Feature selection on real-time application using hybrid of flamingo search algorithm and improved non-dominated sorting genetic algorithm III

An enhanced and efficient approach for feature selection for chronic human disease prediction: A breast cancer study

Battle Royale Optimizer (BRO) is a recently proposed optimization algorithm that has added a new category named game-based optimization algorithms to the existing categorization of optimization algorithms. Both continuous and binary versions of this algorithm have already been proposed. Generally, optimization problems can be divided into single-objective and multi-objective problems. Although BRO has successfully solved single-objective optimization problems, no multi-objective version has been proposed for it yet. This gap motivated us to design and implement the multi-objective version of BRO (MOBRO). Although there are some multi-objective optimization algorithms in the literature, according to the no-free-lunch theorem, no optimization algorithm can efficiently solve all optimization problems. We applied the proposed algorithm to four benchmark datasets: CEC 2009, CEC 2018, ZDT, and DTLZ. We measured the performance of MOBRO based on three aspects: convergence, spread, and distribution, using three performance criteria: inverted generational distance, maximum spread, and spacing. We also compared its obtained results with those of three state-of-the-art optimization algorithms: the multi-objective Gray Wolf optimization algorithm (MOGWO), the multi-objective particle swarm optimization algorithm (MOPSO), the multi-objective artificial vulture's optimization algorithm (MOAVAO), the optimization algorithm for multi-objective problems (MAOA), and the multi-objective non-dominated sorting genetic algorithm III (NSGA-III). The obtained results approve that MOBRO outperforms the existing optimization algorithms in most of the benchmark suites and operates competitively with them in the others.

In today's increasingly interconnected digital world, ensuring the security and reliability of network traffic has become a critical concern. Traditional rule-based and signature-driven approaches to network anomaly detection are often inadequate in identifying novel and evolving cyber threats. Machine learning (ML) techniques provide a powerful solution by learning patterns from historical network traffic data and detecting deviations that may indicate security threats or network malfunctions. This paper explores the application of various machine learning models, such as supervised, unsupervised, and deep learning techniques, for real-time anomaly detection in network traffic. Key challenges, including data preprocessing, feature selection, and the handling of class imbalance, are addressed. Through a comparative analysis of algorithms such as Decision Trees, Support Vector Machines (SVMs), and Neural Networks, we demonstrate the effectiveness of machine learning models in identifying both known and unknown network anomalies. The results highlight the potential of hybrid models and ensemble techniques to improve detection accuracy and reduce false positives. This study underscores the importance of leveraging advanced machine learning techniques to strengthen network security frameworks and maintain the integrity of digital communications.

ABSTRACTFeature selection is a vital preprocessing step aimed at identifying a subset of the most relevant features from high‐dimensional data to enhance model performance and reduce computational complexity. Differential Evolution (DE) algorithms have been extensively applied to this task by iteratively optimizing the selection probabilities or weights of features. However, many existing DE‐based approaches suffer from premature convergence and local optima entrapment due to an insufficient balance between global exploration and local exploitation. To address these challenges, we propose a niching‐based two‐stage mutation DE algorithm for feature selection. Firstly, the mutual information is utilized to initialize the population and reduce the number of features. Then, an improved two‐stage mutation operator is employed to balance the algorithm's exploitation and exploration. Additionally, duplicate individuals generated during the evolutionary process are replaced using a one‐bit evolutionary mutation to aid population evolution. Experimental results on 16 benchmark datasets demonstrate that the proposed method achieves superior classification accuracy compared to several state‐of‐the‐art approaches, validating its effectiveness and robustness in diverse feature selection scenarios.

Optimisation and interpretation of machine and deep learning models for improved water quality management in Lake Loktak

Background This study aimed to establish and validate a machine learning (ML) model for predicting in-hospital mortality in critically ill patients with chronic kidney disease (CKD). Methods This study collected data on CKD patients from 2008 to 2019 using the Medical Information Mart for Intensive Care IV. Six ML approaches were used to build the model. Accuracy and area under the curve (AUC) were used to choose the best model. In addition, the best model was interpreted using SHapley Additive exPlanations (SHAP) values. Results There were 8527 CKD patients eligible for participation; the median age was 75.1 (interquartile range: 65.0–83.5) years, and 61.7% (5259/8527) were male. We developed six ML models with clinical variables as input factors. Among the six models developed, the eXtreme Gradient Boosting (XGBoost) model had the highest AUC, at 0.860. According to the SHAP values, the sequential organ failure assessment score, urine output, respiratory rate, and simplified acute physiology score II were the four most influential variables in the XGBoost model. Conclusions In conclusion, we successfully developed and validated ML models for predicting mortality in critically ill patients with CKD. Among all ML models, the XGBoost model is the most effective ML model that can help clinicians accurately manage and implement early interventions, which may reduce mortality in critically ill CKD patients with a high risk of death.

The role of higher moments in predicting China's oil futures volatility: Evidence from machine learning models

Drug-Protein Interaction (DPI) identification is crucial in drug discovery. The high dimensionality of drug and protein features poses challenges for accurate interaction prediction, necessitating the use of computational techniques. Docking-based methods rely on 3D structures, while ligand-based methods have limitations such as reliance on known ligands and neglecting protein structure. Therefore, the preferred approach is the chemogenomics-based approach using machine learning, which considers both drug and protein characteristics for DPI prediction. In machine learning, feature selection plays a vital role in improving model performance, reducing overfitting, enhancing interpretability, and making the learning process more efficient. It helps extract meaningful patterns from drug and protein data while eliminating irrelevant or redundant information, resulting in more effective machine-learning models. On the other hand, classification is of great importance as it enables pattern recognition, decision-making, predictive modeling, anomaly detection, data exploration, and automation. It empowers machines to make accurate predictions and facilitates efficient decision-making in DPI prediction. For this research work, protein data was sourced from the KEGG database, while drug data was obtained from the DrugBank data machine-learning base. To address the issue of imbalanced Drug Protein Pairs (DPP), different balancing techniques like Random Over Sampling (ROS), Synthetic Minority Over-sampling Technique (SMOTE), and Adaptive SMOTE were employed. Given the large number of features associated with drugs and proteins, feature selection becomes necessary. Various feature selection methods were evaluated: Correlation, Information Gain (IG), Chi-Square (CS), and Relief. Multiple classification methods, including Support Vector Machines (SVM), Random Forest (RF), Adaboost, and Logistic Regression (LR), were used to predict DPI. Finally, this research identifies the best balancing, feature selection, and classification methods for accurate DPI prediction. This comprehensive approach aims to overcome the limitations of existing methods and provide more reliable and efficient predictions in drug-protein interaction studies.

Chronic pain around the temporomandibular joint (TMJ) and masticatory muscles is a primary symptom of temporomandibular disorders (TMD). However, the clinical significance of magnetic resonance imaging (MRI) features in predicting TMD-related pain remains unclear. This study aimed to develop and interpret machine learning (ML) models based on MRI characteristics for predicting pain severity in patients with TMD. The present retrospective study included 584 patients with TMD between January 2022 and December 2024, yielding a total of 755 TMJ MRI data sets. Pain severity was classified using the visual analogue scale (VAS). Demographic variables (age, sex) and MRI features-including lesion side, disc position, disc morphology, disc signal, disc perforation, bilaminar zone tear, joint space, joint effusion, condylar movement, bony changes and morphology/signal of the lateral pterygoid muscle-were collected. Eleven ML models based on demographic and MRI features were developed: logistic regression (LR), support vector machine (SVM), random forest (RF), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), adaptive boosting (AdaBoost), gradient boosting classifier (GBC), bagging classifier (BC), extremely randomised trees (ETC), decision tree classifier (DTC) and multilayer perceptron (MLP). Model performance was evaluated using multiple metrics, including the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity and F1 score. Precision-recall (PR) curves and calibration curves were plotted to assess discrimination and model calibration. Decision curve analysis (DCA) was conducted to evaluate the clinical net benefit across a range of threshold probabilities. Model interpretability was enhanced using Shapley Additive Explanations (SHAP), which quantified the contribution of each feature to individual predictions. Feature selection was conducted based on mean SHAP values, and separate LightGBM models were constructed using the Top 3, 5, and 9 most important features, as well as the full-feature set, for performance comparison. The data set was randomly divided into a training set (n = 604) and a test set (n = 151). Among the 11 ML models, the LightGBM model demonstrated the best predictive performance, with an AUC of 0.899, and was therefore identified as the optimal model. SHAP analysis identified age, disc position and condylar movement as the top three contributing features. Feature selection analysis indicated that selecting the top nine SHAP-ranked variables led to the highest diagnostic performance, with an AUC of 0.829. This study developed an interpretable, high-performing MRI-based ML model incorporating SHAP analysis to integrate imaging and clinical features for objective pain assessment, which may help identify high-risk TMD patients and guide personalised treatment strategies.

Text classification has been highlighted as the key process to organize online texts for better communication in the Digital Media Age. Text classification establishes classification rules based on text features, so the accuracy of feature selection is the basis of text classification. Facing fast-increasing Chinese electronic documents in the digital environment, scholars have accumulated quite a few algorithms for the feature selection for the automatic classification of Chinese texts in recent years. However, discussion about how to adapt existing feature selection algorithms for various types of Chinese texts is still inadequate. To address this, this study proposes three improved feature selection algorithms and tests their performance on different types of Chinese texts. These include an enhanced CHI square with mutual information (MI) algorithm, which simultaneously introduces word frequency and term adjustment (CHMI); a term frequency–CHI square (TF–CHI) algorithm, which enhances weight calculation; and a term frequency–inverse document frequency (TF–IDF) algorithm enhanced with the extreme gradient boosting (XGBoost) algorithm, which improves the algorithm’s ability of word filtering (TF–XGBoost). This study randomly chooses 3000 texts from six different categories of the Sogou news corpus to obtain the confusion matrix and evaluate the performance of the new algorithms with precision and the F1-score. Experimental comparisons are conducted on support vector machine (SVM) and naive Bayes (NB) classifiers. The experimental results demonstrate that the feature selection algorithms proposed in this paper improve performance across various news corpora, although the best feature selection schemes for each type of corpus are different. Further studies of the application of the improved feature selection methods in other languages and the improvement in classifiers are suggested.

High-dimensional datasets often contain a large number of irrelevant, redundant, or noisy features, presenting significant challenges for feature selection and modeling. As the dimensionality increases, models become prone to overfitting, and the computational cost rises. To address these issues, this paper proposes a symmetry-based feature selection evolutionary algorithm (SSFE), which aims to effectively reduce data dimensionality and improve model prediction performance. By calculating the Symmetry Uncertainty SU values of features and combining the roulette wheel selection strategy, the algorithm is able to filter out the most informative features and avoid local optima by incorporating an evolutionary algorithm. The method gradually reduces the number of features, optimizing the feature selection process for high-dimensional data, significantly improving the efficiency and accuracy of feature selection. Experimental results show that SSFE outperforms traditional feature selection algorithms on multiple high-dimensional datasets, effectively reducing data dimensionality and enhancing model performance.

Boosting chameleon swarm algorithm with consumption AEO operator for global optimization and feature selection

This study addresses key limitations of traditional algorithms in green supply chain management, including vulnerability to local optima, unsystematic population initialization, and inadequate parameter tuning. To overcome these challenges, a collaborative optimization framework is developed by integrating an Improved Sparrow Search Algorithm (ISSA) with the Non-dominated Sorting Genetic Algorithm III (NSGA-III), forming the ISSA-NSGA-III model. The model begins with Tent chaotic mapping to generate a well-distributed initial population, ensuring broad coverage of the solution space. An adaptive periodic convergence factor is then introduced to dynamically balance global exploration and local exploitation during the optimization process. To further strengthen search performance, Lévy flight and elite opposition-based learning are incorporated, enhancing the model’s ability to escape local optima. These improvements are embedded within the NSGA-III framework to achieve robust multi-objective optimization. Performance is evaluated using a public supply chain management dataset. Compared with the standard Sparrow Search Algorithm, which serves as its baseline, the ISSA-NSGA-III model reduces total supply chain cost by approximately 14.0%, lowers carbon emissions by 14.2%, and increases resource utilization by 15.4%. The spacing metric also improves by 40.2%, indicating a more uniform and diverse distribution of Pareto-optimal solutions. Overall, the proposed algorithm demonstrates strong potential for coordinating economic performance and environmental sustainability in green supply chains, offering reliable technical support for complex decision-making.Supplementary InformationThe online version contains supplementary material available at 10.1038/s41598-025-20612-7.

Urban Microgrids have complex topologies and operating environments. This leads to extreme volatility and instability when high percentage of renewable energy is integrated into them. To address these problems, we propose a day-ahead optimal scheduling model for the smart community microgrid on the basis of the improved non-dominated sorting genetic algorithm III (NSGA-III). It minimizes the day-ahead operating cost of the microgrid while balancing electricity load. Firstly, we design a wind/solar/hydrogen storage self-consistent energy system inside the community microgrid to realize the efficient utilization of renewable energy. Secondly, we introduce an adaptive mutation-crossover strategy, and propose a fuzzy inference-based NSGA-III algorithm, to solve the slow convergence speed and poor convergence stability of the current multi-objective optimization algorithms. Finally, we design an optimal microgrid scheduling strategy based on typical day. In the day ahead operation cycle of the community microgrid, it maximizes the absorption of wind/solar unit outputs. This improves the operational efficiency of the microgrid and effectively reducing system operating costs. Extensive experiments demonstrate that the proposed model achieves superior performance compared with the original NSGA-III methods. The total daily operating costs of the proposed microgrid is reduced by 4.5%, and the renewable energy consumption rates is increased by 8.1%.

ObjectiveTo develop an interpretable stacking ensemble model for predicting in-hospital mortality in intensive care unit (ICU) patients with CKD and sepsis and to deploy it as a web-based tool for bedside clinical use.MethodsData were extracted from the MIMIC-IV 3.0 database and split into training and test sets at a 7:3 ratio. Feature selection was performed by combining the least absolute shrinkage and selection operator (LASSO) regression with the Boruta algorithm. Eight machine learning (ML) models were trained and optimized via ten-fold cross-validation and grid search. The two models with the highest area under the curve (AUC) in the training set were combined using a stacking ensemble strategy. SHapley Additive exPlanations (SHAP) were applied to improve interpretability. Model performance was compared with the SOFA score.ResultsA total of 5344 ICU patients with CKD and sepsis were included, with an in-hospital mortality rate of 19.1%. After feature selection, 16 variables were retained. In the training set, XGBoost and LightGBM performed best. The stacking model achieved an AUC of 0.757 on the test set, outperforming SOFA (AUC = 0.668). SHAP analysis identified age, Acute Physiology Score III, Simplified Acute Physiology Score II, and respiratory rate as the top predictors. The model was also deployed as a publicly accessible web application.ConclusionThe stacking ensemble model demonstrated good discriminatory performance and interpretability for predicting in-hospital mortality in ICU patients with CKD and sepsis. Its web-based deployment provides a convenient platform for early risk assessment, although external validation is needed to confirm its broader applicability.