Feature Subset Research Articles

Variability of radiological and clinical features in cases with usual interstitial pneumonia without honeycombing

BackgroundUsual interstitial pneumonia (UIP) cases without honeycombing (possible UIP) included various CT features and was often difficult to diagnose. PurposeThis study aimed to classify the cases with possible UIP on CT features using cluster analysis and evaluate the features of subsets of participants and the correlation of prognosis. Materials and MethodsThe study included 85 patients with possible UIP in the 2011 idiopathic pulmonary fibrosis (IPF) guideline with radiological diagnosis. All cases underwent surgical biopsies and were diagnosed by multidisciplinary discussion (MDD) from the nationwide registry in Japan. The readers evaluated pulmonary opacity, nodules, cysts, and predominant distribution which were reclassified by IPF guidelines in 2018. Additionally, cases were classified into four groups by cluster analysis based on CT findings. The differences in survival among IPF classification and the clusters were evaluated. ResultsCases were diagnosed as IPF (n = 55), NSIP (n = 4), unclassifiable (n = 23), and others (n = 3) by MDD. Cluster analysis revealed 4 clusters by CT features (n = 47, 16, 19 and 3, respectively). Cluster 1 had fewer lesions overall. Cluster 2 have many pure ground-glass opacities and ground-glass opacities with reticulation. Cluster 3 had many reticular opacities and nodules with few lower predominant distributions. Cluster 4 was characterized by peribronchovascular consolidation.The mean survival time of cluster 1 (4518 days) was significantly better than cluster 2, 3, and 4 (1843, 2196, and 1814 days, respectively) (p = 0.03). ConclusionIn conclusion, UIP without honeycombing included various CT patterns and MDD diagnoses. Significangly differences in prognosis were observed among clusters classified by CT findings.

Predicting creep life of CrMo pressure vessel steel using machine learning models with optimal feature subset selection

The data-driven approach for creep life prediction typically integrates numerous characteristics, including material compositions, manufacturing details, and service conditions, into machine learning models. In this study, a machine learning-based creep life prediction approach with optimal feature subset selection is established for 2.25Cr1Mo pressure vessel steel. Before model training and testing, six critical features that significantly impact the creep life of 2.25Cr1Mo steel are selected, specifically the applied stress, temperature, and chemical compositions consisting of Cr, Ni, Mn, and Mo. Various machine learning algorithms, along with the traditional L–M method, are utilized for model training and performance evaluation. Additionally, the developed models undergo validation using experimental data independent of the training and testing datasets to assess their generalization abilities. The results reveal that, among all tested models, the support vector regression (SVR) model, coupled with the optimal feature subset, demonstrates superior prediction accuracy and generalization capability. Finally, the creep life prediction model exhibiting optimal performance is deployed into a software application, leveraging the Python programming language. This predictor tool facilitates rapid and precise creep life predictions for 2.25Cr1Mo pressure vessel steel, relying solely on a limited amount of input information, and provides a clear and visual presentation of the prediction results.

Machine Learning based Lung Cancer Diagnostic System using Optimized Feature Subset Selection

Lung is a vital organ that plays a major role in respiration. Without breathing, one may not survive in this world. Hence lung is an important organ that acts as filter to absorb oxygen and supply it to heart where pumping takes place through blood vessel in the circulatory system .The pumped blood takes oxygen and other nutrients to every other parts of the body. Hence one must take care of lung. There are various diseases associated with lungs. Lung Cancer is a deadly disease that spread across the countries all over the world. An early detection of lung cancer has been proved to improve the survival rate of human life. There are various resources are available to detect the lung cancer disease. They are low dose CT-scans, X-rays, blood-based screening, pathology slide reading, biopsy’s test, survey data(clinical dataset) etc. helps to predict the disease well in advance. Our proposed work uses two clinical datasets that has various features to detect how likely the persons get affected from the lung disease. Dataset1 includes features such as age, gender, smoking, yellow fingers, anxiety, peer-pressure, chronic disease, fatigue, allergy, wheezing, alcohol, coughing, shortness of breath, swallowing difficulty, and chest pain. Also, the work has experimented with another dataset2 that represents causes of lung cancer due to exposure of pesticide. Our proposed diagnostic system consider all these features in total and perform feature selection to extract optimal feature subsets using cuckoo search algorithm then perform classification using machine learning algorithms such as Linear Support Vector Machine, Logistic Regression and Random Forest algorithm. It is observed that with the cuckoo search algorithm, dataset 1 achieves an accuracy of 100%, precision of 100%, recall of 100%, and F1-score of 100% by LR Classifier. The Linear SVC classifier achieves an accuracy of 90%, a precision of 88%, a recall of 86%, and an F1-score of 87%.The Random forest Classifier achieves an accuracy of 91%, precision of 86%, recall of 93%, and F1-score of 90%. For dataset 2, both the LR classifier and Linear SVC classifier outperform with an accuracy of 100%, precision of 100%, recall of 100%, and F1-score of 100%. Whereas Random Forest provides accuracy of 97%, precision of 97%, recall of 96%, and F1-score of 97%.

Design of a Computational Intelligence System for Detection of Multiple Sclerosis with Visual Evoked Potentials

In this study, a new approach for modification of membership functions of a fuzzy inference system (FIS) is demonstrated, in order to serve as a pattern recognition tool for classification of patients diagnosed with multiple sclerosis (MS) from healthy controls (HC) using their visually evoked potential (VEP) recordings. The new approach utilizes Krill Herd (KH) optimization algorithm to modify parameters associated with membership functions of both inputs and outputs of an initial Sugeno-type FIS, while making sure that the error corresponding to training of the network is minimized.This novel pattern recognition system is applied for classification of VEP signals in 11 MS patients and 11 HC's. A feature extraction routine was performed on the VEP signals, and later substantial features were selected in an optimized feature subset selection scheme employing Ant Colony Optimization (ACO) and Simulated Annealing (SA) algorithms. This alone provided further information regarding clinical value of many previously unused VEP features as an aide for making the diagnosis. The newly designed computational intelligence system is shown to outperform popular classifiers (e.g., multilayer perceptron, support-vector machine, etc.) and was able to distinguish MS patients from HC's with an overall accuracy of 90%.

A multiscale approach for network intrusion detection based on variance–covariance subspace distance and EQL v2

As an important network defense approach, network intrusion detection is mainly used to identify anomaly traffic behavior. However, dominant network intrusion detection approaches are now struggling to identify the complex and variable means of attack, leading to high false alarm rate. Additionally, the feature redundancy and class imbalance problem in the intrusion detection dataset also constrain the performance of detection methods. This paper proposes a multiscale intrusion detection approach based on variance–covariance subspace distance and Equalization Loss v2 (EQL v2). Firstly, the variance–covariance subspace distance is used for feature selection on the preprocessed dataset to determine a set of representative feature subsets that can effectively approximate the original feature space. Secondly, the loss function, EQL v2, is adopted to balance the positive and negative gradients, addressing the class imbalance problem. Finally, a pyramid depthwise separable convolution model is proposed to capture the multiscale information of the traffic, and the convolutional layer in the depthwise convolution is replaced with self-supervised predictive convolutional attention block to compensate for the performance loss caused by the parameter reduction. Extensive experiments demonstrated that the proposed approach exhibits better performance on the three datasets of NSL-KDD, UNSW_NB15, and CIC-IDS-2017, with accuracy rates of 99.19%, 97.81%, and 99.83%, respectively, effectively improve the intrusion detection performance.

Fault identification of rolling bearing based on improved salp swarm algorithm

Due to the rapid development of industrial manufacturing technology, modern mechanical equipment involves complex operating conditions and structural characteristics of hardware systems. Therefore, the state of components directly affects the stable operation of mechanical parts. To ensure engineering reliability improvement and economic benefits, bearing diagnosis has always been a concern in the field of mechanical engineering. Therefore, this article studies an effective machine learning method to extract useful fault feature information from actual bearing vibration signals and identify bearing faults. Firstly, variational mode decomposition decomposes the source signal into several intrinsic mode functions according to the actual situation. The vibration signal of the bearing is decomposed and reconstructed. By iteratively solving the variational model, the optimal modulus function can be obtained, which can better describe the characteristics of the original signal. Then, the feature subset is efficiently searched using the wrapper method of feature selection and the improved binary salp swarm algorithm (IBSSA) to effectively reduce redundant feature vectors, thereby accurately extracting fault feature frequency signals. Finally, support vector machines are used to classify and identify fault types, and the advantages of support vector machines are verified through extensive experiments, improving the ability of global search potential solutions. The experimental findings demonstrate the superior fault recognition performance of the IBSSA algorithm, with a highest recognition accuracy of 97.5%. By comparing different recognition methods, it is concluded that this method can accurately identify bearing failure.

Analyzing Resampling Techniques for Addressing the Class Imbalance in NIDS using SVM with Random Forest Feature Selection

The purpose of Network Intrusion Detection Systems (NIDS) is to ensure and protect computer networks from harmful actions. A major concern in NIDS development is the class imbalance problem, i.e., normal traffic dominates the communication data plane more than intrusion attempts. Such a state of affairs can pose certain hazards to the effectiveness of detection algorithms, including those useful for detecting less frequent but still highly dangerous intrusions. This paper aims to utilize resampling techniques to tackle this problem of class imbalance in NIDS using a Support Vector Machine (SVM) classifier alongside utilizing features selected by Random Forest to improve the feature subset selection process. The analysis highlights the combativeness of each sampling method, offering insights into their efficiency and practicality for real-world applications. Four resampling techniques are analyzed. Such techniques include Synthetic Minority Over-sampling Technique (SMOTE), Random Under-sampling (RUS), Random Over-sampling (ROS) and SMOTE with two different combinations i.e., RUS SMOTE and RUS ROS. Feature selection was done using Random Forest, which was improved by Bayesian methods to create subsets of features with feature rankings determined by Cumulative Feature Importance Score (CFIS). The CIDDS-2017 dataset is used for the performance evaluation, and the metrics used include accuracy, precision, recall, F-measure and CPU time. The algorithm that performs best overall in the CFIS feature subsets is SMOTE, and the features that give the best result are selected at the 90% level with 25 features. This subset accomplishes a relative accuracy enhancement of 0.08% than the other approaches. The RUS+ROS technique is also fine but somehow slower than SMOTE. On the other hand, RUS+SMOTE shows relatively poor results although it consumes less time in terms of computational time compared to other methods, giving about 50% of the performance shown by the other methods. This paper's novelty is adapting the RUS method as a standalone test for screening new and potentially contaminated datasets. The standalone RUS method is more efficient in terms of computations; the algorithm returned the best result of 98.13% accuracy at 85% at the CFIS level of 34 features with a computation time of 137.812 s. It is also noted that SMOTE is considered to be proficient among all resampling techniques used for handling the problem of class imbalance in NIDS, vice 90% CFIS feature subset. Future research directions could include using these techniques in different data sets and other machine learning and deep learning methods together with ROC curve analysis to provide useful pointers to NIDS designers on how to select the right data mining tools and strategies for their projects.

Impact Analysis of Filter and Wrapper-Based Feature Selection Techniques for Webpages Phishing Attacks Identification

Phishing, which involves fraudulently gaining access to sensitive assets of unsuspecting individuals through deceptive and malicious emails, is a major global threat to internet users. The proliferation of phishing sites and their operations is occurring at an alarming rate, raising significant concerns about how to forestall them. Numerous research efforts are underway to detect phishing attempts before they can compromise important information and cause damage. Compared to conventional methods, machine learning has proven highly effective at detecting phishing attacks by analyzing different features. This study analyzed the behaviors of seven classification data mining algorithms on optimal subset features selection using Wrapper (Boruta) and Filter-based (Mutual-Information). Real-life phishing webpage datasets were used for the analysis. Ensemble classifiers such as Voting, Gradient Boosting, and Random Forest were used in the experiments. Two experiments were conducted. In the first experiment, K-Nearest Neighbor (K-NN) yielded the highest accuracy among single classifiers, with a score of 94.1%, while Random Forest (RF) ensemble achieved 96.7%. In the second experiment, using another baseline feature set, RF performed excellently under the Boruta method with an accuracy of 97.25%, while K-NN retained the highest accuracy of 95.20% among single classifiers. This study provides empirical evidence that feature selection techniques have a great impact on the performance of ML models, for both single and ensemble classifiers, in the detection of phishing attacks.

Wind power forecasting with metaheuristic-based feature selection and neural networks

Accurate forecasting of wind power generation is crucial for ensuring a stable and efficient energy supply, reducing the environmental impact of energy production, and promoting a cleaner and more sustainable energy supply. Inaccurate forecasts can lead to a mismatch between wind power generation and energy demand, resulting in wasted energy, increased emissions, and reduced grid stability. Therefore, improving the accuracy of wind power generation forecasting is essential for optimizing energy storage and grid management, reducing the reliance on fossil fuels, decreasing greenhouse gas emissions, and promoting a more sustainable energy future. This study proposes an innovative approach to enhance wind power generation forecasting accuracy by leveraging the strengths of metaheuristic algorithms for feature selection and integrating them with Neural Networks (NN). Specifically, five distinct algorithms - Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Teaching-Learning-Based Optimization (TLBO), and Evolutionary Mating Algorithm (EMA) - are integrated with NN model to identify optimal feature subsets from a comprehensive dataset of 18 diverse features. The results show that the GA consistently outperforms other algorithms in selecting the most influential features, leading to improved precision in wind power predictions. Notably, the GA achieves the best root mean square error (RMSE) of 37.1837 and the best mean absolute error (MAE) of 18.6313, outperforming the other algorithms and demonstrating the importance of feature selection in improving the accuracy of wind power forecasting. This innovative framework advances the field of renewable energy forecasting and provides valuable insights into optimizing feature sets for improved predictions across diverse domains.

A leader-adaptive particle swarm optimization with dimensionality reduction strategy for feature selection

Feature selection (FS) is a key data pre-processing method in machine learning tasks. It aims to obtain better classification accuracy of an algorithm with the smallest size of selected feature subset. Particle Swarm Optimization has been widely applied in FS tasks. However, when solving FS task on high-dimensional datasets, most of the PSO-based FS methods are easy to get premature convergence and fall into the local optimum. To address this issue, a leader-adaptive particle swarm optimization with dimensionality reduction strategy (LAPSO-DR) is proposed in this paper. Firstly, a hybrid initialization strategy based on feature importance is formulated. The population is divided into two parts, which have different initialization ranges. It can not only improve the diversity of the population but also eliminate some redundant features. Secondly, the leader-adaptive strategy is proposed to improve the exploitation ability of the population, in which each particle can have a different learning exemplar selected from the elite sub-swarm. Finally, the dimensionality reduction strategy based on Markov blanket is introduced to reduce the size of the optimal feature subset. LAPSO-DR is compared with 8 representative FS methods on 18 benchmark datasets. The experimental results show that LAPSO-DR can obtain smaller sizes of feature subsets with highest classification accuracies on 17 out of 18 datasets. The classification accuracies of LAPSO-DR are over 90% on 14 datasets and the feature elimination rates are higher than 60% on 18 datasets.

Harnessing probabilistic neural network with triple tree seed algorithm-based smart enterprise quantitative risk management framework

Enterprise risk management (ERM) frameworks convey vital principles that help create a consistent risk management culture, irrespective of employee turnover or industry standards. Enterprise Management System (EMS) are becoming a popular research area for assuring a company’s long-term success. Statistical pattern recognition, federated learning, database administration, visualization technology, and social networking are all used in this field, which includes artificial intelligence (AI), data science, and statistics. Risk assessment in EMS is critical for enterprise decision-making to be effective. Recent advancements in AI, machine learning (ML), and deep learning (DL) concepts have enabled the development of effective risk assessment models for EMS. This special issue seeks groundbreaking research articles that showcase the application of applied probability and statistics to interdisciplinary studies. This study offers Improved Metaheuristics with a Deep Learning Enabled Risk Assessment Model (IMDLRA-SES) for Smart Enterprise Systems. Using feature selection (FS) and DL models, the provided IMDLRA-SES technique estimates business risks. Preprocessing is used in the IMDLRA-SES technique to change the original financial data into a usable format. In addition, an FS technique based on oppositional lion swarm optimization (OLSO) is utilized to find the best subset of features. In addition, the presence or absence of financial hazards in firms is classified using the triple tree seed algorithm (TTSA) with a probabilistic neural network (PNN) model. The TTSA is used as a hyperparameter optimizer to improve the efficiency of the PNN-based categorization. An extensive set of experimental evaluations is performed on German and Australian credit datasets to illustrate the IMDLRA-SES model’s improved performance. The performance validation of the IMDLRA-SES model portrayed a superior accuracy value of 95.70% and 96.09% over existing techniques.

Noise-resistant fuzzy multineighbourhood rough set-based feature selection with label enhancement and its application for multilabel classification

Noise pollution in process of feature selection greatly reduces the classification efficacy of multilabel data, and the estimation of label descriptions is insufficient because of the lack of label enhancement for label distribution learning. To overcome the limitations, this work presents a noise-resistant fuzzy multineighbourhood rough set-based feature selection methodology with label enhancement and its application for multilabel classification. First, under the fuzzy T-equivalence relation, to construct new adaptive fuzzy neighbourhood class, the multineighbourhood radius set on feature space is integrated with fuzzy neighbourhood radius via sample interval on label space; then, the adaptive fuzzy multineighbourhood granules are obtained. Second, by integrating the parameterized fuzzy decision of labels and adaptive fuzzy multineighbourhood granules, noise-resistant lower and upper approximations via fuzzy multineighbourhood are constructed. A noise-resistant multilabel fuzzy multineighbourhood rough set model and its noise-resistant approximate accuracy can be proposed. Third, the description degree of label is computed to design label proportion after label enhancement. Certain fuzzy multineighbourhood entropy measures are developed to obtain label enhancement-based mutual information. When the algebraic and information perspectives are fused, label enhancement-based mutual information with fuzzy multineighbourhood via approximate accuracy is presented to evaluate the final association relationship between the features and label sets. Finally, a multilabel feature selection strategy via label enhancement will be constructed to obtain the best feature subset. The experimental results applied to 14 multilabel datasets indicate that this algorithm is significant.

Extraction of Maize Distribution Information Based on Critical Fertility Periods and Active–Passive Remote Sensing

This study proposes a new method for integrating active and passive remote sensing data during critical reproductive periods in order to extract maize areas early and to address the problem of low accuracy in the classification of maize-growing areas affected by climate change. Focusing on Jiaozuo City, this study utilized active–passive remote sensing images to determine the optimal time for maize identification. The relative importance of features was assessed using a feature selection method combined with a machine learning algorithm, the impact of both single-source and multi-source features on accuracy was analyzed to generate the optimal feature subset, and the classification accuracies of different machine learning classification methods for maize at the tasseling stage were compared. Ultimately, this study identified the most effective remote sensing features and methods for maize detection during the optimal fertility period. The experimental results show that the feature set optimized for the tasseling stage significantly enhanced maize recognition accuracy. Specifically, the random forest (RF) method, when applied to the multi-source data fusion feature set, yielded the highest accuracy, improving classification accuracy by 24.6% and 4.86% over single-source features, and achieving an overall accuracy of 93.38% with a Kappa coefficient of 0.91. Data on the study area’s maize area were also extracted for the years 2018–2022, with accuracy values of 93.83%, 98.77%, 97%, and 98.05%, respectively.

Selecting the Optimal Classifier for Wrapper-Based Feature Selection Methods

Dimensionality reduction, the elimination of irrelevant features, and the selection of an optimal subset of features are critical components in the construction of an efficacious machine learning model. Among the various feature selection methodologies, wrapper-based methods yield superior results due to their evaluation of candidate subsets. Numerous meta-heuristic methods have been employed in this feature selection process. A significant and complex issue in feature selection utilizing these methods is the selection of the most suitable classifier. In this study, we propose a novel method for selecting the optimal classifier during the feature selection process. We employ ten distinct classifiers for two swarm intelligence methods, namely Bat and Gray Wolf, and compute their results on four cancer datasets: Leukemia, SRBCT, Prostate, and Colon. Our findings demonstrate that the proposed method identifies the optimal classifiers for all four datasets. Consequently, when employing wrapper-based methods to select features for each dataset, the optimal classifier is identified.

Reflective Distributed Denial of Service Detection: A Novel Model Utilizing Binary Particle Swarm Optimization-Simulated Annealing for Feature Selection and Gray Wolf Optimization-Optimized LightGBM Algorithm.

The fast growth of the Internet has made network security problems more noticeable, so intrusion detection systems (IDSs) have become a crucial tool for maintaining network security. IDSs guarantee the normal operation of the network by tracking network traffic and spotting possible assaults, thereby safeguarding data security. However, traditional intrusion detection methods encounter several issues such as low detection efficiency and prolonged detection time when dealing with massive and high-dimensional data. Therefore, feature selection (FS) is particularly important in IDSs. By selecting the most representative features, it can not only improve the detection accuracy but also significantly reduce the computational complexity and attack detection time. This work proposes a new FS approach, BPSO-SA, that is based on the Binary Particle Swarm Optimization (BPSO) and Simulated Annealing (SA) algorithms. It combines these with the Gray Wolf Optimization (GWO) algorithm to optimize the LightGBM model, thereby building a new type of reflective Distributed Denial of Service (DDoS) attack detection model. The BPSO-SA algorithm enhances the global search capability of Particle Swarm Optimization (PSO) using the SA mechanism and effectively screens out the optimal feature subset; the GWO algorithm optimizes the hyperparameters of LightGBM by simulating the group hunting behavior of gray wolves to enhance the detection performance of the model. While showing great resilience and generalizing power, the experimental results show that the proposed reflective DDoS attack detection model surpasses conventional methods in terms of detection accuracy, precision, recall, F1-score, and prediction time.

Multi-population differential evolution approach for feature selection with mutual information ranking

Feature selection is a crucial aspect of data preprocessing because of the significant effect of redundant features on classification performance and the extensive computational resources required. Evolutionary algorithm-based feature-selection methods have shown remarkable results in determining the optimal feature subset. To further enhance classification performance, this paper proposes a novel multi-population differential evolution approach for feature selection with mutual information ranking (MI-MPODE). Firstly, population preprocessing guided by mutual information is employed to reduce the dimensionality of the initial feature space. Then, the feature subset obtained from mutual information serves as the initial population for MI-MPODE. MI-MPODE incorporates a novel multi-population information-sharing mechanism, with common individuals from three layers contributing to inter-subpopulation information sharing. Additionally, an individual enhancement strategy is proposed to handle the variations of individuals in the population, and a Lens imaging opposition-based learning method is adopted to improve the algorithm’s optimization capability. MI-MPODE is compared with several state-of-the-art evolutionary algorithm-based feature selection methods through experimental comparisons. The results show that MI-MPODE outperforms all comparison algorithms on more than half of the datasets, with a significant reduction in the number of features used, demonstrating a significant advantage over competitors.

Distributed enhanced multi-objective evolutionary algorithm based on decomposition for cluster analysis in wireless sensor network

Conventional clustering algorithms do not recognize patterns and structures with contradicting objectives in large, distributed datasets. Distributed clustering leverages rapid processing capabilities to allow multiple nodes to work together. This paper proposes a Distributed clustering based on Multiobjective Evolutionary Algorithm by Decomposition (D-MOEA/d) to solve various multiobjective optimization problems in wireless sensor networks (WSNs). In MOEA/d, a multiobjective optimization problem decomposes into several scalar optimization subproblems, each focusing on a distinct objective. Each subproblem is expressed as a clustering problem that uses local data to perform distributed clustering. The proposed method has been extended to achieve improved accuracy in less time by using a smaller feature subset with less redundancy. The Distributed Enhanced MOEA/d (DE-MOEA/d) avoids local optima by achieving diversity in the population using fuzzy-based nearest neighbor selection, sparse population initialization, and evolved mutation operator. This integration improves the accuracy of the clustering process at WSN nodes, ensuring the attainment of well-balanced solutions across multiple optimization criteria in the distributed environment. Average Euclidean and total symmetrical deviations are the two cost functions used to minimize while clustering on the MOEA/d framework. Six real-life WSN datasets are used to assess the performance of the proposed technique: (1) the Delhi air pollution dataset, (2) the Canada weather station dataset, (3) the Thames River water quality dataset, (4) the Narragansett Bay water quality dataset, (5) the Cook Agricultural land dataset and 6) Gordon Soil dataset. The simulation results of both proposed algorithms are compared with Multiobjective distributed particle swarm optimization (DMOPSO) and Distributed K-means (DK-Means). The proposed algorithm DE-MOEA/d performs better in terms of the Silhouette index (SI), Dunn index (DI), Davies–Bouldin index (DBI), and Kruskal–Wallis (KW) statistical test.

A Machine Learning-Based Wrapper Method for Feature Selection

This paper presents a two-stage feature selection scheme using machine learning techniques. In the first stage a wrapper method is adopted to select various combinations of subsets of features from the original dataset. The performance of the model is evaluated by three classifiers: K-Nearest Neighbor (KNN), Support Vector Machines (SVM), and Random Forest (RF). In the second and final stage, a sequential backward feature selection Method is applied. The proposed method is demonstrated on eighteen datasets and the average classification accuracy of eighteen datasets achieved is 89.81%, 87.55%, and 89.82% using the KNN, SVM, and RF classifiers, respectively with a maximum reduced size of the subset being ten only. Comparing the proposed method to eight other feature selection methods, the former achieves better classification accuracy in terms of selecting the most useful but a smaller number of features.

Intelligent cardiovascular disease diagnosis using deep learning enhanced neural network with ant colony optimization

To identify patterns in big medical datasets and use Deep Learning and Machine Learning (ML) to reliably diagnose Cardio Vascular Disease (CVD), researchers are currently delving deeply into these fields. Training on large datasets and producing highly accurate validation results is exceedingly difficult. Furthermore, early and precise diagnosis is necessary due to the increased global prevalence of cardiovascular disease (CVD). However, the increasing complexity of healthcare datasets makes it challenging to detect feature connections and produce precise predictions. To address these issues, the Intelligent Cardiovascular Disease Diagnosis based on Ant Colony Optimisation with Enhanced Deep Learning (ICVD-ACOEDL) model was developed. This model employs feature selection (FS) and hyperparameter optimization to diagnose CVD. Applying a min–max scaler, medical data is first consistently prepared. The key feature that sets ICVD-ACOEDL apart is the use of Ant Colony Optimisation (ACO) to select an optimal feature subset, which in turn helps to upgrade the performance of the ensuring deep learning enhanced neural network (DLENN) classifier. The model reforms the hyperparameters of DLENN for CVD classification using Bayesian optimization. Comprehensive evaluations on benchmark medical datasets show that ICVD-ACOEDL exceeds existing techniques, indicating that it could have a significant impact on CVD diagnosis. The model furnishes a workable way to increase CVD classification efficiency and accuracy in real-world medical situations by incorporating ACO for feature selection, min–max scaling for data pre-processing, and Bayesian optimization for hyperparameter tweaking.

Predicting costs of local public bus transport services through machine learning methods

The present study developed several machine learning-based cost models to predict an efficient total economic cost per vehicle revenue-mile of urban public bus transport. The models were trained on a built-in dataset from 269 transit agencies providing urban services in the United States from 2015 to 2019. A feature selection strategy was implemented, finding that, for each proposed model, a subset of features determined a large impact on unit cost. These “core” features included commercial speed, average salary expenses per employee, vehicle productivity, and fleet ownership cost per vehicle. Machine learning techniques outperformed the linear regression method in terms of predictive power and robustness (understood as the dispersion of predictive power measures over the training sets). Based on SHAP values, the sensitivity analyses showed that the proposed models could be used to predict the impact of changes in some critical features on corresponding unit costs. The results may be useful for: (i) introducing regulatory constraints to the allocation of national public resources to local public bus transport services, aimed at minimizing the resources needed to provide a given level of service; (ii) defining the maximum economic compensation required by firms involved in competitive tendering for the allotment of service concessions, or firms with monopoly rights (by political choice and/or local public ownership); and (iii) improving service contract management and design by identifying key cost drivers of transit services.