Bayesian Classifier Research Articles

QTc interval prolongation impact on in-hospital mortality in acute coronary syndromes patients using artificial intelligence and machine learning

Abstract Background Prediction of mortality in hospitalized patients is a crucial and important problem. Several severity scoring systems over the past few decades and machine learning models for mortality prediction have been developed to predict in-hospital mortality. Our aim in this study was to apply machine learning (ML) algorithms using QTc interval to predict in-hospital mortality in ACS patients and compare them to the validated conventional risk scores. Results This study was retrospective, using supervised learning, and data mining. Out of a cohort of 500 patients admitted to a tertiary care hospital from September 2018 to August 2020, who presented with ACS. Prediction models for in-hospital mortality in ACS patients were developed using 3 ML algorithms. We employed the ensemble learning random forest (RF) model, the Naive Bayes (NB) model and the rule-based projective adaptive resonance theory (PART) model. These models were compared to one another and to two conventional validated risk scores; the Global Registry of Acute Coronary Events (GRACE) risk score and Thrombolysis in Myocardial Infarction (TIMI) risk score. Out of the 500 patients included in our study, 164 (32.8%) patients presented with unstable angina, 148 (29.6%) patients with non-ST-elevation myocardial infarction (NSTEMI) and 188 (37.6%) patients were having ST-elevation myocardial infarction (STEMI). 64 (12.8%) patients died in-hospital and the rest survived. Performance of prediction models was measured in an area under the receiver operating characteristic curve (AUC) ranged from 0.83 to 0.93 using all available variables compared to the GRACE score (0.9 SD 0.05) and the TIMI score (0.75 SD 0.02). Using QTc as a stand-alone variable yielded (0.67 SD 0.02) with a cutoff value 450 using Bazett’s formula, whereas using QTc in addition to other variables of personal and clinical data and other ECG variables, the result was 0.8 SD 0.04. Results of RF and NB models were almost the same, but PART model yielded the least results. There was no significant difference of AUC values after replacing the missing values and applying class balancer. Conclusions The proposed method can effectively predict patients at high risk of in-hospital mortality early in the setting of ACS using only clinical and ECG data. Prolonged QTc interval can be used as a risk predictor of in-hospital mortality in ACS patients.

An Optimized Approach for Detection and Classification of Spam Email’s Using Ensemble Methods

AbstractSince the advent of email services, spam emails have been a major concern because users’ security depends on the classification of emails as ham or spam. It’s a malware attack that has been used for spear phishing, whaling, clone phishing, website forgery, and other harmful activities. However, various ensemble Machine Learning (ML) algorithms used for the detection and filtering of spam emails have been less explored. In this research, we offer a ML-based optimized algorithm for detecting spam emails that have been enhanced using Hyper-parameter tuning approaches. The proposed approach uses two feature extraction modules, namely Count-Vectorizer and TFIDF-Vectorizer that provide the most effective classification results when we apply them to three different publicly available email data sets: Ling Spam, UCI SMS Spam, and the Proposed dataset. Moreover, to extend the performance of classifiers we used various ML methods such as Naive Bayes (NB), Logistic Regression (LR), Extra Tree, Stochastic Gradient Descent (SGD), XG-Boost, Support Vector Machine (SVM), Random Forest (RF), Multi-layer Perception (MLP), and parameter optimization approaches such as Manual search, Random search, Grid search, and Genetic algorithm. For all three data sets, the SGD outperformed other algorithms. All of the other ensembles (Extra Tree, RF), linear models (LR, Linear-SVC), and MLP performed admirably, with relatively high precision, recall, accuracies, and F1-score.

Abstract 4140120: Artificial intelligence-driven morbidity prediction in acute kidney injury after acute type A aortic dissection surgery

Background: Acute kidney injury (AKI) often complicates acute type A aortic dissection (ATAAD), with elevated comorbidity rates and a significant tie to in-hospital mortality. Identifying risk factors early can mitigate AKI severity. Research Questions: This research endeavors to develop and corroborate predictive models leveraging Machine Learning (ML) techniques from Artificial Intelligence to forecast AKI occurrences in ATAAD-afflicted individuals. Methods: The study employed various machine learning (ML) algorithms including Gradient Boosting Machine (GBM), LightGBM, Random Forest (RF), K-Nearest Neighbors (KNN), Multi-Layer Perceptron Neural Network (MLP-NN), Naive Bayes (NB), Logistic Regression (LR), and ensemble methods (combining LR&LightGBM), employing tenfold cross-validation. Model performance was evaluated using SHapley Additive exPlanations (SHAP). A web-based tool for predicting AKI incidence was developed using Streamlit, based on the most effective model. The analysis involved 1350 ATAAD patients, among whom 586 (43.4%) developed post-operative AKI. Patients were divided into two cohorts: 85% for training and 15% for testing, with 126 features included in the predictive model. Results: Incorporating top 10 features, LightGBM (AUROC=0.886, 95% CI 0.841-0.930) excelled in predictive accuracy, calibration, and clinical utility, identifying key factors such as ventilation time in ICU, hourly urine output post-surgery, diuretic use, Scr, heart rate, urea, administration of recombinant human brain natriuretic peptide and ebrantil, MCHC, and blood glucose as associated with ATAAD-AKI. Conclusion(s): These ML models are robust tools for predicting AKI in ATAAD patients, with LightGBM's superior predictive ability standing out. They offer valuable support for clinical decision-making in ATAAD management, helping optimize postoperative strategies to minimize AKI occurrence after surgery.

Can the Plantar Pressure and Temperature Data Trend Show the Presence of Diabetes? A Comparative Study of a Variety of Machine Learning Techniques

This study aimed to explore the potential of predicting diabetes by analyzing trends in plantar thermal and plantar pressure data, either individually or in combination, using various machine learning techniques. A total of twenty-six participants, comprising thirteen individuals diagnosed with diabetes and thirteen healthy individuals, walked along a 20 m path. In-shoe plantar pressure data were collected and the plantar temperature was measured both immediately before and after the walk. Each participant completed the trial three times, and the average data between the trials were calculated. The research was divided into three experiments: the first evaluated the correlations between the plantar pressure and temperature data; the second focused on predicting diabetes using each data type independently; and the third combined both data types and assessed the effect of such to enhance the predictive accuracy. For the experiments, 20 regression models and 16 classification algorithms were employed, and the performance was evaluated using a five-fold cross-validation strategy. The outcomes of the initial set of experiments indicated that the machine learning models were significant correlations between the thermal data and pressure estimates. This was consistent with the findings from the prior correlation analysis, which showed weak relationships between these two data modalities. However, a shift in focus towards predicting diabetes by aggregating the temperature and pressure data led to encouraging results, demonstrating the effectiveness of this approach in accurately predicting the presence of diabetes. The analysis revealed that, while several classifiers demonstrated reasonable metrics when using standalone variables, the integration of thermal and pressure data significantly improved the predictive accuracy. Specifically, when only plantar pressure data were used, the Logistic Regression model achieved the highest accuracy at 68.75%. Those predictions based solely on temperature data showed the Naive Bayes model as the lead with an accuracy of 87.5%. Notably, the highest accuracy of 93.75% was observed when both the temperature and pressure data were combined, with the Extra Trees Classifier performing the best. These results suggest that combining temperature and pressure data enhances the model’s predictive accuracy. This can indicate the importance of multimodal data integration and their potentials in diabetes prediction.

Predicting Student Dropout Rates in Higher Education: A Comparative Study of Machine Learning Algorithms

Recent years have seen a significant increase in study interest in the areas of predicting student performance, avoiding failure, and identifying the variables affecting student dropout. One important indicator in online and open distance learning courses is the student dropout rate. We purpose the naive bayes classification method to construct the student dropout prediction using naive bayes. This work examines the critical topic of forecasting student dropout rates in higher education using machine learning approaches, with a particular emphasis on the random forest algorithm and the naive bayes algorithm. The study's goal is to properly anticipate dropout rates using data mining methods and machine learning algorithms after conducting a thorough evaluation of existing literature and approaches. The systematic method consists of data collection from a Kaggle dataset, data preparation to solve class imbalance via SMOTE oversampling, and algorithm selection. Random forest and naive Bayes approaches outperform other machine learning algorithms in terms of accuracy, sensitivity, specificity, and precision. The study underscores the importance of considering diverse factors such as demographic data, socioeconomic factors, and academic performance in dropout prediction models. The implications of this research extend beyond academia, with the potential to inform proactive interventions and support systems, ultimately leading to improved student outcomes and institutional effectiveness. According to this paper, the paper outputs that for the binary classification on the data set used in this project has best performed with Naive Bayes and Random Forest Algorithm with SMOTE oversampling. Keywords- SMOTE oversampling, machine learning, Random forest, naive bayes.

SENTIMENT ANALYSIS OF PUBLIC OPINION ON PRESIDENTIAL ADVISORY APPOINTMENTS USING NAIVE BAYES CLASSIFICATION

Social media platforms such as Twitter, Facebook, and YouTube have become significant channels for public discourse, where users freely express opinions, including negative sentiments and hate speech. To better understand public opinion, particularly in politically charged contexts, sentiment analysis can classify user comments as either positive or negative. This study aims to analyze public sentiment regarding the formation of a special advisory team for President Jokowi, using a sentiment classification approach. The study employed a Naïve Bayes classifier to analyze sentiment from 3,000 comments gathered from Twitter, Facebook, and YouTube. The dataset was divided into 80% training data (used to train the model with known sentiment) and 20% test data. The Naïve Bayes algorithm was chosen for its simplicity and effectiveness in handling large datasets in text classification tasks. The Naive Bayes classification on sentiment analysis of public opinion regarding the appointment of presidential advisors achieved an overall accuracy of 71% in classifying the test data. Negative sentiment was classified with an accuracy of 71%, while positive sentiment was classified with an accuracy of 70%. The results demonstrate that the Naïve Bayes classifier is a viable method for sentiment analysis in political discourse, although the model's performance indicates room for improvement. The novelty of this research lies in its focus on sentiment analysis of public opinion specifically related to presidential advisory appointments, an area not yet extensively explored in sentiment analysis studies. This study contributes to the field by providing insights into the public’s perception of political decisions using machine learning techniques. The implications for future research include refining classification methods for better accuracy and applying the model to other political or governmental topics.

Hybrid Learning Model for intrusion detection system: A combination of parametric and non-parametric classifiers

The growing digital transformation has increased the need for effective intrusion detection systems. Traditional intrusion detection systems face challenges in accurately classifying complex patterns. To address this issue, this study proposed a Hybrid Learning Model (HLM) that combines both parametric and non-parametric classifiers. The proposed HLM consist of two stages: the first stage employs a non-parametric Base Learner (np-BL) to analyze the data patterns and the second stage involves meta-modelling to generalize the overall performance of the model, named the Parametric Meta-Learning (PML) model. The proposed HLM blends the outcomes of np-BL and PML models using a stacking ensemble. As a base learning model K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), Gradient Boosting Machine (GBM), and Support Vector Classification with Radial Basis Function (SVC-RBF), are adopted from a non-parametric classifier group. The parametric classifiers Logistic Regression (LR), Naïve Bayes Classifier (NBC), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA) and Support Vector Machine with linear kernel (Linear SVM) were used as meta-models. The HLM, as proposed, enhances the adaptability and robustness of the model by combining non-parametric and parametric models. To evaluate the competence of the proposed HLM, a performance analysis was conducted using the NSL-KDD, UNSW-NB15, and CICIDS2017 datasets. The effectiveness was assessed using various metrics, including classification accuracy, precision, recall, F1-Score (F1), Receiver Operating Characteristic (ROC) curve, Detection Rate (DR), and False Alarm Rate (FAR). The proposed HLM achieves a better accuracy rate across different datasets when compared with the existing models. The achieved accuracies are 99.02 %, 99.98 % and 99.63 % for the NSL-KDD, UNSW-NB15, and CICIDS2017 datasets respectively. Furthermore, the HLM gave a significant reduction in FAR, with values of 0.0126, 0.0001, and 0.0016 for the above-mentioned datasets.

Application of Machine Learning for the Prediction of Absorption, Distribution, Metabolism and Excretion (ADME) Properties from Cichorium intybus Plant Phytomolecules

Drug discovery is the process by which new drug candidates are discovered and drug development takes place. To enhance the efficiency, accuracy, and speed of the drug discovery process, machine learning (ML) could play a transformative role. For this research study, antidiabetic natural compounds from C. intybus, which is commonly known as chicory, were selected, as they have promising antidiabetic properties that can complement conventional diabetes treatments. A bioactive natural compound dataset was retrieved on the chicory plant using Indian Medicinal Plants, Phytochemistry, and Therapeutics (IMPPAT) public source information. This collected dataset was analyzed for its absorption, distribution, metabolism, and excretion (ADME) properties using the SwissADME online tool. Principal component analysis (PCA) and correlation analysis were performed using trial-version XLSTAT software 2014.5.03 and Python. The obtained dataset from SwissADME was subjected to cleaning, after that, it was used to develop machine learning models, such as support vacuum (SVM) ML, random forest (RF), Naive Bayes (NB), and decision tree (DT). The Lipinski rule of violation was chosen as the target variable. To improve the vitality of the created ADME dataset, PCA, a biplot graph, and correlation analysis were carried out. A large dataset of naturally occurring antidiabetic compounds was used to predict the drug-likeness of ML models that were effectively deployed on heterogeneous ADME datasets. Among all these ML models, DT performed better than the rest of the models.

A data-driven ISM-BN model for safety analysis of inland shipping in the Pearl River Basin

Inland shipping of the Pearl River plays an important role in the Chinese shipping system. To ensure navigation safety, we collect reports of maritime accidents from 2015 to 2022 in the Pearl River basin. This article extracts influencing factors by collecting the experience of inland waterway safety navigation and analyzing accident reports. Then, this paper uses the interpretative structural modeling method (ISM) to build a correlation model. Using a data-driven Bayesian network (BN), it analyzes the impact of various factors on the safety navigation in the Pearl River. The model validation is completed by compared with tree augmented naive Bayes classifiers (TAN) network using the same validation samples, through validation with the test set, the prediction accuracy has improved by 25%. The results indicate factors such as vessel type, accident month, accident day and time, etc. have a significant impact on the safety of navigation in the inland Pearl River waterway. The method used can identify important risk factors for accidents and the average predictive probability of validation samples reaches 87.03%. These research results could be extended to maritime management efforts in the Pearl River Basin.

Implementation of PPCA Imputation, SMOTE-N Class Balancing in Hepatitis Classification Using Naïve Bayes

The availability of complete data in research is crucial, especially in the initial stages. The Hepatitis data used in this study encountered issues such as missing data and class imbalance, which hindered its optimal utilization. The method employed to address missing data was the PPCA imputation method. After filling in the missing data, the data was balanced using the SMOTE-N class balancing method and classified using Gaussian Naïve Bayes. The aim of this research was to compare the classification evaluation of hepatitis disease using Naive Bayes with the PPCA imputation approach and SMOTE-N class balancing. The best results from each scenario yielded an AUC value of 0.833 in the first scenario with an 80:20 data split for training and testing, and 0.875 in the second scenario with a 90:10 data split. The highest AUC value was obtained in the application of PPCA imputation with SMOTE-N class balancing using Naive Bayes classification. This demonstrates that the implementation of PPCA imputation with SMOTE-N class balancing has a better impact on the performance of Naïve Bayes classification.

Machine Learning Techniques for Heart Disease Prediction Using a Multi-Algorithm Approach

This analysis explores the efficiency of machine learning systems for heart disease identification through a multi-algorithm approach. The main objective is to identify the best performing algorithm for accurate disease prediction, improving clinical decision making. Using criteria including accuracy, precision, recall, F1 score, and recall, the study assessed four algorithms: Random Forest (RF), Naïve Bayes (NB), Support Vector Machine (SVM), and Decision Tree (DT). The results show that Random Forest outperforms the others, achieving 86.23% precision, 93.76% recall, 89.84% F1 score, and 88.41% accuracy. Random Forest gets an AUC ROC result of 0.94, so Random Forest is considered a superior model in this scenario, especially because it has higher accuracy. The algorithms showed a strong balance between sensitivity and specificity. Decision Tree showed reasonable performance with a precision of 84.18% and a recall of 90.27%, while Naïve Bayes recorded a precision of 87.68% and a recall of 87.03%. SVM showed a precision of 87.40% and a recall of 84.78%, indicating some limitations in capturing positive cases. The novelty of this study lies in the comparative analysis of several algorithms to optimize the heart disease prediction model for clinical use. The random forest algorithm is one of the choices, but there is still a medical standard for classifying people as either indicating or not experiencing heart failure, according to the study.

Enhancing sound source localization and music teaching through integrated computational resource allocation

In contemporary educational and computational settings, the incorporation of cutting-edge technologies like sound source localization and personalized music teaching helps in offering an effective resource allocation strategies. Previous systems for sound localization and music teaching frequently lacked real-time flexibility and effective resource use, reducing their efficiency in dynamic learning settings and tasks involving computation. To overcome these shortcomings, the SoundLocMusicTeachRA (SLMTRA) algorithm is presented, a single, integrated platform made to maximize sound localization accuracy, improve music teaching efficiency, and enhance computational resource oversight. However, the existing study did not highlight the importance of computation resource allocation but this proposed algorithm will address it. SLMTRA uses a new Bagging ensemble approach incorporating Random Forest (RF), Decision Trees (DT), Naive Bayes (NB), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN), with hyperparameter tuning to enhance the effectiveness of the approach. These classifiers are trained utilizing sound localization datasets from recordings made with microphones, music teaching feedback datasets from data on student performance, and resource allocation datasets from metrics for computer utilization. Experimental findings indicate SLMTRA’s high accuracy in sound source localization, improved music teaching feedback capacities, as well as effective resource allocation tactics, guaranteeing the best performance of the system. The implementation of SLMTRA represents a noteworthy development in combining sound localization, music teaching, and resource allocation within a unified computational framework, offering a more flexible and effective system compared to previous methodologies.

Research on Climactic Chapter Recognition of a Chinese Long Novel Based on Plot Description

Many readers continue to pursue Chinese long novels in the past several decades because of diverse characters and fascinating plots. The climactic chapter is an important part of a Chinese long novel, where the key conflict develops to the extreme point. However, how to quickly and accurately recognize the climactic chapter remains a common problem for many readers in their reading choices. This paper conducts research on recognizing the climactic chapter of a Chinese long novel by accurately describing its plot. The proposed method consists of two parts; one is the extraction of key elements, such as viewpoint paragraphs, non-viewpoint paragraphs, chapter keywords, major characters etc. The other part is the climactic chapter recognition, which applies the Bidirectional Gate Recurrent Unit (BiGRU) model and the multi-head attention to recognize the climactic chapter, on the basis of the chapter plot description matrix. Comparative experiments on the corpus named The Condor Trilogy show that the proposed method in this paper has a better recognition performance compared with the existing models, such as Naive Bayesian (NB), Support Vector Machine (SVM), Roberta-large, and the Bidirectional Long-Short Term Memory (BiLSTM) network. Ablation experiments validated the effectiveness of primary components in the proposed method.

Interpretable prediction of 30-day mortality in patients with acute pancreatitis based on machine learning and SHAP.

Severe acute pancreatitis (SAP) can be fatal if left unrecognized and untreated. The purpose was to develop a machine learning (ML) model for predicting the 30-day all-cause mortality risk in SAP patients and to explain the most important predictors. This research utilized six ML methods, including logistic regression (LR), k-nearest neighbors(KNN), support vector machines (SVM), naive Bayes (NB), random forests(RF), and extreme gradient boosting(XGBoost), to construct six predictive models for SAP. An extensive evaluation was conducted to determine the most effective model and then the Shapley Additive exPlanations (SHAP) method was applied to visualize key variables. Utilizing the optimized model, stratified predictions were made for patients with SAP. Further, the study employed multivariable Cox regression analysis and Kaplan-Meier survival curves, along with subgroup analysis, to explore the relationship between the machine learning-based score and 30-day mortality. Through LASSO regression and recursive feature elimination (RFE), 25 optimal feature variables are selected. The XGBoost model performed best, with an area under the curve (AUC) of 0.881, a sensitivity of 0.5714, a specificity of 0.9651 and an F1 score of 0.64. The first six most important feature variables were the use of vasopressor, high Charlson comorbidity index, low blood oxygen saturation, history of malignant tumor, hyperglycemia and high APSIII score. Based on the optimal threshold of 0.62, patients were divided into high and low-risk groups, and the 30-day survival rate in the high-risk group decreased significantly. COX regression analysis further confirmed the positive correlation between high-risk scores and 30-day mortality. In the subgroup analysis, the model showed good risk stratification ability in patients with different gender, renal replacement therapy and with or without a history of malignant tumor, but it was not effective in predicting peripheral vascular disease. the XGBoost model effectively predicts the severity of SAP, serving as a valuable tool for clinicians to identify SAP early.

Hidden in Plain Sight: A Data-Driven Approach to Safety Risk Management for Highway Traffic Officers

Highway traffic officers (HTOs) are often exposed to life-threatening workplace incidents while performing their duties. However, scant research has been undertaken to address these safety concerns. This research explores case study data from highway incident reports (held by National Highways, a UK government company) and employs deep neural network (DNN) in unearthing patterns which inform safety decision makers on pertinent safety challenges confronting HTOs. A mixed philosophical stance of positivism and interpretivism was adopted to synthesise the findings made. A four-phase sequential method was implemented to evaluate the validity of the research viz.: (i) architectural design; (ii) data exploration; (iii) predictive modelling; and (iv) performance evaluation. The DNN model’s predictive performance is benchmarked against three other machine learning models, namely Support Vector Machines (SVM), Random Forest (RF), and Naïve Bayes (NB). The DNN model outperformed the other three models. Findings from the data exploration also show that most work operations undertaken by HTOs have a medium risk level with night shifts posing the greatest risk challenges. Carriageways and traffic management enclosures had the highest incident occurrence. This is the first study to uncover such hidden patterns and predict risk levels using a database specifically for HTOs. This study presents evidence-based information for proactive risk management for HTOs.

Intratumoral and peritumoral radiomics for preoperative prediction of neoadjuvant chemotherapy effect in breast cancer based on 18F-FDG PET/CT

ObjectiveTo investigate the value of 18F-FDG PET/CT-based intratumoral and peritumoral radiomics in predicting the efficacy of neoadjuvant chemotherapy (NAC) for breast cancer.Methods190 patients who met the inclusion and exclusion criteria from 2017 to 2022 were studied. Features were extracted from the PET/CT intratumoral and peritumoral regions, feature selection was performed through the correlation analysis, t-tests, and least absolute shrinkage and selection operator regression (LASSO). Four classifiers, support vector machine (SVM), k-nearest neighbor (KNN), logistic regression (LR), and naive bayes (NB) were used to build the prediction models. The receiver operating characteristic (ROC) curves were plotted to measure the predictive performance of the models. Concurrent stratified analysis was conducted to establish subtype-specific features for each molecular subtype.ResultsCompared to intratumoral features alone, intratumoral + peritumoral features achieved higher AUC values in each classifier. The SVM model constructed with intratumoral + peritumoral features achieved the highest AUC values in both the train and test set (train set: 0.95 and test set: 0.83). Subtype-specific features improve performance in predicting the efficacy of NAC (luminal group: 0.90; HER2 + group: 0.86; triple negative group: 0.92).ConclusionIntratumoral and peritumoral radiomics models based on 18F-FDG PET/CT can reliably forecast the efficacy of NAC, thereby assisting clinical decision-making.

Intrusion Detection System in Network Security Using Naive Bayes and Support Vector Machine

An Intrusion Detection System (IDS) is designed to detect suspicious activities or security threats within a network, necessitating continuous advancements in the field. Both implementation techniques and algorithmic research play pivotal roles in enhancing IDS capabilities. This study addresses this need by focusing on the implementation and comparison of two prominent classification models: Naive Bayes and Support Vector Machine (SVM). The study is centered within the domain of Intrusion Detection System (IDS) tailored for network security. In the course of this research, a relevant dataset sourced from Kaggle serves as the foundation for training and testing both classification models. The findings of this study underscore the models' efficacy in intrusion detection. The SVM model, in particular, emerges as a standout performer, showcasing an accuracy rate that approaches 100%, thus exemplifying its potential in real-world scenarios. Meanwhile, the Naive Bayes model delivers commendable accuracy, surpassing 88%. This investigation not only contributes to the advancement of intrusion detection methodologies but also highlights the viability of these classification models for bolstering network security against the ever-evolving threat landscape.

Precision medicine in hepatology: harnessing IoT and machine learning for personalized liver disease stage prediction

<span>In this research, we used a dataset from Siksha ‘O’ Anusandhan (S’O’A) University Medical Laboratory containing 6,780 samples collected manually and through internet of things (IoT) sensor sources from 6,780 patients to perform a thorough investigation into liver disease stage prediction. The dataset was carefully cleaned before being sent to the machine learning pipeline. We utilised a range of machine learning models, such as Naïve Bayes (NB), sequential minimal optimisation (SMO), K-STAR, random forest (RF), and multi-class classification (MCC), using Python to predict the stages of liver disease. The results of our simulations demonstrated how well the SMO model performed in comparison to other models. We then expanded our analysis using different machine learning boosting models with SMO as the base model: adaptive boosting (AdaBoost), gradient boost, extreme gradient boosting (XGBoost), CatBoost, and light gradient boosting model (LightGBM). Surprisingly, gradient boost proved to be the most successful, producing an astounding 96% accuracy. A closer look at the data showed that when AdaBoost was combined with the SMO base model, the accuracy results were 94.10%, XGBoost 90%, CatBoost 92%, and LightGBM 94%. These results highlight the effectiveness of proposed model i.e. gradient boosting in improving the prediction of liver disease stage and provide insightful information for improving clinical decision support systems in the field of medical diagnostics.</span>

Mutual information-MOORA based feature weighting on naive bayes classifier for stunting data

Mutual information-MOORA based feature weighting on naive bayes classifier for stunting data

Determining the influence of data on working with video materials on the accuracy of student success prediction models

The object of this study is models for predicting students’ success, constructed on the basis of machine learning methods. The paper reports results of research into the problem of improving their accuracy by expanding the data set for training the specified models. The most available are data on student actions, which are automatically collected by learning management systems. Entering additional information about students’ work increases time and resources but allows the improvement of the accuracy of the models. In the study, information about students’ work with video materials, particularly the number and duration of views, was entered into the original data set. To automate the collection of this data, the plugin for the Moodle system has been developed, which stores information about user’s actions with the video player and the duration of watching video materials in the database. Model training was carried out using Naive Bayes (NB), logistic regression (LR), random forest (RF), and neural networks (NN) algorithms with and without video data. For the models using video viewing data, accuracy increased by 10 %, balanced accuracy by 15 %, and overall performance, expressed as area under the curve (AUC), increased by 14 %. The highest prediction accuracy, with a difference of 1.8 %, was obtained by models built using RF algorithms – 87.1 % and NN – 85.3 %. At the same time, the accuracy of the models obtained by the NB and LR algorithms was 70.7 % and 76.5 %. The increase in accuracy for them was 2.3 % and 8.1 %, respectively. Analysis of calculations confirms the assumption that students’ work with educational video materials is correlated with their success. The results make it possible to find a reasonable compromise between model development costs and its accuracy at the stage of data preparation for model training.