Feature Selection Method Research Articles

Does Maternal HIV Infection Affect Neonatal Outcomes?

Pregnancy among women infected with HIV is classified as a high-risk pregnancy. While previous research has indicated an elevated likelihood of preterm birth, low birth weight, and early gestational age in infants born to mothers with HIV, the correlation between maternal HIV infection and different neonatal results remains unclear. This study aims to investigate the impact of maternal HIV infection on after-birth neonatal outcomes using machine learning (ML) and statistical methods. A case-control study is conducted through a three-stage process: Initially, the outcomes among newborns from HIV-positive mothers are identified through a combination of literature review and expert survey. Subsequently, data are paired at a 1:2 ratio based on gestational age with infants from HIV-positive mothers (n=48) compared to HIV-negative mothers (n=96) as the control group. Finally, various feature selection techniques are applied to identify outcomes that exhibit significant differences between the two groups. The statistical analysis showed that the rate of addiction among HIV-positive mothers is higher than that of the HIV-negative group. The need for mechanical ventilation and duration of ventilator-assisted breathing in infants born to HIV-positive mothers are significantly higher than in infants born to HIV-negative mothers. Moreover, based on feature selection methods, increasing the need for mechanical ventilation and reducing surfactant administration were two important outcomes. To investigate the impact of maternal HIV infection on neonatal outcomes, various statistical and machine learning-based feature selection techniques were implemented, and the results showed that the presented methods can be utilized to examine the potential impacts of different diseases contracted by the mother on the infant.

An improved intrusion detection method for IIoT using attention mechanisms, BiGRU, and Inception-CNN

In the field of Industrial Internet of Things (IIoT), existing intrusion detection models face challenges in three main areas: low accuracy in detecting attack traffic, feature redundancy when dealing with high-dimensional and complex attack traffic, making it difficult to capture critical information, and a tendency to favor learning common categories while neglecting rare categories when handling imbalanced data. To tackle these challenges, this study introduces an intrusion detection method that combines an attention mechanism, Bidirectional Gated Recurrent Units (BiGRU), and Inception Convolutional Neural Network (Inception-CNN) to enhance the model’s detection rate. Simultaneously, the method employs a mixed sampling strategy for data resampling to address the bias learning issue caused by data imbalance. Additionally, the method employs a hybrid sampling strategy for data resampling to address the bias learning issue caused by data imbalance. It also incorporates denoising techniques to handle potential dataset noise introduced by hybrid sampling. Furthermore, a feature selection method combining Pearson correlation coefficient and Random Forest is applied to eliminate feature redundancy, enhancing the model’s ability to capture crucial information from high-dimensional attack traffic. Experimental validation on internationally recognized datasets (Edge-IIoTset, CIC-IDS2017, and CIC IoT 2023) affirms the reliability of the proposed intrusion detection method. This approach underscores the significance of intrusion detection in the security of Industrial IoT and showcases its potential in addressing pertinent challenges in network security.

Machine learning model predicts airway stenosis requiring clinical intervention in patients after lung transplantation: a retrospective case-controlled study

BackgroundPatients with airway stenosis (AS) are associated with considerable morbidity and mortality after lung transplantation (LTx). This study aims to develop and validate machine learning (ML) models to predict AS requiring clinical intervention in patients after LTx.MethodsPatients who underwent LTx between January 2017 and December 2019 were reviewed. The conventional logistic regression (LR) model was fitted by the independent risk factors which were determined by multivariate LR. The optimal ML model was determined based on 7 feature selection methods and 8 ML algorithms. Model performance was assessed by the area under the curve (AUC) and brier score, which were internally validated by the bootstrap method.ResultsA total of 381 LTx patients were included, and 40 (10.5%) patients developed AS. Multivariate analysis indicated that male, pulmonary arterial hypertension, and postoperative 6-min walking test were significantly associated with AS (all P < 0.001). The conventional LR model showed performance with an AUC of 0.689 and brier score of 0.091. In total, 56 ML models were developed and the optimal ML model was the model fitted using a random forest algorithm with a determination coefficient feature selection method. The optimal model exhibited the highest AUC and brier score values of 0.760 (95% confidence interval [CI], 0.666–0.864) and 0.085 (95% CI, 0.058–0.117) among all ML models, which was superior to the conventional LR model.ConclusionsThe optimal ML model, which was developed by clinical characteristics, allows for the satisfactory prediction of AS in patients after LTx.

Single-objective and multi-objective mixed-variable grey wolf optimizer for joint feature selection and classifier parameter tuning

Feature selection plays an essential role in data preprocessing, which can extract valuable information from extensive data, thereby enhancing the performance of machine learning classification. However, existing feature selection methods primarily focus on selecting feature subsets without considering the impact of classifier parameters on the optimal subset. Different from these works, this paper considers jointly optimizing the feature subset and classifier parameters to minimize the number of features and achieve a low classification error rate. Since feature selection is an optimization problem with binary solution space while classifier parameters involve both continuous and discrete variables, our formulated problem becomes a complex multi-objective mixed-variable problem. To address this challenge, we consider a single-objective optimization method and a multi-objective optimization approach. Specifically, in the single-objective optimization method, we adopt the linear weight method to convert our multiple objectives into a fitness function and then propose a mixed-variable grey wolf optimizer (MGWO) to optimize the function. The proposed MGWO introduces Chaos-Faure initialization, Log convergence factor adjustment, and optimal solution adaptive update operators to enhance its adaptability and balance the global and local search of the algorithm. Subsequently, an improved multi-objective grey wolf optimizer (IMOGWO) is introduced to directly address the problem. The proposed IMOGWO introduces improved initialization, local search, and binary variable mutation operators to balance its exploration and exploitation abilities, making it more suitable for our mixed-variable problem. Extensive simulation results show that our MGWO and IMOGWO outperform recent and classic baselines. Moreover, we also find that jointly optimizing classifier parameters can significantly improve classification accuracy.

Democratizing cheminformatics: interpretable chemical grouping using an automated KNIME workflow

With the increased availability of chemical data in public databases, innovative techniques and algorithms have emerged for the analysis, exploration, visualization, and extraction of information from these data. One such technique is chemical grouping, where chemicals with common characteristics are categorized into distinct groups based on physicochemical properties, use, biological activity, or a combination. However, existing tools for chemical grouping often require specialized programming skills or the use of commercial software packages. To address these challenges, we developed a user-friendly chemical grouping workflow implemented in KNIME, a free, open-source, low/no-code, data analytics platform. The workflow serves as an all-encompassing tool, expertly incorporating a range of processes such as molecular descriptor calculation, feature selection, dimensionality reduction, hyperparameter search, and supervised and unsupervised machine learning methods, enabling effective chemical grouping and visualization of results. Furthermore, we implemented tools for interpretation, identifying key molecular descriptors for the chemical groups, and using natural language summaries to clarify the rationale behind these groupings. The workflow was designed to run seamlessly in both the KNIME local desktop version and KNIME Server WebPortal as a web application. It incorporates interactive interfaces and guides to assist users in a step-by-step manner. We demonstrate the utility of this workflow through a case study using an eye irritation and corrosion dataset.Scientific contributionsThis work presents a novel, comprehensive chemical grouping workflow in KNIME, enhancing accessibility by integrating a user-friendly graphical interface that eliminates the need for extensive programming skills. This workflow uniquely combines several features such as automated molecular descriptor calculation, feature selection, dimensionality reduction, and machine learning algorithms (both supervised and unsupervised), with hyperparameter optimization to refine chemical grouping accuracy. Moreover, we have introduced an innovative interpretative step and natural language summaries to elucidate the underlying reasons for chemical groupings, significantly advancing the usability of the tool and interpretability of the results.

Forecasting ground-level ozone and fine particulate matter concentrations at Craiova city using a meta-hybrid deep learning model

Air quality forecasting is vital for managing and mitigating the adverse effects of air pollution on human health, crops, and the environment. This study aims to forecast daily time series of ozone and fine particulate matter (PM) concentrations using a meta-hybrid deep NARMAX (Nonlinear Auto-Regressive Moving Average with eXogenous inputs) model. Two datasets were utilised: (a) data on meteorological parameters (temperature, air pressure, relative humidity) and air pollutant concentrations (particulate matter, ozone, dioxide of carbon, volatile organic compounds, formaldehyde) provided by a sensor model A3 situated in the centre of Craiova city, and (b) data on wind direction, wind speed, and sunshine duration provided by the National Meteorological Administration. The data sets covered a time interval from December 10, 2020, to January 05, 2024. Initially, a statistical analysis was conducted to assess the correlation between variables. Results revealed that ozone concentration is primarily influenced by meteorological variables such as temperature (r = 0.79), sunshine duration (r = 0.55), and relative humidity (r = −0.48), and secondarily by air pollution indicators including VOC (r = −0.34), PM concentrations (r = −0.34), and CO2 (r = −0.3). In the subsequent stage, thirteen Machine Learning (ML) models were employed in conjunction with an integral feature selection (IFS) method to identify the best combinations of predictor variables for predicting ozone and PMs. Finally, a deep NARMAX model was developed to forecast the next periods of ozone and PMs based on the optimal combinations identified earlier. Results indicated the selection of sixty best models for ozone forecasting and four best models for PMs. The R2 values surpassed 0.97 for ozone and exceeded 0.8 for PMs, demonstrating the efficacy of the forecasting approach.

Classification and spatio-temporal evolution analysis of coastal wetlands in the Liaohe Estuary from 1985 to 2023: based on feature selection and sample migration methods

Classification and spatio-temporal evolution analysis of coastal wetlands in the Liaohe Estuary from 1985 to 2023: based on feature selection and sample migration methods

Tree-based ensemble machine learning models in the prediction of acute respiratory distress syndrome following cardiac surgery: a multicenter cohort study

BackgroundAcute respiratory distress syndrome (ARDS) after cardiac surgery is a severe respiratory complication with high mortality and morbidity. Traditional clinical approaches may lead to under recognition of this heterogeneous syndrome, potentially resulting in diagnosis delay. This study aims to develop and external validate seven machine learning (ML) models, trained on electronic health records data, for predicting ARDS after cardiac surgery.MethodsThis multicenter, observational cohort study included patients who underwent cardiac surgery in the training and testing cohorts (data from Nanjing First Hospital), as well as those patients who had cardiac surgery in a validation cohort (data from Shanghai General Hospital). The number of important features was determined using the sliding windows sequential forward feature selection method (SWSFS). We developed a set of tree-based ML models, including Decision Tree, GBDT, AdaBoost, XGBoost, LightGBM, Random Forest, and Deep Forest. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC) and Brier score. The SHapley Additive exPlanation (SHAP) techinque was employed to interpret the ML model. Furthermore, a comparison was made between the ML models and traditional scoring systems. ARDS is defined according to the Berlin definition.ResultsA total of 1996 patients who had cardiac surgery were included in the study. The top five important features identified by the SWSFS were chronic obstructive pulmonary disease, preoperative albumin, central venous pressure_T4, cardiopulmonary bypass time, and left ventricular ejection fraction. Among the seven ML models, Deep Forest demonstrated the best performance, with an AUC of 0.882 and a Brier score of 0.809 in the validation cohort. Notably, the SHAP values effectively illustrated the contribution of the 13 features attributed to the model output and the individual feature's effect on model prediction. In addition, the ensemble ML models demonstrated better performance than the other six traditional scoring systems.ConclusionsOur study identified 13 important features and provided multiple ML models to enhance the risk stratification for ARDS after cardiac surgery. Using these predictors and ML models might provide a basis for early diagnostic and preventive strategies in the perioperative management of ARDS patients.

Uncovering waterlogging-responsive genes in cucumber through machine learning and differential gene correlation analysis

As climate change intensifies, the frequency and severity of waterlogging are expected to increase, necessitating a deeper understanding of the cucumber response to this stress. In this study, three public RNA-seq datasets (PRJNA799460, PRJNA844418, and PRJNA678740) comprising 36 samples were analyzed. Various feature selection algorithms including Uncertainty, Relief, SVM (Support Vector Machine), Correlation, and logistic least absolute shrinkage, and selection operator (LASSO) were performed to identify the most significant genes related to the waterlogging stress response. These feature selection techniques, which have different characteristics, were used to reduce the complexity of the data and thereby identify the most significant genes related to the waterlogging stress response. Uncertainty, Relief, SVM, Correlation, and LASSO identified 4, 4, 10, 21, and 13 genes, respectively. Differential gene correlation analysis (DGCA) focusing on the 36 selected genes identified changes in correlation patterns between the selected genes under waterlogged versus control conditions, providing deeper insights into the regulatory networks and interactions among the selected genes. DGCA revealed significant changes in the correlation of 13 genes between control and waterlogging conditions. Finally, we validated 13 genes using the Random Forest (RF) classifier, which achieved 100% accuracy and a 1.0 Area Under the Curve (AUC) score. The SHapley Additive exPlanations (SHAP) values clearly showed the significant impact of LOC101209599, LOC101217277, and LOC101216320 on the model’s predictive power. In addition, we employed the Boruta as a wrapper feature selection method to further validate our gene selection strategy. Eight of the 13 genes were common across the four feature weighting algorithms, LASSO, DGCA, and Boruta, underscoring the robustness and reliability of our gene selection strategy. Notably, the genes LOC101209599, LOC101217277, and LOC101216320 were among genes identified by multiple feature selection methods from different categories (filtering, wrapper, and embedded). Pathways associated with these specific genes play a pivotal role in regulating stress tolerance, root development, nutrient absorption, sugar metabolism, gene expression, protein degradation, and calcium signaling. These intricate regulatory mechanisms are crucial for cucumbers to adapt effectively to waterlogging conditions. These findings provide valuable insights for uncovering targets in breeding new cucumber varieties with enhanced stress tolerance.

Maximal cliques-based hybrid high-dimensional feature selection with interaction screening for regression

Studies on feature selection have been extensively conducted in the literature, as it plays a significant role in both supervised and unsupervised machine learning tasks. Since the bulk of features in high-dimensional data sets might not be significant, feature selection plays a key role in removing unimportant variables and improving prediction and data analysis performance. Many of the current feature selection methods, meanwhile, become ineffective when used on contemporary datasets, which exhibit an escalating number of features in relation to sample size. This paper introduces a novel supervised feature selection method for regression problems. The proposed algorithm is called maximal Clique with Interaction Screening (ISClique). The ISClique algorithm’s overall structure can be described in two steps. Initially, a filter approach is used to select relevant features from an initial feature space and examine the different interactions between them. This is done using an innovative coefficient based on Kendall’s tau and partial Kendall’s tau. Secondly, the maximal clique strategy is applied as a wrapper to the selected set from the previous step to construct subsets of features. The most optimal subset that minimizes prediction error is selected. The proposed method integrates the advantages of graph theory with feature screening. Additionally, because the criteria employed in developing the ISClique method accommodate variable heterogeneity, this method is equally suitable for classification tasks. The proposed hybrid approach has been evaluated through applications involving various simulation scenarios and real datasets. Experimental findings demonstrate the advantages of ISClique over comparable methods.

Multi-Objective Unsupervised Feature Selection and Cluster Based on Symbiotic Organism Search

Unsupervised learning is a type of machine learning that learns from data without human supervision. Unsupervised feature selection (UFS) is crucial in data analytics, which plays a vital role in enhancing the quality of results and reducing computational complexity in huge feature spaces. The UFS problem has been addressed in several research efforts. Recent studies have witnessed a surge in innovative techniques like nature-inspired algorithms for clustering and UFS problems. However, very few studies consider the UFS problem as a multi-objective problem to find the optimal trade-off between the number of selected features and model accuracy. This paper proposes a multi-objective symbiotic organism search algorithm for unsupervised feature selection (SOSUFS) and a symbiotic organism search-based clustering (SOSC) algorithm to generate the optimal feature subset for more accurate clustering. The efficiency and robustness of the proposed algorithm are investigated on benchmark datasets. The SOSUFS method, combined with SOSC, demonstrated the highest f-measure, whereas the KHCluster method resulted in the lowest f-measure. SOSFS effectively reduced the number of features by more than half. The proposed symbiotic organisms search-based optimal unsupervised feature-selection (SOSUFS) method, along with search-based optimal clustering (SOSC), was identified as the top-performing clustering approach. Following this, the SOSUFS method demonstrated strong performance. In summary, this empirical study indicates that the proposed algorithm significantly surpasses state-of-the-art algorithms in both efficiency and effectiveness. Unsupervised learning in artificial intelligence involves machine-learning techniques that learn from data without human supervision. Unlike supervised learning, unsupervised machine-learning models work with unlabeled data to uncover patterns and insights independently, without explicit guidance or instruction.

Multi-label feature selection based on minimizing feature redundancy of mutual information

Multi-label feature selection is an indispensable technology in the preprocessing of multi-label high-dimensional data. Approaches utilizing information theory and sparse models hold promise in this domain, demonstrating strong performance. Although there have been extensive literatures using l1 and l2,1-norms to identify label-specific features and common features in the feature space, they all ignore the redundant information interference problem when different features are learned simultaneously. Considering that features and labels in multi-label data are rarely linearly correlated, the MFS-MFR approach is presented to generate a representation of the nonlinear correlation between features and labels using the mutual information estimator. Following that, MFS-MFR detects specific and common features in the feature-label mutual information space using two coefficient matrices constrained by the l1 and l2,1-norms, respectively. In particular, we define a non-zero correlation constraint that effectively minimizes the redundant correlation between the two matrices. Moreover, a manifold regularization term is devised to preserve the local information of the mutual information space. To solve the optimization model with nonlinear binary regular term, we employ a novel solution approach called S-FISTA. Extensive experiments across 15 multi-label benchmark datasets, comparing against 11 top-performing multi-label feature selection methods, demonstrate the superior performance of MFS-MFR.

Supervised spectral feature selection with neighborhood rough set

Spectral feature selection, an excellent dimensionality reduction method, is extensively used in knowledge mining and protein sequence analysis. However, the graph representation derived from data with potential noises significantly impacts feature selection performance. Similarly, its performance deteriorates when label information is ignored, as the selected features have poor discrimination ability. To overcome these drawbacks, this article optimizes neighborhood structure and further constructs the conditional entropy based on neighborhood purity to generate a precise graph representation incorporating label information to enhance the compactness of intra-class samples and increase the dispersion between inter-class samples. Then this article proposes a novel spectral feature selection method. Specifically, the method dynamically learns the precise graph representation from low-dimension space, which can effectively preserve the local structure of data, and the global structure is preserved by introducing a constraint term that maintains the graph representation before and after dimension reduction. Additionally, ℓ2,1-norm is introduced to ensure row sparsity and select the valuable features. The alternative optimization algorithm is employed to solve the optimization problem and its convergence is theoretically analyzed. Finally, to assess the performance of the proposed method, a series of comprehensive experiments are performed on several real-world datasets.

An adaptive pyramid PSO for high-dimensional feature selection

Feature selection (FS) is an important data pre-processing method in machine learning tasks. However, FS becomes an NP-hard combinatorial optimization problem due to the huge search space of high-dimensional datasets and the complex interaction among features. As a simple implementation algorithm, particle swarm optimization (PSO) has been employed for dealing with FS problems. At the same time, it still suffers from issues such as the premature convergence and falling into local optimum. In this paper, an adaptive pyramid PSO (APPSO) is proposed for FS on dataset classification problems. In APPSO, a weighted initialization strategy based on correlation and the cubic chaotic map is employed to generate particles in the initial stage, aiming to improve the diversity of a population. Then, an adaptive constrained updating strategy, based on the pyramid structure, is proposed to enhance the exploration ability of the population. Moreover, a new dynamical flip strategy (DFS), which combines feature correlation and occurrence frequencies of features, is proposed to improve the exploitation ability of the population. The proposed APPSO is compared with 8 representative wrapper-based FS methods. Experimental results show that APPSO significantly outperforms these competitors on all 18 datasets.

Coal mine gas emission prediction based on multifactor time series method

The prediction of coal mine gas emission is an important indicator for ventilation systems reliability and a data basis for mine gas extraction design. The traditional gas emission prediction methods have weak universal applicability, and the existing prediction models are mostly based on single-factor time series prediction. To solve this problem, the gas emission prediction method based on Recursive Feature Elimination with cross-validation (RFECV) and Bidirectional Long and Short-Term Memory (Bi-LSTM) was proposed. Aiming at the problems of numerous influencing factors, strong nonlinear characteristics and time correlation, feature selection methods based on RFECV were applied. The RFECV method embedding of two base models, Ridge Regression (Ridge) and Random Forest (RF), obtained four gas emission prediction multifactor combinations. The predictive accuracy of different models was compared with multifactor combinations when the training set accounted for 60, 70 and 80 % of the total sample. The RMSE, MAE, R2, model stability, and running time of the RF-RFECV-Bi-LSTM model were 0.2455,0.1914,0.9897,0.9431 and 12.20 s, respectively. The result indicated that the constructed prediction model had high accuracy and reliability, which can be used as a basis for the accurate prediction of gas emission in multifactor time series.

Development of Statistically Modelled Feature Selection Method for Microwave Breast Cancer Detection

Development of Statistically Modelled Feature Selection Method for Microwave Breast Cancer Detection

Gravimetric inhibition efficiency prediction model of AA7075-T7351 alloy using Treculia africana extract in 1.0 M HCl through input feature optimization

The applications of four machine learning (ML) algorithms, namely: Support Vector Regressor (SVR), Extreme Gradient Boosting (XGBoost), Least absolute shrinkage and selection operator (Lasso), and Ridge, in predicting the corrosion inhibition efficiency (IE) of Treculia africana (TA) leaves extract on AA7075-T7351 alloy, in corrosive 1.0 M HCl environment, with a small (42) sample space, have been studied. Time and resource constraints in traditional corrosion study methods have been avoided through feature engineering to expedite prediction process. The dominant features, which affected the IE, were done through feature importance and selection processes using pair plot matrix of features and Kendall correlation etc., to remove redundant features. The results in the form of data visualization, feature importance, and the performance of each algorithm on the test set were explicitly depicted. The evaluation metrics, including coefficients of determination (R2) and root mean square error (RMSE), validated the efficacy of the models in predicting the IE of TA on AA7075-T7351 in 1.0 M HCl environments. Ridge model demonstrated superior accuracy, with R2 score of 0.972, particularly in handling the highly correlated dataset used in this study. SVR followed closely in performance (0.969). XGBoost proved reliable at R2 score of 0.953. Lasso with R2 of 0.952 was the least of the four models, due to its random feature selection method. The RMSE scores corroborated the prediction accuracies with values; 4.145, 4.408, 5.138 and 5.462 respectively. This study revealed the viability of using the four machine learning algorithms in potential generalization ability of IE prediction accuracy, while offering an efficient and accurate alternative to traditional methods.Graphical

Sparse feature selection using hypergraph Laplacian-based semi-supervised discriminant analysis

Feature selection, as a dimension reduction technique in data mining and pattern recognition, aims to select the most discriminative features and improve the learning performance. With an abundance of unlabeled data readily available across various applications, semi-supervised feature selection has emerged as a promising approach. While most semi-supervised feature selection methods rely on simple graphs to preserve the geometrical structure of data, this approach often fails in capturing the high-order relationships present in many real-world applications. In contrast, hypergraphs offer the ability to encode more complex structures of data beyond what a simple graph can achieve. In this paper, we propose a feature selection method formulated in the trace ratio form, integrating hypergraph Laplacian-based semi-supervised discriminant analysis (SDA) and the mixed convex and non-convex ℓ2,p-norm (0<p≤1) regularization. The proposed trace ratio-based method, called HSDAFS, leverages the discriminative information from labeled data to maximize class separability while also utilizing the hypergraph Laplacian to capture the geometrical structure and high-order relationships within both labeled and unlabeled data. The ℓ2,p-norm regularization in the proposed HSDAFS provides improved sparsity over the ℓ2,1-norm. It ensures that the projection matrix is row-sparse, enabling the effective joint selection of discriminative features across all data. To solve the trace ratio-based HSDAFS method, we convert it into a trace difference method and propose an iterative algorithm. Experiments on several datasets demonstrate that HSDAFS is more effective in selecting the most discriminative features compared to other methods.

Explainable Deep Learning-Based Feature Selection and Intrusion Detection Method on the Internet of Things.

With the rapid advancement of the Internet of Things, network security has garnered increasing attention from researchers. Applying deep learning (DL) has significantly enhanced the performance of Network Intrusion Detection Systems (NIDSs). However, due to its complexity and "black box" problem, deploying DL-based NIDS models in practical scenarios poses several challenges, including model interpretability and being lightweight. Feature selection (FS) in DL models plays a crucial role in minimizing model parameters and decreasing computational overheads while enhancing NIDS performance. Hence, selecting effective features remains a pivotal concern for NIDSs. In light of this, this paper proposes an interpretable feature selection method for encrypted traffic intrusion detection based on SHAP and causality principles. This approach utilizes the results of model interpretation for feature selection to reduce feature count while ensuring model reliability. We evaluate and validate our proposed method on two public network traffic datasets, CICIDS2017 and NSL-KDD, employing both a CNN and a random forest (RF). Experimental results demonstrate superior performance achieved by our proposed method.

CFRP-RC fracture strength prediction: A novel approach using deep learning

Externally bonded carbon fiber-reinforced polymer (CFRP) composites have been widely adopted for strengthening and repairing aging concrete structures. However, premature fracture at the CFRP-concrete interface remains a significant concern, necessitating a better understanding of the interfacial bond behavior and fracture mechanisms. Traditional experimental studies and numerical simulations have limitations in accurately capturing the complex nonlinear factors influencing this fracture behavior. This paper explores the novel application of machine learning (ML), specifically artificial neural networks (ANNs), for predicting the fracture strength of CFRP-reinforced concrete (CFRP-RC) members. ANNs enable mapping the intricate relationships between input parameters (e.g., CFRP/concrete properties, geometric configurations) and fracture responses through iterative training on experimental data. Key aspects include comprehensive data collection, preprocessing techniques, feature selection methods like mean impact value (MIV) analysis, and neural network architecture design. The paper highlights successful ANN applications in predicting CFRP-RC bond strength, shear capacity, and overall fracture behavior. A systematic approach is proposed for developing robust ANN models tailored to CFRP-RC fracture prediction, encompassing data curation, input variable screening, network training/validation, and model interpretability analyses. By leveraging ML’s ability to handle multifaceted nonlinearities, this data-driven framework offers a powerful alternative to traditional methods, potentially enhancing the design, analysis, and performance evaluation of CFRP-strengthened concrete structures.