Search

• 252 chemicals were identified by SNTS in groundwater from four regions with diverse contamination histories. • A novel and robust systematic machine learning-based workflow for predicting chemical indicators was proposed. • The proposed workflow showed good predictive ability (Q2) of 0.897. • 51 chemical indicators for tracking groundwater contamination sources were suggested. In this study, the strong analytical power of gas chromatography coupled to a high resolution mass spectrometry (GC-HRMS) in suspect and non-target screening (SNTS) of organic micropollutants was combined with machine learning tools for proposing a novel and robust systematic environmental forensics workflow, focusing on groundwater contamination. Groundwater samples were collected from four different regions with diverse contamination histories (namely oil [OC], agricultural [AGR], industrial [IND], and landfill [LF]), and a total of 252 organic micropollutants were identified, including pharmaceuticals, personal care products, pesticides, polycyclic aromatic hydrocarbons, plasticizers, phenols, organophosphate flame retardants, transformation products, and others, with detection frequencies ranging from 3 % to 100 %. Amongst the SNTS identified compounds, a total of 51 chemical indicators (i.e., OC: 13, LF: 12, AGR: 19, IND: 7) which included level 1 and 2 SNTS identified chemicals were pinpointed across all sampling regions by integrating a bootstrapped feature selection method involving the bootfs algorithm and a partial least squares discriminant analysis (PLS-DA) model to determine potential prevalent contamination sources. The proposed workflow showed good predictive ability (Q2) of 0.897, and the suggested contamination sources were gasoline, diesel, and/or other light petroleum products for the OC region, anthropogenic activities for the LF region, agricultural and human activities for the AGR region, and industrial/human activities for the IND region. These results suggest that the proposed workflow can select a subset of the most diagnostic features in the chemical space that can best distinguish a specific contamination source class. [Display omitted] [ABSTRACT FROM AUTHOR]

[Display omitted] • A real-time grading method of roasted tobacco quality based on near infrared spectroscopy. • A key indicators selection method based on information gain and Fisher criterion was proposed. • A chemical indicator grading table was designed for reference. • Chemical indicator grading based on near infrared spectroscopy is a convenient, rapid and promising grading method. Traditional tobacco quality grading methods have limitations such as high human resource consumption and poor consistency, resulting in the grading accuracy being affected. Near infrared spectroscopy (NIRS) technology, as a rapid and non-destructive analytical method, has been widely used for online inspection. This study aims to accomplish rapid, accurate and reliable real-time grading of tobacco quality by employing online near-infrared spectroscopy to detect key chemical indicators. A key indicators selection method based on information gain and Fisher criterion (IFRI) was proposed in this paper by associating tobacco chemical indicators with traditional quality grades. The key chemical indicators were selected from many indicators by two classical feature selection functions, and a chemical indicator grading table was designed based on a large number of statistical data on tobacco chemical indicators, and the table was applied to grade the tobacco quality of real data from different years. The results show that the IFRI algorithm is an effective method for selecting key indicators, and the selected reducing sugars-to-total nitrogen ratio and nicotine are the key indicators for tobacco quality grading. Moreover, we demonstrated that the designed grading table is reasonable and feasible. Compared with traditional grading, chemical indicator grading based on near infrared spectroscopy can not only be realized quickly by using an online near infrared instrument, but also the tobacco of the same grade is less discrete, better consistency and more representative after grading, and it is applicable to tobacco samples of different years, which is a convenient, rapid and promising grading method that can provide a reference for tobacco quality grading. Furthermore, the formulation design by utilizing different grades after grading can greatly improve the utilization rate of tobacco leaves. Notably, the method can also be applied to other fields, such as quality control of agricultural products, monitoring of food processing processes, etc. [ABSTRACT FROM AUTHOR]

Text processing tasks commonly grapple with the challenge of high dimensionality. One of the most effective solutions to this challenge is to preprocess text data through feature selection methods. Feature selection can select the most advantageous features for subsequent operations (e.g., classification) from the native feature space of the text. This process effectively trims the feature space's dimensionality, enhancing subsequent operations' efficiency and accuracy. This paper proposes a straightforward and efficient filter feature selection method based on document-term matrix unitization (DTMU) for text processing. Diverging from previous filter feature selection methods that concentrate on scoring criteria definition, our method achieves more optimal feature selection by unitizing each column of the document-term matrix. This approach mitigates feature-to-feature influence and reinforces the role of the weighting proportion within the features. Subsequently, our scoring criterion subtracts the sum of weights for negative samples from positive samples and takes the absolute value. We conduct numerical experiments to compare DTMU with four advanced filter feature selection methods: max–min ratio metric, proportional rough feature selector, least loss, and relative discrimination criterion, along with two classical filter feature selection methods: Chi-square and information gain. The experiments are performed on four ten-thousand-dimensional feature space datasets: b o o k , d v d , m u s i c , m o v i e and two thousand-dimensional feature space datasets: i m d b , a m a z o n _ c e l l s , sourced from Amazon product reviews and movie reviews. Experimental findings demonstrate that DTMU selects more advantageous features for subsequent operations and achieves a higher dimensionality reduction rate than those of the other six methods used for comparison. Moreover, DTMU exhibits robust generalization capabilities across various classifiers and dimensional datasets. Notably, the average CPU time for a single run of DTMU is measured at 1.455 s. • This paper offers DTMU, a filter feature selection method enhancing feature quality via unitization for improved properties. • DTMU is notably user-friendly, involving only two straightforward steps. • This paper substantiates, through numerical experiments, that DTMU stands as an advanced and effective method. [ABSTRACT FROM AUTHOR]

Ammonia emerges as a promising substitute for traditional fuels, offering a potential reduction in fossil fuel consumption and the associated emissions. Given its weak reactivity, an effective strategy to harness the potential of ammonia involves cofiring it with methane, to establish a self-sustaining combustion process. The understanding of heat release rate (HRR) in the cofiring process of ammonia and methane is crucial for burner design. This study introduces novel HRR indicators through a machine learning-based approach, focusing on species significantly contributing to HRR. Kinetic analysis is carried out utilizing a one-dimensional freely propagating flame model, applying a mechanism including 59 species and 356 reactions. Domain knowledge-based feature selection narrows down the search space, enhancing computational efficiency during HRR indicator identification. A random forest model is then employed to identify radical/radical combinations and their respective reaction orders, representing HRR optimally based on mean decrease impurity. The proposed HRR markers are [CH 4 ]0·76[OH]1.08, [HCO]0·65[NO]0.24, [CH 3 ]0.65[O]0.63, [NH 2 ][O]0.59, and [NH 3 ]0·93[OH]0.96. The root mean square error for each marker was extracted and compared with literature data, demonstrating higher reliability of the proposed indicators over those previously suggested. Additionally, the paper concludes with a discussion of the feasibility of measuring these markers from an experimental perspective. [Display omitted] • Thorough kinetic analysis of focusing on key HRR contributors. • Pioneering ML for crucial HRR indicator identification in ammonia-methane cofiring. • Domain-based feature selection streamlines HRR marker identification for efficiency. • Proposed 5 HRR markers that are superior in accuracy compared to existing markers. [ABSTRACT FROM AUTHOR]

Quantitative structure-activity relationship modeling techniques are widely employed in diverse areas of chemistry, including environmental risk assessment of compounds and virtual screening of drugs. The modeling process entails optimizing the hyper parameters of the model and selecting appropriate molecular descriptors. It is a typical optimization problem with high-dimensional, nonlinear, continuous and discrete variables coexisting. To address this challenge, this paper proposes an enhanced snake optimizer with multiple strategies. First, new food emergence and temperature change mechanisms are introduced to balance the exploration and exploitation. Second, a death and regeneration mechanism is employed to enhance the algorithm's ability to escape from local optima. Third, new formulas for food searching, fighting, mating and eating are designed to simplify the complexity of the algorithm and improve its search efficiency and accuracy. Fourth, the performance of the proposed algorithm is evaluated using the CEC2017 benchmark functions, eight engineering cases with continuous variables, and six feature selection cases with discrete variables. Experimental results demonstrate that the algorithm significantly outperforms comparison algorithms. Finally, the algorithm was applied to quantitative structure-activity relationship modeling for environmental toxicity prediction. Compared with other algorithms, the algorithm can better configure hyper-parameters and select fewer and more effective features for environmental toxicity prediction model. It will be an effective tool to improve the performance of quantitative structure-activity relationship models. • New food emergence and temperature change mechanisms are presented to better balance exploration and exploitation. • Death and regeneration mechanism is adopted to avoid local optima. • The performance of the proposed algorithm is validated in CEC2017, engineering design and feature selection problems. • A joint optimization approach is proposed for quantitative structure-activity relationship modeling. • An environmental toxicity prediction model is obtained by jointly optimizing hyper-parameters and molecular descriptors. [ABSTRACT FROM AUTHOR]

• Feature selection is studied by a role-oriented binary grey wolf optimizer. • Foraging-following is combined with top grey wolves to improve convergence. • Lévy flight is integrated into ordinary grey wolves to improve population diversity. • The performance of feature selection is enhanced by more than 5%. • The performance of Improved algorithm is demonstrated by 29 benchmark functions. Feature selection can effectively define the feature subset, remove redundant, irrelevant, and noisy features. In order to adapt the feature selection problem, this paper adopts role-oriented modeling paradigm to make up for the defects of binary grey wolf optimizer such as premature, declining diversity, and insufficient convergence, then comes up with novel V-shaped linear transfer functions. Ultimately, a role-oriented binary grey wolf optimizer is proposed. The top grey wolves combine the foraging-following to enhance convergence, while the ordinary grey wolves integrate Lévy flight to avoid premature and improve diversity. The outstanding ability of role-oriented binary grey wolf optimizer in balance of exploitation and exploration is verified by benchmarks and the effectiveness in solving feature selection is demonstrated through feature selection tasks. The results of benchmark and feature selection task have comprehensively demonstrated the competitiveness of role-oriented modeling paradigm in improving metaheuristic algorithms. [ABSTRACT FROM AUTHOR]

The dehydrogenation enthalpy, a crucial thermodynamic parameter, determines the difficulty of hydrogen desorption in V–Ti–Cr–Fe alloy, but it is unaffordable to predict and modify the dehydrogenation enthalpy and investigate the synergistic effects of structural and chemical parameters relying on conventional experimental methods. In this paper, an extreme gradient boosting (Xgboost) model with feature selection is developed, which can obtain a relative error under 15% in prediction on most of the data. Moreover, the genetic algorithm is utilized for optimizing alloy composition having suitable dehydrogenation enthalpy. The accuracy of prediction and optimization is demonstrated by the subsequent experimental validation, where the error between calculation and experiment is within 4.5%. Density function theory (DFT) is used to analyze the key features provided by machine learning, with results suggesting that the volumes, valence electrons, and bulk module factors have a significant impact. This research supplies an efficient way of using machine learning to predict and optimize the dehydrogenation enthalpy. In addition, DFT calculation also validates the feature importance outputted by machine learning and reveals the principle of feature effects at the microscopic aspect. • ML models predict precisely the dehydrogenation enthalpy of V–Ti–Cr–Fe alloy. • Properties calculation optimized by GA have good agreement with experiments. • Explanation of volume, electron and module factors affecting enthalpy using DFT. [ABSTRACT FROM AUTHOR]

This paper analyzes diverse features extracted from spoken language to select the most discriminative ones for dementia detection. We present a two-step feature selection (FS) approach: Step 1 utilizes filter methods to pre-screen features, and Step 2 uses a novel feature ranking (FR) method, referred to as dual dropout ranking (DDR), to rank the screened features and select spoken language biomarkers. The proposed DDR is based on a dual-net architecture that separates FS and dementia detection into two neural networks (namely, the operator and selector). The operator is trained on features obtained from the selector to reduce classification or regression loss. The selector is optimized to predict the operator's performance based on automatic regularization. Results show that the approach significantly reduces feature dimensionality while identifying small feature subsets that achieve comparable or superior performance compared with the full, default feature set. The Python codes are available at https://github.com/kexquan/dual-dropout-ranking. • Dual-net architecture enables automatic regularization. • Ensemble from multiple cross-validations stabilizes detection performance. • Two-step feature selection significantly reduces feature dimensions. • Identified spoken language biomarkers boost detection performance. • Codes are available at https://github.com/kexquan/dual-dropout-ranking. [ABSTRACT FROM AUTHOR]

[Display omitted] Three-dimensional data have become increasingly present in earth observation over the last decades. However, many 3D surveys are still underexploited due to the lack of accessible and explainable automatic classification methods, for example, new topo-bathymetric lidar data. In this work, we introduce explainable machine learning for 3D data classification using Multiple Attributes, Scales, and Clouds under 3DMASC, a new workflow. This workflow introduces multi-cloud classification through dual-cloud features, encrypting local spectral and geometrical ratios and differences. 3DMASC uses classical multi-scale descriptors adapted to all types of 3D point clouds and new ones based on their spatial variations. In this paper, we present the performances of 3DMASC for multi-class classification of topo-bathymetric lidar data in coastal and fluvial environments. We show how multivariate and embedded feature selection allows the building of optimized predictor sets of reduced complexity, and we identify features particularly relevant for coastal and riverine scene descriptions. Our results show the importance of dual-cloud features, lidar return-based attributes averaged over specific scales, and of statistics of dimensionality-based and spectral features. Additionally, they indicate that small to medium spherical neighbourhood diameters (<7 m) are sufficient to build effective classifiers, namely when combined with distance-to-ground or distance-to-water-surface features. Without using optional RGB information, and with a maximum of 37 descriptors, we obtain classification accuracies between 91 % for complex multi-class tasks and 98 % for lower-level processing using models trained on less than 2000 samples per class. Comparisons with classical point cloud classification methods show that 3DMASC features have a significantly improved descriptive power. Our contributions are made available through a plugin in the CloudCompare software, allowing non-specialist users to create classifiers for any type of 3D data characterized by 1 or 2 point clouds (airborne or terrestrial lidar, structure from motion), and two labelled topo-bathymetric lidar datasets, available on https://opentopography.org/. [ABSTRACT FROM AUTHOR]

Affected by a large number of radio frequency interference signals, it has become an important task for astronomical data processing to quickly and accurately identify single pulse signals from massive observation data. Designing and extracting effective data features is the key issue for efficient identification of single pulse signals using machine learning. This paper proposes an ensemble feature selection method for single pulse signal classification. The method first mixed three types of features, including the parametric features, statistical features, and abstract features of single pulse signals, and then used five individual feature selection methods to select the corresponding optimal feature set, respectively. At last, the features selected by the five individual methods are mixed, and the greedy strategy was used to select the optimal ensemble feature set. The experimental results show that the ensemble feature set can improve F1-score by a value of 1.8% at most, and can obtain higher accuracy than the features selected by individual methods. Under the background of high-speed and large-scale sky survey, the ensemble feature selection method plays an important role in reducing the number of features, improving classification performance, and speeding up data processing. [ABSTRACT FROM AUTHOR]

• Introducing a novel density measurement utilizing shared nearest neighbors, enhancing the assessment of data point density. • Developing an advanced K-means enhancement technique to dynamically determine cluster quantity and initial cluster center. • Integration of density-based and partition-based clustering methodologies, refining the K-means method's performance. • Achievement of peak performance in clustering outcomes via the proposed K-means modification. • Synergizing with various feature selection strategies for optimal clustering results proves its superior adaptability. User clustering is crucial for tapping the flexibility of the load side and realizing dynamic management of power loads in new power system. K-means method is widely used in clustering analysis due to its simplicity, high efficiency, and scalability, but it needs to specify the number of clusters in advance, and is sensitive to the initial clustering centers. The current initialization method does not take into account the neighborhood distribution of the data points, and the direct use of data that has undergone dimensionality reduction processing leads to inaccurate selection of the initial clustering centers. To address the above problems, a new K-means improvement method that takes into account the initialization problem and the adaptive determination of the number of clusters: K-means clustering method based on nearest-neighbor density matrix is proposed in this paper. The method improves the efficiency of nearest neighbor search by building a K-D tree, and enhances the performance of unsupervised classification by utilizing the adaptive selection strategy of the number of clusters and the initial clustering centers selection algorithm. The proposed method is applied to real datasets, and its effectiveness is assessed by calculating three clustering evaluation metrics of the clustering results in comparison with several existing initialization and clustering methods. The experimental results show that the method proposed in this paper has higher stability and better clustering performance than existing clustering methods. [ABSTRACT FROM AUTHOR]

• This paper proposes a novel unsupervised feature selection called CPSLR. • CPSLR uses a specific formula to obtain the central point matrix. Construct a link graph through the central matrix and the Laplacian matrix to retain the similarity between the data. • The link graph and the data graph form a dual graph structure, which can not only preserve more complete data information but also holds on to the manifold structure of the data. • Feature selection is conducted in the latent representation space, and interconnection information among data is mined by using latent representation learning to preserve the connections among data itself. • CPSLR applies l 2,1/2-norm constraint on the feature transformation matrix to select robust and low-redundancy features. Before conducting unsupervised feature selection, it is usually assumed that these data are independent of each other. On the contrary, real data will influence each other. Therefore, traditional feature selection methods may lose information related to each other between data. This can lead to inaccurately generated pseudo-label information and may result in poor feature selection results. To find solutions to this issue, this paper proposes robust feature selection via central point link information and sparse latent representation (CPSLR). Firstly, structure a link graph by calculating the center matrix to store the distance information from the sample to the center point. If two samples have similar distances to the center point, it can be determined that they belong to the same class. Therefore, the similarity between samples is preserved, and more accurate pseudo-label information is obtained. Secondly, CPSLR uses data graph and link graph to form a dual graph structure. It can not only retain the link information between samples but also retain the manifold structures of the samples. Then, CPSLR saves the interconnection contents between samples by sparse latent representation. That is, the constraint l 2,1 -norm is exerted on the expression of latent representation, and sparse non-redundant interconnection information is preserved. And by combining central point link information with sparse latent representation makes the interconnections between data reserved more comprehensive. That is to say, the pseudo-labels obtained are more like the real labels of the classes. Finally, CPSLR constrains the feature transformation matrix by l 2,1/2 -norm constraint so as to select robust and sparse features. CPSLR uses l 2,1/2 -norm constraint to assure that the feature transformation matrix is sparse, selecting more discriminative features, thereby obtaining the feature selection that can improve its efficiency. The experiments demonstrate that the clustering result of CPSLR outperform six classical or latest compared algorithms on eight datasets. [ABSTRACT FROM AUTHOR]

The existing feature selection algorithms often utilize local structure of data, but do not fully mine internal structure and ignore potential correlation information between samples. To address the problems and fully utilize manifold information of data, this paper proposes non-convex feature selection based on feature correlation representation and dual manifold optimization (FDNFS). Firstly, FDNFS constructs feature graph of original data, which can obtain feature correlation representation to represent the interconnection information. Based on the obtained interconnection information, FDNFS unifies feature correlation representation learning and feature selection through feature transformation matrix, so that the interconnection information between data guides feature selection. Secondly, to make multivariate frameworks guide feature selection, FDNFS introduces self-representation on the improved sparse regression model. Using self-representation can make basis matrix and reconstruction coefficient matrix reconstruct original data more accurately. Next, in order to preserve local structure information abundantly, FDNFS has two-part manifold regularization on the pseudo-label matrix in sparse regression model and the reconstructed coefficient matrix in self-representation framework. This can fully use the manifold information of data. In addition, FDNFS imposes the non-convex constraints. It can ensure the sparsity of feature selection matrix. In turn, this can select features with lower redundancy, and then select a better feature subset. Finally, this paper adopts an iterative optimization method. FDNFS is compared with nine algorithms on seven datasets. The clustering results reflect better performance of FDNFS. • Feature correlation representation and dual manifold optimization is proposed. • It constructs feature graph to represent the interconnection information. • It unifies feature correlation representation learning and feature selection. • It introduces self-representation on the improved sparse regression model. • It has two-part manifold regularization on the pseudo-label matrix. [ABSTRACT FROM AUTHOR]

In this paper, data-driven models for wind speed forecasting are established by incorporating atmospheric variables, such as temperature, humidity divergence and etc. as input, and using forecasted wind speed as the output. Input data, statistics in every 3-h interval, utilized in this study are from CERA-20C within a period from the year 2001–2010. In the models, a feature selection technique is proposed to identify the relative dependence of each input to the output. Through a comparison between results with and without the selection technique, it is observed that the technique helps to select the most pertinent inputs, and thus further improve the forecast performance, accuracy and efficiency. In addition, three data-driven models are further revealed to acquire the best forecast accuracy, by including temporal effect, spatial effect, or coupled temporal and spatial effects on atmospheric conditions, which are named as temporal-based, spatial-based and hybrid data-driven models, respectively. By comparing the forecast performance among different models, it is revealed that the newly proposed hybrid data-driven model with feature selection technique is more suitable in dealing with wind speed forecasting. Moreover, an additional case study further reinforces the feasibility of the newly proposed hybrid data-driven model for forecasting of wind direction. The proposed date-driven models in the paper provide a high-cost efficiency alternative for wind speed forecast using machine learning instead of physical models. This approach can assist engineers in making prompt and informed decisions even when resources are constrained during emergency conditions. • Cost-efficiency wind speed forecast methods are developed by incorporating atmospheric variables into data-driven models. • Data-driven models are generated by considering temporal and spatial effects of atmospheric conditions on wind fields. • The feature selection is utilized to select the appropriate inputs and to enhance the accuracy of wind speed forecasts. • The important atmospheric variables that significantly affect wind fields are identified. • The feasibility of the newly proposed hybrid data-driven model for wind direction forecasting is demonstrated. [ABSTRACT FROM AUTHOR]

Keyword extraction involves the application of Natural Language Processing (NLP) algorithms or models developed in the realm of text mining. Keyword extraction is a common technique used to explore linguistic patterns in the corpus linguistic field, and Dunning's Log-Likelihood Test (LLT) has long been integrated into corpus software as a statistic-based NLP model. While prior research has confirmed the widespread applicability of keyword extraction in corpus-based research, LLT has certain limitations that may impact the accuracy of keyword extraction in such research. This paper summarized the limitations of LLT, which include benchmark corpus interference, elimination of grammatical and generic words, consideration of sub-corpus relevance, flexibility in feature selection, and adaptability to different research goals. To address these limitations, this paper proposed an extended Term Frequency-Inverse Document Frequency (TF-IDF) method. To verify the applicability of the proposed method, 20 highly cited research articles on climate change from the Web of Science (WOS) database were used as the target corpus, and a comparison was conducted with the traditional method. The experimental results indicated that the proposed method could effectively overcome the limitations of the traditional method and demonstrated the feasibility and practicality of incorporating the TF-IDF algorithm into relevant corpus-based research. [ABSTRACT FROM AUTHOR]

Recently, the image retrieval process appears to be a challenging task to filter out a huge volume of objectionable images from retrieval. It is very easy for people of all ages to obtain such obscene images with just a few clicks on the internet, which could harm the adolescent. To prevent such serious social problems, this paper introduces a content-based image filtering (CBIF) framework in an image retrieval system. The proposed CBIF approach is split into two components. In the first component, the skin region of exposed human body parts is extracted based on a color segmentation method, and an efficient feature vector generation process is introduced based on frequent skin color pixels and scale-invariant structural features. A novel texture feature representation is presented in the retrieval and filtering process obtained by block-paired local binary pattern (BP-LBP). The final component introduces a novel image filtering framework for the retrieved images found from the first component based on a majority of voting method on three different machine learning classifiers backed by SVM, MLP, and CNN. The retrieval efficiency is analyzed with standard performance indicators such as precision, recall, and F -score on two large datasets: NPDI and NSFW. [Display omitted] • This paper presents a CBIF framework to prevent obscene image retrieval. • Skin regions of exposed body parts are extracted using color segmentation and feature selection. • A novel texture feature selection using BP-LBP is presented to reduce the semantic gap. • A robust obscene content filtering using MoV method is introduced to reduce misclassification. [ABSTRACT FROM AUTHOR]

• This paper proposes a synchronous feature selection technique based on graph-embedded cluster label orthogonal decomposition and collaborative particle swarm optimization (GOD-cPSO). • GOD-cPSO extends the feature selection framework of clustering label orthogonal decomposition by graph embedding. • The l 2,1-2-norm with strong global convergence is extended to the graph embedding clustering label orthogonal decomposition framework. • The local structure preserving of low-dimensional manifolds is integrated into the graph-embedded clustering label orthogonal decomposition framework. • GOD-cPSO synchronously guides the graph-embedding clustering labeling orthogonal decomposition framework for feature selection through collaborative particle swarm optimization. In unsupervised feature selection, the clustering label matrix has the ability to distinguish between projection clusters. However, the latent geometric structure of the clustering labels is often ignored. In addition, the optimal sub-feature selection performance of feature selection techniques relies greatly on the choice of balanced parameters, and the selection range of most technical parameters is limited and fixed. To solve the above-mentioned problems, this paper proposes a synchronous feature selection technique based on graph-embedded cluster label orthogonal decomposition and collaborative particle swarm optimization (GOD-cPSO). First, GOD-cPSO extends the feature selection framework of clustering label orthogonal decomposition by graph embedding to retain the latent geometric structure of clustering labels, thus maintaining the correlation between clustered sample labels. Then, the l 2,1-2 -norm with strong global convergence is extended to the graph embedding clustering label orthogonal decomposition framework. By imposing this non-convex constraint, GOD-cPSO can achieve low-dimensional sparse and low-redundant sub-features. In addition, the local structure preserving of low-dimensional manifolds is integrated into the graph-embedded clustering label orthogonal decomposition framework to obtain good cluster separation and effectively maintain the latent local structure of the data. Finally, to ensure the adaptive parameter selection over a large range, GOD-cPSO synchronously guides the graph-embedding clustering labeling orthogonal decomposition framework for feature selection through collaborative particle swarm optimization. GOD-cPSO has synchronous parameter optimization and feature selection and picks parameters in a larger range. Comprehensive numerical experiments are performed on nine datasets to test the validity of the GOD-cPSO. The experimental results demonstrate that the sub-features selected by the GOD-cPSO have stronger discriminative power and are superior to other techniques in the clustering assignments. [ABSTRACT FROM AUTHOR]

Accurate land valuation is necessary for tax purposes, land resources allocation, real estate management and urban development and planning. Since various factors from different domains affect land prices through non-linear relationships, automating the land valuation process on a large scale is a complex task. Advanced technologies in big data analysis and artificial intelligence have demonstrated superior capabilities in knowledge extraction in such cases. Accordingly, this paper develops and compares the performance of four Automated Valuation Models (AVMs) based on machine learning and deep learning techniques utilizing physical, geographical, socio-economic, environmental, legal and planning factors in Melbourne Metropolitan, Australia. According to the results, the eXtreme Gradient Boosting (XGBoost) method outperforms other algorithms of Support Vector Regression (SVR), random forest and Deep Neural Network (DNN). This method has achieved the coefficient of determination (R2) of 0.862, Mean Absolute Percentage Error (MAPE) of 0.139, and normalized Root Mean Square Error (nRMSE) of 0.281. The achieved high accuracy is due to incorporating a wide range of driving factors and applying innovative feature selection and hyperparameter tuning procedures evaluating various possible feature sets and hyperparameters. Accordingly, this paper can contribute to research, governmental and industry-based activities in terms of developing AVMs for mass land valuation. • Automated land valuation models using machine learning and deep learning • Comprehensive feature set and hybrid feature selection process for robust model performance • Spatial mapping of land values in large urban areas • Contribution to fair housing policies and urban development by accurate land valuation • Practical insights for housing affordability strategies in terms of land management [ABSTRACT FROM AUTHOR]

Electricity load exhibits daily and weekly cyclical patterns as well as random characteristics. At present, prevailing deep learning models cannot learn electricity load cyclical and stochastic features adequately. This results in insufficient prediction accuracy and the scalability of current methods. To tackle these difficulties, this paper proposes a framework for electrical load prediction based on an Attention Mechanism Time Series Depthwise Separable Convolutional Neural Network (ELPF-ATDSCN). The framework starts by using the Maximum Information Coefficient for exogenous variable selection. It then incorporates a seasonal decomposition algorithm with manual feature engineering to extract the cyclical and stochastic features of the electrical load. Subsequently, the framework employs the ATDSCN to learn the cyclical and stochastic features of the electrical load. In addition, the Bayesian algorithm optimizes model hyperparameters for optimal model performance. Experimental results of point and interval load prediction on datasets from the US and Nordic power markets reveal that the ATDSCN model proposed in this paper enhances load prediction accuracy compared with other models. It can provide more reliable predictions for power system operation and dispatch. • A new attention mechanism is designed to improve the model memory capability. • The ATDSCN model is proposed for learning periodic and stochastic features of electricity loads. • A framework for electricity load prediction is proposed to improve the accuracy of electricity load forecasting. • The effectiveness of the proposed method is validated on the real world dataset. [ABSTRACT FROM AUTHOR]

• Newbie study using standard ML techniques with HAR Application and Discussions. • Activities found in Literature with the corresponding reference. • Co-occurrences between activities and sensors with the corresponding reference. • Summary and comparison among the different datasets found in Literature. • Summary of the experimentation settings with performance scores found in Literature. Human Activity Recognition (HAR) is an essential area of research related to the ability of smartphones to retrieve information through embedded sensors and recognize the activity that humans are performing. Researchers have recognized people's activities by processing the data received from the sensors with Machine Learning Models. This work is intended to be a hands-on survey with practical's tables capable of guiding the reader through the sensors used in modern smartphones and highly cited developed machine learning models that perform human activity recognition. Several papers in the literature have been studied, paying attention to the preprocessing, feature extraction, feature selection, and classification techniques of the HAR system. In addition, several summary tables illustrating HAR approaches have been provided: most popular human activities in the literature with paper references, the most popular datasets available for download (Analyzing their characteristics, such as the number of subjects involved, the activities recorded, and the sensors with online-availability), co-occurrences between activities and sensors, and a summary table showing the performance obtained by researchers. =The paper's goal is to recommend, through the discussion phase and thanks to the tables, the current state of the art on this topic. [ABSTRACT FROM AUTHOR]

Roundwood sorting is still a manual process in many Swiss sawmills, requiring employees to visually inspect and categorize thousands of logs per day. The heavy workload can be both physically and mentally taxing and can lead to increased rates of human error. State-of-the-art automation systems like X-ray log scanners are expensive and difficult to integrate into existing process lines. This paper proposes a novel recommendation system that leverages recent advances in image classification to automate roundwood classification by quality and species. The system integrates a camera to capture cross-sectional images of logs and record numerical data, such as length, taper, and diameter. The analysis of the resulting dataset highlights the challenges of data imbalance and noise, which makes classification difficult and, in some cases, impossible. However, by using selected datasets with reduced noise, state-of-the-art Convolutional Neural Networks (CNNs) can extract quality and species features. Quality models learn from a manually selected and simplified dataset, featuring samples that experts can clearly classify based on the image's information. Species models are trained on a label-noise-reduced dataset, reflecting real-world complexity. The accuracy on the selected dataset for three quality classes is 80%. The species determination is less challenging and reaches 91% accuracy on a synchronized dataset for the main species spruce and fir. Overall, this paper highlights the potential of Machine Learning in augmenting the roundwood sorting processes and presents a novel system that can improve the efficiency and accuracy of the process. [Display omitted] • Automation of roundwood sorting: Replaces manual sorting with image-based AI. • Integrated camera system in roundwood sorting to collect labeled dataset. • Species prediction: 91% accuracy in spruce–fir distinction. • Quality prediction on complexity reduced dataset: 80% accuracy between three main quality levels. • Efficient, adaptable & scalable system which is easy to integrate into existing process lines. [ABSTRACT FROM AUTHOR]

This paper presents a study on the salinity determination and flow rate estimation in a two-phase air-water system. For this purpose, an automated air-water test loop capable of generating different flow patterns in a horizontal pathway was utilized to do numerous experiments at varying flow rates. A nuclear measuring setup, comprising Cs-137 and Am-241 as radiation sources, one NaI (Tl) scintillation detector to register transmission counts of Cs and three scintillator detectors for registering transmission and scattering counts from Am, was prepared. A pressure drop pipe was also employed for flow rate measurement, with MLPs were selected as the processing element. Notable innovations of this paper can be considered from two perspectives. Firstly, a novel paradigm in nuclear measurement geometry. This novelty uses the benefits of three scintillator detectors to extract features with the maximum potential for classifying and determining salinity. Secondly, there is a new method in data processing and utilizing optimum features to achieve the best performance in predicting flow rates. Results in flow rate prediction independent of salinity and flow regime indicate that the proposed paradigm and method are reliable for using in industrial fields related to multi-phase metering. • This paper proposes a novel paradigm in nuclear measurement geometry. • This paper employs seven ANNs to develop the optimal prediction model. • The combination of wavelet transform and statistical features shows the best performance to determine the flow rates. • The results indicated that the proposed prediction model achieved an MAE of less than 4/237 L/min and an MRE% of 4/842 % for predicting flow rates. [ABSTRACT FROM AUTHOR]

The prediction of the occupancy in buildings is essential to design efficient energy control strategies that optimize consumption and reduce losses while guaranteeing the comfort of the occupants. For this reason, many works address the problem of detecting, estimating, and predicting buildings' occupancy using different techniques, devices, and technologies. The occupancy prediction process can be described in four stages: data acquisition, modeling, evaluation, and testing, which are closely related. This paper reviews the most relevant recent literature on building occupancy estimation and prediction, analyzing the key aspects of its stages. A detailed description of the variables and design considerations is presented, including measurement methods, sensor selection, modeling techniques, evaluation metrics, and different applications. Through its examination, this paper elaborates significant remarks on the interaction between the stages, providing an overview of the suitable design of the occupancy prediction process. Finally, current and future trends are discussed. • A systematic review of the occupancy estimation and prediction process is presented. • Data acquisition, modeling, evaluation, and testing are the four general stages. • The importance of sensor fusion in overcoming individual limitations is presented. • Occupancy detection methods include deterministic, stochastic, and machine learning. • Some potential future research directions are discussed. [ABSTRACT FROM AUTHOR]

• This paper explores the capabilities of machine-learning based fault detection and diagnosis. • The scope of the research is narrowed to the identification of transient events. • The K-Nearest Neighbors model achieved the highest accuracy of 97% in the primary system. The increasing interest in artificial intelligence and automation within the nuclear industry stems from the hope of elevating the safety and reliability of nuclear power plants by minimizing the impact of human errors. This paper explores the capabilities of machine-learning based fault detection and diagnosis (FDD) models in accurately classifying transient events in a nuclear power plant using the Classification Learners Application from MATLAB. The scope of the research is narrowed to the identification of transient events of the same nature occurring at various locations within the plant. To accomplish this, the Generic Pressurized Water Reactor (GPWR) from the Western Services Cooperation (WSC) was used to simulate 14 transients in the primary system and 10 transients in the secondary system, resulting in two distinct datasets of 108,000 and 79,200 observations. Nine types of classifiers, including Decision Trees, Discriminant Analysis, Support Vector Machines, Logistic Regression, Nearest Neighbors, Naive Bayes, Kernel Approximation, Ensembles, and Neural Networks, with a total of 33 predefined models, were trained and validated. The K-Nearest Neighbors model achieved the highest accuracy of 97% in the primary system, while the Efficient Linear Discriminant and Logistic Regression models achieved the highest average accuracy of 99% in the secondary system. The assessment of the top-performing models was conducted through a comprehensive analysis employing key classification model evaluation metrics, such as the confusion matrix, accuracy, precision, recall, and the F1 score. In an effort to optimize the models, the study integrated feature selection using the minimum Redundancy Maximum Relevance (mRMR) algorithm. Additionally, the investigation explored different validation schemes, including both holdout and k-fold cross-validation schemes, resulting in a substantial reduction in training time without significantly compromising the overall accuracy of the models. The optimized models in this study demonstrated remarkable prediction accuracies, consistently exceeding 94%. Despite the complexity of the models and the intricacies involved in the training process, the training times ranged from 10 to 1800 s, reflecting the efficiency and robustness of the implemented optimization techniques. The results of this study underscore the potential of machine learning models in identifying transient events in nuclear reactors, showcasing their promising capabilities while maintaining low computational and execution costs. This suggests their efficacy in optimizing safe and efficient operational practices within nuclear facilities. [ABSTRACT FROM AUTHOR]

Intrusion Detection System (IDS) can ensure the network security by identifying network intrusions according to the abnormal traffic data. However, the intrusion detection data has the problem of high dimensionality and changes with network and attack environments, which leads to the poor performance and poor portability of intrusion detection algorithms. Therefore, this paper proposes an intrusion detection algorithm based on joint symmetric uncertainty and hyperparameter optimized fusion neural network. Firstly, a feature selection method based on symmetric uncertainty and approximate Markov blanket is proposed, which fully considers the correlation and redundancy of features, and also the correlation between combined features and the class label, so as to reduce the data dimensionality. Secondly, the CNN-LSTM classifier fused with Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) is used to extract the spatial features and temporal features to improve the classification performance. Finally, the Particle Swarm Optimization (PSO) algorithm is improved and used to automatically optimize the hyperparameters of the classifier, so that the classifier can be applied to different intrusion detection datasets with better generalization ability and portability. Experiments have verified the effectiveness and superiority of the proposed algorithm on multiple evaluation indicators. • An effective algorithm for intrusion detection is proposed in this paper. • Feature selection is based on symmetric uncertainty and approximate Markov blanket. • A fusion neural network is constructed to extract the spatial and temporal features. • The PSO algorithm is improved to automatically optimize the hyperparameters. [ABSTRACT FROM AUTHOR]

High-dimensional feature selection is of particular interest to researchers. In some domains, such as microarray data, it is quite common for a group of highly correlated explanatory variables to be of equal importance for inclusion in the predictive model. This paper proposes a new hybrid feature selection approach that integrates feature screening based on Kendall's tau and Elastic Net regularized regression (K -EN). K -EN as an approach that embeds the Elastic Net, has the advantage of the grouping effect, which automatically includes all the highly correlated variables in the group. The K -EN approach offers insightful solutions to high-dimensional regression problems and improves Elastic Net performance since the screening phase is preceded by a step that further reduces the number of explanatory variables by removing those that disagree with the target based on Kendall's tau. The use of Kendall's tau further enhances Elastic Net performance, as it is robust enough to handle heavy-tailed distributions, non-parametric models, outliers, and non-normal data with greater ease. K -EN is therefore a time-saving approach. The proposed algorithm is evaluated on four simulation scenarios and four publicly available datasets, including riboflavin, eyedata, Longley, and Boston Housing, and achieves 0.2528, 0.0098, 0.1007, and 0.4121 respectively as the Mean Squared Error (MSE). K -EN's MSEs are the best compared to those achieved by the state-of-the-art approaches reviewed in this paper. In addition, K -EN selects up to 100% of relevant features when run on simulated data. [ABSTRACT FROM AUTHOR]

Changes in wind speed directly affect the output of wind turbines, so in power system planning, accurate prediction of future wind speed can help adjust the stability and reliability of power networks. In order to solve the problem that unknown wind speed prediction systems are unable to select features autonomously and to alleviate the insufficient prediction accuracy of single interval type 2 fuzzy models, this paper proposes a new deep convolutional interval type 2 fuzzy system (DCIT2FS) based on adaptive feature selection. First off, type 2 fuzzy sets are employed in the construction of two stage interval type 2 fuzzy curves and surfaces to address the issue of dimensionality explosion brought on by complex system modelling. By removing inaccurate and redundant information, this strategy achieves automated screening of key input aspects of an unknown system. Second, the model's interpretability is improved by the addition of the interval type 2 fuzzy system to the deep convolutional structure, which also addresses the issue that a single interval type 2 fuzzy model cannot achieve the required level of prediction accuracy. Thirdly, the incorporation of the feature pyramid structure boosts the mining of underlying data to increase the model's capacity to predict outcomes accurately while simultaneously strengthening its resistance to interference. Finally, model prediction performance tests are completed using meteorological feature data for both time periods, and generalisability tests are conducted using the benchmark dataset. The experimental results show that the prediction accuracy of the model proposed in this paper is improved by at least 7.70% and 1.23% in two wind speed prediction experiments compared to other models. • A new deep convolutional interval type 2 fuzzy prediction model is designed. • The feature pyramid structure is added to DCIT2FS in an innovative way. • A method TSIT2FCS is designed to realise the automatic selection of input features. • The hybrid model TSIT2FCS-DCIT2FS is successfully applied in wind speed prediction. [ABSTRACT FROM AUTHOR]

Effective selection of climate predictors is a fundamental aspect of climate modeling research. Predictor Screening (PS) plays a crucial role in identifying regional climate drivers, reducing noise, expediting convergence, and minimizing time consumption, ultimately leading to the development of robust models. This review delves into the complex landscape of PS techniques within the context of Numerical Climate Modeling (NCM), with a specific focus on their applicability across various Köppen climate classifications and PS model structures. The analysis revealed substantial variations in the performance of PS methods, shedding light on their ability to capture –and prioritize predictors related to precipitation and temperature within distinct climate contexts. Furthermore, the provided methods have been categorized into two subsections: Feature Selection (FS) and Feature Extraction (FE), with FS encompassing filter, wrapper, embedded, and ensemble/hybrid techniques, and FE covering Linear Feature Extraction (LFE), Time-Domain Analysis (TDA), deep learning, and clustering methods. The initial compilation of papers, acquired through a keyword search on Scopus, consisted of 3650 documents. Following a meticulous evaluation process, 206 papers were identified as fitting for inclusion in the literature review, covering the time frame from 1974 to November 3, 2023. In conclusion, the results provide a detailed understanding of the strengths and limitations of each approach, establishing a hierarchy of effectiveness contingent upon the specific climate context. Additionally, insights into promising avenues for future research in this field are offered. This review follows the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) standard as its foundation. [ABSTRACT FROM AUTHOR]

In recent years, vibration signals have been widely applied for the identification of mechanical states in oil-immersed transformers. This paper, following the framework of 'vibration generation – sensing – processing – recognition – evaluation – solution,' introduces the progress in mechanical state recognition of oil-immersed transformers based on vibration signals from a novel sensor-oriented perspective, which covers sensor deployment, sensor specialization, and equipment integration. The advancements in signal processing and feature selection are also discussed and compared with the identification of states in rotating machinery. To Address challenges like limited rule transferability and the weakness in vibration characteristics and models, some emerging technologies such as Operational Modal Analysis and multisource data fusion are introduced, which may bring new prospects. This paper aims to provide scholars engaged in research on the mechanical state identification of transformers and other electrical equipment with some technical references. • Advances in transformer mechanical state recognition via vibration signals are discussed from a sensor-oriented view. • A cross-comparison of vibration characteristics used for diagnostics in transformers and rotating machinery is conducted. • Emerging tech like Operational Modal Analysis and sensor specialization are discussed for rule transfer challenges. [ABSTRACT FROM AUTHOR]

This paper introduces a novel feature selection method, called Feature Selection based on Importance Measures (FS-IM), to enhance the forecasting of crude oil returns. FS-IM innovatively combines active learning with the application of Gaussian noise to input features and selects the most relevant features using an optimal threshold value. The paper applies a ridge regression (RR) model based on FS-IM (FS-RR) to identify the factors that have important information for crude oil return forecasting. The paper compares FS-IM with other dimension reduction methods such as Principal Component Analysis (PCA), Kernel Principal Component Analysis (KPCA), and Independent Component Analysis (ICA). The results show that FS-IM can significantly improve model accuracy, demonstrating its effectiveness in finding key features. Moreover, FS-IM is more stable and consistent than other dimension reduction methods in enhancing the prediction accuracy in different scenarios, indicating its superior capability in capturing complex relationships between input and output variables. Furthermore, this study compares FS-RR model with other 13 prediction models by conducting experiments using a series of evaluation metrics, different statistical tests, and different step-ahead predictions and training sets. The results confirm that the RR model based on FS-IM can consistently outperform other model in terms of predictive performance and economic value, proving its effectiveness and robustness. This study contributes to the literature on crude oil price forecasting by addressing the challenges of high-dimensional and complex data, and by providing a robust, practical tool for professionals in energy economics and finance. • A new feature selection method for crude oil forecasting using importance scores and Gaussian noise is proposed. • The method selects the most relevant features based on the prediction errors of a base forecasting model. • The method enhances the accuracy and value of ridge regression model compared to other methods. • The method handles high-dimensional and complex data without losing information or interpretability. [ABSTRACT FROM AUTHOR]

This paper reports new insights into how the selection of route based characteristic parameters can influence the predicted energy consumption for next generation battery electric buses. 24 characteristic parameters have been studied to understand their relative importance on vehicle energy consumption and to develop new data-driven prediction models. The parameters are grouped into two scenarios, representative of the varying levels of route information available to a typical bus operator. A combination of feature selection methods was used to determine which characteristic parameters had the greatest influence on energy consumption. Regression based prediction models were developed, and models were then validated using standard and real vehicle drive cycles. The prediction models had a mean absolute percentage difference of 2.10–10.67%. This paper presents a novel methodology to estimate energy consumption of operating zero emission vehicles, which will support public transport operators, policy makers and energy suppliers in the decarbonisation of public transport. [ABSTRACT FROM AUTHOR]

The prime challenge of unsupervised symmetric heterogeneous cross-domain adaptation is to train the source domain and apply the trained knowledge to the target domain. Most of the existing algorithms for unsupervised transfer learning create the subspace of the source domain features and target domain features for training purposes. It is an extensive computational process as most of the techniques require labeled source data. Many techniques also suffer from the loss of originality of features in both domains. This paper aims to consider the feature vectors of both the source and target domain for training the data based on the similarity of exemplar (feature) vectors of different instances, known as Instance Similarity Feature (ISF). The use of vectorization method for the similarity of features is proposed in this paper. The exemplar vectors are chosen randomly for the target datasets. Hence, to acquire relevant factual data in the knowledge base for training in our research, we worked to increase the domain separation error between source and target instances. To avoid the instability caused due to poor exemplar vector selection, the K-means clustering approach is followed after feature similarity, known as K-means Instance Similarity Feature (KISF). Many existing transfer learning techniques are based on the original feature set, which can cause degeneracy, hence affecting Accuracy. In order to vanquish the limitations of existing approaches, we have introduced novel optimal models with KISF and Ant Lion Optimizer (KISFA), KISF with Particle Swarm Optimization (KISFP) and KISF with Biogeography Based Optimization (KISFB). High-dimensionality can impact efficacy of the model, hence, feature selection with nature-based optimizer namely: Ant Lion Optimizer, Particle Swarm Optimization and Biogeography-Based Optimization are applied. We measure the performance of the proposed models by using Support Vector Machine, Logistic Regression, Random Forest, Naive Baye's, K-Nearest Neighbor and Decision Tree as classifiers, and Accuracy and F1-score as fitness functions. Extensive experiments are performed on four datasets with 50 iterations. The proposed model is compared with eleven other techniques and our technique outperforms all other techniques in average Accuracy. The validation is performed on the dataset using 10-fold cross-validation. The statistical test was performed using ANOVA, proving that our technique is significantly better than other techniques. [ABSTRACT FROM AUTHOR]

Fuzzy information-theoretic metrics have been demonstrated to be effective in evaluating feature relevance and redundancy in both categorical and numerical feature selection tasks. Most existing feature selection methods based on fuzzy information-theoretic metrics treat all classes as a single entity, resulting in the selection of a consistent feature subset for all classes. This approach overlooks the fact that diverse classes may exhibit distinct discriminative characteristics, which requires the selection of diverse feature subsets for each class. Consequently, these methods lack the capability to handle this variability in feature selection required for optimal performance. To address this limitation, this paper proposes a class-specific feature selection method based on fuzzy information-theoretic metrics. To be more specific, we introduce several class-specific fuzzy information-theoretic metrics. Building upon these metrics, we formulate a class-specific feature selection algorithm, which is referred to as class-specific fuzzy information-theoretic feature selection. This algorithm enables the selection of highly relevant feature subsets tailored to each individual class. Furthermore, we present a class-specific ensemble classification framework that integrates the classification results obtained from the feature subsets generated by our method. Finally, we conduct extensive tests on 21 publicly available datasets using four popular classifiers to compare the performance of our method with eight up-to-date classification-specific methods. Test results demonstrate that our method outperforms the eight compared classification-specific methods in terms of performance. • Introduce several class-specific fuzzy information-theoretic metrics. • Develop a class-specific fuzzy information-theoretic feature selection algorithm. • Design a class-specific ensemble classification framework. • Perform extensive tests to verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Due to its efficiency and flexibility, many unsupervised feature selection models based on dictionary learning have been proposed to select prominent features for improving the accuracy of data clustering and classification in pattern recognition, data mining, and machine learning. However, these models generally focus on how to investigate data distribution but ignore the issue that data may be contaminated by outliers, making the existing models ineffective. Motivated by this, we propose Joint Cauchy Dictionary Learning and Graph Learning for Unsupervised Feature Selection in this paper. This method makes an effort to incorporate dictionary learning, dual representation learning, and adaptive graph learning into a unified framework, so that both the global and local correlation information can be utilized to facilitate feature selection. Specifically, we first propose Cauchy dictionary learning to get high-quality latent representations that are resistant to data outliers. Following the high-quality representations, we re-encode latent features (features of latent representations) into the feature space and get dual representations to quantify the significance of data features in retaining the global correlation information of data. Then, the local similarity structure is adaptively learned in the projection space to quantify the significance of data features in retaining the local correlation information of data. Finally, we design an efficient optimization algorithm to optimize this model and theoretically analyze its convergence and computational complexity. The evaluation results on eight real-world datasets show that our method outperforms several state-of-the-art feature selection methods. [ABSTRACT FROM AUTHOR]

Feature selection in small-sample high-dimensional datasets enhances classification accuracy and reduces computational time for model training. This paper introduces the filter Classification Error Impurity (CEI) as a frequency-based ranker that improves upon existing methods by better identifying non-linear patterns. According to this, the top features identified by the ensemble of CEI, along with Mutual Information (MI) and Fisher Ratio (FR), form the feature space utilized by the Adaptive Genetic Algorithm with External Repository (AGAwER) to identify the optimal feature combination in a wrapper approach. AGAwER leverages an external repository, incorporating the best solutions to enrich the Genetic Algorithm's (GA) population, thus promoting diversity and enhancing exploration. As a result, a hybrid method called CMF-AGAwER is proposed, which surpasses existing modern feature selection methods. The implementation and data are accessible on GitHub at https://github.com/KhaosResearch/CMF-AGAwER. [Display omitted] • A Classification Error Impurity (CEI) algorithm is proposed as a frequency-based filter ranker. • An Adaptive Genetic Algorithm with an External Repository (AGAwER) is proposed as a wrapper method to augment the exploration of GA. • It is explored that the ensemble of the top features obtained by CEI, Mutual Information (MI), and Fisher Ratio (FR) yields an informative feature space. • The hybrid CMF-AGAwER is introduced, demonstrating superiority over existing modern feature selection methods. [ABSTRACT FROM AUTHOR]

In most data dimensionality reduction tasks, feature selection (FS) is an essential preprocessing stage. The slime mould algorithm (SMA) is a novel metaheuristic optimization algorithm. This paper proposes a feature selection method for banknote dirtiness recognition based on mathematical functions driven slime mould algorithm. This method is applied to the feature selection of banknote dirtiness recognition, and the Lévy flight operator is used to replace the control parameter vc in SMA, and a series of mathematical functions are added to replace the control parameter vb in the slime mould algorithm to enhance the global search capability. Test results show that this method achieves the highest accuracy of 76.85 % in recognizing the banknote dirtiness. Additionally, by applying the same method to feature selection and recognition of dirtiness for the left middle white area images of banknotes, the highest accuracy reaches 74.99 %. This suggests that the left middle white area can essentially replace the whole banknote. To verify the performance of the proposed feature selection method, comparative tests with four other optimization algorithms are carried out, and the results demonstrate that three improvement strategies can effectively improve the performance of SMA while maintaining a balance between exploration and exploitation. Tests have revealed that these three algorithms have significant advantages over the past SMA in terms of recognition accuracy and convergence speed when it comes to identifying the dirtiness of banknotes. Therefore, this method is considered to be one of the most effective methods to solve the feature selection problem of banknote dirtiness. [ABSTRACT FROM AUTHOR]

• Enhanced feature combinational optimization for power system dynamic early warning. • Maximal information coefficient-enabled enhancement for evolutionary computation. • Feature selection framework embedded with multivariate time series learning models. • Multivariate time series classification-based transmission congestion early warning. Multivariate time series (MTS) learning-based dynamic early warning (DEW) shows promising potential in preventing power systems from underlying risks. However, as a fundamental and essential step for constructing DEW models, performing efficient feature selection (FS) within high-dimensional candidate features (HDCF) of power grids is challenging, especially considering the MTS format and security-dominated characteristics of electric utilities. This paper proposes an enhanced feature combinational optimization (FCO) method to select beneficial variables for MTS-based DEW models within the HDCF of power grids. First, to identify features that contain valuable temporal patterns for DEW, a wrapper FCO framework combined MTS learning and evolutionary computation is designed. Then, to improve the FCO efficiency and solution quality when facing HDCF, a maximal information coefficient (MIC) based enhancement scheme is developed, semi-guiding the FCO initialization and evolution. Finally, by integrating MIC and iterative search, hybrid end-to-end FS is achieved. Experiments on the synthetic data from the IEEE 39-bus system and the real-world data acquired from a provincial power grid in China show that, via the MIC semi-guidance, the proposed method possesses higher FCO efficiency and better results within HDCF compared to wrapper benchmarks. Compared to filter benchmarks, it is more compatible with supervised MTS and can consider the practical performance of features by interacting with the embedded learning models. Results also verify that, with the features from the proposed method, more accurate DEW models can be obtained to predict the target event in early stages. [ABSTRACT FROM AUTHOR]

The rapid growth of computer networks has heightened system vulnerabilities, challenging traditional Machine Learning (ML) techniques in network anomaly detection due to the abundance of data, imbalanced attack classes, and large-scale datasets. This paper introduces a novel approach leveraging the AWID3 dataset, utilizing advanced preprocessing techniques such as data splitting and normalization. We propose the Mountaineering Team-Based Optimization (MTBO) algorithm for robust feature selection, inspired by social behavior and human collaboration. Additionally, we deploy a Quad-LSTM framework, integrating ConvLSTM, CNN-LSTM, E3D-LSTM, and SAConvLSTM models, fine-tuned by the Technical and Vocational Education and Training-Based Optimizer (TVETBO). Our approach achieves a remarkable 99.91 % accuracy, significantly surpassing existing models, thus enhancing network security by effectively addressing the complexities of anomaly detection. [ABSTRACT FROM AUTHOR]

Microarray data often comprises numerous genes, yet not all genes are relevant for predicting cancer. Feature selection becomes a crucial step to reduce the high dimensionality in these kinds of data. While no single feature selection method consistently outperforms others across diverse domains, the combination of multiple feature selectors or rankers tends to produce more effective results compared to relying on a single ranker alone. However, this approach can be computationally expensive, particularly when handling a large quantity of features. Hence, this paper presents a parallel feature rank aggregation that utilizes borda count as the rank aggregator. The concept of vertically partitioning the data along feature space was adapted to ease the parallel execution of the aggregation task. Features were selected based on the final aggregated rank list, and their classification performances were evaluated. The model's execution time was also observed across multiple worker nodes of the cluster. The experiment was conducted on six benchmark microarray datasets. The results show the capability of the proposed distributed framework compared to the sequential version in all the cases. It also illustrated the improved accuracy performance of the proposed method and its ability to select a minimal number of genes. [Display omitted] • A novel parallel feature rank aggregation is proposed. • Fewer genes are selected from microarray dataset for accurate prediction of cancer. • Significant scale down of computational time is achieved due to parallel implementation. [ABSTRACT FROM AUTHOR]

• Wavelet feature extraction reduces the dimensionality of lung cancer microarray data. • Cuckoo Search and Dragonfly feature selection algorithms preserve relevant gene data. • Versatile classifiers based on probability, distribution, tree, and nonlinear kernels. • Our framework reported better results than the conventional machine learning methods. In this paper, we unleash the potential of wavelet-based feature extraction on Microarray gene expression lung cancer datasets that exhibit high-dimensional feature spaces with thousands of genes, posing dimensionality reduction and feature selection challenges. The Biorthogonal 2.2 wavelet, Coiflets 2 wavelet, and Daubechies 6 wavelet extract features, thereby reducing the dimension of the Microarray gene expression datasets. Afterwards, the Dragonfly and Cuckoo Search bio-inspired algorithms choose the relevant features from the dimensionally reduced microarray data. Further, in the classification phase, the following classifiers are used: Nonlinear Regression, Bayesian Linear Discriminant, Softmax Discriminant, Gaussian Mixture Model, Naive Bayesian, Random Forest, Decision Tree, and Support Vector Machine with linear, polynomial, and Radial Basis Function kernels. The Daubechies 6 wavelet feature extraction and Dragonfly feature selection attained the highest accuracy in the range of 97.23, with an F1 score of 98.32, MCC of 0.90, YI of 91.54 and Kappa of 0.90. [ABSTRACT FROM AUTHOR]

• A novel feature selection method integrating maximal discernibility and minimal redundancy was proposed. • A real water pipeline leakage acoustic signal dataset was constructed and used to validate the proposed method. • The key features that significantly impact on leak detection in water pipelines are interpreted by the SHAP method. • The proposed feature selection method can achieve higher leak detection accuracy and fewer features. Water pipelines often have small cracks and leaks over time due to various degradation process. Acoustic emission technique is an outstanding method in leak detection for low cost and carrying out easily. Currently, the existing leak detection methods using acoustic signals consider only the contribution of individual features without considering the interactions between features in the feature selection process. To address this gap, this study introduces a generalized feature selection framework called Maximal Discernibility and Minimal Redundancy and Improved Sequential Floating Forward Selection (MDMR_ISFFS). In this study, time and frequency domain features are extracted from acoustic leakage signals observed in real water supply pipes. The effectiveness of the feature selection method is verified by different machine learning methods and interpretability methods. Moreover, the method proposed in this paper is also compared with other feature selection methods. The results demonstrate that four key features (i.e., Mean of frequency, Zero-crossing Rate, Peak frequency and Mean) are identified as the crucial features consistently regardless of the classifiers. All five classification models using MDMR_ISFFS can achieve high leak detection accuracies, ranging from approximately 94 % to 98 %. When compared to other feature selection methods (i.e., DFS_SFFS, KL distance and original feature set), the proposed MDMR_ISFFS can achieve the highest accuracy with a smaller number of features. Moreover, the study reveals significant interactions among the four key leakage features. In summary, this research provides valuable insights for selecting key leak features in actual pipeline leak detection. [ABSTRACT FROM AUTHOR]

Numerous high-dimension multilabel data are generated, posing a challenge for multilabel learning. Building effective learning models with discriminative features is essential to improve the performance of multilabel learning. Multilabel feature selection can filter out the discriminative features according to their contribution to classification. However, ambiguity, uncertainty, and missing labels coexist in real-life multilabel data, which brings adverse effects to multilabel feature selection. The multi-scale fuzzy rough set gives an effective way to mine intrinsic knowledge hidden in uncertain data. This paper first extends the multi-scale learning to multilabel data with missing labels and proposes a feature selection method for multilabel classification with missing labels via multi-scale fusion fuzzy uncertainty measures called FSMML. The missing label space construction and feature evaluation metric are carefully investigated in the framework of multi-scale learning. A multilabel multi-scale learning strategy is formalized with the fuzzy granularity cognitive mechanism as the core, and the multi-scale fusion fuzzy label learning is given to reconstruct the missing label space. Then, a novel multilabel multi-scale fuzzy rough sets with missing labels is developed, and the significance of each scale is quantified. Moreover, some multi-scale fusion fuzzy uncertainty measures are defined by capturing the sample fuzzy similarity in the feature and reconstructed label spaces. Accordingly, the relevance between features and label set and the interactivity and redundancy between features in feature evaluation are discussed. Finally, FSMML chooses high-quality features to maximize relevance and interactivity and minimize redundancy. Extensive experiments demonstrate the effectiveness of FSMML on fifteen datasets with missing labels. • A universal multilabel multi-scale data analysis method is presented. • Multi-scale fusion fuzzy label learning is devised to reconstruct missing labels. • Multi-scale fusion fuzzy uncertainty measures are defined to guide feature evaluation. • Experimental results show the method's validity for data with missing labels. [ABSTRACT FROM AUTHOR]

Feature selection is a key technique to tackle the curse of dimensionality in multi-label learning. Lots of embedded multi-label feature selection methods have been developed. However, they face challenges in identifying and excluding redundant features. To address these issues, this paper proposes a multi-label feature selection method that combines robust structural learning and discriminative label regularization. The proposed method starts from the feature space rather than data space, motivated by the principle that redundant features have high similarity or strong correlation. To exclude redundant features, a regularization on the feature selection matrix is designed by combining ℓ 2 , 1 -norm penalty with inner products of feature weight vectors. This regularization can help to learn a robust structure in the feature selection matrix. Meanwhile, both of the similarity and dissimilarity of labels of instances are involved in exploring discriminative label correlations. Extensive experiments verified the effectiveness of the proposed model for feature selection. • ℓ 2 , 1 -norm and inner product penalties are integrated to learn feature selection matrix. • Discriminative label correlation is used to restrict the structure of predicted labels. • An optimization algorithm is given and its convergence is proved. • Experimental results show the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

Developing an efficient embedded feature selection method for both binary and multiclass classification problems is a fundamental topic to be further studied. In this paper, the conventional radial basis function (RBF) network is modified for joint feature selection and classification. By utilizing the anisotropic Gaussian basis function, an individual weight parameter is assigned to each feature for feature weighting. The L 1 -regularized loss function is designed by combining the softmax cross entropy loss with L 1 regularization terms imposing on feature and output weights. A specialized active-set limited-memory projected Quasi-Newton (SAL-PQN) algorithm is proposed to minimize the L 1 -regularized loss function, which can optimize all the adjustable parameters and zero out the redundant feature and output weights simultaneously. Furthermore, a safe dynamic pruning strategy is integrated into the SAL-PQN algorithm for dynamic sparse training of the modified RBF network, which continuously excludes the dynamically zeroed-out feature weights from the training process. It is theoretically assured of yielding the same gradient updates as SAL-PQN, thus the relevant computation of the zeroed-out feature weights in the forward and backward propagations can be safely eliminated. The experimental results demonstrate the effectiveness and efficiency of the proposed methods for joint feature selection and classification, and illustrate the practical utility of the inherent feature weighting capability. [ABSTRACT FROM AUTHOR]

The fast proliferation of electric vehicles (EVs) profoundly affects the stable operation of the power system. Since EV charging demand is affected by users volatile behaviors and many other environmental and social factors, their uncertainty is quite pronounced. Traditional deterministic forecasting methods which provide little information on the uncertainty may not be informative to the decision-making of power system with massive EVs. This paper proposes a novel feature-enhanced deep learning method (FEDM) for EV charging demand probabilistic forecasting of individual station, in which a two-stage feature selection model is constructed to introduce the Pearson correlation coefficient between charging demand and external features as a prior knowledge to reweight the initial weights. The performance is improved compared to which is without feature-enhanced. In the comparison with eight benchmarks, FEDM shows superiority in both deterministic and probabilistic evaluation metrics. With high computational efficiency, FEDM has low dependence on the historical data stock, which can still achieve good performance in the case of low data volume. It provides a fast and accurate forecasting scheme for the demand forecasting of individual stations under the limitation of low data stock. • The proposed approach improves the accuracy rate, qualified rate, sharpness and computational efficiency. • A novel feature enhanced mechanism is proposed to introduce the correlation coefficient as the prior knowledge of the neural network. • The proposed approach can provide an excellent forecasting performance in the constraints of low data volume. [ABSTRACT FROM AUTHOR]

This paper proposes a new, novel ranking method called Inverse-Reinforcement Learning Ranking. The main goal is to find a reward function representing the user's perceived utility after clicking on each result. It is necessary to utilize log information of all users' queries in the search engine dataset to reach this goal while assuming that the decisions (clicks) of the users are the best (optimal policy). The respective reward function is constructed using features extracted through a feature selection, and their corresponding weights are obtained by two optimization models, which are applicable for ranking results represented to the new users. In addition, new performance criteria were developed to illustrate the performance of the presented ranking method. To evaluate and test the proposed ranking algorithm, a real medium-sized dataset from a search engine is preprocessed and used in this research. Findings show promising results and decisive superiority over the default ranking method. It is illustrated that clicks on the top five results, top ten, and even the first results are remarkably improved by about 13–19% in all experiments, and the perplexity remarkably decreases by almost 23% after applying the ranking method. [ABSTRACT FROM AUTHOR]

Granular structures are mathematical representations of knowledge used in granular computing. As a new type of granular structure, fuzzy β -covering has attracted widespread attention in recent years. One of the most critical related studies is measuring the uncertainty of fuzzy β -coverings. It is the foundation for studying fuzzy β -covering applications, such as classification and clustering. In this paper, we investigate the uncertainty measures of fuzzy β -coverings from the viewpoints of algebra and information theory, and propose the corresponding methods of fuzzy β -covering reduction for feature selection. Firstly, a generalized fuzzy β -neighborhood and the associated fuzzy β -covering rough sets are presented. Secondly, three types of accuracy measures of fuzzy β -coverings are constructed via fuzzy β -covering rough sets. On this basis, the self-information of fuzzy β -coverings is defined by fusing accuracy and roughness measures. Based on the proposed uncertainty measures, two heuristic methods of fuzzy β -covering reduction are put forward and the corresponding algorithms are designed for monotonic feature selection. Finally, the performance of the proposed methods is compared with several mainstream feature selection methods and experimental results demonstrate the rationality and superiority of our proposed methods. • The concept of generalized fuzzy β -neighborhood is introduced. • Multi-fuzzy β -covering fusion-based accuracy and self-information are proposed. • Fuzzy dependency function and fuzzy self-information are defined. • Two monotonic fuzzy β -covering reduction methods are proposed. [ABSTRACT FROM AUTHOR]

Feature selection refers to the process of identifying the most relevant and valuable features or characteristics in a dataset, and it is an important step that can improve the performance and accuracy of predictive models for machine learning and data mining. Feature selection is crucial in efficiently reducing the number of features, thereby enhancing classification accuracy. This, in turn, alleviates computational burdens and elevates the overall performance of machine learning algorithms. This paper extended the conventional manta ray foraging optimization (MRFO) algorithm to an improved binary MRFO (IBMFO) algorithm. IBMRFO serves as a search strategy for designing a wrapper-based feature selection approach. To commence, we introduce a novel mechanism, termed the chaotic tent map (CTM), aimed at initializing the population to fortify both the algorithm's exploitation capabilities and population diversity. Second, an adaptive somersault foraging (ASF) factor is tuned to avoid premature convergence. Finally, a binary mechanism is introduced to adapt the algorithm for binary feature selection dilemmas. Experiments are performed on 30 renowned UC Irvine machine learning repository datasets. The results of the student's t-test show that the classification algorithm has statistical significance. The findings unequivocally exhibit the superior performance of the proposed IBMRFO compared to other algorithms under scrutiny. Notably, the efficiency of the enhanced factors is assessed through rigorous testing. For post-publications supporting this work, readers can refer to https://github.com/ELF-CHEUNG/IBMRFO. • Novel chaotic tent map for population initialization from evolutionary computation. • Optimization methods based on enhanced evolutionary computation. • Adaptive factor enhances convergence rate and search efficiency of algorithm. • Extensive numerical and scientific simulations for verifications with UCI dataset. [ABSTRACT FROM AUTHOR]

The sparsity and redundancy of high-dimensional data poses challenges during processing. Dimensionality reduction is a commonly used approach, which helps to reduce data redundancy and noise, lower the complexity of learning algorithms, and improve classification accuracy. Typically, directly determining the intrinsic dimensionality of a dataset is challenging. Many of the present dimensionality reduction techniques suffer from pre-set target dimensions without considering the specific dataset features. To address this problem, a novel dimensionality reduction method based on flow model, which is called adaptive flow encoder (AFE), is proposed in this paper. Initially, the flow model is employed to achieve feature transformation and project the data onto an equip-dimensional feature space. Subsequently, a gating layer is utilized for feature selection. By configuring the gating layer parameters to be learnable, the model gains the ability to adaptively select features. To assess the efficacy of the proposed approach, the model's ability to preserve data characteristics is first qualitatively evaluated through visual inspection by projecting the data onto a two-dimensional space. Subsequently, five standard datasets are employed and compared against six traditional dimensionality reduction techniques to ascertain the impact on downstream classification tasks under the adaptive learning of intrinsic feature dimensions by the model. Moreover, the impact of key parameters, including the initialization scheme of the gate layer, amplification factor, and dimension factor, on the test results is examined. [ABSTRACT FROM AUTHOR]

In recent years, two competitive time series classification models, namely, ROCKET and MINIROCKET, have garnered considerable attention due to their low training cost and high accuracy. However, they rely on a large number of random 1-D convolutional kernels to comprehensively capture features, which is incompatible with resource-constrained devices. Despite the development of heuristic algorithms designed to recognize and prune redundant kernels, the inherent time-consuming nature of evolutionary algorithms hinders efficient evaluation. To efficiently prune models, this paper eliminates feature groups contributing minimally to the classifier, thereby discarding the associated random kernels without direct evaluation. To this end, we incorporate both group-level (l 2 , 1 -norm) and element-level (l 2 -norm) regularizations to the classifier, formulating the pruning challenge as a group elastic net classification problem. An ADMM-based algorithm is initially introduced to solve the problem, but it is computationally intensive. Building on the ADMM-based algorithm, we then propose our core algorithm, POCKET, which significantly speeds up the process by dividing the task into two sequential stages. In Stage 1, POCKET utilizes dynamically varying penalties to efficiently achieve group sparsity within the classifier, removing features associated with zero weights and their corresponding kernels. In Stage 2, the remaining kernels and features are used to refit a l 2 -regularized classifier for enhanced performance. Experimental results on diverse time series datasets show that POCKET prunes up to 60% of kernels without a significant reduction in accuracy and performs 11 × faster than its counterparts. Our code is publicly available at https://github.com/ShaowuChen/POCKET. [ABSTRACT FROM AUTHOR]