Machine Learning Decision Research Articles

Optimizing Photocatalytic Dye Degradation: A Machine Learning and Metaheuristic Approach for Predicting Methylene Blue in Contaminated Water

Dye contamination in water sources has severe environmental and public health risks; therefore, it needs effective monitoring and remediation strategies. The aim of the study is to use machine learning techniques to develop predictive models that may be used to evaluate methylene blue dye degradation capacity in contaminated water. Ten different machine learning models, including AdaBoost, Bagging, CatBoost, Decision Tree, Extra Trees, Gradient Boosting, HistGradientBoosting, LightGBM, Random Forest, and XGBoost, were evaluated using CuWO₄@TiO₂ as a photocatalyst. R², MSE, RMSE, MAE, and MedAE were used to assess the performance of the models. Among all models, HistGradientBoosting had a very well-balanced performance. It reached a very high R² of 0.9998 on the training set and 0.9915 on the test set, coupled with low error metrics, showcasing its strong generalization capability. However, Gradient Boosting and CatBoost exhibited impressive predictive performance, while AdaBoost and Decision Tree models suffered from overfitting. The maximum prediction obtained in the case of the integral approach for MB dye degradation is 98.99%. Experimental validation indicated that the effectiveness under optimized conditions reached 98.5%. In the case of initial MB concentration at 10 mg/L, a dosage of CuWO4@TiO2 photocatalyst at 200.33 mg/L, light intensity at 150 mW/cm², contact time at 88.6 minutes at room temperature, and near-neutral pH 7.0. The final model metrics included an R² score of 0.9915, MedAE of 1.171, MSE of 5.634, MAE of 1.735, and RMSE of 2.374. This work points out the possibility of taking complete advantage of advanced machine learning algorithms along with metaheuristics optimization in improving photocatalytic processes, hence opening a bright avenue for real applications in water treatment.

Random Forest and Decision Tree Facies Classification Models for Well Log Data of the Mishrif Formation from Basrah Oil Company, Southern Iraq

Facies collected from wells drilled in the study area were interpreted manually by using cores at every 10 meters of depth during well drilling. This depth of cores does not give true facies of all wells because the cores every 10 meters are considered very large. Extracting cores is financially expensive and takes a long time. The methodology of machine learning consists of four steps (Data gathering, Data preprocessing, Model training, and Model evaluation). This work intends to apply two of the supervised machine learning techniques random forest and decision tree models. (1) Data gathering, this dataset was collected from the Basrah Oil Company. It contains of ten wells (B-3, B-4, B-5, B-15, B-17, B-18, B-19, B-34, B-39, and B-40). Every well contains six features (logs): Sonic log, Resistivity Deep, Micro Spherically Focused Log, Neutron porosity, Density log, and Gamma-ray. Also, the dataset contains ten facies labels: mudstone, wack stone, packstone, roundstone, floatstone, shale, mud and wack stone, wack and pack stone, pack and grain stone and pack and float stone. These logs cover all the thickness of the Mishrif Formation, which is the goal of our study. (2) Preprocess, the data must be cleaned of outlier values; these values reduce the accuracy of the model during training. It is necessary at this stage to understand the relationships between all the features, because the highly correlated relationship between any two features, the more useless it will be in machine learning. The well B-5 blinded it for training to demonstrate the ability of machine learning models to predict lithofacies, then splitting randomly the dataset into 70% for training, validation 10%, and 20% for testing to verify the performance. (3) Training two models machine learning models decision tree and random forest. (4) Four statistics are computed for two models from the confusion matrix (accuracy of classification, recall, precision, and F1-score) showing the random forest was more accurate than the decision tree because the random forest model deals very well with this amount of dataset. Receiver Operating Characteristics curves of the random forest model have obtained the largest Area Under the Curve than the decision tree, is positive and above the main diagonal for all lithotypes, and the values for all classes reached more than 95%, except class 6 (shale), because of the 100% accuracy of classification. Facies classification by machine learning approach has two benefits (1) Increased accuracy of describing oil reservoirs and (2) Reducing the time, which a geologist needs to interpret logs data.

Analyzing and predicting short-term substance use behaviors of persons who use drugs in the great plains of the U.S.

Substance use induces large economic and societal costs in the U.S. Understanding the change in substance use behaviors of persons who use drugs (PWUDs) over time, therefore, is important in order to inform healthcare providers, policymakers, and other stakeholders toward more efficient allocation of limited resources to at-risk PWUDs. This study examines the short-term (within a year) behavioral changes in substance use of PWUDs at the population and individual levels. 237 PWUDs in the Great Plains of the U.S. were recruited by our team. The sample provides us longitudinal survey data regarding their individual attributes, including drug use behaviors, at two separate time periods spanning 4-12 months. At the population level, we analyze our data quantitatively for 18 illicit drugs; then, at the individual level, we build interpretable machine learning logistic regression and decision tree models for identifying relevant attributes to predict, for a given PWUD, (i) which drug(s) they would likely use and (ii) which drug(s) they would likely increase usage within the next 12 months. All predictive models were evaluated by computing the (averaged) Area under the Receiver Operating Characteristic curve (AUROC) and Area under the Precision-Recall curve (AUPR) on multiple distinct sets of hold-out sample. At the population level, the extent of usage change and the number of drugs exhibiting usage changes follow power-law distributions. At the individual level, AUROC's of the models for the top-4 prevalent drugs (marijuana, methamphetamines, amphetamines, and cocaine) range 0.756-0.829 (+2.88-7.66% improvement with respect to baseline models using only current usage of the respective drugs as input) for (i) and 0.670-0.765 (+4.34-18.0%) for (ii). The corresponding AUPR's of the said models range 0.729-0.947 (+2.49-13.6%) for (i) and 0.348-0.618 (+26.9-87.6%) for (ii). The observed qualitative changes in short-term substance usage and the trained predictive models for (i) and (ii) can potentially inform human decision-making toward efficient allocation of appropriate resources to PWUDs at highest risk.

Study on predicting new onset heart failure events in patients with hypertrophic cardiomyopathy using machine learning algorithms based on clinical and magnetic resonance features

Objective: To explore the value of predicting new-onset heart failure events in patients with hypertrophic cardiomyopathy (HCM) using clinical and cardiac magnetic resonance (CMR) features based on machine learning algorithms. Methods: The study was a retrospective cohort study. Patients with a confirmed diagnosis of HCM who underwent CMR examinations at Beijing Anzhen Hospital from May 2017 to March 2021 were selected and randomly divided into the training set and the validation set in a ratio of 7∶3. Clinical data and CMR parameters (including conventional parameters and radiomics features) were collected. The endpoint events were heart failure hospitalization and heart failure death, with follow-up ending in January 2023. Features with high stability and P value<0.05 in univariate Cox regression analysis were selected. Subsequently, three machine learning algorithms-random forest, decision tree, and XGBoost-were used to build heart failure event prediction models in the training set. The model performance was then evaluated using the independent validation set, with the performance assessed based on the concordance index. Results: A total of 462 patients were included, with a median age of 51 (39, 62) years, of whom 332 (71.9%) were male. There were 323 patients in the training set and 139 in the validation set. The median follow-up time was 42 (28, 52) months. A total of 44 patients (9.5% (44/462)) experienced endpoint events (8 cases of heart failure death and 36 cases of heart failure hospitalization), with 31 events in the training set and 13 in the validation set. Univariate Cox regression analysis identified 39 radiomic features, 4 conventional CMR parameters (left ventricular end-diastolic volume index, left ventricular end-systolic volume index, left ventricular ejection fraction, and late gadolinium enhancement ratio), and 1 clinical feature (history of non-sustained ventricular tachycardia) that could be included in the machine learning model. In the prediction models built with the training set, the concordance indices for the random forest, decision tree, and XGBoost models were 0.966 (95%CI 0.813-0.995), 0.956 (95%CI 0.796-0.992), and 0.973 (95%CI 0.823-0.996), respectively. In the validation set, the concordance indices for the random forest, decision tree, and XGBoost models were 0.854 (95%CI 0.557-0.964), 0.706 (95%CI 0.399-0.896), and 0.703 (95%CI 0.408-0.890), respectively. Conclusion: Integrating clinical and CMR features of HCM patients through machine learning aids in predicting heart failure events, with the random forest model showing superior performance.

Analysis of the possibility of using exploration and learning algorithms in the production of castings

The research presented in the article indicates the process of building models based on machine learning algorithms, linear regression, decision trees, ensemble learning, random forest, ensemble averaging, Boosting, stacking, and support vector regression (SVR) algorithms. The basis for building these models are experimental data collected during research conducted at the Łukasiewicz Research Network-Krakow Institute of Technology. An analysis of the initial state and the analysis of the state of correlation in the set were performed, which facilitated the development of models. To increase the amount of data, augmentation was performed using the Bootstrapping. For selected results, castings were made and tested in real conditions. The research results indicate the possibility of identifying the most appropriate input parameters for specific production processes of austempered ductile iron (ADI), the possibility of predicting the expected mechanical parameters based on the indicated parameters of the production process, chemical composition, specific parameters of the heat treatment process, and the thickness of the target product. A set of such models constitutes the basis of the system, enabling the end user to estimate the final parameters of the casting planned to be produced.

Exploring Spotify's Music Popularity Dynamics and Forecasting with Machine Learning

Abstract. Spotify, one of the largest music streaming service providers, boasts a vast user base and an extensive music catalog. To gain a deeper understanding of Spotify users' music preferences and behavioral patterns, this paper conducts a thorough analysis and explores the correlation between music features and user behavior. It collects Spotify users' music listening data and extracts various music features such as energy, danceability, valence, and beats per minute (BPM). These features not only reflect the musical style and rhythm but also potentially correlate with users' preferences and listening habits. Then we employ two machine learning models, Decision Trees and Random Forests, to model and analyze Spotify users' behavior data. Through these models, we can accurately identify potential relationships between music features and user behavior. The experimental results indicate that music features such as energy, danceability, valence, and BPM have a significant impact on users' music selection and preferences. By analyzing the most popular songs on Spotify over different time periods, we discover that songs with high energy, danceability, and valence tend to be more popular among users. This finding not only validates the correlation between music features and user behavior but also reveals the user preferences and market demands behind music trends. For music streaming service providers, understanding users' music preferences and behavioral patterns is crucial. By deeply analyzing user data, music streaming services can better satisfy users' needs, enhance user experience, and stand out in the fiercely competitive market. These findings have important practical implications for music streaming service providers and provide new insights and methodologies for the research and development of the music industry.

Evaluating the impact of construction delays on project duration using machine learning and multi-criteria decision analysis

Evaluating the impact of construction delays on project duration using machine learning and multi-criteria decision analysis

Developing a machine learning model with enhanced performance for predicting COVID-19 from patients presenting to the emergency room with acute respiratory symptoms.

Artificial Intelligence is playing a crucial role in healthcare by enhancing decision-making and data analysis, particularly during the COVID-19 pandemic. This virus affects individuals across all age groups, but its impact is more severe on the elderly and those with underlying health issues like chronic diseases. This study aimed to develop a machine learning model to improve the prediction of COVID-19 in patients with acute respiratory symptoms. Data from 915 patients in two hospitals in Saudi Arabia were used, categorized into four groups based on chronic lung conditions and COVID-19 status. Four supervised machine learning algorithms-Random Forest, Bagging classifier, Decision Tree, and Logistic Regression-were employed to predict COVID-19. Feature selection identified 12 key variables for prediction, including CXR abnormalities, smoking status, and WBC count. The Random Forest model showed the highest accuracy at 99.07%, followed by Decision Tree, Bagging classifier, and Logistic Regression. The study concluded that machine learning algorithms, particularly Random Forest, can effectively predict and classify COVID-19 cases, supporting the development of computer-assisted diagnostic tools in healthcare.

Machine learning algorithm approach to complete blood count can be used as early predictor of COVID-19 outcome.

Although the SARS-CoV-2 infection has established risk groups, identifying biomarkers for disease outcomes is still crucial to stratify patient risk and enhance clinical management. Optimal efficacy of COVID-19 antiviral medications relies on early administration within the initial five days of symptoms, assisting high-risk patients in avoiding hospitalization and improving survival chances. The complete blood count can be an efficient and affordable option to find biomarkers that predict the COVID-19 prognosis due to infection-induced alterations in various blood parameters. This study aimed to associate hematological parameters with different COVID-19 clinical forms and utilize them as disease outcome predictors. We performed a complete blood count in blood samples from 297 individuals with COVID-19 from Belo Horizonte, Brazil. Statistical analysis, as well as ROC Curves and machine learning Decision Tree algorithms were used to identify correlations, and their accuracy, between blood parameters and disease severity. In the initial four days of infection, traditional hematological COVID-19 alterations, such as lymphopenia, were not yet apparent. However, the monocyte percentage and granulocyte-to-lymphocyte ratio proved to be reliable predictors for hospitalization, even in cases where patients exhibited mild symptoms that later progressed to hospitalization. Thus, our findings demonstrate that COVID-19 patients with monocyte percentages lower than 7.7% and a granulocyte-to-lymphocyte ratio higher than 8.75 are assigned to the hospitalized group with a precision of 86%. This suggests that these variables can serve as important biomarkers in predicting disease outcomes and could be used to differentiate patients at hospital admission for managing therapeutic interventions, including early antiviral administration. Moreover, they are simple parameters that can be useful in minimally equipped health care units.

Recovering MRI magnetic field strength properties using machine learning based on image compression quality scores

AbstractOver the years, significant hardware advancements have led to higher magnetic field MRI (Magnetic Resonance Imaging) acquisitions, providing improved diagnostic image quality at a higher cost. While higher image quality is desired, the investment required for high-field MRI imaging systems remains a significant consideration. Furthermore, historical patient records may still contain low-field magnetic strength MRI data. In this work, we present how image compression quality scores of MRI images could be used to recover their magnetic field strength properties. This work presents an interesting inverse problem scenario where output properties are used to recover an input property of an image. We implemented supervised machine learning models that utilize compressed image quality scores - based on Mean Squared Error (MSE), Structural Similarity Index (SSIM), Visual Information Fidelity (VIF), and Earth Movers Distance (EM) metrics - as inputs. These models classify images into specific classes of magnetic field strength at which they were acquired (Low, Medium, and High) based solely on the quality scores of their compressed copies. The trained machine learning models (Support Vector Machine (SVM), Logistic Regression, K-nearest Neighbours (KNN), Decision Tree and Random Forest) achieved nearly 100% performance efficiency based on accuracy and F-1 score for all considered quality measures. This comprehensive evaluation offers insights into how compression techniques and quality factors impact image fidelity across various MRI magnetic field strengths. The findings of this study may prove valuable in recovering missing meta-tag information in historical image DICOM records and Context-Based Retrieval Systems (CBRS). The approach of using quality scores as features in training machine learning models, as demonstrated in this work, can be extended to other image groups where input parameters create statistically significant distinctions or are challenging to extract from images.

Spectral data driven machine learning classification models for real time leaf spot disease detection in brinjal crops

This study presents the development and evaluation of machine learning models for detecting leaf spot disease in brinjal crops using spectral sensor data. The spectral reflectance of diseased and healthy tissues was recorded across nine wavelength bands (F1: 415 nm, F2: 445 nm, F3: 480 nm, F4: 515 nm, F5: 555 nm, F6: 590 nm, F7: 630 nm, F8: 680 nm, and F9: NIR-750 nm). The data revealed distinct spectral signatures, particularly between F5 (555 nm) and F9 (NIR), where diseased tissues consistently showed lower reflectance compared to healthy tissues. Two machine learning algorithms, Decision Tree (DT) and Support Vector Machine (SVM), were employed to classify the spectral data. The DT model achieved a maximum testing accuracy of 88.2 %, with a Gini index and a depth of 4 as optimal hyperparameters. The confusion matrix indicated that the DT model correctly identified 883 diseased instances and 667 healthy cases, while misclassifying 213 healthy tissues as diseased and 25 diseased tissues as healthy. The SVM model, configured with a cost parameter of 10.0 and a tolerance of 0.01, outperformed the DT model, achieving a testing accuracy of 92.4 %. The SVM model correctly classified 99.3 % of diseased instances and 94.1 % of healthy cases. The results demonstrate the potential of spectral sensor data combined with ML algorithms for precise disease detection, facilitating targeted pesticide application, and reducing input costs. The high accuracy of the SVM model underscores its utility in agricultural disease management, enabling early intervention and enhancing crop health monitoring. Future research may explore integrating multiple sensors and advanced feature extraction methods to further improve the efficiency and accuracy of these systems.

Justice-centered best practices for accessibility to public buildings in a tier II city: Insights from a Delphi expert consensus

Background Despite beneficial progress in policies, awareness and advocacy, accessibility gaps exist in public buildings in India. Challenges achieving full inclusivity still exist, due to a lack of clear guidance for implementing accessible solutions. Retrofitting older buildings, particularly in developing tier II cities is a major challenge. The authors of this paper aimed to address this issue using a four-round Delphi method to generate a Justice-Centered Best Practices (JCBPs) for accessibility provisions for individuals with mobility disabilities. Methods Conducted in Udupi, the study involved experts including administrators, policy implementers, auditors, advocates, healthcare professionals, individuals with disabilities and their caregivers. In the first round, a 117-item list was generated through triangulation of three methods. In subsequent rounds, experts rated each item using a 5-point Likert scale on feasibility, affordability and priority. Responses were considered valid if the agreement reached ≥80% on the total score. The prioritised list of JCBPs was finalised at a consensus meeting. Results Out of forty-eight experts who began the study, 16 participated in the final meeting. The Wilcoxon signed rank test (p value&gt;0.05) of expert ranking indicated that the scoring of items remained consistent between the two rounds. A machine learning decision tree analysis identified items securing ≥ 80% agreement as the most reliable decision with an accuracy=71.43%. The McNemar’s Test p value=0.79 confirmed consistency of expert scoring on the items with high agreement rates. Conclusion Finally, 33 built and non-built environment items scored highest rank. Stakeholder engagement, use of low-cost technology solutions, coordination between public administrations, funding, good governance practice, awareness, and advocacy were few of the solutions that can help ensure accessibility is in place for individuals with mobility disabilities. The study methodology and findings create a robust foundation for evidence-based JCBPs for accessibility provisions for individuals with mobility disabilities.

Identifying at-risk patients for congenital heart disease using integrated predictive models and fuzzy clustering analysis: A cross-sectional study

Congenital heart disease (CHD) remains a significant global health concern, affecting approximately 1 % of newborns worldwide. While its accurate causes often remain elusive, a combination of genetic and environmental factors is implicated. In this cross-sectional study, we propose a comprehensive prediction framework leveraging Machine Learning (ML) and Multi-Attribute Decision Making (MADM) techniques to enhance CHD diagnostics and forecasting. Our framework integrates supervised and unsupervised learning methodologies to remove data noise and address imbalanced datasets effectively. Through the utilization of imbalance ensemble methods and clustering algorithms such as K-means, we enhance predictive accuracy, particularly in non-clinical datasets where imbalances are prevalent. Our results demonstrate an improvement of 8 % in recall compared to existing literature, showcasing the efficacy of our approach. Moreover, our framework identifies clusters of patients at the highest risk using MADM techniques, providing insights into susceptibility to CHD. Fuzzy clustering techniques further assess the degree of risk for individuals within each cluster, enabling personalized risk evaluation. Importantly, our analysis reveals that unhealthy lifestyle factors, annual per capita income, nutrition, and folic acid supplementation emerge as crucial predictors of CHD occurrences. Additionally, environmental risk factors and maternal illnesses significantly contribute to the predictive model. These findings underscore the multifactorial nature of CHD development, emphasizing the importance of considering socioeconomic and lifestyle factors alongside medical variables in CHD risk assessment and prevention strategies. Our proposed framework offers a promising avenue for early identification and intervention, potentially mitigating the burden of CHD on affected individuals and healthcare systems globally.

An Accurate Classification for Human Sport Activity Recognition from Sensor Data Using Hybrid Machine Learning Models

The significance of human sports activities recognition (HSAR) in many computing applications, including sports analytics, smart surroundings, and healthcare monitoring is huge. The current use of vision sensors for HSAR is a difficult task due to the intricate movements involved in sports and fitness workouts, as well as fluctuations in illumination conditions. Therefore, a comprehensive review of machine learning algorithms (such as XGBoost, Random Forest (RF), Decision Trees (DT), and K-Nearest Neighbors (KNN)) and their usage for human sports activities classification based on sensor data called ML-HSAR is presented in this article. A dataset containing 19 different human activities gathered from 8 different people through different types of sensors was used for this work; the dataset contains activities like sitting and standing, as well as other activities that require serious movements, such as running, cycling, and playing basketball. This study primarily aims to determine the performance of the considered ML models in accurately classifying these activities found in the dataset. The training of the algorithms and the subsequent evaluation were done on the segmented sensor data, effectively leveraging the dataset’s temporal aspect. In addition to the presented results for each of these algorithms, the limitations of each algorithm and their strengths in handling the complexities involved in HSAR were also presented. The contribution of this analysis is towards the understanding of the most appropriate ML models for HSAR tasks; it also offers valuable insights for future research and practical applications.

Enhancing prediction of elemental composition through machine learning decision tree models for biomass gasification optimization

Abstract The worldwide transition to cleaner, sustainable energy sources, prompted by population growth and industrialization, responds to uncertain fossil fuel prices and environmental concerns, highlighting the substantial benefits of renewable energy in reducing greenhouse gas emissions and addressing climate change. Derived from non-fossilized organic materials, biomass emerges as a significant and sustainable contributor to renewable energy. Its diverse nature is complemented by a range of conversion technologies, encompassing combustion, pyrolysis, gasification, and liquefaction, providing versatile avenues for biomass energy transformation. Gasification, the transformative process of converting organic matter into combustible gases under controlled oxygen levels, is accomplished through direct oxygen supply or pyrolysis. This method yields a dependable gaseous fuel versatile for heating, industrial processes, power generation, and liquid fuel production. Machine learning employs advanced statistical techniques for modeling across diverse industries, showcasing particular efficacy in optimizing thermochemical processes by precisely identifying the optimal operating conditions required for achieving desired product properties. These models utilize proximate biomass data to predict the elemental compositions of N2 and H2. Assessment of both single and two hybrid models indicated that the introduced optimizers significantly enhanced the estimation of N2 and H2 when combined with Decision Tree (DT), with Decision Tree Coupled with Artificial Hummingbird Algorithm (DTAH) proving particularly effective. Notably, DTAH demonstrated outstanding performance with remarkable R 2 values of 0.990 for N2 and 0.992 for H2. Additionally, the minimal Root Mean Square Error (RMSE) values of 1.291 and 1.550 for N2 and H2 predictions respectively underscore the precision of DTAH, establishing it as a suitable choice for practical real-world applications.

Flood risk decomposed: Optimized machine learning hazard mapping and multi-criteria vulnerability analysis in the city of Zaio, Morocco

Urban flood risk mapping has become crucial for effective mitigation and urban planning. This study assesses and maps flood risk in the city of Zaio, Morocco, using machine learning and Multi-Criteria Decision Analysis (MCDA) techniques to overcome data scarcity challenges. We employed the Random Forest (RF) model with nine flood conditioning factors for flood hazard and the Analytical Hierarchy Process (AHP) for vulnerability assessment. To enhance RF model performance, we compared three hyperparameter tuning techniques: Bayesian Optimization (RF-BO), Genetic Algorithm (RF-GA), and Grid Search (RF-GS). RF-BO demonstrated superior accuracy in flood hazard modelling. Flood vulnerability was assessed using AHP, incorporating social and physical factors. The final flood risk map was produced by combining the RF-BO hazard model with the AHP vulnerability assessment. Results indicate that flood hazard in Zaio is significantly affected by factors such as topography and distance to rivers. Moreover, areas with high population density closer to rivers, especially in the south-western residential area, were found to be more exposed to flood risk. The findings highlight the utility of ML models, MCDA, and hyperparameter optimization in urban flood risk mapping, enabling the identification of high-risk urban areas that should be prioritized for flood protection efforts. This approach proves especially valuable in ungauged regions with limited hydrological data.

Quantification of Color Variation of Various Esthetic Restorative Materials in Pediatric Dentistry.

The goal of this paper is to find an association between the staining capacity of dental restorations used in pediatric patients and food items and to develop an optimum model to predict the most informative factor that causes the highest amount of color change through machine learning algorithms. Color changes in restorative materials occur as a result of intrinsic and extrinsic factors, such as the type of restorative material, food items used, polished status of the material, and time interval. This was an "in vitro study" conducted at Aligarh Muslim University, Aligarh, Uttar Pradesh, India. The study included 200 specimens, that is, 40 in each group A (orange juice), group B (Amul Kool Café), group C (Pepsi), group D (Amul Kesar Milk), and group E (artificial saliva). The materials were glass ionomer cement (GIC), resin-modified glass ionomer cement (RMGIC), microhybrid composite resin, and nanohybrid composite resin. These were further divided into polished and unpolished groups. The optimum modeling of the prediction of color change in materials by different effective factors was done by machine learning decision tree. We applied two algorithms: Chi-square automatic interaction detector (CHAID) and classification and regression tree (CART). In prediction modeling in the decision tree by CHAID and CART, color change is taken as the dependent variable, and group (type of restorative material), food items, time interval, and polished status are taken as independent variables. The various beverages caused significant color variation due to different pigmentation agents. The agent that caused the highest color change was Kool Café. The Kesar Milk had the lowest pigmentation capacity. The greatest color variation was found on Glasionomer FX-II submerged in Pepsi and the least on Ivoclar Te-Econom Plus in Kesar Milk. The mean absolute error for the training dataset in the CART model and CHAID model is 0.379 and 0.332, and for the testing data set, it is 0.398 and 0.333, respectively. Therefore, the prediction of color change by the CHAID model is optimum, and we found that the restorative materials have a maximum predictor importance of 0.86 (86%), time interval 0.07 (7%), food items 0.04 (4%), and polished status has the least importance, that is, 0.03 (3%). The staining capacity of restorative material highly depends on the material itself, the initial time interval, and least on the food items used. The clinical performance of dental restorations could be affected by various beverages consumed by children. This study thus provides important clinical insights into esthetic dentistry by offering valuable information on long-term color stability and the effect of polishing on common esthetic restorative materials used in pediatric dentistry. Varshney P, Khan SY, Jindal MK, et al. Quantification of Color Variation of Various Esthetic Restorative Materials in Pediatric Dentistry. Int J Clin Pediatr Dent 2024;17(7):754-765.

Drought assessment in Kabul River basin using machine learnings

Droughts significantly impact water resources and agriculture, leading to economic losses and potential human fatalities. This study aims to predict droughts by analysing changes in the Standardised Precipitation Evapotranspiration Index (SPEI) for the Kabul River basin using data from 1981 to 2022. The research is divided into three phases: calculating SPEI, splitting the dataset into training (80%) and testing (20%) subsets, and evaluating model performance. Various machine learning algorithms, including XGBoost, Decision tree, AdaBoost, and KNN, were employed alongside different climatic variables. The models were assessed using statistical metrics such as R², RMSE, MAE, MSE for regression, and confusion matrix, accuracy, precision, recall, F1 score, ROC AUC, and Log loss for classification. Results showed strong performance, with R² values of 0.97, 0.86, 0.92, and 0.96 for XGBoost, KNN, Decision tree, and AdaBoost, respectively. SPEI demonstrated significant potential for drought forecasting, and spatial distribution mapping revealed persistent moderate drought occurrences.

Prediction and Feature Importance Investigation for Bank Churn Based on Machine Learning

Since bank customers are one of the main sources of bank income, preventing the loss of bank customers has always been the primary and struggle problem for banks. This paper chooses three machine learning methods, random forest, decision tree and logistic regression should focus to predict the leaving customers. In order to more accurately determine the factors affecting the departure of bank customers, this paper grouped the data set according to the age of over and under 40. The results shows that the prediction performance of random forest is the best one in both groups, and the logistic regression is the worst one. The precision of this model is higher in younger group than in older group, the accuracy in each group is about 90% and 76% respectively. Then the random forest method is used to return the important features for two groups. For people older than 40 years old, whether to continue to stay in the bank to buy its products is greatly affected by their Balance and Age factors. Having more balance and being younger, the more possibility to keep purchasing. While for under 40 years old customers, their counterpart behaviors are more determined by the Estimated Salary and Credit Score. Thus, when banks managers tackle customer management, they should focus more on the above factors to better prevent the loss of customers.

Electroretinogram Analysis Using a Short-Time Fourier Transform and Machine Learning Techniques.

Electroretinography (ERG) is a non-invasive method of assessing retinal function by recording the retina's response to a brief flash of light. This study focused on optimizing the ERG waveform signal classification by utilizing Short-Time Fourier Transform (STFT) spectrogram preprocessing with a machine learning (ML) decision system. Several window functions of different sizes and window overlaps were compared to enhance feature extraction concerning specific ML algorithms. The obtained spectrograms were employed to train deep learning models alongside manual feature extraction for more classical ML models. Our findings demonstrated the superiority of utilizing the Visual Transformer architecture with a Hamming window function, showcasing its advantage in ERG signal classification. Also, as a result, we recommend the RF algorithm for scenarios necessitating manual feature extraction, particularly with the Boxcar (rectangular) or Bartlett window functions. By elucidating the optimal methodologies for feature extraction and classification, this study contributes to advancing the diagnostic capabilities of ERG analysis in clinical settings.