This paper proposes an approach to estimate the parameters of an AC-DC boost power factor corrector converter which includes an EMI filter. To this end, once the topology is known, measurements at the input and output terminals of the converter are done to identify the values of the passive elements. The proposed methodology is based on the trust-region nonlinear least squares algorithm to identify the parameters of the converter. The steady-state and the transient signals of the converter at the input/output terminals are acquired non-intrusively without any internal modification of the circuitry. The accuracy of the parameter identification carried out is determined by comparing the estimated values with the actual values provided by the manufacturer, and by contrasting the measured signals with the ones obtained with a simulation model with the estimated values of the parameters. The results presented in this paper prove the accuracy of the proposed approach, which can be extended to other power converters and filters.

Of all the renewable energy sources, solar photovoltaic (PV) power is estimated to be a popular source due to several advantages such as its free availability, absence of rotating parts, integration to building such as rooftops, and less maintenance cost. The nonlinear current-voltage (I–V) characteristics and power generated from a PV array primarily depend on solar insolation/irradiation and panel temperature. The extracted PV output power is influenced by the accuracy with which the nonlinear power–voltage (P–V) characteristic curve is traced by the maximum power point tracking (MPPT) controller. In this paper, a bio-inspired roach infestation optimization (RIO) algorithm is proposed to extract the maximum power from the PV system (PVS). To validate the usefulness of the RIO MPPT algorithm, MATLAB/Simulink simulations are performed under varying environmental conditions, for example, step changes in solar irradiance, and partial shading of the PV array. Furthermore, the search performance of the RIO algorithm is examined on different unconstrained benchmark functions, and it is that realized that the RIO algorithm has improved convergence characteristics in terms of finding the optimal solution than Particle swarm optimization (PSO). The results demonstrated that the RIO-based MPPT performs remarkably in tracking with high accuracy as the PSO-based MPPT.

This study aims to implement a SSDBI (single-stage differential boost inverter, SSDBI) applying in a single-stage BESS (battery energy storage system, BESS) topology, which can supply power from lower voltage battery module to AC load. Compared with the common two-stage topology, which has a two-stage converter and higher voltage battery module array, the single-stage topology can reduce the number of cells and components, and improve the power density. In addition, a modified SPWM control was proposed to reduce the control complexity of the SSDBI while improving the THD of the inverter. The modified SPWM control can reduce the duty ratio of the SSDBI and the stress on the components to improve the AC voltage output waveform and reduce the THD value about 2.654%.

In this research paper, a high gain transformer less inverter modeling which is used for the smart grid technology or as the stand alone for home appliances is proposed. The proposed transformer less topology provides a higher voltage gain, low cost, small size and simple control stand alone transformer less inverter for home appliances. The above inverter is modeled by using software which is known as MATLAB/ Simulimk.

Various natural disasters such as floods, fires, earthquakes, etc. have affected human life. Detection and classification of large and small earthquakes caused by natural or abnormal events have been always important to Earth scientist. One of the most important research challenges in this field is the lack of an effective method for identifying and categorizing various types of seismic events at less important and important levels. Based on latest achievements of Data Mining international institutions such as Rexer-KDnugget-Gartner and also newest authentic articles, SVM, KNN, C4.5, MLP are from most important and popular and leading classifiers in data world.Therefor in present study, a boost learning system consisting support vector machine algorithms with linear regression, MLP Neural Network ، C4.5 decision tree and KNN near neighborhood have been utilized in a combined form to detect and categorize micro seismic events. In general, the steps involved in the proposed method are: 1) performing artificial seismic tests, 2) data gathering and analysis, 3) conducting preprocessing and separating training and testing samples, 4) generating relevant models with training samples and detecting and categorizing test samples and 5) extracting a cluster with the maximum candidate using boost learning. After simulations, it was observed that the accuracy of proposed boost method to the best answer was about 6.1% higher compare to other methods and the error rate was 0.082% of recalling. Accuracy of detection and classification to the best answer were also improved compare to other methods up to 2.31% and 6.34%, respectively.

Video segmentation is crucial in a variety of practical applications especially in computer visions. Most of recent works in video segmentation are focusing on Deep learning based video segmentation, there are rooms for improvement in respect of the evolutionary algorithms. This paper aims to propose the novel method to video segmentation by using the optimization of segmentation parameters based on ensemble-based random forest and gradient boosting decision tree. The experimental results show Pareto front of segmentation parameters (hue, brightness, luminance, and saturation). Our optimization model yields accuracy: 85% +/-8.85 % (micro average: 85.00 %), average class precision: 84.88%, and average class recall: 85%. We also show the video segmentation results based on our optimization method and compare our results with Kinect-based video segmentation.

The use of different sources to energize a load is convenient in many applications, particularly those where two or more renewable energy sources are employed as: energy harvesting, hybrid vehicles, and off-grid systems. In these cases, a multi-input converter able to admit sources with different characteristics and, if necessary, select the output power of each source. Several topologies of multi-input converters have been proposed to this aim, however, most of them are based on multi-stage designs, which decreases efficiency and increases control complexity, particularly when more than two sources are used. In this work, a three-input step-up converter easy to control in open loop condition is analyzed. A designed procedure is described, and experimental results are presented for a 1 kW power converter. The implemented converter results in a higher voltage gain, less storage element keeping high efficiency compared to similar topologies. Using the procedure here proposed, this converter that was initially proposed for photovoltaic applications is enabled to be used in medium and high-power applications, for example when renewable energy sources are used.

Power converters with coupled inductors are very promising due to the high efficiency and high voltage gain. Apart from the aforementioned advantages, the boost-flyback converter reduces the voltage stress on the semiconductors. However, to obtain good performance with high voltage gains, the controller must include two control loops (current and voltage), and a compensation ramp. One of the most used control techniques for power converters is the peak current-mode control with compensation ramp. However, in the case of a boost-flyback converter there is no mathematical expression in the literature, to compute the slope of the compensation ramp. In this paper, a formula to compute the slope of the compensation ramp is proposed in such a way that a stable period-1 orbit is obtained. This formula is based on the values of the circuit parameters, such as inductances, capacitances, input voltage, switching frequency and includes some assumptions related to internal resistances, output voltages, and some other electrical properties related with the physical construction of the circuit. The formula is verified numerically using the saltation matrix and experimentally using a test circuit.

The integrated DC-DC converter is appropriate for use in many domains, namely, display, cellular, and portable applications. This paper presents an integrated monolithic voltage-mode DC-DC boost converter with a low-power control circuit. The driver circuit requires an integrated converter to power up a digital logic circuit and converts the unregulated DC input to the controlled DC output at the desired voltage level. It is the integration of both power switches and control circuitry within the same CMOS technology to buck down and boost voltages using a switch mode regulator. In order to increase power efficiency in the DC-DC boost converter that provides low-power operation with a small chip size, a low-voltage operation is applied to the unique circuit characteristic. The operational transconductance amplifier(OTA), comparator, and oscillator in the control circuit are designed with the supply voltage of 3.3V and the operating frequency of 5.5 MHz. A compensator is used to create a pole that has sufficient phase margin for high stability. The DC- DC boost converter is measured in both experiment and simulation. Testing of the proposed circuit on the 0.35μm CMOS process shows that the output transient time of the amplifier can be controlled within of 7μsec and the output voltage is accurately controlled with a ripple ratio of 3%.

This paper proposes a novel single-stage buck-boost three-Level neutral-point-clamped (NPC) inverter with two independent dc sources coupled for the grid-tied photovoltaic (PV) application, which can effectively solve the unbalanced operational conditions generally appeared between two coupled independent PV sources induced by the unequal irradiation and temperature distribution. The proposed control scheme can simultaneously guarantee the maximum power point (MPP) operation of both PV sources and maintain the output waveform quality. Compared to the traditional two-stage PV inverter, the proposed NPC inverter could reduce the PV array voltage requirement and dc-link capacitors’ voltage rating, meanwhile show the advantage in operational efficiency. MATLAB simulations and the captured experimental results are presented to show the performance of the proposed three-level inverter.

The concepts of fractional calculus and the related techniques have been gaining momentum in circuit system fields, and an increasing body of evidence suggests that fractional-order characteristics are widely distributed in electronic components. In this paper, we consider the fractional characteristics of non-solid aluminum electrolytic capacitors and focus on the nonlinear dynamic characteristics of peak-current-mode controlled (PCMC) dc-dc boost converters with such components. In the work, we establish a piecewise smooth non-commensurate fractional-order model to describe the converter, in which the fractional-order equivalent impedance model of capacitors is adopted and the detailed control loop is considered. In order to analyze the converter, we use the fractional Adams-Bashforth-Moulton typed method (F-ABM) and stroboscopic map technique to obtain the time-domain solutions and the bifurcation diagram. The results of bifurcation diagrams indicate that, with the change of different parameters, the converter enters chaotic state through period doubling bifurcation. In order to provide empirical evidence for the nonlinear dynamic analysis, we consider both circuit-level simulation and experiments in the work, the results of which further confirm the results of theoretical analysis.

Therapeutic vaccine studies should be designed to elicit durable, high magnitude, and efficacious T cell responses, all of which can be impacted by the choice of vaccination schedule. Here, we compare different prime-boost intervals (PBI) in a human papillomavirus (HPV) model using HPV16E6E7 Venezuelan equine encephalitis virus replicon particle (VRP) vaccination to address the optimal boosting schedule, quality of immune response, and overall in vivo efficacy. Six different vaccine regimens were tested with each group receiving booster vaccinations at different time intervals. Analysis of T-cell responses demonstrated a significant HPV16 E7 specific CD8+T cell response with minimally a one-week PBI between antigen re-exposure. Significant E7-specific in vivo cytotoxicity was also observed with longer PBIs. Additionally, longer PBIs led to an enhanced memory recall response to tumor challenge, which correlated with differential expansion of T cell memory subsets. Our findings imply that when using alphavirus vector platforms as a vaccination strategy, a one-week PBI is sufficient to induce high magnitude effector T cells with potent anti-tumor activity. However, longer PBIs lead to enhanced long-term protective anti-tumor immunity. These findings have implications for therapeutic vaccine clinical trials in which shorter intervals of prime-boost regimens may lead to suboptimal durable immune responses.

This article discusses a transformer-free, high-efficiency DC-DC converter besides renewable energy applications. The traditional buck-boost, classic Zeta, Sepic, and Cuk converter does have the benefits of a simple design, low cost, as well as the capacity to execute voltage step-up and step-down. Conversely, because of the detrimental consequences of the parasitic constraints of the device, the voltage conversion gain of the traditional DC-DC converter is much more restricted and the efficiency is also significantly smaller, whereas this proposed converter does have a higher voltage gain and efficiency because it is used in a single power switch, resulting in reduced switching losses and voltage stress. The said converter's design is very simple, which simplifies the operation control and reduces switching and conduction losses, leading to an efficiency of 97.4 percent. This converter seems to have the same capabilities as the Zeta converter, including continuous desired output current and desired buck-boost operation. Such an article offers the operation principle and steady evaluation, as well as a comparison with other existing high step-up configurations. The proposed converter employs a fuzzy logic controller, which improves the voltage level as well as reduces the time taken to set the voltage output of a conventional PI and ANN controller, especially in comparison to the FLC controller. For deployment, Experimental Result and MATLAB/Simulink has been used, and the modeling results indicate that the proposed controller performance has improved

It aims to utilize more solar energy, which is both environmentally friendly and easily accessible, to satisfy the energy needs of developing countries. Therefore, maximum power generation should be provided from photovoltaic panels. Several maximum power point tracking(MPPT) methods are utilized for the maximum power generation in photovoltaic panels systems under different weather conditions. In this paper, a novel hybrid and clever maximum power point monitoring fuzzy logic controller maximum power point tracking algorithm established on the perturb and observe (PO) algorithm is presented. The proposed fuzzy logic controller algorithm and the incremental conductivity maximum power point tracking algorithm were simulated in MATLAB/SIMULINK environment and evaluated by comparing the results. Four Sharp ND-F4Q295 solar panels, two in series and two in parallel were used for the simulation. The hybrid method proposed here was found to reduce the voltage and current ripple compared to the classical incremental conductivity method. The proposed intelligent method has been shown to stabilise the system more quickly in the event of sudden weather changes.

In this paper, based on the pseudo-totem pole (PTP) circuit, a family of five-level PTP dual boost converters (PDBC) is proposed. Dual boost converter has some unique advantages such as no bridge arm shoot-through risk and no switch body diode reverse recovery problem, so that it has a good application prospect. Compared with conventional three-level PTP converters, PDBCs has higher power density, higher efficiency, and low voltage and current stress. The topological derivation process, working principle, modulation and strategy of the topology are analyzed firstly. Further, the number of power devices, the switches voltage and current stress of the proposed topology is analyzed. Finally, a representative five-level PDBC experimental prototype is designed with AC input 220V/50Hz, DC output 400V/1kW, and peak efficiency of 98.27%. The experimental results show that the five-level PDBC proposed in this paper has higher efficiency and verify the correctness of the topology.

In a limestone quarry mine, fragmentation is a crucial outcome of blasting operations. The optimization of blasting operations greatly benefits from the prediction of rock fragmentation. The main factors that affect fragmentation are rock mass characteristics, blast geometry, and explosive properties. This paper is a step towards the implementation of machine learning and deep learning algorithms for predicting the extent of fragmentation (in percentage) in opencast mining. Various parameters can affect fragmentation. But, in this paper initially, ten parameters (spacing, drill hole diameter, burden, average bench height, powder factor, number of holes, charge per delay, uniaxial compressive strength, specific drilling, and stemming) are collected to train the model. However, due to a weak correlation with rock fragmentation, drill diameter, Average bench height, compressive strength, stemming, and charge per delay are eliminated to reduce model complexity. A total of 219 data sets having five input features i.e., the number of holes, spacing, burden, specific drilling, and powder factor are used to develop the models. To predict rock fragmentation due to blasting in limestone quarry mines, both machine learning models (Random Forest Regression (Bagging), Support Vector Regression, and XG Boost Regression (Boosting)), as well as a deep learning model (Neural Network Regression), are applied to develop a model that can optimize the prediction of fragmentation. The Artificial neural network model optimization showed that the model with architecture 64-32-16-1 can perform well giving MSE (mean squared error) values of 41.32 and 28.59 on training and test data respectively. The R2 value for both training and test is 0.83. Random Forest regression is also performing well compared to SVR and XG boost with the MSE value 12.37 and 9.89 on training and testing data respectively. Here, the R2 value for both sets are 94%. Based on the permutation importance and Shapely plot values, the powder factor has the highest impact, and the burden has the lowest impact on fragmentation.

This paper presents a new high-efficiency-high-step-up based converter integrating two stype DC-DC Boost and Flyback coupled magnetic converter with recovery stage dedicated to smart HVDC distributed architecture in renewable energy production systems. Appropriate duty cycle ratio assumes that the recovery stage work with parallel charge and discharge to achieve high step-up voltage gain. Besides, the voltage stress on the main switch is reduced with a passive clamp circuit and thus, low on-state resistance Rdson of the main switch can be adopted to reduce conduction losses. The circuit is simple to control. As a final point of this research, the simulation and the prototype investigational results are presented to demonstrate the effectiveness of this proposed converter.

Unmanned aerial vehicle (UAV) systems are widely used in many forest-related fields owing to their cost-intensive and precise surveying technology. This study classified erosion susceptibility (ES) in a timber harvesting area using machine learning (ML) and statistical approaches. In dataset generation for the training and testing process, the digital surface model (DSM) of difference (DoD) for July–June was utilized as a dependent variable, and six terrain maps of the DSM for June were used as independent variables. The ES threshold was set at 5 cm for the binary classification of ES pixels while processing using ML (e.g., random forest and extra gradient boost [XGB]) and statistical (e.g., logistic regression) algorithms for model development. The overall accuracy (OA), receiver operating characteristics, and area under the curve (AUC) were calculated for model accuracy and validation. Although the AUC of all models did not appear acceptable (AUC > 0.7), the XGB model showed the best performance regarding time duration, OA, and AUC by 2 h, 64%, and 0.63, respectively. Despite the low AUC and accuracy of the XGB model, the wheel tracks and edges of the operation road were determined to be susceptible areas in the ES map of the XGB.

The renewable energy source plays a major role in the grid side power production. The stability analysis is very essential in the renewable energy converters. In this paper the bifurcation is analyzed in ZETA converter and Continuous input and output(CIO) power Buck Boost converter. The ZETA converter gives positive step down and step up output voltage and the CIO power converter gives the negative step up and step down output voltage. These converters are used in the DC micro grid with renewable energy as the source. The current mode control technique is applied to analyze the bifurcation behavior and the reference current is taken as the bifurcation parameter. When the reference current is varied, both the converters loses its stability and it enters into chaotic region through period doubling bifurcation. The simulation results are presented to study the performance behavior of both the converters. The stability region of both the converters are determined by deriving the Monodromy matrix approach.

Portable Document Format (PDF) files are one of the most universally used file types. This has fascinated hackers to develop methods to use these normally innocent PDF files to create security threats via infection vectors PDF files. This is usually realized by hiding embedded malicious code in the victims’ PDF documents to infect their machines. This, of course, results in PDF Malware and requires techniques to identify benign files from malicious files. Research studies indicated that machine-learning methods provide efficient detection techniques against such malware. In this paper, we present a new detection system that can analyze PDF documents in order to identify benign PFD files from malware PFD files. The proposed system makes use of the AdaBoost decision tree with optimal hyperparameters, which is trained and evaluated on a modern-inclusive dataset, viz. Evasive-PDFMal2022. The investigational assessment demonstrates a lightweight-accurate PDF detection system, achieving a 98.84% prediction accuracy with a short prediction interval of 2.174 μSec. To this end, the proposed model outperforms other state-of-the-art models in the same study area. Hence, the proposed system can be effectively utilized to uncover PDF malware at high detection performance and low detection overhead.

The geodesics on a relativistic manifold are given by the well-known equation involving the Christoffel coefficients. This equation can be solved numerically step by step and transposed into a quantization. We study here the effect of this quantization on the Schwarzschild spacetime, more precisely in the Kruskal-Szekeres map.

This article is a big picture of how electrical noise or conducted Electromagnetic Interference (EMI) is generated and mitigated in power converters. It gives an overview of what EMI in power converters is – from generation through to conduction and mitigation. It is meant to cover the complete subject as a summary so that the reader will have an outline of how to control conducted EMI by design (where possible) and how to mitigate by filtering. A clear distinction is made between Differential Mode (DM) and Common Mode (CM) EMI generation and mitigation. By using a boost converter as an example the trade-offs for DM noise control are discussed. It is shown how CM EMI is generated in a boost converter using the concept of the “Imbalance Difference Model” (IDM). Practical measurements for an in-line power filter is given showing the effect of the filter on the total EMI of a boost converter. Measurements for the CM current produced due to the imbalance difference for different values of the boost conductor are also shown. The main contribution of this study is linking CM noise generation to DM EMI. It is shown that CM noise is a direct consequence of DM noise (although circuit imbalance and coupling to a common ground also play a role). This paper will be useful to designers seeking the “bigger picture” of how EMI is generated in power converters and what can be done to mitigate the noise.

The paper examines design and operating data of current concentrated solar power (CSP) solar tower (ST) plants. The study includes CSP with or without boost by combustion of natural gas (NG), and with or without thermal energy storage (TES). The latest, actual specific costs per installed capacity are very high, 6085 $/kW for Ivanpah Solar Electric Generating System (ISEGS) with no TES, and 9227 $/kW for Crescent Dunes with TES. The actual production of electricity is very low and much less than the expected. The actual capacity factors are 22% for ISEGS, despite combustion of a significant amount of NG largely exceeding the planned values, and 13% for Crescent Dunes. The design values were 33% and 52%. The study then reviews the proposed technology updates to produce better ratio of solar field power to electric power, better capacity factor, better matching of production and demand, lower plant’s cost, improved reliability and increased life span of plant’s components. The key areas of progress are found in materials and manufacturing processes, design of solar field and receiver, receiver and power block fluids, power cycle parameters, optimal management of daily and seasonal operation of the plant, new TES concepts, integration of solar plant with thermal desalination, integration of solar plant with combined cycle gas turbine (CCGT) installations and finally, specialization and regionalization of the project specification.

Abstract: High step-up voltage gain nonisolated DC-DC converter have attracted much attention in photovoltaic, fuel cells and other renewable energy system applications. In this paper, by combining input current ripple-free boost cell with coupled-inductor voltage-doubler cell, an input current ripple-free high voltage gain nonisolated converter is proposed. In addition, passive lossless clamp circuit is adopted to recycle the leakage inductor energy and to reduce the voltage spike across the power switch. By utilizing voltage-doubler cell consisting of diode and capacitor, the voltage stress of switch is further reduced and the resonance between the leakage inductor and the stray capacitor of the output diode is eliminated. A low switch-on-resistance low-voltage-rated MOSFET can therefore be employed to reduce the conduction loss and cost. The reverse recovery loss of output diode is reduced, and the efficiency of converter can be improved. Furthermore, the proposed converter can achieve nearly zero input current-ripple and make the design of electromagnetic interference (EMI) filter easy. Steady state analysis and operation mode of the converter is performed. Finally, experimental results are presented to verify the analysis results of the proposed converter.

This study introduces a data obfuscation technique, leveraging the exponential map associated with the generators of Lie groups. Originating from quantum machine learning frameworks, our method illustrates the practical application of quantum mechanics principles in data processing. Specifically, it employs the exponential map of a generator algebra to introduce controlled noise into the data, achieving obfuscated data while preserving its utility for machine learning tasks. This strategy is shown to safeguard privacy in sensitive datasets, such as discussed medical records, and to enhance dataset volume and diversity through augmentation. Our empirical analysis, benchmarked against standard machine learning approaches, demonstrates that our method can maintain or even improve the predictive accuracy of the original data. This research highlights the potential of Lie group theory for advancing data privacy in medicine, marking a significant contribution to machine learning methodologies by offering the dual benefits of data obfuscation and enrichment. Through this synthesis of algebraic structures and machine learning, we propose new pathways for the secure and effective use of data in sensitive areas.

One of the industries with the fastest rate of growth is healthcare, and this industry's enormous data requires extensive cloud storage. The cloud may offer some protection, but there is no assurance that data owners can rely on it for refuge and privacy amenities. Therefore, it is essential to offer security and privacy protection. Increased customer satisfaction with security and privacy preservation is crucial since healthcare big data and its sources are stored in the cloud and contain increasingly private and sensitive information. However, maintaining privacy and security in an untrusted green cloud environment is difficult, thus the data owner should have complete data control. A new work SecPri-BGMPOP(security and privacy of Boost graph Convolutional Network -Pinpointing-Optimization Performance) is suggested that can offer a solution that involves several different steps in order to handle the numerous problems relating to security and protecting privacy. Initially Boost Graph Convolutional Network Clustering (BGCNC) algorithm, which reduces computational complexity in terms of time and memory measurements, is first applied to the input dataset to begin the clustering process. Second, enlarge by employing a piece of the magnifying bit string to generate a safe key, pinpointing based encryption avoids amplify leakage even if a rival or attacker decrypts the key or asymmetric encryption. Finally, to determine the accuracy of the method, an optimal key was created using a meta-heuristic algorithmic framework called Hybrid fragment horde bland lobo Optimization (HFHBLO). Our proposed method currently kept in a cloud environment, allowing analytics users to utilize it without risking their privacy or security.

In this article, we investigate the applicability of quantum machine learning for classification tasks using two quantum classifiers from the Qiskit Python environment: the Variational Quantum Classifier (VQC) and the Quantum Kernel Estimator (QKE). We evaluate the performance of these classifiers on six widely known and publicly available benchmark datasets and analyze how their performance varies with the number of samples on two artificially generated test classification datasets. As quantum machine learning is based on unitary transformations, this paper explores data structures and application fields that could be particularly suitable for quantum advantages. Hereby, we developed a data set based on concepts from quantum mechanics using the exponential map of a Lie algebra. This dataset will be made publicly available and contributes a novel contribution to the empirical evaluation of quantum supremacy. We further compared the performance of VQC and QKE on six widely applicable datasets to contextualize our results.\\ Our results demonstrate that the VQC and QKE perform better than basic machine learning algorithms such as advanced linear regression models (Ridge and Lasso). They do not match the accuracy and runtime performance of sophisticated modern boosting classifiers like XGBoost, LightGBM, or CatBoost. Therefore, we conclude that while quantum machine learning algorithms have the potential to surpass classical machine learning methods in the future, especially when physical quantum infrastructure becomes widely available, they currently lag behind classical approaches. Our investigations also show that classical machine learning approaches have superior performance classifying datasets based on group structures, compared to quantum approaches that particularly use unitary processes.\\ Furthermore, our findings highlight the significant impact of different quantum simulators, feature maps, and quantum circuits on the performance of the employed quantum estimators. This observation emphasizes the need for researchers to provide detailed explanations of their hyperparameter choices for quantum machine learning algorithms, as this aspect is currently overlooked in many studies within the field.\\ To facilitate further research in this area and ensure the transparency of our study, we have made the complete code available in a linked GitHub repository.

Stroke constitutes a significant public health concern due to its impact on mortality and morbidity. This study investigates the utility of machine learning algorithms in predicting stroke and identifying key risk factors using data from the Suita study, comprising 7,389 participants and 53 variables. Initially, unsupervised K-prototype clustering categorized participants into risk clusters, while five supervised models including Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosted Machine (Light-GBM) were employed to predict stroke outcomes. Stroke incidence disparities among identified risk clusters using the unsupervised K-prototype clustering method are substantial, according to the findings. Supervised learning, particularly RF was a preferable option because of the higher levels of performance metrics. The Shapley Additive Explanations (SHAP) method identified age, systolic blood pressure, hypertension, estimated glomerular filtration rate, metabolic syndrome, and blood glucose level as key predictors of stroke, aligning with findings from the unsupervised clustering approach in high-risk groups. Additionally, previously unidentified risk factors such as elbow joint thickness, fructosamine, hemoglobin, and calcium level demonstrate potential for stroke prediction. In conclusion, machine learning facilitated accurate stroke risk predictions and highlighted potential biomarkers, offering a data-driven framework for risk assessment and biomarker discovery.