Empowering early detection: A web-based machine learning approach for PCOS prediction

Informatics in Medicine Unlocked, Journal Year: 2024, Volume and Issue: 47, P. 101500 - 101500

Published: Jan. 1, 2024

Nowadays, Polycystic Ovary Syndrome (PCOS) affects many women, making it a prevalent concern. It is hormonal disorder that causes irregular, delayed, or absent menstrual cycles in the female body. This condition can lead to development of type 2 diabetes, gestational weight gain, unwanted body hair, and various other complications. In severe cases, PCOS result infertility, posing challenge for patients trying conceive. Statistics show incidence rate has significantly increased recent years, which alarming. If identified early, people may follow their doctor's recommendations live better life. The dataset used this research contains records 541 patients. aim study employ machine learning models identify patterns disorder. information learned then inputted into algorithms assess accuracy, specificity, sensitivity, precision using different ML models, such as Logistic Regression (LR), Decision Tree (DT), AdaBoost (AB), Random Forest (RF), Support Vector Machine (SVM) among others. utilized Mutual Information model feature selection compared determine most accurate one. Employing engineering, AB RF achieved highest accuracy 94%.

Language: Английский

---

Machine learning approaches for predicting shielding effectiveness of carbon fiber-reinforced mortars

Case Studies in Construction Materials, Journal Year: 2024, Volume and Issue: 20, P. e03189 - e03189

Published: April 22, 2024

The exponential growth of communication technologies and the ubiquitous use electronic devices raise concerns about unintended electromagnetic interference (EMI). Existing research exploring mortars incorporated with carbon fibers for EMI shielding primarily relies on empirical experiments investigating interplay between effectiveness (SE) mixed design parameters. This aims to establish predictive models SE, focusing frequency radiation mortar constituents (water-to-cement ratio (W/C), fiber content, sand-to-cement (S/C), aspect ratio). Employing a diverse array machine learning algorithms, including stochastic gradient descent (SGD), boosting, random forest, gene expression programming (GEP), AdaBoost, decision tree, K-nearest neighbors, stepwise linear regression, this study forecast efficacy mortar. Results demonstrate robust model performance, R2 values correlation coefficients surpassing 0.85 0.95, respectively, across training, testing, validation datasets. Modeling errors, such as MSE, RMSE, MAE, MAPE, remain within acceptable bounds all models. accuracy predictions is evidenced by experimental-to-predicted SE ratios falling 0.5-1.5 range. Based available data, parametric investigations conducted using GEP-derived equation reveal positive S/C ratio, frequency, while indicating an inverse relationship W/C ratio. Moreover, employing Shapley additive explanation (SHAP)—a technique grounded in cooperative game theory—enhances interpretability SE. In summary, provides valuable insights into prediction reinforced cement mortar, underscoring enhancing

Language: Английский

---

Examining evolutionary scale modeling‐derived different‐dimensional embeddings in the antimicrobial peptide classification through a KNIME workflow

Protein Science, Journal Year: 2024, Volume and Issue: 33(4)

Published: March 19, 2024

Abstract Molecular features play an important role in different bio‐chem‐informatics tasks, such as the Quantitative Structure–Activity Relationships (QSAR) modeling. Several pre‐trained models have been recently created to be used downstream either by fine‐tuning a specific model or extracting feed traditional classifiers. In this regard, new family of Evolutionary Scale Modeling (termed ESM‐2 models) was introduced, demonstrating outstanding results protein structure prediction benchmarks. Herein, we studied usefulness different‐dimensional embeddings derived from classify antimicrobial peptides (AMPs). To end, built KNIME workflow use same modeling methodology across experiments order guarantee fair analyses. As result, 640‐ and 1280‐dimensional 30‐ 33‐layer models, respectively, are most valuable since statistically better performances were achieved QSAR them. We also fused it concluded that fusion contributes getting than using single model. Frequency studies revealed only portion is for tasks between 43% 66% never used. Comparisons regarding state‐of‐the‐art deep learning (DL) confirm when performing methodologically principled AMPs, non‐DL based yield comparable‐to‐superior DL‐based models. The developed available‐freely at https://github.com/cicese-biocom/classification-QSAR-bioKom . This can avoid unfair comparisons computational methods, well propose

Language: Английский

---

Explainable AI for enhanced accuracy in malaria diagnosis using ensemble machine learning models

BMC Medical Informatics and Decision Making, Journal Year: 2025, Volume and Issue: 25(1)

Published: April 11, 2025

Language: Английский

---

Forecasting water quality through machine learning and hyperparameter optimization

Indonesian Journal of Electrical Engineering and Computer Science, Journal Year: 2024, Volume and Issue: 33(1), P. 496 - 496

Published: Jan. 1, 2024

Forecasting water quality through machine learning and hyperparameter optimization is a research endeavor aimed at enhancing the prediction process. The primary goal of this study to employ various algorithms for refine existing models from previous research. paper encompasses comprehensive literature review studies introduces novel theoretical insights. employs classic problem-solving approach, predominantly utilizing extreme gradient boost (XGBoost) algorithm. Additionally, it evaluates other algorithms, including random forest (RF) classifier, decision tree (DT) adaptive boosting (AdaBoost) support vector (SVM), Naïve Bayes, extra classifier comparison. evaluation process utilizes classification report, providing insights into precision, recall, f1-score, accuracy each model. Notably, XGBoost model exhibits superior performance, achieving an impressive 97.06% accuracy. Precision stands 94.22%, recall 81.5%, F1-score 87.4%. These results represent significant advancement over prior models, emphasizing potential enhance forecasting in environmental monitoring.

Language: Английский

---

An AdaBoost Ensemble Model for Fault Detection and Classification in Photovoltaic Arrays

IEEE Journal of Radio Frequency Identification, Journal Year: 2022, Volume and Issue: 6, P. 794 - 800

Published: Jan. 1, 2022

The photovoltaic (PV) arrays are susceptible to numerous faults. Fault diagnosis is essential in improving a PV system's output power, reliability, and life span. This research paper suggests an AdaBoost Ensemble Model (AEM) approach for detecting classifying system AEM includes several weak base learners stacked sequentially so that they learn from the mistakes of prior produce improved predictive model. study considers open-circuit fault (OCF), short-circuit (SCF), degradation (DF). A complete quantitative evaluation suggested compared earlier machine learning classification techniques diagnose faults arrays. results proposed superior those traditional methods, with accuracy 97.84 percent detection. findings indicate improves performance while preserving powerful generalization capability diagnostics. Consequently, more effective at array systems.

Language: Английский

---

Ensemble Machine Learning-Based Approach to Predict Cervical Cancer with Hyperparameter Tuning and Model Explainability

Deleted Journal, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 10, 2025

Cervical cancer remains the top killer of women at a young age in world, 85% cases are detected low-income countries. Preventive measures and therapeutic response enhanced if potential hazards identified early. This research belongs to this field by introducing an end-to-end prediction model based on individual medical records early screening data thus emphasizing discovery meaningful predictors. In order overcome issues with feature selection class imbalances, our study creates ensemble framework that blends Random Forest Logistic Regression techniques. addition achieving astounding accuracy 99.75%, guarantees transparency its decision-making processes utilizing sophisticated machine learning algorithms conjunction interpretability tools like SHAP LIME, which is essential for applications healthcare. The creation extensive method combines several classifiers, advanced techniques locating important predictive factors, help healthcare professionals better understand complex predictions some research's main investments. By offering accurate comprehensible risk assessments, novel has revolutionize clinical enhance cervical cavity identification. promotes development more proactive individualized methods fusing cutting-edge computational technology diagnostics, improving health outcomes everywhere.

Language: Английский

---

Enhancing thyroid nodule classification: A comprehensive analysis of feature selection in thermography

Infrared Physics & Technology, Journal Year: 2025, Volume and Issue: unknown, P. 105730 - 105730

Published: Jan. 1, 2025

Language: Английский

---

Early PCOS Detection: A Comparative Analysis of Traditional and Ensemble Machine Learning Models With Advanced Feature Selection

Engineering Reports, Journal Year: 2025, Volume and Issue: 7(2)

Published: Feb. 1, 2025

ABSTRACT PCOS (polycystic ovary syndrome) is a common hormonal disorder that affects many women during their reproductive years. It marked by imbalances, leading to ovarian cysts, and can result in health issues such as infertility, diabetes, even heart problems. Diagnosing accurately early be challenging, it requires specific medical expertise. However, spotting promptly allows individuals follow recommendations, which lead healthier lifestyles. In this study, we examined dataset consisting of 541 patient records enhance the detection using advanced machine learning techniques. We established data preprocessing pipeline rigorously addressed missing values identified outliers, while also normalizing ensure was ready for input. For feature selection, applied techniques SelectKBest, Chi‐Square, XGBoost. These methods helped us pinpoint most predictive attributes, improved interpretability efficiency our models. Hyperparameter tuning carefully performed through grid search cross‐validation, ensuring each model optimized best prediction accuracy. Importantly, research highlights how effective predicting PCOS. The logistic regression support vector stood out with its remarkable accuracy 99.7753%. Furthermore, created user‐friendly web application facilitate smooth deployment real‐time analysis. This provides healthcare professionals handy tool identifying risks related features an intuitive interface where users easily input clinical information receive immediate risk assessments.

Language: Английский

---

Ensemble-Based Machine Learning Techniques for Adaptive Wireless Sensor Networks

Advances in computer and electrical engineering book series, Journal Year: 2025, Volume and Issue: unknown, P. 319 - 360

Published: Feb. 7, 2025

Wireless sensor networks (WSN) have gained popularity in next-generation IoT connectivity due to their sustainability and low maintenance. However, the dynamic nature of energy sources environmental conditions presents challenges security reliability WSNs, particularly mitigating various network attacks. Machine learning offers solutions these by enabling adaptive real-time behaviour. This chapter addresses WSN applying ML techniques a multi-class dataset attacks such as normal, flooding, TDMA, grayhole, blackhole. SMOTE is applied manage class imbalance, an ensemble framework proposed with classifiers logistic regression, random forest, gradient boost, xtreme decision tree, LGBM, SVM, CatBoost were predict WSN-DS dataset. The models are rigorously tested evaluated using accuracy, precision, recall, F1-score. Gradient catboost outperform all other achieving 98% accuracy.

Language: Английский

---