imaging
Biometric recognition systems;
Integration of machine learning in imaging devices, imaging sequences, and imaging-guided intervention;
Anomaly detection, signal denoising, and signal classification;
Signal filtering and reconstruction.
Dr. Siamak Pedrammehr
Guest Editor
https://www.frontiersin.org/research-topics/61562/artificial-intelligence-advancements-in-neural-signal-processing-and-neurotechnology
https://www.mdpi.com/journal/electronics/special_issues/E78O481SR2
The integration of machine learning (ML) with image and signal processing has revolutionized various fields by enhancing researchers’ ability to analyse and interpret complex data. ML algorithms can extract meaningful features from signals and images, improve classification accuracy, and enable advanced functionalities such as real-time processing and automated decision-making. This synergy between ML and image/signal processing has broad applications, including medical diagnostics, remote sensing, security, and multimedia.
This Special Issue highlights innovative research and addresses ongoing challenges in this field, with a particular focus on signal and image processing, signal reconstruction, image quantization, and advanced medical imaging applications. It serves as a platform for researchers to share their cutting-edge research, insights, and experiences, fostering collaboration and advancing the field.
This Special Issue’s scope includes a wide range of topics related to the machine learning applications in image and signal processing. Topics of interest include, but are not limited to, the following:
Pre-trained models for imaging diagnosis;
Image segmentation, quantization, classification and dimensionality reduction;
Pattern recognition;
Molecular imaging and nuclear medicine;
X-ray, CT-scan, MRI, NMR, FMRI, and ultrasonography analysis;
Machine learning applications in OCT, OCTA, and other ophthalmology imaging
Biometric recognition systems;
Integration of machine learning in imaging devices, imaging sequences, and imaging-guided intervention;
Anomaly detection, signal denoising, and signal classification;
Signal filtering and reconstruction.
Dr. Siamak Pedrammehr
Guest Editor
https://www.frontiersin.org/research-topics/61562/artificial-intelligence-advancements-in-neural-signal-processing-and-neurotechnology