Comparative Analysis of Four Machine Learning Algorithms for Smoke Detection Using SMOTE-Rebalanced Sensor Data

Alzheimer’s disease (AD) is a gradient degeneration of essential cognitive activities such as memory, thinking, and cognition. AD mainly affects elderly individuals and is recognized as the most common cause of dementia. This study investigates the predictive performance of nine supervised machine learning algorithms—Logistic Regression, Decision Tree, Random Forest, K-Nearest Neighbors, Support Vector Machine, Gaussian Naïve Bayes, Multi-Layer Perceptron, eXtreme Gradient Boost, and Gradient Boosting—using neuropsychological assessment data. We applied two classification techniques—binary and multiclass—to classify 1761 subjects into three categories: cognitively normal (CN), mild cognitive impairment (MCI), and Alzheimer's disease (AD). Binary classification tasks focused on CNvsAD and CNvsMCI subsets, while multiclass classification used the full dataset (TriClass). Hyperparameter tuning was performed to optimize model performance. The results indicate that ensemble learning models, particularly Gradient Boosting (GB) and Random Forest (RF), exhibited superior accuracy compared to other algorithms. Most models for the CNvsAD subset achieved the highest accuracy (97.74%), while GB achieved the best performance (94.98%) for the CNvsMCI subset. For multiclass classification, RF achieved the highest accuracy at 84.70%. These findings highlight the robustness and efficiency of ensemble learning algorithms, especially in handling complex, non-linear data structures. This study underscores the potential of RF and GB as reliable tools for early detection and classification of Alzheimer’s disease using neuropsychological data.

PurposeThis study aims to emphasize utilization of Predictive Six Sigma to achieve process improvements based on machine learning (ML) techniques embedded in define, measure, analyze, improve, control (DMAIC). With this aim, this study presents selection and utilization of ML techniques, including multiple linear regression (MLR), artificial neural network (ANN), random forests (RF), gradient boosting machines (GBM) and k-nearest neighbors (k-NN) in the analyze and improve phases of Six Sigma DMAIC.Design/methodology/approachA data set containing 320 observations with nine input and one output variables is used. To achieve the objective which was to decrease the number of fabric defects, five ML techniques were compared in terms of prediction performance and best tools were selected. Next, most important causes of defects were determined via these tools. Finally, parameter optimization was conducted for minimum number of defects.FindingsAmong five ML tools, ANN, GBM and RF are found to be the best predictors. Out of nine potential causes, “machine speed” and “fabric width” are determined as the most important variables by using these tools. Then, optimum values for “machine speed” and “fabric width” for fabric defect minimization are determined both via regression response optimizer and ANN surface optimization. Ultimately, average defect number was decreased from 13/roll to 3/roll, which is a considerable decrease attained through utilization of ML techniques in Six Sigma.Originality/valueAddressing an important gap in Six Sigma literature, in this study, certain ML techniques (i.e. MLR, ANN, RF, GBM and k-NN) are compared and the ones possessing best performances are used in the analyze and improve phases of Six Sigma DMAIC.

Diabetes Mellitus is a chronic disease that has a huge impact on human life. The changes in the body occur due to various factors such as age, Body Mass Index, glucose level, pregnancy, etc. The increase in the complexity of the problem has inspired many researchers to acquire more knowledge on Type-2 Diabetes Mellitus using Machine Learning Techniques. The algorithms such as Decision Tree (DT), K-Nearest Neighbour (KNN), Random Forest (RF), Naive Bayes (NB), Support Vector Machine (SVM), Gradient Boosting Machine (GBM), and Light Gradient Boosting Machine (LGBM) can be used. These classifiers are implemented to identify the best working model. A set of two or more classifiers can also be used as an ensemble model to determine performance in predicting Diabetes. The Pima Indian Dataset is extracted from the UCI Repository for the study. The performance metrics used for evaluation are accuracy score, five-fold cross-validation, precision, and Receiver operating characteristics curve. The proposed model is an ensemble model using LGBM, GBM, and RF Classifiers. The concepts of Bagging and Boosting are incorporated to reduce high variance and bias. A voting classifier can also be used to identify the result based on the probability of the output. The results obtained from the experimental analysis indicates that the accuracy obtained from the prediction ensemble-model provides better results than the Traditional Machine Learning model.

Lung cancer is one of the three deadliest diseases in the world and has rapidly developed. Based on this, researchers conducted research to predict the factors that influence lung cancer. One method to identify this is using data mining methods and classification techniques. Researchers used several popular algorithms in classification to make comparisons of the most accurate algorithms for lung cancer classification. The algorithms used include K-Nearest Neighbor, Random Forest Classifier, Logistic Regression, Linear SVM, Naïve Bayes, Decision Tree, Random Forest, Gradient Boosting, Kernel SVM, and MLPClassifier. The researcher used this algorithm because, in the research that the researcher found on the Kaggle platform, he examined the comparison of the algorithm using the breast cancer dataset. In previous studies, their researchers used SVM, which obtained an accuracy of 96.47%, Neural Networks of 97.06%, and Naïve Bayes with an accuracy of 91.18% to study breast cancer. The difference from previous research is that this study uses several existing algorithms in Machine Learning such as K-Nearest Neighbor, Random Forest Classifier, Logistic Regression, Linear SVM, Naïve Bayes, Decision Tree, Random Forest, Gradient Boosting, Kernel SVM, and MLPClassifier. In addition, this research was conducted to see whether the results of the accuracy of the algorithm that the researchers carried out using the lung cancer dataset had different results. The results of this study found that the more accurate algorithms were Random Forest and Gradient Boosting with an accuracy value of 100%, whereas in previous studies, it was the same. Still, Gradient Boosting had a higher accuracy value than Random Forest. Then, based on the data used in this study, the most influencing factors in predicting a diagnosis of lung cancer are obesity and coughing up blood. The results of this study found that the more accurate algorithms were Random Forest and Gradient Boosting with an accuracy value of 100%, whereas in previous studies, it was the same. Still, Gradient Boosting had a higher accuracy value than Random Forest. Then, based on the data used in this study, the most influencing factors in predicting a diagnosis of lung cancer are obesity and coughing up blood. The results of this study found that the more accurate algorithms were Random Forest and Gradient Boosting with an accuracy value of 100%, whereas in previous studies, it was the same. Still, Gradient Boosting had a higher accuracy value than Random Forest. Then, based on the data used in this study, the most influencing factors in predicting a diagnosis of lung cancer are obesity and coughing up blood.

Sub-Saharan Africa continues to shoulder the heaviest burden of malaria. The 2024 World Health Organisation (WHO) malaria report highlighted that Africa contributed an alarming 94% of the global cases and 95% of the deaths. In the WHO African region, progress towards elimination and management of malaria is hindered by weak health systems and a lack of traditional diagnostic methods such as microscopy and malaria Rapid Diagnostic Tests (mRDTs). The primary aim of this paper is to develop a machine learning (ML) ensemble model for malaria diagnosis using clinical and demographic data, tailored for resource-limited settings. A retrospective study was conducted using 637 patient records from Gutu Mission Hospital and Gweru Provincial Hospital in Zimbabwe. Clinical symptoms (fever, chills, abdominal pain, headache and diarrhea) and demographic features (age, gender, residence and travel history) were analysed. Data preprocessing included handling class imbalance using the Synthetic Minority Oversampling Technique (SMOTE) and feature selection using Recursive Feature Elimination (RFE). Seven individual ML models, including Logistic regression (LR), Random Forest (RF), Decision Trees (DT), Gradient Boosting (GB), K-Nearest Neighbour (KNN), Naive Bayes (NB) and XGBoost were trained and evaluated on the malaria dataset. The individual models were further combined to build, train and evaluate ensemble models such as Bagging, Stacking, Soft Voting and AdaBoost. Model performance was assessed using accuracy, precision, confusion matrices, recall, F1 score, and AUC-ROC metrics. Clinical symptoms (chills: p-value=0.001, fever: p=0.003, diarrhea: p=0.01, abdominal pain: p< 0.001) were statistically significant predictors of malaria. Of the demographic factors, only travel history (p=0.02) showed a significant association with malaria. Among the seven individual ML models, GB achieved the highest predictive performance (Accuracy =0.94), followed by RF (Accuracy =0.94) and XGBoost (Accuracy =0.93). The stacking ensemble model outperformed all individual ML models and other ensemble models (bagging, soft voting and AdaBoost), achieving accuracy =0.96, precision =0.95, recall =0.98, F1 score =0.96 and AUC-ROC =0.98. This study demonstrates that ML, particularly ensemble models, can be used to improve malaria diagnosis significantly. The integration of these models into a web-based application could provide a scalable and accessible diagnostic tool for healthcare workers in resource-limited settings.

Lung cancer is becoming more common, which emphasizes the significance of precise and user-friendly prediction methods for risk assessment and early identification. This research makes use of a dataset (284 cases and 16 attributes) that was acquired from the Online Lung Cancer Prediction System. The main goal is to find out how well machine learning techniques can predict the likelihood of lung cancer and give people useful information for making decisions. The collection contains a wide range of characteristics, such as lifestyle factors, health markers, and demographic data. To thoroughly assess predictive models, the study uses a variety of machine learning methods, including Logistic Regression, K-Nearest Neighbors (KNN), Support Vector Classifier (SVC), Decision Tree, Random Forest, XGBOOST, CATBOOST, LightGBM and Gradient Boosting. The study also investigates the effects of hyperparameter tuning, visualization strategies, and data preprocessing techniques on model performance. Keywords: Cancer prediction· Machine learning· Ensemble models

INTRODUCTION: Although maximizing the extent of ablation (EOA) following laser interstitial thermal therapy (LITT) can improve outcomes in patients with brain tumors, the pre-operative factors that predict a supralesional ablation (EOA >100%) remain unclear. METHODS: A retrospective study of patients with glioblastoma, metastasis, or radiation necrosis receiving LITT at a tertiary care referral center between 2013 to 2023 was conducted. Using the EOA >100% as a primary outcome, several clinical and radiographic pre-operative factors were evaluated. Five ML models, Decision Trees, Random Forest, Gradient Boosting, XGBoost, and AdaBoost, were trained using an 80/20 training/testing split and 5-fold cross validation. The models were optimized using hyperparameter tuning and evaluated against traditional logistic regression. The area under the receiver operating characteristic curve (AUC-ROC) was used to evaluate model performance. The optimal pre-operative volume cutoff for constituting an EOA >100% was also explored. RESULTS: 201 patients were included in the final cohort. Multivariate logistic regression showed that lower pre-operative volume (p < 0.001) and deep-seated lesions (p = 0.041) have a greater likelihood to undergo a supralesional ablation. Of the five ML models analyzed, Random Forest had the highest F1-score of 0.889, and XGBoost had the highest AUC-ROC of 0.74. Additionally, Random Forest (p = 0.02), Gradient Boosting (p < 0.001) and XGBoost (p = 0.01) showed statistically improved predictive performance compared to logistic regression. Features of importance were pre-operative volume, deep-seated lesions, and ellipsoid ratio. The pre-operative lesion volume cutoff for achieving an EOA >100% was 4.38 cc. CONCLUSIONS: This study shows the improved predictive ability of ML models over a traditional regression model in determining pre-operative factors for a supralesional ablation of brain tumors following LITT. Notably, the ML models identified pre-operative tumor volume, deep-seated tumors, and ellipsoid tumors as important factors, which could optimize treatment decisions and patient outcomes.

Bone marrow is the source of many blood-related diseases, such as blood cancers, and Bone Marrow Transplantation (BMT), also known as Hematopoietic Stem Cell Transplantation (HSCT), is a life-saving surgical procedure. However, this treatment is associated with a high risk of mortality. Predicting survival after BMT is therefore essential for effective and accurate treatment. BMT is considered a treatment-related mortality due to several primary causes of death such as infections, toxicity, and Graft-versus-Host Disease (GvHD) that occur after treatment. In addition, several risk factors affect the success of BMT and long-term survival after treatment. Therefore, there is a need for a prediction system based on machine learning techniques that can predict whether the patient will survive after BMT or not, which will definitely help the physicians to make the right decisions before performing the surgery for the patient. In this paper, using a publicly available BMT dataset from the University of California, Irvine ML repository (UCI ML repository), different machine learning models were investigated to predict the survival status of children undergoing BMT treatment. In particular, Random Forest (RF), Bagging Classifier, Extreme Gradient Boost (XGBoost), Adaptive Boosting (AdaBoost), Decision Tree (DT), Gradient Boost (GB), and K-Nearest Neighbors (KNN) were trained on the given dataset. The dataset consists of 45 variables after applying a series of preprocessing steps and removing the multicollinearity features based on the correlation heat map. Then, a feature engineering and modelling step was applied to identify the most significant features, followed by the use of machine learning models to simplify the overall classification process. It’s important to note that the most important features obtained by DT and those obtained by GB were the most suitable for training the Bagging classifier and the KNN model, respectively. In addition to that, hyper-parameters optimization using Grid Search Cross-Validation (GSCV) was applied to both approaches to improve the accuracy of the survival prediction. RF, AdaBoost, GB, and Bagging techniques have achieved the best accuracy of 97.37%

The technology known as cemented paste backfill (CPB) has gained considerable popularity worldwide. Yield stress (YS) is a significant factor considered in the assessment of CPB’s flowability or transportability. The minimal shear stress necessary to start the flow is known as Yield stress (YS), and it serves as an excellent measure of the strength of the particle-particle interaction. The traditional evaluation and measurement of YS performed by experimental tests are time-consuming and costly, which induces delays in construction projects. Moreover, the YS of CPB depends on numerous factors such as cement/tailing ratio, solid content and oxide content of tailing. Therefore, in order to simplify YS estimation and evaluation, the Artificial Intelligence (AI) approaches including eight Machine Learning techniques such as the Extreme Gradient Boosting algorithm, Gradient Boosting algorithm, Random Forest algorithm, Decision Trees, K-Nearest Neighbor, Support Vector Machine, Multivariate Adaptive Regression Splines and Gaussian Process are used to build the soft-computing model in predicting the YS of CPB. The performance of these models is evaluated by three metrics coefficient of determination (R2), Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). The 3 best models were found to predict the Yield Stress of CPB (Gradient Boosting (GB), Extreme Gradient Boosting (XGB) and Random Forest (RF), respectively) with the 3 metrics of the three models, respectively, GB {R2 = 0.9811, RMSE = 0.1327 MPa, MAE = 0.0896 MPa}, XGB {R2 = 0.9034, RMSE = 0.3004 MPa, MAE = 0.1696 MPa} and RF {R2 = 0.8534, RMSE = 0.3700 MPa, MAE = 0.1786 MPa}, for the testing dataset. Based on the best performance model including GB, XG and RF, the other AI techniques such as SHapley Additive exPlanations (SHAP), Permutation Importance, and Individual Conditional Expectation (ICE) are also used for evaluating the factor effect on the YS of CPB. The results of this investigation can help the engineers to accelerate the mixed design of CPB.

Prenatal prediction of CD34+ adequacy supports cord-blood banking by reducing expenses on low-yield units and reserving capacity for clinically promising grafts. We have developed and evaluated a prenatal machine learning model that predicts whether an umbilical cord blood (UCB) unit will meet a clinically supported adequacy threshold (≥1.5×105 CD34+ cells/kg recipient) before collection for single-unit grafts. In this retrospective study, we analysed 126,406 records from the Royan Stem Cell Technology Company (RSCT; Tehran, Iran), which included routinely available maternal, neonatal, and family-history variables. A pipeline of imputation (IterativeImputer numeric; SimpleImputer+OrdinalEncoder categorical), feature selection (Extra Trees), and hyperparameter tuning using Bayesian optimisation with model training/evaluation was performed within cross-validation folds. Decision Tree (DT), K-Nearest Neighbours (KNN), Random Forest (RF), Support Vector Machine (SVM), and Multilayer Perceptron (MLP) classifiers were tuned via Bayesian optimisation. Models were ranked by the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). Majority voting (MV) ensembles were constructed from the top-k models. Model interpretability used SHapley Additive exPlanations (SHAP). The MV (top-4: RF, KNN, DT, MLP) ensemble achieved an area under the receiver operating characteristic curve (ROC-AUC)=0.808 and an area under the precision-recall curve (PR-AUC)=0.744 on the held-out test set, with an accuracy=0.757, precision=0.726, recall/sensitivity=0.804, F1=0.762, specificity=0.716, and Brier score=0.181. SHAP highlighted history of hepatitis C, birth place, hyperthyroidism, history of anaemia, oral fungus, and rheumatism among the most influential features. Prenatal prediction of UCB CD34+ adequacy using an interpretable MV ensemble is feasible and accurate to support pre-collection triage and can potentially improve banking efficiency. The resultant model offers a non-invasive tool to enhance the efficiency of cord blood banking by prioritising units with higher transplantation potential.

Child mortality is a big problem around the world, especially in low- and middle-income nations where there are big differences in health care and social conditions. This investigation seeks to create a predictive model for child mortality and pinpoint the key factors that significantly contribute to it, employing machine learning (ML) methodologies. The dataset includes various features such as parental age, maternal education, birth weight, wealth index, and access to healthcare services. Thirteen machine learning classifiers were used, categorized into four model groups: Traditional Models (Logistic Regression, K-Nearest Neighbors, Support Vector Machine, Naive Bayes), Tree-Based Models (Decision Tree, Random Forest, Extra Trees), Boosting Models (AdaBoost, Gradient Boosting, XGBoost), and Ensemble Learning Models (Soft Voting, Hard Voting, Stacking). The efficacy of each model was assessed using classification metrics, including Accuracy, Precision, Recall, and F1-Score within a 10-fold cross-validation framework to guarantee robustness. Results indicate that ensemble models, particularly AdaBoost, achieved the highest predictive accuracy, with perfect scores across all metrics (1.00). XGBoost and Stacking also demonstrated strong and consistent performance. The findings indicate that ensemble learning methods are effective in predicting child mortality and can assist policymakers and healthcare planners in identifying high-risk populations and implementing targeted interventions to reduce child mortality.

ObjectiveEnhanced technology in computer and internet has driven scale and quality of data to be improved in various areas including healthcare sectors. Machine Learning (ML) has played a pivotal role in efficiently analyzing those big data, but a general misunderstanding of ML algorithms still exists in applying them (e.g., ML techniques can settle a problem of small sample size, or deep learning is the ML algorithm). This paper reviewed the research of diagnosing mental illness using ML algorithm and suggests how ML techniques can be employed and worked in practice.MethodsResearches about mental illness diagnostic using ML techniques were carefully reviewed. Five traditional ML algorithms-Support Vector Machines (SVM), Gradient Boosting Machine (GBM), Random Forest, Naïve Bayes, and K-Nearest Neighborhood (KNN)-frequently used for mental health area researches were systematically organized and summarized.ResultsBased on literature review, it turned out that Support Vector Machines (SVM), Gradient Boosting Machine (GBM), Random Forest, Naïve Bayes, and K-Nearest Neighborhood (KNN) were frequently employed in mental health area, but many researchers did not clarify the reason for using their ML algorithm though every ML algorithm has its own advantages. In addition, there were several studies to apply ML algorithms without fully understanding the data characteristics.ConclusionResearchers using ML algorithms should be aware of the properties of their ML algorithms and the limitation of the results they obtained under restricted data conditions. This paper provides useful information of the properties and limitation of each ML algorithm in the practice of mental health.

Using speech data, it is difficult to learn through machine learning how to diagnose Parkinson's disease (PD) and evaluate the effects of treatment. For this issue, the article has developed a three-stage PD discovery method. The base classifiers used in the initial stage are logistic regression (LR), K-nearest neighbor (KNN), naive bayes (NB), support vector machine (SVC), and decision tree (DT). The second stage, or stack model, is a meta-model that combines all of the classifiers mentioned earlier. The third stage ensemble model consists of Bagging, AdaBoost, Random Forest (RF), and Gradient Boosting (GBC) components. The RF and GBC classifiers are utilized to estimate the most important features from the PD dataset. The models' validation has been evaluated using the confusion matrix and validation metrics like precision, recall, and F1 score. Out of all the ensemble models, the GBC—the third model—had the highest accuracy with testing data—97.43%. KNN from the base model and stacking from the meta-model, on the other hand, had the highest accuracy, with 94.87% each. Out of all the models mentioned in this manuscript, the GBC is the only ensemble model classifier with the highest accuracy. The proposed classifier appears to be an extremely useful model for the discovery of Parkinson's disease, as demonstrated by the exploratory findings and factual analyses.

Defects that occur in software products are a universal occurrence. Software defect prediction is usually carried out to determine the performance, accuracy, precision and performance of the prediction model or method used in research, using various kinds of datasets. Software defect prediction is one of the Software Engineering studies that is of great concern to researchers. This research was conducted to determine the performance of tree-based classification algorithms including Decision Trees, Random Forests and Deep Forests without using feature selection and using firefly feature selection. And also know the tree-based classification algorithm with firefly feature selection which can provide better software defect prediction performance. The dataset used in this study is the ReLink dataset which consists of Apache, Safe and Zxing. Then the data is divided into testing data and training data with 10-fold cross validation. Then feature selection is performed using the Firefly Algorithm. Each ReLink dataset will be processed by each tree-based classification algorithm, namely Decision Tree, Random Forest and Deep Forest according to the results of the firefly feature selection. Performance evaluation uses the AUC value (Area under the ROC Curve). Research was conducted using google collab and the average AUC value generated by Firefly-Decision Tree is 0.66, the average AUC value generated by Firefly-Random Forest is 0.77, and the average AUC value generated by Firefly-Deep Forest is 0, 76. The results of this study indicate that the approach using the Firefly algorithm with Random Forest classification can work better in predicting software damage compared to other tree-based algorithms. In previous studies, tree-based classification with hyperparameter tuning on software defect prediction datasets obtained quite good results. In another study, the classification performance of SVM, Naïve Bayes and K-nearest neighbor with firefly feature selection resulted in improved performance. Therefore, this research was conducted to determine the performance of a tree-based algorithm using the firefly selection feature.

Given the exponential availability of data in health centers and the massive sensorization that is expected, there is an increasing need to manage and analyze these data in an effective way. For this purpose, data mining (DM) and machine learning (ML) techniques would be helpful. However, due to the specific characteristics of the field of healthcare, a suitable DM and ML methodology adapted to these particularities is required. The applied methodology must structure the different stages needed for data-driven healthcare, from the acquisition of raw data to decision-making by clinicians, considering the specific requirements of this field. In this paper, we focus on a case study of cervical assessment, where the goal is to predict the potential presence of cervical pain in patients affected with whiplash diseases, which is important for example in insurance-related investigations. By analyzing in detail this case study in a real scenario, we show how taking care of those particularities enables the generation of reliable predictive models in the field of healthcare. Using a database of 302 samples, we have generated several predictive models, including logistic regression, support vector machines, k-nearest neighbors, gradient boosting, decision trees, random forest, and neural network algorithms. The results show that it is possible to reliably predict the presence of cervical pain (accuracy, precision, and recall above 90%). We expect that the procedure proposed to apply ML techniques in the field of healthcare will help technologists, researchers, and clinicians to create more objective systems that provide support to objectify the diagnosis, improve test treatment efficacy, and save resources.