K-fold Cross Validation Technique Research Articles

Artificial intelligence-based estimation of ultra-high-strength concrete's flexural property

Advancement in Artificial Intelligence (AI) techniques and their applications in the construction industry, particularly for predicting mechanical properties of concrete, leads to conservation of efforts, time and cost. However, insufficient research has been done on the Ultra-high-strength concrete (UHSC). For this reason, this study aims to predict the UHSC flexural strength by applying sophisticated AI approaches. Ensembled machine learning techniques performed well compared to the individual decision tree (DT) model. In the current research, UHSC flexural strength is predicted by employing supervised Machine Learning (ML) approaches, i.e., DT-Bagging, DT-Gradient Boosting, DT-AdaBoost, and DT- XG Boost. Moreover, the model performance is assessed with the help of R2, Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). In addition to that, the validation of model performance is also done by using the k-fold cross-validation technique. Higher R2 of 0.95 and lesser error (i.e., RMSE and MAE) values, in the case of the DT-Bagging model, depict improved model performance with respect to other applied ensemble methods. The assessment output shows that anticipated outcomes from proposed models, i.e., DT-Bagging, are much closer to actual results from experiments, which indicates the enhanced prediction of flexural strength for UHSC. Further, the SHapley Additive exPlanations (SHAP) analysis shows that steel fiber content has the highest positive influence on UHSC flexural strength.

Exploring the Use of Waste Marble Powder in Concrete and Predicting Its Strength with Different Advanced Algorithms.

Recently, the high demand for marble stones has progressed in the construction industry, ultimately resulting in waste marble production. Thus, environmental degradation is unavoidable because of waste generated from quarry drilling, cutting, and blasting methods. Marble waste is produced in an enormous amount in the form of odd blocks and unwanted rock fragments. Absence of a systematic way to dispose of these marble waste massive mounds results in environmental pollution and landfills. To reduce this risk, an effort has been made for the incorporation of waste marble powder into concrete for sustainable construction. Different proportions of marble powder are considered as a partial substitute in concrete. A total of 40 mixes are prepared. The effectiveness of marble in concrete is assessed by comparing the compressive strength with the plain mix. Supervised machine learning algorithms, bagging (Bg), random forest (RF), AdaBoost (AdB), and decision tree (DT) are used in this study to forecast the compressive strength of waste marble powder concrete. The models’ performance is evaluated using correlation coefficient (R2), root mean square error, and mean absolute error and mean square error. The achieved performance is then validated by using the k-fold cross-validation technique. The RF model, having an R2 value of 0.97, has more accurate prediction results than Bg, AdB, and DT models. The higher R2 values and lesser error (RMSE, MAE, and MSE) values are the indicators for better performance of RF model among all individual and ensemble models. The implementation of machine learning techniques for predicting the mechanical properties of concrete would be a practical addition to the civil engineering domain by saving effort, resources, and time.

Aplicação de um modelo de aprendizado de máquina em estudo de eficiência energética de edificações: foco para sistemas construtivos leves

The use of machine learning techniques in thermoenergetic performance studies of buildings emerges as an alternative to conventional methods which analysis require greater data complexity. This research aims to apply a machine learning technique in the study of energy efficiency of a building executed in a light construction system. Thus, an algorithm was implemented referring to an optimized model of classification and regression tree (CART) for application in a data set. This data set includes 2048 parametric simulations of a housing in a light construction system to the climate of the city of São Paulo, whose output indicators are the annual thermal load for heating and the annual thermal load for cooling. From the application of a tree pruning methodology and the use of Grid Search and k-fold Cross Validation techniques, the training and testing of the model was repeated 100 times, thus obtaining average results of 1.11\% of error for heating loads and 1.52\% of error for predicting cooling loads. Subsequently, a sensitivity analysis was performed, revealing the thermal transmittance property of the walls as the parameter with the greatest influence on the prediction of heating load and the condition of contact between the ground and the floor as the parameter with the greatest influence on the prediction of cooling load. Finally, decision trees were generated for visual analysis of strategies that can be adopted to obtain better levels of thermoenergetic performance. Thus, a more simplified diagnosis of energy efficiency was obtained, with low complexity in the interpretation of its results, favoring greater diffusion of the technology in light systems.

Credit Risk Evaluation in Banking and Lending Sectors Using Neural Network Model

This study presents the results of an experiment made with google colaboratory. The Google Colaboratory is also known as google colab it is a free online cloud-based Jupyter notebook environment that allows us to train our machine learning and deep learning models on CPUs, GPUs, and TPUs. We can determine the accuracy of the credit risk evaluation based on the dataset that was run in google colab using a neural network. The dataset has been thoroughly evaluated in creating a test harness for evaluating candidate models by calculating accuracy using k-fold cross-validation. When compared to a single train-test split, the k-fold cross-validation technique provides a reasonable general approximation of model performance. Based on the result, the correct number of rows was loaded, and through the one-hot encoding of the categorical input variables, it increased the number of input variables from 20 to 61. That suggests that the 13 categorical variables were encoded into a total of 54 columns. The result of the evaluation can help the banking and other financial sectors to assess a person before they are given a loan and if they can pay on time. This is a big help to reduce the losses of a company. Not only in the banking and other financial sectors as well as in lenders of goods.

Runtime prediction of big data jobs: performance comparison of machine learning algorithms and analytical models

Due to the rapid growth of available data, various platforms offer parallel infrastructure that efficiently processes big data. One of the critical issues is how to use these platforms to optimise resources, and for this reason, performance prediction has been an important topic in the last few years. There are two main approaches to the problem of predicting performance. One is to fit data into an equation based on a analytical models. The other is to use machine learning (ML) in the form of regression algorithms. In this paper, we have investigated the difference in accuracy for these two approaches. While our experiments used an open-source platform called Apache Spark, the results obtained by this research are applicable to any parallel platform and are not constrained to this technology. We found that gradient boost, an ML regressor, is more accurate than any of the existing analytical models as long as the range of the prediction follows that of the training. We have investigated analytical and ML models based on interpolation and extrapolation methods with k-fold cross-validation techniques. Using the interpolation method, two analytical models, namely 2D-plate and fully-connected models, outperform older analytical models and kernel ridge regression algorithm but not the gradient boost regression algorithm. We found the average accuracy of 2D-plate and fully-connected models using interpolation are 0.962 and 0.961. However, when using the extrapolation method, the analytical models are much more accurate than the ML regressors, particularly two of the most recently proposed models (2D-plate and fully-connected). Both models are based on the communication patterns between the nodes. We found that using extrapolation, kernel ridge, gradient boost and two proposed analytical models average accuracy is 0.466, 0.677, 0.975, and 0.981, respectively. This study shows that practitioners can benefit from analytical models by being able to accurately predict the runtime outside of the range of the training data using only a few experimental operations.

Weed Identification by Single-Stage and Two-Stage Neural Networks: A Study on the Impact of Image Resizers and Weights Optimization Algorithms.

The accurate identification of weeds is an essential step for a site-specific weed management system. In recent years, deep learning (DL) has got rapid advancements to perform complex agricultural tasks. The previous studies emphasized the evaluation of advanced training techniques or modifying the well-known DL models to improve the overall accuracy. In contrast, this research attempted to improve the mean average precision (mAP) for the detection and classification of eight classes of weeds by proposing a novel DL-based methodology. First, a comprehensive analysis of single-stage and two-stage neural networks including Single-shot MultiBox Detector (SSD), You look only Once (YOLO-v4), EfficientDet, CenterNet, RetinaNet, Faster Region-based Convolutional Neural Network (RCNN), and Region-based Fully Convolutional Network (RFCN), has been performed. Next, the effects of image resizing techniques along with four image interpolation methods have been studied. It led to the final stage of the research through optimization of the weights of the best-acquired model by initialization techniques, batch normalization, and DL optimization algorithms. The effectiveness of the proposed work is proven due to a high mAP of 93.44% and validated by the stratified k-fold cross-validation technique. It was 5.8% improved as compared to the results obtained by the default settings of the best-suited DL architecture (Faster RCNN ResNet-101). The presented pipeline would be a baseline study for the research community to explore several tasks such as real-time detection and reducing the computation/training time. All the relevant data including the annotated dataset, configuration files, and inference graph of the final model are provided with this article. Furthermore, the selection of the DeepWeeds dataset shows the robustness/practicality of the study because it contains images collected in a real/complex agricultural environment. Therefore, this research would be a considerable step toward an efficient and automatic weed control system.

Accurate discharge coefficient prediction of streamlined weirs by coupling linear regression and deep convolutional gated recurrent unit

ABSTRACT Streamlined weirs, which are a nature-inspired type of weir, have gained tremendous attention among hydraulic engineers, mainly owing to their established performance with high discharge coefficients. Computational fluid dynamics (CFD) is considered as a robust tool to predict the discharge coefficient. To bypass the computational cost of CFD-based assessment, the present study proposes data-driven modeling techniques, as an alternative to CFD simulation, to predict the discharge coefficient based on an experimental dataset. To this end, after splitting the dataset using a k-fold cross-validation technique, the performance assessment of classical and hybrid machine learning–deep learning (ML-DL) algorithms is undertaken. Among ML techniques, linear regression (LR), random forest (RF), support vector machine (SVM), k-nearest neighbor (KNN) and decision tree (DT) algorithms are studied. In the context of DL, long short-term memory (LSTM), convolutional neural network (CNN) and gated recurrent unit (GRU), and their hybrid forms, such as LSTM-GRU, CNN-LSTM and CNN-GRU techniques, are compared using different error metrics. It is found that the proposed three-layer hierarchical DL algorithm, consisting of a convolutional layer coupled with two subsequent GRU levels, which is also hybridized with the LR method (i.e. LR-CGRU), leads to lower error metrics. This paper paves the way for data-driven modeling of streamlined weirs.

Deep-Neural-Network-Based Estimation of Site Amplification Factor from Microtremor H/V Spectral Ratio

ABSTRACT Site amplification factors (SAFs) of S wave at ground surface are crucial for evaluating and predicting seismic ground motions. This study proposed a novel methodology for directly estimating S-wave SAF from microtremor horizontal-to-vertical spectral ratio (MHVR) based on deep neural network (DNN) model. We analyzed site amplifications obtained from generalized spectral inversion technique and microtremor data observed at Kyoshin net and Kiban–Kyoshin network sites in Chugoku district, western Japan. The DNN model was developed using peak frequency and the frequency-dependent relationship between MHVRs and SAFs. The sites were divided into training set, validation set, and test set. The training set and validation set were used in k-fold cross-validation technique to evaluate and select optimal model. Once the optimal model had been determined, the model was employed on the test set that was completely independent of the training and validation set for evaluating the generalization performance. Residuals and root mean square errors between the estimated and observed SAFs were evaluated to discuss the applicability of the proposed model. We also confirmed that the DNN model shows better performance in estimating SAFs compared with the existing double empirical correction method.

Improved Machine Learning-Based Predictive Models for Breast Cancer Diagnosis.

Breast cancer death rates are higher than any other cancer in American women. Machine learning-based predictive models promise earlier detection techniques for breast cancer diagnosis. However, making an evaluation for models that efficiently diagnose cancer is still challenging. In this work, we proposed data exploratory techniques (DET) and developed four different predictive models to improve breast cancer diagnostic accuracy. Prior to models, four-layered essential DET, e.g., feature distribution, correlation, elimination, and hyperparameter optimization, were deep-dived to identify the robust feature classification into malignant and benign classes. These proposed techniques and classifiers were implemented on the Wisconsin Diagnostic Breast Cancer (WDBC) and Breast Cancer Coimbra Dataset (BCCD) datasets. Standard performance metrics, including confusion matrices and K-fold cross-validation techniques, were applied to assess each classifier’s efficiency and training time. The models’ diagnostic capability improved with our DET, i.e., polynomial SVM gained 99.3%, LR with 98.06%, KNN acquired 97.35%, and EC achieved 97.61% accuracy with the WDBC dataset. We also compared our significant results with previous studies in terms of accuracy. The implementation procedure and findings can guide physicians to adopt an effective model for a practical understanding and prognosis of breast cancer tumors.

A Method for Improving Prediction of Human Heart Disease Using Machine Learning Algorithms

A great diversity comes in the field of medical sciences because of computing capabilities and improvements in techniques, especially in the identification of human heart diseases. Nowadays, it is one of the world’s most dangerous human heart diseases and has very serious effects the human life. Accurate and timely identification of human heart disease can be very helpful in preventing heart failure in its early stages and will improve the patient’s survival. Manual approaches for the identification of heart disease are biased and prone to interexaminer variability. In this regard, machine learning algorithms are efficient and reliable sources to detect and categorize persons suffering from heart disease and those who are healthy. According to the recommended study, we identified and predicted human heart disease using a variety of machine learning algorithms and used the heart disease dataset to evaluate its performance using different metrics for evaluation, such as sensitivity, specificity, F-measure, and classification accuracy. For this purpose, we used nine classifiers of machine learning to the final dataset before and after the hyperparameter tuning of the machine learning classifiers, such as AB, LR, ET, MNB, CART, SVM, LDA, RF, and XGB. Furthermore, we check their accuracy on the standard heart disease dataset by performing certain preprocessing, standardization of dataset, and hyperparameter tuning. Additionally, to train and validate the machine learning algorithms, we deployed the standard K-fold cross-validation technique. Finally, the experimental result indicated that the accuracy of the prediction classifiers with hyperparameter tuning improved and achieved notable results with data standardization and the hyperparameter tuning of the machine learning classifiers.

Application of novel data-mining technique based nitrate concentration susceptibility prediction approach for coastal aquifers in India

In water resource management and pollution control research, prediction of nitrate concentration in groundwater gets utmost priority in the last few years. Thus, our current research work aims to identify the nitrate susceptibility areas of coastal districts of eastern India using three data mining techniques of random forest (RF), boosting and bagging approach. To make groundwater nitrate concentration susceptibility map, fifteen nitrate conditioning factors were identified using multi-collinearity analysis and identify relative importance of nitrate variability using MDA method. The resampling method of four K-Fold cross validation (CV) technique was used to preparing inventory dataset and respective modelling purpose. Seven statistics methods including receiver operating characteristics-area under curve (ROC-AUC) and Taylor diagram have been applied for evaluating the performance of all applied models. The outcomes ensure that boosting model is more efficient followed by bagging and RF. Taylor diagram also revealed Boosting (r = 0.93) is most optimal model followed by Bagging (r = 0.89) and RF (r = 0.88). From aforementioned results, our study revealed that boosting is the well performed model to delineate groundwater nitrate concentrate susceptibility map (GNCSM) in regional level which also will be helpful to worldwide researcher to find out nitrate susceptibility zone in coastal environment and it may be fruitful to the different policy makers to take accurate decision for water management in the current study area.

Forecasting ATM Cash Demand Before and During the COVID-19 Pandemic Using an Extensive Evaluation of Statistical and Machine Learning Models.

The overarching goal of this paper is to accurately forecast ATM cash demand for periods both before and during the COVID-19 pandemic. To achieve this, first, ATMs are categorized based on accessibility and surrounding environmental factors that significantly affect the cash withdrawal pattern. Then, several statistical and machine learning models under different algorithms and strategies are employed. In aiming to provide the feature matrix for machine learning models, some new influential variables are added to the literature. Finally, a modified fitness measure is proposed for the first time to correctly choose the most promising model by considering both the prediction errors and accuracy of direction’s change simultaneously. The results obtained by a comprehensive analysis—a statistical analysis together with grid search and k-fold cross-validation techniques—reveal that (i) category-wise prediction enhances forecasting quality; (ii) before COVID-19 and in times when there are only minor disturbances in withdrawal patterns, forecasting quality is higher, and in general, the machine learning models can more appropriately forecast ATM’s cash demand; (iii) despite studies in the literature, sophisticated models will not always outperform simpler models. It is found that during COVID-19 and in times when there is a sudden shock in demand and massive volatility in withdrawal patterns, the statistical models of the autoregressive integrated moving average (ARIMA) and seasonal ARIMA (SARIMA) can mainly provide better forecasting likely due to high performance of such models for short-term prediction, while minimizing overfitting.Supplementary InformationThe online version contains supplementary material available at 10.1007/s42979-021-01000-0.

Decision Support System for Determining the Feasibility of Material Utilization Using the Naïve Bayes Method

A company is engaged in the mechanical and electrical industry in providing goods and services, especially in medium and high power installations. In this company, the data management process carried out is still semi-computer, on a sheet of paper then copied into a computer with the Microsoft Excel application. Every work done by a technician in using material contains materials that are not used up or used materials. The material is then returned to the warehouse to be used as a report which is then carried out by the utilization process. The purpose of this research is to create a system that can assist in providing suggestions for used or used materials in the warehouse for utilization by applying the Naïve Bayes method. Naïve Bayes is a data mining technique with a classification function. This data mining application methodology uses the KDD (Knowledge Discovery in Database) stage starting from the selecting, preprocessing, transformation, data mining, evaluation stages. The testing technique used for data validation uses the k-fold cross-validation technique accompanied by a Confusion Matrix. This research has produced a decision support system application and has been tested with an accuracy rate of 73.33%.

Risk predictors selection and predict for the first-day neonatal mortality in Bangladesh using machine learning techniques

Although the neonatal mortality rate has been diminished over time in Bangladesh, the rate is still very high. The day of birth is the most vulnerable period for newborns. This study assessed to predict and detect associated risk predictors of the first-day neonatal mortality through Machine Learning (ML) algorithm. We investigated the potential risk factors on the information collected from 43,772 evermarried women of different backgrounds extracted from the 2014 Bangladesh Demographic and Health Survey (BDHS). Based on this demographic and socio-economic risk factors, our goal is to predict the prevalence of first-day neonatal mortality in Bangladesh. Analysis was done using different ML algorithms. Boruta algorithm and Support Vector Machine (SVM) were used to extract the relevant risk factors of the first-day neonatal mortality. Prediction of the prevalence of the first-day neonatal mortality was executed using Decision Tree (DT), Random Forest (RF), SVM, and Logistic Regression (LR), and their performances were appraised using different parameters of confusion matrix, Receiver Operating Characteristics (ROC) curves, and k-fold cross-validation techniques. About two-thirds of the firstday neonatal mortality occurred in the rural area. Male children had high neonatal mortality, with a rate of 51.2%. Mother Age at 1st birth, Husband/partner’s education level, Type of cooking fuel, Total children ever born, Wealth index, Mother’s education level, Access to media, and Type of place of residence were selected as significant risk predictors for predicting the first-day neonatal mortality. Results found that the SVM with Gaussian kernel (Accuracy = 0.8358, Sensitivity = 0. 8637, Specificity = 0.3333, Precision = 0.9588, area under the ROC curve (AUC) = 0.6596, k-fold accuracy=0.8530) performed better among the four machine learning models to predict the firstday neonatal mortality in Bangladesh. Machine learning framework can detect significant predictors of the first-day neonatal mortality, therefore may help the health-policymakers, stakeholders, and family members to understand and prevent this public health problem. Keywords: infant health; decision tree; random forest; support vector machine; feature selection; logistic regression; boruta algorithm; confusion matrix; ROC; k-fold cross-validation.

Acoustic impedance and lithology-based reservoir porosity analysis using predictive machine learning algorithms

Porosity prediction and analysis is crucial for reservoir delineation, characterization and well placement. Basically, porosity measurements are obtained from well logs and core samples. However, methods based on core samples and well logs are sometimes challenging, time-consuming and very expensive. In this paper we attempt to predict and analyze porosity using machine learning algorithms. Porosity prediction is performed as a supervised multiple regression problem. Every data point of the training sample from the study area is made of lithology and acoustic impedance which are defined as independent variables or predictors while measured value of porosity is the dependent variable, provided as the label to be predicted. Deep neural network, Random forest and Decision tree algorithms were subjected to training and learning of rich and proper features that are important for the prediction of porosity thus, good generalization ability is crucial to the successful training of a machine learning model. Therefore, we used several optimization functions to train the deep neural network in order to choose the best performing one, on which we retrained the model using k-fold cross-validation technique. Although all the algorithms showed very good performance, deep neural network proved to be the most efficient with 0.042% of the mean squared error as the learning loss and 0.051% of the training mean absolute error. Our result was further tested for effectiveness by using new set of non-labeled lithology and acoustic impedance data and the result was compared with measured porosity and the result showed 89% of the Pearson correlation. Compared with measured porosity, prediction results displayed accurate prediction of porosity within milliseconds thus saving the working time. The result of this study shows that machine-learning algorithms can be time saving and reliable alternative for reservoir porosity prediction and analysis.

The ultimate kernel machine for diagnosis of breast cancer

In this paper, an extensive study of diagnosis of breast cancer is made using support vector machine (SVM) technique. To build the cost-effective kernel machine for breast cancer diagnosis, the tools of principal component analysis (PCA) and k-fold cross-validation (CV) techniques are employed. The model is implemented on WDBC and WBC datasets to check the condition of the tumour for its malignancy. Classification accuracy and computation time are obtained and comparative experimental results are analysed under different conditions. For WBC dataset, 100% accuracy is obtained using polynomial kernel in just 0.03 second.

A Performance-Optimized Deep Learning-Based Plant Disease Detection Approach for Horticultural Crops of New Zealand

Deep learning-based plant disease detection has gained significant attention from the scientific community. However, various aspects of real horticultural conditions have not yet been explored. For example, the disease should be considered not only on leaves, but also on other parts of plants, including stems, canes, and fruits. Furthermore, the detection of multiple diseases in a single plant organ at a time has not been performed. Similarly, plant disease has not been identified in various crops in the complex horticultural environment with the same optimized/modified model. To address these research gaps, this research presents a dataset named NZDLPlantDisease-v1, consisting of diseases in five of the most important horticultural crops in New Zealand: kiwifruit, apple, pear, avocado, and grapevine. An optimized version of the best obtained deep learning (DL) model named region-based fully convolutional network (RFCN) has been proposed to detect plant disease using the newly generated dataset. After final the most suitable DL model, data augmentation techniques were successively evaluated. Subsequently, the effects of image resizers with interpolators, weight initializers, batch normalization, and DL optimizers were studied. Finally, performance was enhanced by empirical observation of position-sensitive score maps and anchor box specifications. Furthermore, the robustness/practicality of the proposed approach was demonstrated using a stratified k-fold cross-validation technique and testing on an external dataset. The final mean average precision of the RFCN model was found to be 93.80%, which was 19.33% better than the default settings. Therefore, this research could be a benchmark step for any follow-up research on automatic control of disease in several plant species.

Microscopic identification of brazilian commercial wood species via machine-learning

Background: Multiple challenges are faced by industry and certification agencies when commercializing tropical species. Anatomical similarities of tropical hardwoods impair identification. Deep learning models can facilitate microscopic identification of wood by using sophisticated techniques such as deep convolutional networks (DCNN). Our objective was to microscopically identify 23 commercially available Brazilian wood species using a custom DCNN model. Results: Photographs from microscopic slides of each wood species were processed, and the final data set contained 2,448 images. We applied stratified k-fold cross-validation technique during training to increase model’s robustness and trustworthiness. Thus, the dataset was divided into approximately 80% training (1,958 images) and 20% validation (490 images) for each fold. A series of augmentations were performed only on training data to include variations in rotation, zoom, and perspective. Image augmentation was performed on-the-fly. The network consisted of convolutions, max pooling, global average pooling, and fully connected layers. We tested the performance of the DCNN against accuracy, precision, recall, and F1-score on the validation set for each fold. Conclusion: The custom machine learned model accuracy was higher than 0.90. The model’s worst performance was identified in distinguishing between Toona ciliate and Khaya ivorensis, which was due more to wood variability than to a machine learning deficiency. Future studies should focus on integration, verification/monitoring, and updating of current models for end user manipulation, trust, ethics, and security.

Speaker Accent Recognition Using MFCC Feature Extraction and Machine Learning Algorithms

Speech and speaker recognition systems aim to analyze parametric information contained in the human voice and recognize it at the highest possible rate. One of the most important features in the audio signal for the speaker to be recognized successfully by the system is the speaker's accent. Speaker accent recognition systems are based on the analysis of patterns such as the way the speaker speaks and the word choice he uses while speaking. In this study, the data obtained by the MFCC feature extraction technique from voice signals of 367 speakers with 7 different accents were used. The data of 330 speakers in the data set were taken from the "Speaker Accent Recognition" data set in the UC Irvine Machine Learning (ML) open data source. The data of the other 37 speakers were obtained by converting the voice recordings in the "Speaker Accent Archive" data set created by George Mason University into data using the MFCC feature extraction technique. 9 ML classification algorithms were used for the designed speaker accent recognition system. Also, the k-fold cross-validation technique was used to test the data set independently. In this way, the performance of ML algorithms is shown when the data set is divided into a k number of parts. Information about the classification algorithms used in the designed system and the hyperparameter optimizations made in these algorithms are also given. The success performances of the classification algorithms are shown with performance metrics.

KNN Algorithm Used for Heart Attack Detection

Machine Learning, a branch of artificial intelligence, has become more accurate than human medical professionals in predicting the incidence of heart attack or death in patients at risk of coronary artery disease. In this paper, we attempt to employ Artificial Intelligence (AI) to predict heart attack. For this purpose, we employed the popular classification technique named the K-Nearest Neighbor (KNN) algorithm to predict the probability of having the Heart Attack (HA). The dataset used is the cardiovascular dataset available publicly on Kaggle, knowing that someone suffering from cardiovascular disease is likely to succumb to a heart attack. In this work, the research was conducted using two approaches. We use the KNN classifier for the first time, aided by using a correlation matrix to select the best features manually and faster computation, and then optimize the parameters with the K-fold cross-validation technique. This improvement led us to have an accuracy of 72.37% on the test set.