Correlation Analysis and Predictive Factors for Building a Mathematical Model

The article examines the application of statistical data analysis algorithms in diagnostics and the identification of significant factors influencing observed phenomena. The use of statistical methods, such as multiple regression, logistic regression, and neural networks, is discussed. The study focuses on determining the most impactful factors, establishing relationships between variables, and evaluating the effectiveness of technologies and methods. The dataset, provided by Universidad Cardenal Herrera, CEU, Madrid, Spain, includes factors related to patients’ demographics, health conditions, and lifestyle. The analysis involves deductive analysis, correlation analysis, and Kohonen maps to identify relevant factors. Decision tree analysis is conducted using different combinations of factors, including average glucose levels and body mass index. The results show varying error rates for different methods and factor combinations. Overall, statistical data analysis demonstrates its potential for faster and more accurate identification of significant diagnostic factors.

Application of statistical data analysis algorithms and determination of the most significant diagnostic factors

Rozhkova,

Kukartsev,

Kvesko

et al. 2024

Predictive modelling of post-monsoon groundwater quality in Telangana using machine learning techniques

Olentsova,

Kukartsev,

Orlov

et al. 2024

Groundwater quality is vital for public health, agriculture, and industry, especially in regions like Telangana, India. This study analyses and predicts post-monsoon 2020 groundwater quality using data from the Telangana State Groundwater Department. We employed Linear Regression and Random Forest Regression to predict key parameters: pH and Total Dissolved Solids (TDS). Exploratory data analysis revealed significant correlations, such as between TDS and Electrical Conductivity (E.C). The Linear Regression model for TDS performed exceptionally well, with an R2 of 0.985, while the Random Forest model also showed strong results. However, both models exhibited moderate accuracy in predicting pH. The study demonstrates the effectiveness of machine learning models in predicting groundwater quality, offering valuable tools for groundwater management. These findings can aid policymakers and environmental managers in making informed decisions to safeguard water resources.

Machine learning approaches for water potability prediction: Addressing class imbalance with SMOTE

Stepanova,

Orlov,

Kukartsev

et al. 2024

Ensuring access to safe drinking water is a fundamental public health priority. Traditional methods for assessing water quality are laborintensive and require specialized equipment, which may not be feasible for continuous monitoring. This study explores the use of machine learning models to predict water potability based on various chemical properties. Specifically, we evaluate the performance of Logistic Regression and Random Forest models in the presence of class imbalance, a common issue in environmental datasets. To mitigate this, we apply the Synthetic Minority Over-sampling Technique (SMOTE). Our results indicate that before applying SMOTE, both models exhibited a strong bias towards the majority class (non-potable water), achieving an accuracy of 69.36% and a ROCAUC of 0.63. However, the application of SMOTE significantly improved the model’s ability to identify potable water samples, particularly for the Random Forest model, which achieved an accuracy of 67.07% and a ROCAUC of 0.64 post-SMOTE. In contrast, the Logistic Regression model showed a decline in performance after SMOTE, suggesting the need for further optimization or alternative approaches. This study highlights the importance of addressing class imbalance in machine learning tasks, especially for critical applications like water quality assessment. Our findings suggest that the Random Forest model, combined with SMOTE, offers a robust solution for predicting water potability. These insights can aid environmental scientists and public health officials in implementing more efficient and accurate water quality monitoring systems. Future research should explore a broader range of models and advanced techniques to further enhance prediction accuracy.