Net Algorithm Research Articles

Predicting ICU Admission for Hospitalized COVID-19 Patients by Artificial Neural Network Combined with Elastic Net

Background: Machine learning models could assist physicians in identifying high-risk COVID-19 patients. This study aimed to predict the Intensive Care Unit (ICU) admission in COVID-19 hospitalized patients by the Artificial Neural Network (ANN) model combined with Elastic Net algorithm. Methods: In this prospective study, the data of 139 COVID-19 patients admitted to Imam Reza Hospital in Tabriz between 20 March and 5 April 2020, were analyzed. The Elastic Net method was used to choose features with high importance. The chosen variables were standardized and ANN was fitted to the data with one hidden layer based on the descending gradient algorithm. To validate the model, the training and test group method with a ratio of 70 to 30 was used. The model’s predictive power was reported by calculating the overall accuracy, sensitivity, specificity, and Area Under the ROC curve (AUC). Results: According to the results of the Elastic Net, the ANN model was constructed based on age, sex, body mass index, diabetes mellitus status, history of heart disease, and vital signs including systolic and diastolic blood pressure, saturated oxygen level, pulse rate, respiration rate, and body temperature. The overall accuracy of this model was 93.15%, sensitivity 80%, specificity 95.8%, and AUC 0.90. Saturated oxygen level, pulse rate, and age were the most important and predictive variables. Conclusion: In the investigated sample of patients admitted with COVID-19, the fitted ANN model had acceptable performance to predict the ICU admission. This finding could be useful for physicians and policy makers.

Notation for mass parallel algorithms: computing Petri net state space on GPU case study

We introduce a novel notation for mass parallel algorithms, in particular, algorithms for GPU, which is based on graphical specification of the cube of threads combined with textual expressions, specifying a thread algorithm. We abstract from the peculiarities of a definite GPU preserving basic features of mass-parallel computations. As a case study for the notation, we developed, and implemented in CUDA, a reachability graph algorithm for Petri nets. Parallel hash tables have been introduced to reduce the time complexity. About a hundred time speed-up has been obtained, compared with the best known toolset Tina.

New estimates for inequality of opportunity in Europe using elastic net algorithms

ABSTRACT This paper provides new estimates for inequality of opportunity (IOp) in Europe between 2005 and 2019, using data from EU-SILC and elastic net algorithms. We document three different trends: some countries showed significant improvement over time; others saw a notable increase in IOp; and yet others reversed the rise in inequality post-Great Recession. Importantly, our new machine-learning estimates show consistency with more established approaches.

Priority-Elastic net for binary disease outcome prediction based on multi-omics data

BackgroundHigh-dimensional omics data integration has emerged as a prominent avenue within the healthcare industry, presenting substantial potential to improve predictive models. However, the data integration process faces several challenges, including data heterogeneity, priority sequence in which data blocks are prioritized for rendering predictive information contained in multiple blocks, assessing the flow of information from one omics level to the other and multicollinearity.MethodsWe propose the Priority-Elastic net algorithm, a hierarchical regression method extending Priority-Lasso for the binary logistic regression model by incorporating a priority order for blocks of variables while fitting Elastic-net models sequentially for each block. The fitted values from each step are then used as an offset in the subsequent step. Additionally, we considered the adaptive elastic-net penalty within our priority framework to compare the results.ResultsThe Priority-Elastic net and Priority-Adaptive Elastic net algorithms were evaluated on a brain tumor dataset available from The Cancer Genome Atlas (TCGA), accounting for transcriptomics, proteomics, and clinical information measured over two glioma types: Lower-grade glioma (LGG) and glioblastoma (GBM).ConclusionOur findings suggest that the Priority-Elastic net is a highly advantageous choice for a wide range of applications. It offers moderate computational complexity, flexibility in integrating prior knowledge while introducing a hierarchical modeling perspective, and, importantly, improved stability and accuracy in predictions, making it superior to the other methods discussed. This evolution marks a significant step forward in predictive modeling, offering a sophisticated tool for navigating the complexities of multi-omics datasets in pursuit of precision medicine’s ultimate goal: personalized treatment optimization based on a comprehensive array of patient-specific data. This framework can be generalized to time-to-event, Cox proportional hazards regression and multicategorical outcomes. A practical implementation of this method is available upon request in R script, complete with an example to facilitate its application.

Influence of Protected Areas in the Carbon Cycle: A Machine Learning Approach for Future Forecasting

Protected Areas (PAs) are destined to the conservation of natural resources, whose quantity and quality are menaced by Climate Change and anthropogenic pressure. The objective of this research was to quantify and forecast the Carbon Absorption of PAs, attending these factors. We used the Net Primary Productivity (NPP) and implemented machine learning algorithms, as Random Forests (RF), Gradient Boosting Trees (GBT), and Multilayer Perceptrons (MLPNN), to forecast it in four differentiated PAs of Galicia (NW Spain): the Central Massif, the Sil Canyons, Fragas do Eume, and the Tambre River. Two testing stages were carried, one in the areas where the model was trained, and another in the whole territory. Finally, we set several scenarios based on projections SSP2-4.5 and SSP 5-8.5 in and land use changes. GBT was the most accurate algorithm, with a Root Mean Squared Error (RMSE) of 0.05 kgC/m2 (5.7% of the average NPP) and correlation of 0.9. RF obtained an error of 0.07 and correlation of 80%, and MLPNN 0.06 and 86%, respectively. The GBT obtained a RMSE of 0.04 kgC/m2 and R2 of 0.95 in the first test. These results were worsened in the second test, with an RMSE of 0.09 kgC/m2 and 71% of correlation. For the SSP2-4.5 scenarios, a decrease around 7% can be expected, barely influenced by the land use. On the other hand, the SSP5-8.5 is expected to record a decrease of 5% in the NPP, with no significant differences between the land uses, but with a significant trend. All the pilot sites stick to this trend, except for the Tambre River, which was forecasted to record a slight increase of the NPP (~ 3%). The prediction and analysis of future scenarios can help the management of the territory, focusing on the mitigation of the effects of Climate Change in PAs.Graphical

Machine learning and computer vision technology to analyze and discriminate soil samples

Soil texture is one of the most important elements to consider before planting and tillage. These features affect the product selection and regulate its water permeability. Discrimination of soils by determining soil texture features requires an intense workload and is time-consuming. Therefore, having a powerful tool and knowledge for texture-based soil discrimination could enable rapid and accurate discrimination of soils. This study focuses on presenting new models for 6 different soil sample groups (Soil_1 to Soil_6) based on 12 different machine learning algorithms that can be utilized for various problems. As a result, overall accuracy values were determined as greater than 99.2% (Trilayered Neural Network). The greatest accuracy value was found in Bayes Net (99.83%) and followed by Subspace Discriminant (99.80%). In the Bayes Net algorithm, MCC (Matthews Correlation Coefficient) and F-measure values were obtained as 0.994 and 0.995 for Soil_4 and Soil_6 sample groups while these values were 1.000 for other soil groups. Soil types can visually vary based on their texture, mineral composition, and moisture levels. The variability of this can be influenced by fertilization, precipitation levels, and soil cultivation. It is important to capture the images in soil conditions that are more stable. In conclusion, the present study has proven the feasibility of rapid, non-destructive, and accurate discrimination of soils by image processing-based machine learning.

Predictive analysis of breast cancer metastasis and identification of genetic markers using machine learning.

4 Background: The study devises a framework integrating machine learning (ML) paradigms with explainable artificial intelligence (XAI) to prognosticate the metastatic trajectory of breast cancer (BC) and delineate critical genomic indicators pertinent to metastasis. Methods: An examination was conducted on 98 initial BC specimens, which included 34 instances evolving into distant metastasis within a quintennial monitoring phase and 44 instances evincing no recurrence for a minimum pentad post-diagnosis. Genomic datasets underwent rigorous biostatistical scrutiny, followed by the implementation of an elastic net algorithm for feature discernment, thereby constraining the scope to a salient subset of genomic markers implicated in BC metastasis. An ensemble of advanced predictive models encompassing Light Gradient Boosting Machine (LightGBM), Categorical Boosting (CatBoost), Extreme Gradient Boosting (XGBoost), Gradient Boosting Trees (GBT), and Adaptive Boosting (AdaBoost) was deployed. Model efficacy was gauged through metrics such as accuracy, F1 score, precision, recall, the Area Under the Receiver Operating Characteristic Curve (AUC), and the Brier score. To elucidate the reasoning behind the ML predictions and to navigate the opacity inherent in such models, a SHapley Additive exPlanations (SHAP) approach was invoked. Results: The predictive acumen of the LightGBM model was superior, evidenced by a striking accuracy of 96% and an AUC of 99.3%. Parallel to biostatistical assessments, SHAP analysis leveraging XAI illuminated that augmented expression levels of specific genes, namely TSPYL5, ATP5E, CA9, NUP210, SLC37A1, ARIH1, PSMD7, UBQLN1, PRAME, and UBE2T (with statistical significance p ≤ 0.05), correlated with an escalated risk of BC metastasis. Conversely, diminished expression of CACTIN, TGFB3, SCUBE2, ARL4D, OR1F1, ALDH4A1, PHF1, and CROCC (p ≤ 0.05) was similarly associated with heightened metastatic susceptibility in BC. Conclusions: The insights garnered from this investigation may catalyze preventative strategies against BC progression and metastatic dissemination, thereby enhancing therapeutic efficacy through personalized intervention modalities for BC patients.

Resilient multi-objective mission planning for UAV formation: A unified framework integrating task pre- and re-assignment

Combat effectiveness of unmanned aerial vehicle (UAV) formations can be severely affected by the mission execution reliability. During the practical execution phase, there are inevitable risks where UAVs being destroyed or targets failed to be executed. To improve the mission reliability, a resilient mission planning framework integrates task pre- and re-assignment modules is developed in this paper. In the task pre-assignment phase, to guarantee the mission reliability, probability constraints regarding the minimum mission success rate are imposed to establish a multi-objective optimization model. And an improved genetic algorithm with the multi-population mechanism and specifically designed evolutionary operators is used for efficient solution. As in the task-reassignment phase, possible trigger events are first analyzed. A real-time contract net protocol-based algorithm is then proposed to address the corresponding emergency scenario. And the dual objective used in the former phase is adapted into a single objective to keep a consistent combat intention. Three cases of different scales demonstrate that the two modules cooperate well with each other. On the one hand, the pre-assignment module can generate high-reliability mission schedules as an elaborate mathematical model is introduced. On the other hand, the re-assignment module can efficiently respond to various emergencies and adjust the original schedule within a millisecond. The corresponding animation is accessible at bilibili.com/video/BV12t421w7EE for better illustration.

A Novel Machine-Learning Algorithm to Predict the Early Termination of Nutrition Support Team Follow-Up in Hospitalized Adults: A Retrospective Cohort Study.

For hospitalized adults, it is important to initiate the early reintroduction of oral food in accordance with nutrition support team guidelines. The aim of this study was to develop and validate a machine learning-based algorithm that predicts the early termination of medical nutritional therapy (the transition to oral feeding). This retrospective cohort study included consecutive adult patients admitted to the Hacettepe hospital (from 1 January 2018 to 31 December 2022). The outcome of the study was the prediction of an early transition to adequate oral feeding before discharge. The dataset was randomly (70/30) divided into training and test datasets. We used six ML algorithms with multiple features to construct prediction models. ML model performance was measured according to the accuracy, area under the receiver operating characteristic curve, and F1 score. We used the Boruta Method to determine the important features and interpret the selected features. A total of 2298 adult inpatients who were followed by a nutrition support team for medical nutritional therapy were included. Patients received parenteral nutrition (1471/2298, 64.01%), enteral nutrition (717/2298, 31.2%), or supplemental parenteral nutrition (110/2298, 4.79%). The median (interquartile range) Nutritional Risk Screening (NRS-2002) score was 5 (1). Six prediction algorithms were used, and the artificial neural network and elastic net models achieved the greatest area under the ROC in all outcomes (AUC = 0.770). Ranked by z-value, the 10 most important features in predicting an early transition to oral feeding in the artificial neural network and elastic net algorithms were parenteral nutrition, surgical wards, surgical outcomes, enteral nutrition, age, supplemental parenteral nutrition, digestive system diseases, gastrointestinal complications, NRS-2002, and impaired consciousness. We developed machine learning models for the prediction of an early transition to oral feeding before discharge. Overall, there was no discernible superiority among the models. Nevertheless, the artificial neural network and elastic net methods provided the highest AUC values. Since the machine learning model is interpretable, it can enable clinicians to better comprehend the features underlying the outcomes. Our study could support personalized treatment and nutritional follow-up strategies in clinical decision making for the prediction of an early transition to oral feeding in hospitalized adult patients.

Swarm-to-swarm orbital pursuit method under delta-v maneuver for space pursuit-evasion

This paper investigates the orbital pursuit strategy for spacecraft swarms, where both pursuers and evaders possess limited delta-v maneuvering capabilities. Given that swarms can consist of numerous members, ranging from dozens to thousands, the swarm-to-swarm problem has significant coupling effects that cannot be solved by merely superimposing one-to-one or few-to-few problems. Otherwise, one would cause a dimension explosion in decision-making space. To avoid this issue, the swarm orbital pursuit problem is divided into two coupled problems: swarm target allocation and orbital maneuver. First, considering the relative orbit state between pursuers and evaders and estimated orbital maneuver costs of pursuit, the swarm target allocation problem is formulated into three coupled sub-problems, i.e., target allocation order, target allocation for sub-swarms, and target allocation for individuals. These sub-problems are solved by the presented double-layer contract net protocol algorithm to maximize task completion efficiency. Then, the orbital maneuver problem is decomposed into two coupled problems to maximize pursuit benefits, i.e., long-range rendezvous, and close-distance game maneuvers. For the long-range rendezvous, the optimal Lambert algorithm is developed to efficiently obtain the discrete optimal pursuit time and corresponding orbital transfer maneuver. To address close-distance games more proficiently, a hybrid orbital maneuver algorithm, combining the proximal policy optimization and the Lambert algorithm is proposed. Finally, comparison simulations verified the effectiveness and superiority of the proposed method.

Tire Texture Monitoring (VGG 19 VS Efficient Net b7)

Tires are crucial components of vehicles, continuously in contact with the road. Monitoring tire conditions is vital for safety and performance, as degradation in tire treads and sidewalls can affect traction, fuel efficiency, longevity, and road noise. This research leverages both VGG19 and Efficient Net B7 algorithms to enhance tire image rendering, addressing limitations of traditional techniques. Using a binary classification algorithm, we classify tire images as healthy or cracked. By fine-tuning VGG19 and EfficientNet B7 on a specialized tire dataset, we achieve high-quality, photorealistic renderings. Our results demonstrate remarkable improvements in texture quality and visual realism compared to traditional methods. The rendered images exhibit finer details and more accurate representations of the tire’s tread patterns and material properties. This research contributes to the field of computer graphics by presenting a novel application of deep learning techniques to a specific industrial need, paving the way for future advancements in high-quality rendering of complex tire textures. Key Words: VGG19,Photorealistic rendering, deep learning.

Deep Learning-Based Hybrid Precoding Approach in the Massive Multiple-Input Multiple-Output System

Precoding is a critical signal processing technique used in wireless communication systems to enhance transmission performance. This paper initially provides a brief overview of various conventional precoding algorithms. The exploration includes various nonlinear precoding algorithms which outperform linear techniques in high signal-to-noise ratio (SNR) scenarios. Moreover, the paper delves into practical considerations and provides insights into selecting the most suitable technique for specific communication scenarios. The deep learning-based hybrid precoder is designed using the MDL-AltMin algorithm and simulated results show a spectral efficiency of (SE) 40.96 dB compared with different precoding algorithms. The precoder model is modified with a Hybrid Precoding Net algorithm with a spectral efficiency of 21.07 dB for high values of SNR such as −30 and again compared with deep learning precoders. The HPNet model is proposed with a spectral efficiency of 23.04 dB with and without CSI (Channel State Information) at the transmitter. Furthermore, the HPNet model is compared with optimal digital precoders.

Predicting lymph node metastasis in colorectal cancer patients: development and validation of a column chart model

Lymph node metastasis (LNM) is one of the crucial factors in determining the optimal treatment approach for colorectal cancer. The objective of this study was to establish and validate a column chart for predicting LNM in colon cancer patients. We extracted a total of 83,430 cases of colon cancer from the Surveillance, Epidemiology, and End Results (SEER) database, spanning the years 2010–2017. These cases were divided into a training group and a testing group in a 7:3 ratio. An additional 8545 patients from the years 2018–2019 were used for external validation. Univariate and multivariate logistic regression models were employed in the training set to identify predictive factors. Models were developed using logistic regression, LASSO regression, ridge regression, and elastic net regression algorithms. Model performance was quantified by calculating the area under the ROC curve (AUC) and its corresponding 95% confidence interval. The results demonstrated that tumor location, grade, age, tumor size, T stage, race, and CEA were independent predictors of LNM in CRC patients. The logistic regression model yielded an AUC of 0.708 (0.7038–0.7122), outperforming ridge regression and achieving similar AUC values as LASSO regression and elastic net regression. Based on the logistic regression algorithm, we constructed a column chart for predicting LNM in CRC patients. Further subgroup analysis based on gender, age, and grade indicated that the logistic prediction model exhibited good adaptability across all subgroups. Our column chart displayed excellent predictive capability and serves as a useful tool for clinicians in predicting LNM in colorectal cancer patients.

Dissecting Crucial Gene Markers Involved in HPV-Associated Oropharyngeal Squamous Cell Carcinoma from RNA-Sequencing Data through Explainable Artificial Intelligence

Background: The incidence rate of oropharyngeal squamous cell carcinoma (OPSCC) worldwide is alarming. In the clinical community, there is a pressing necessity to comprehend the etiology of the OPSCC to facilitate the administration of effective treatments. Methods: This study confers an integrative genomics approach for identifying key oncogenic drivers involved in the OPSCC pathogenesis. The dataset contains RNA-Sequencing (RNA-Seq) samples of 46 Human papillomavirus-positive head and neck squamous cell carcinoma and 25 normal Uvulopalatopharyngoplasty cases. The differential marker selection is performed between the groups with a log2FoldChange (FC) score of 2, adjusted p-value < 0.01, and screened 714 genes. The Particle Swarm Optimization (PSO) algorithm selects the candidate gene subset, reducing the size to 73. The state-of-the-art machine learning algorithms are trained with the differentially expressed genes and candidate subsets of PSO. Results: The analysis of predictive models using Shapley Additive exPlanations revealed that seven genes significantly contribute to the model’s performance. These include ECT2, LAMC2, and DSG2, which predominantly influence differentiating between sample groups. They were followed in importance by FAT1, PLOD2, COL1A1, and PLAU. The Random Forest and Bayes Net algorithms also achieved perfect validation scores when using PSO features. Furthermore, gene set enrichment analysis, protein-protein interactions, and disease ontology mining revealed a significant association between these genes and the target condition. As indicated by Shapley Additive exPlanations (SHAPs), the survival analysis of three key genes unveiled strong over-expression in the samples from “The Cancer Genome Atlas”. Conclusions: Our findings elucidate critical oncogenic drivers in OPSCC, offering vital insights for developing targeted therapies and enhancing understanding its pathogenesis.

Management of Traditional Business into Modern: from Microsoft Excel to Deep Learning for prototyping classification Swiftlet’s nests

In this article, the transformation of traditional management of Swiftlet’s nests into modern business is proposed. Traditional business means that data management of Swiftlet’s nests is done manually, sorted by recording in Microsoft Excel. This is done by PT Waleta Asia Jaya, a company engaged in processing Swiftlet’s nests. This sorting is done because the number of feathers in the Swiftlet’s nests determines the price and cost of workers in processing feather cleaning. In addition, the shape of the Swiftlet’s nests needs attention. However, because it is complex, sorting is done simpler. Originally, Swiftlet’s nests were sorted into 50 categories. To facilitate sorting, deep learning is used with the SSD Mobile Net V2 algorithm as an algorithm to classify into 7 categories based on feather intensity. The device is still a prototype that shows an 85% accuracy rate but has been quite helpful in the process of purchasing Swiftlet’s nests before processing.

Screening the influence of features for metabolic syndrome in occupational population based on Lasso and Elastic Net algorithms

Abstract Funding Acknowledgements None. Objective Screening features associated with metabolic syndrome (MetS) is essential for early detection in the occupational population. In this study, we utilized two machine learning algorithms to screen MetS features and compared the performance of models constructed from these screened features. Method A total of 3,077 workers’examination records were considered from our hospital. However, 233 records were excluded due to incompleteness and errors, resulting in a final dataset of 2,844 workers’examination records used for the study. We collected and analyzed available data to extract usable indicators initially. Then, we applied the Least Absolute Shrinkage and Selection Operator (Lasso) algorithm and Elastic Net algorithm to identify features related to MetS. Subsequently, different models, namely K-Nearest Neighbors (KNN), Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM),were established using these two groups of features to predict the probability of MetS in the occupational population. The performance of these models was evaluated using the Area Under the Receiver Operating Characteristic Curve (AUC), Calibration Curve, and Decision Curve Analysis (DCA). Results It was indicated that features screened by the Elastic Net algorithm were more stable and demonstrated better predictive performance compared to LASSO, particularly when the data had high dimensionality and correlations. Furthermore, this study presents the first application of the Elastic Net algorithm in screening features related to MetS and establishing a risk prediction model for routine physical examinations of the occupational population. Conclusion Notably, Elastic Net demonstrated improved stability when dealing with multiple indicators exhibiting high dimensional correlations. This enhanced stability allowed for a more accurate prediction of MetS, providing a basis for utilizing common universal indicators in health screening for the general occupational population.Study the basic characteristics of the p(a) AUC performance of 9 features screen

Facial Emotion Recognition using Convolutional Neural Network

Emotion is an expression that human use in expressing their feelings. It can be express through facial expression, body language and voice tone. Humans' facial expression is a major way in conveying emotion since it is the most powerful, natural and universal signal to express humans' emotion condition. However, humans' facial expression has similar patterns, and it is very confusing in recognizing the expression using naked eye. For instance, afraid and surprised is very similar to one another. Thus, this will lead to confusion in determining the facial expression. Hence, this study aims to develop a application for emotion recognition that can recognize emotion based on facial expression in real-time. The Deep Learning based technique, Convolutional Neural Network (CNN) is implemented in this study. The Mobile Net algorithm is deployed to train the model for recognition. There are four types of facial expressions to be recognized which are happy, sad, surprise, and disgusting. Keywords: Facial Emotion Recognition, Deep Learning, CNN, Image Processing.

Generic Framework for Vehicle Identification System with Deep Learning Models

In contemporary vehicle scenario, different kinds of vehicles are playing vital role for the customers. Day by day, vehicles are increasing with different properties and identifications. Monitoring and maintain the records of vehicles in digital platform is the challenging task as well as a crucial task for the countries. Here, we have to take the scenario of digitalization of vehicles with deep learning network models for identification and maneuvering process. In our country, different states are following multiple vehicle identification like numbering, coloring and imaging. Many researchers were contributing towards this identification mechanism like supervised, unsupervised models for getting optimum accuracy. Text and Image classification are not sufficient to solve this vehicle identification problem. We are incorporating text, image and video related unstructured data set to solve this problem. We have framed a generic architecture for all kind of vehicles analyze the data. For instance, a vehicle is moving towards CCTV camera and it has been recorded as video content. In this paper, we come across video to still pictures and image segmentation and all the identification parameters like White, Yellow and green. We performed both text classification and image classification algorithms to acquire effective result compared to existing algorithms. Bi Directional RNN (LSTM/GRU) and LeNet, Alex Net, Inception, VggNet and ResNet algorithms are analyzed for this entire process. This is one of the globally challenging scenarios for identification with feature extraction, data cleaning and processing. At the end of the result, we achieved 98.94 % accuracy compare than other existing systems.

Leveraging Mobile Net and Yolo Algorithm for Enhanced Perception in Autonomous Driving

This project presents a cutting-edge autonomous navigation system designed to enhance spatial understanding and object recognition for vehicles. Equipped with cameras on both the left and right sides, by capturing comprehensive view of the surroundings, utilizing stereo vision for crucial depth information. The integration of Mobile Net and YOLO (You Only Look Once) algorithms is central to achieving real-time object detection and recognition. Mobile Net is employed for efficient feature extraction, ensuring optimal computational efficiency. Simultaneously, YOLO plays a pivotal role in rapid and accurate identification of objects within the captured images, contributing to the robustness of spatial understanding crucial for autonomous navigation. The result is a comprehensive and reliable autonomous navigation system, showcasing the effectiveness of combining cutting-edge technologies for improved real time decision making.

Elastic Net – MLP – SMOTE (EMS)-Based Model for Enhancing Stroke Prediction

A stroke is a sudden disruption in the blood supply to the brain, affecting one or more blood vessels that nourish the brain. This results in a disturbance or deficiency in the brain’s oxygen supply, causing damage or impairment to brain cells. In some cases, determining the timing and severity of a stroke can be challenging. This study proposes an EMS (Elastic Net – MLP – SMOTE) model built on artificial intelligence, specifically utilizing two machine learning algorithms, Elastic Net and multilayer perceptron (MLP) by using Synthetic Minority Over-sampling Technique (SMOTE). The Elastic Net algorithm was employed for feature selection to identify crucial features, followed by prediction using the MLP algorithm. The Elastic Net algorithm was used due to its incorporation of both L2 and L1 regularization, providing good results in discerning influential features in model performance. The MLP algorithm was employed for its reliance on deep learning techniques, which yield promising results in such cases. This algorithm classified data from a comprehensive dataset containing essential features related to stroke. SMOTE is used to increase the performance of the model. Notably, no previous research study has integrated these three techniques together (Elastic Net – MLP – SMOTE). EMS achieved a prediction accuracy of 95% and MSE = 0.05. This model facilitates predicting the occurrence of stroke by relying on the patient’s historical data, mitigating the sudden onset of this serious disease.