Selection Algorithm Research Articles

A robust multi-label feature selection based on label significance and fuzzy entropy

Multi-label feature selection is one of the key steps in dealing with multi-label classification problems in high-dimensional data. In this step, label enhancement techniques play an important role. However, it is worth noting that many current methods tend to ignore the intrinsic connection between inter-sample similarity and inter-label correlation when implementing label enhancement learning. The neglect may prevent the process of label enhancement from accurately revealing the complex structure and underlying patterns within data. For this reason, a fuzzy multi-label feature selection method based on label significance and fuzzy entropy is proposed. An innovative label enhancement technique that considers not only the intrinsic connection between features and labels, but also the correlation between labels was first devised. Based on this enhanced label representation, the concept of fuzzy entropy is further defined to quantify the uncertainty of features for multi-label classification tasks. Subsequently, a feature selection algorithm based on feature importance and label importance was developed. The algorithm guides the feature selection process by evaluating how much each feature contributes to multi-label classification and how important each label is to the overall classification task. Finally, through a series of experimental validation, the proposed algorithm is proved to have better performance for multi-label classification tasks.

A Study of Transmission Point Selection for Multi-Connectivity in Multi-Band Wireless Networks

In 5th generation mobile communication networks, the frequency band of the millimeter band of 30–100 GHz is supported to provide a transmission speed of 20 Gbps or higher. Furthermore, a huge transmission capacity, i.e., up to 1 Tbps, is one of the main requirements for the 6th generation mobile communication networks. In order to meet this requirement, the terahertz band is considered a new service band. Hence, we consider multi-band network environments, serving the sub-6Hz band, mmWave band, and additionally sub-terahertz band. Furthermore, we introduce the transmission point selection criteria with multiple connections for efficient multi-connectivity operation in a multi-band network environment, serving and receiving multiple connections from those bands at the same time. We also propose a point selection algorithm based on the selection criteria, e.g., achievable data rate. The proposed point selection algorithm attains lower computational complexity with a 2-approximation of the optimal solution. Our simulation results, applying the channel environment and beamforming in practical environments defined by 3GPP, show that selecting and serving multiple transmission points regardless of frequency band performs better than services through single-connectivity operation.

Evaluation of Two-Dimensional DBH Estimation Algorithms Using TLS

Terrestrial laser scanning (TLS) has become a vital tool in forestry for accurately measuring tree parameters, such as diameter at breast height (DBH). However, its application in Mexican forests remains underexplored. This study evaluates the performance of five two-dimensional DBH estimation algorithms (Nelder–Mead, least squares, Hough transform, RANSAC, and convex hull) within a temperate Mexican forest and explores their broader applicability across diverse ecosystems, using published point cloud data from various scanning devices. Results indicate that algorithm accuracy is influenced by local factors like point cloud density, occlusion, vegetation, and tree structure. In the Mexican study area, the Nelder–Mead algorithm achieved the highest accuracy (R² = 0.98, RMSE = 1.59 cm, MAPE = 6.12%), closely followed by least squares (R² = 0.98, RMSE = 1.67 cm, MAPE = 6.42%), with different outcomes in other sites. These findings advance DBH estimation methods by highlighting the importance of tailored algorithm selection and environmental considerations, thereby contributing to more accurate and efficient forest management across various landscapes.

Research on imaging biomarkers for chronic subdural hematoma recurrence.

This study utilizes radiomics to explore imaging biomarkers for predicting the recurrence of chronic subdural hematoma (CSDH), aiming to improve the prediction of CSDH recurrence risk. Analyzing CT scans from 64 patients with CSDH, we extracted 107 radiomic features and employed recursive feature elimination (RFE) and the XGBoost algorithm for feature selection and model construction. The feature selection process identified six key imaging biomarkers closely associated with CSDH recurrence: flatness, surface area to volume ratio, energy, run entropy, small area emphasis, and maximum axial diameter. The selection of these imaging biomarkers was based on their significance in predicting CSDH recurrence, revealing deep connections between postoperative variables and recurrence. After feature selection, there was a significant improvement in model performance. The XGBoost model demonstrated the best classification performance, with the average accuracy improving from 46.82% (before feature selection) to 80.74% and the AUC value increasing from 0.5864 to 0.7998. These results prove that precise feature selection significantly enhances the model's predictive capability. This study not only reveals imaging biomarkers for CSDH recurrence but also provides valuable insights for future personalized treatment strategies.

Machine Learning in Wear Prediction

Abstract As modern devices and systems continue to advance, device wear remains a key factor in limiting their performance and lifetime, as well as environmental and health effects. Traditional approaches often rely on wear prediction based on physical models, but due to device complexity and uncertainty, these methods often fail to provide accurate predictions and accurate wear identification. Machine learning, as a data-driven approach based on its ability to discover patterns and correlations in complex systems, has enormous potential for monitoring and predicting device wear. Here, we review recent advances in applying machine learning for predicting the wear of mechanical components. Machine learning for wear prediction shows significant potential in optimizing material selection, manufacturing processes, and equipment maintenance, ultimately enhancing productivity and resource efficiency. Successful implementation relies on careful data collection, standardized evaluation methods, and the selection of effective algorithms, with artificial neural networks (ANNs) frequently demonstrating notable success in predictive accuracy.

Unveiling the interspecies correlation and sensitivity factor analysis of rat and mouse acute oral toxicity of antimicrobial agents: first QSTR and QTTR Modeling report.

This study aims to identify toxic potential and environmental hazardousness of antimicrobials. In this regard, the available experimental toxicity data with rat and mouse acute oral toxicity have been gathered from ChemID Plus database (n=202) and subjected to data curation. Upon the data curation 51 and 68 compounds were left for the rat and mouse respectively for the modeling. The quantitative structure toxicity relationship (QSTR) and interspecies correlation analysis by quantitative toxicity-toxicity relationship (QTTR) modeling was approached in this study. The models were developed from 2D descriptors under OECD guidelines by using multiple linear regressions (MLR) with genetic algorithm (GA) for feature selection as a chemometric tool. The developed models were robust (Q 2 LOO =0.600-0.679) and predictive enough (Q 2 F n =0.626-0.958, CCC Ext =0.840-0.893). The leverage approach of applicability domain (ad) analysis assures the model's reliability. The antimicrobials without experimental toxicity values were classified as high, moderate and low toxic based on prediction and ad. The occurrence of the same classification from QSTR and QTTR models revealed the reliability of QTTR models.Finally, the applied "sensitivity factor analysis" typifies the sensitivity of chemicals toward each species. Overall, the first report will be helpful in the toxicity assessment of upcoming antimicrobials in rodents.

Incremental feature selection: Parallel approach with local neighborhood rough sets and composite entropy

Rough set theory is a powerful mathematical framework for managing uncertainty and is widely utilized in feature selection. However, traditional rough set-based feature selection algorithms encounter significant challenges, especially when processing large-scale incremental data and adapting to the dynamic nature of real-world scenarios, where both data volume and feature sets are continuously changing. To overcome these limitations, this study proposes an innovative algorithm that integrates local neighborhood rough sets with composite entropy to measure uncertainty in information systems more accurately. By incorporating decision distribution, composite entropy enhances the precision of uncertainty quantification, thereby improving the effectiveness of the algorithm in feature selection. To further improve performance in handling large-scale incremental data, matrix operations are employed in place of traditional set-based methods, allowing the algorithm to fully utilize modern hardware capabilities for accelerated processing. Additionally, parallel computing technology is integrated to further enhance computational speed. An incremental version of the algorithm is also introduced to better adapt to dynamic data environments, increasing its flexibility and practicality. Comprehensive experimental evaluations demonstrate that the proposed algorithm significantly surpasses existing methods in both effectiveness and efficiency.

Modified Metaheuristics Optimization for Cyberbullying Detection on Online Data Science Platform

Online harassment detection faces significant challenges due to its expansive reach and anonymity. Addressing this issue demands effective detection mechanisms capable of processing vast data streams and adapting to evolving online language. Leveraging advancements in artificial intelligence, we propose a novel approach grounded in natural language processing (NLP) and metaheuristic algorithms. Our methodology integrates term frequency-inverse document frequency (TF-IDF) encoding and the AdaBoost algorithm for classification. To tackle the NP-hard problem of hyperparameter selection, we introduce a modified crayfish optimization algorithm (COA), termed GI-COA. This paper represents a pioneering effort in utilizing metaheuristic algorithms for hyperparameter selection in harassment detection models. Through experimentation, we demonstrate the efficacy of our approach in fostering a safer online environment. The best performing optimize models demonstrate and accuracy exceeding 77%.

Innovative Solutions for IK: PROA and Clonal Selection Algorithms Unveiled

Calculating joint angles for sequential manipulators consists of studying the correlation between Cartesian and joint variables. The problem-solving technique encounters two main hurdles described as direct and inverse kinematics. Matrix multiplications usually simplify the direct kinematic problem. However, inverse kinematic problems are harder as they require solving many nonlinear equations and eliminating variables a lot. In our work, we introduce two new methods of handling the complicated inverse kinematic problem for robotic manipulator arms; Poor and Rich Optimization Algorithm and Clonal Selection Algorithm (CSA). These advanced techniques enhance greatly the estimation of various joints in the arm which makes the solution more precise and efficient. To demonstrate the effectiveness, robustness, and potential benefits of these approaches for complicated kinematic problems we present extensive simulation results thereby enabling better performance of robots.

Feature-weighted Random Forest with Boruta for Fault Diagnosis of Satellite Attitude Control Systems

The performance of random forest (RF) based satellite attitude control system (ACS) fault diagnosis methods is limited by uninformative features in high-dimensional data. To solve this problem, we proposed a feature-weighted random forest with Boruta (FWRFB) based fault diagnosis method is proposed for fault diagnosis of ACSs. Firstly, a Boruta feature selection algorithm is used to obtain a feature set and determine significant feature weights. Subsequently, a novel feature-weighted random forest (FWRF) algorithm is designed, which utilizes feature-weighted random sampling instead of simple random sampling to generate feature subsets in the RF. The FWRFB effectively utilizes the feature information while mitigating noise interference. Finally, a FWRFB-based diagnostic module is developed for online fault diagnosis of ACSs. The effectiveness of the proposed method is verified by the ACS data from a semi-physical simulation platform.

The Efficiency Assessment of the Blockchain Networks Adaptive Algorithm as Part of a Multi-Consensus System on Communication Networks

The relevance of the approaches and solutions proposed in the work is due to the desire for distributed computing and decentralization of system modules using blockchain technology in order to increase the autonomy, security and independence of system components. The implementation of blockchain technology for decentralization is hampered by the lack of flexibility in terms of the algorithm for making a single decision in the asynchronous system ‒ consensus, which affects the amount of generated network traffic and the requirements for the hardware component. Due to the changing nature of the transmitted traffic, the load on the communication channel, the time of day of traffic transmission, the equipment, and the network protocols used, the development of a single universal consensus algorithm is not possible, since it depends on a very wide range of variable and specific parameters characteristic of different tasks. The introduction of adaptation mechanisms to current network conditions and a change in the consensus algorithm without losing information and with a satisfactory level of delays would provide sufficient flexibility for further implementation in existing telecommunication systems. The purpose of this paper is to evaluate the effectiveness of the proposed adaptive algorithm for choosing a consensus for blockchain networks.The essence of the presented algorithm is to change the consensus algorithm on a section of the blockchain network upon reaching certain network conditions, which allows regulating the amount of generated load on the communication network to reduce the loss of transaction blocks and the subsequent delay in their processing. The proposed efficiency assessment model is based on mathematical modeling methods, differential equation analysis, queueing theory and network graphs. The analysis of the results showed the efficiency of the proposed model when comparing the results of the analytical calculation and the experiment. The scientific novelty of the proposed approach is to developing an adaptive consensus selection algorithm, as opposed to developing a universal consensus algorithm, and the efficiency assessment model of the proposed algorithm on the communication network, taking into account a number of parameters characterizing the devices and the section of the communication network.The theoretical significance is in the universality of the proposed efficiency assessment model for calculating the synchronization speed of all nodes of the blockchain network with specified network parameters.The practical significance of the proposed algorithm and efficiency assessment method lies in the formation of new approaches and opportunities for integrating blockchain technology into modern communication networks, abstracting from the problem of consensus selection in changing conditions of the communication network section.

ML-Based Stroke Detection Model using Different Feature Selection Algorithms

ML-Based Stroke Detection Model using Different Feature Selection Algorithms

Authenticity markers of cultivated blueberries (Vaccinium sp.) and European wild blueberry (V. myrtillus) assessed by hyperspectral imaging and machine learning algorithms

The present study was undertaken to tackle food fraud in the food chain by developing a novel panel of analytical fingerprints to distinguish the fruit of bilberry (Vaccinium myrtillus), a wild European blueberry grown in Finland, from their commercial cultivated counterparts based on V. corymbosum or other originally American Vaccinium species. The analytical fingerprints were derived using hyperspectral imaging (HSI). The cultivated domestic blueberry samples from Finland (N = 188), those imported (N = 338), and domestic Finnish wild bilberry fruit (N = 247) were imaged using Specim IQ and FX17 HSI cameras. The fruit HSI data were then classified using seven machine learning model types. The supervised evolutionary feature selection algorithm was used to recognize the most separating subset of wavelengths (nm predictors, colors) between the fruit class labels, which were 1) wild bilberry fruit vs. cultivated blueberry fruit and 2) domestic cultivated blueberry fruit vs. imported cultivated blueberry fruit. Moreover, we ran 190,822 individual models and 54,137 predictor combinations to determine whether subsets or all wavelengths better distinguished fruit class labels. Overall, the best model type, the rbf kernel support vector machine (rbf-SVM), showed excellent prediction performance when classifying wild bilberries vs. cultivated blueberries with HSI data obtained using both camera types (4.1% and 3.2% holdout set errors). Also the rbf-SVM performed well when classifying domestic cultivated blueberries vs. those imported with HSI data obtained using an IQ camera (2.3% holdout set error). Our results showed that hyperspectral imaging could predict food fraud attempts concerning the Vaccinium fruit of different origin and species.

Evaluating Feature Impact Prior to Phylogenetic Analysis Using Machine Learning Techniques

The purpose of this paper is to describe a feature selection algorithm and its application to enhance the accuracy of the reconstruction of phylogenetic trees by improving the efficiency of tree construction. Applying machine learning models for Arabic and Aramaic scripts, such as deep neural networks (DNNs), support vector machines (SVMs), and random forests (RFs), each model was used to compare the phylogenies. The methodology was applied to a dataset containing Arabic and Aramaic scripts, demonstrating its relevance in a range of phylogenetic analyses. The results emphasize that feature selection by DNNs, their essential role, outperforms other models in terms of area under the curve (AUC) and equal error rate (EER) across various datasets and fold sizes. Furthermore, both SVM and RF models are valuable for understanding the strengths and limitations of these approaches in the context of phylogenetic analysis This method not only simplifies the tree structures but also enhances their Consistency Index values. Therefore, they offer a robust framework for evolutionary studies. The findings highlight the application of machine learning in phylogenetics, suggesting a path toward accurate and efficient evolutionary analyses and enabling a deeper understanding of evolutionary relationships.

Enhancing the global and local robustness of networks: A network motif-based approach

In the real world, both natural and artificial networks, may experience degradation or failure due to faults or external perturbations, which may negatively impact people's lives. Therefore, optimizing network robustness to maintain functionality under such conditions is a crucial research area. With the deepening of network robustness research, more and more studies have found that the local robustness of networks is related to network motifs. Considering the optimization of the robustness based on the global network properties (global robustness) and local robustness of the network, this paper proposes a motif-based edge rewiring algorithm (MBER), which includes the Edge Selection Algorithm, Edge Rewiring Algorithm, Simplified Calculation Algorithm for the Number of Major Network Motifs and Adjusted Nondominated Sorting Algorithm. We optimize four synthetic networks and four real-world networks using MBER and four other optimization algorithms, respectively. The results demonstrate that the MBER algorithm is more effective in enhancing the global and local robustness of networks. Additionally, we analyse the time complexity of MBER and four other optimization algorithms, revealing that the MBER algorithm exhibits the highest time complexity due to its consideration of local robustness. This paper can provide a reference for enhancing the robustness of real-world networks more comprehensively and enriches the research on network robustness enhancement.

Machine learning-based optimization of photogrammetric JRC accuracy

To improve the accuracy of photogrammetric joint roughness coefficient (JRC) estimation, this study proposes two optimization models based on ground sample distance (GSD), point density, and the root mean square error (RMSE) of checkpoints. First, an algorithm that automatically generates spatial positions for equipment based on the convergence strategy was developed, using principles of Structure from Motion and Multi-View Stereo (SfM-MVS) and the shooting parameter selection algorithm (SPSA). Second, a portable positioning plate containing ground control points and checkpoints was designed based on optical principles, and a moving camera capture strategy guided by SPSA was proposed. Combining SPSA, portable positioning plate, and moving camera capture strategy, a photogrammetric experiment for small-scale rock samples in the field was conducted, collecting 48 datasets with different shooting parameters. Subsequently, a dataset incorporating GSD, point density, RMSE, and three JRC estimation metrics was established, revealing their correlations and sensitivities. Using seven machine learning algorithms, optimization models for photogrammetric JRC accuracy were developed, with Linear Multidimensional Regression and Gaussian Process Regression models improving JRC accuracy by an average of 85.73%. Finally, the applicability and limitations of the newly proposed method were further discussed.

The study of Alzheimer's disease risk diagnosis based on natural killer cell marker genes in the multi-omics data.

Alzheimer's disease (AD) is a common neurodegenerative disorder, currently lacking effective early diagnostic methods. However, natural killer (NK) cells may play a potential role in AD pathogenesis. This study aims to identify AD-related feature genes from NK cell markers to construct a diagnostic model and explore their potential biological mechanisms in AD. Single-cell RNA sequencing data was used to identify NK cell markers. A novel feature selection algorithm, adaptive dynamic graph convolutional network (ADGCN), was proposed to extract AD-related feature genes and construct a diagnostic model. Differential, correlation and enrichment analyses were performed to understand the biological mechanisms of these genes. Immune infiltration analysis compared the immune microenvironment between AD and controls. Two regulatory networks explored interactions between feature genes, transcription factors and microRNAs. The association between SNPs and feature genes' expression was examined through expression quantitative trait loci analysis. Differential CpG sites were identified to analyze their association with the NK cell markers' expression. We developed an optimal diagnostic model (ADGCN-XGBoost) with 17 feature genes, demonstrating high diagnostic effectiveness across datasets. These genes were primarily related to macromolecule biosynthesis, cytoplasmic translation biological processes and ribosome pathway, and potentially modulated immune infiltration of AD patients. We predicted 27 target miRNAs and 21 transcription factors influencing these genes. Multimodal analysis identified 57 significant SNP-gene associations and seven CpG-gene pairs. This study proposed a novel feature selection algorithm and developed a diagnostic model based on 17 feature genes, providing new potential biomarkers for AD diagnosis.

L2T-DFM: Learning to Teach with Dynamic Fused Metric

The loss function plays a crucial role in the construction of machine learning algorithms. Employing a teacher model to set loss functions dynamically for student models has attracted attention. In existing works, (1) the characterization of the dynamic loss suffers from some inherent limitations, ie, the computational cost of loss networks and the restricted similarity measurement handcrafted loss functions; and (2) the states of the student model are provided to the teacher model directly without integration, causing the teacher model to underperform when trained on insufficient amounts of data. To alleviate the above-mentioned issues, in this paper, we select and weigh a set of similarity metrics by a confidence-based selection algorithm and a temporal teacher model to enhance the dynamic loss functions. Subsequently, to integrate the states of the student model, we employ statistics to quantify the information loss of the student model. Extensive experiments demonstrate that our approach can enhance student learning and improve the performance of various deep models on real-world tasks, including classification, object detection, and semantic segmentation scenarios.

Proposed clinical algorithm for hematinic bhasmas selection for Ayurvedic pediatric care

Ayurveda has unique and relevant methods in nosology, symptomatology, and drug selection. These methods need a novel and effective way of presentation for convenient comprehension and implementation. ‘Clinical algorithms’ is one such way, wherein a large amount of data is simplified, conceptual intricacies abstracted, and clinical application made easier. This article uses a modified version of the Horabin and Lewis algorithm to construct a clinical algorithm for Bhasma selection in the management of Pandu (anemia). The textual descriptions regarding the pathology and clinical presentations of Pandu have been compiled, and broadly classified, and the Bhasmas indication in suit each set of disease presentation has been specified. The algorithm is validated and optimized at single centre, while multicentre implementations and post-hoc modifications are warranted.

A comparative study of various recommendation algorithms based on E-commerce big data

With the rapid development of the Internet and the concomitant exponential growth of information, we have entered an era characterized by information overload. The abundance of data has rendered it increasingly arduous for users to pinpoint specific information they require. However, various forms of recommendation algorithms proffer solutions to this challenge. These algorithms predict items or products that may pique users’ interest based on their historical behavior, preferences, and interests. As one of the current hot research fields, recommendation algorithms are extensively employed across E-commerce platforms, movie streaming services, and various other contexts to cater to the diverse needs of users. In this context, a multi-recommendation algorithms comparison platform is proposed, which includes a two-fold model: online evaluation and offline evaluation. Taking the data set of the Chinese Amazon online shopping mall as the experimental data, item-based collaborative filtering (Item-CF) algorithm, content-based (TF-IDF) algorithm, item2vec model, alternating least squares (ALS) algorithm and neural network algorithm are evaluated in the offline model. In the real-time recommendation part, model-based algorithm is used to achieve the users’ rating mechanism. And the metrics used for evaluation include: precision, recall, accuracy and performance. The experimental results show that the average performance of hybrid algorithms such as ALS algorithm and neural network algorithm is higher than that of other traditional algorithms, and the real-time recommendation system achieves the purpose of improving recommendation speed. By integrating various recommender algorithms into the multi-recommendation algorithms comparison platform, this platform automatically computes and presents various performance indicators based on the user-provided dataset. It aids E-commerce platforms in making informed decisions regarding algorithm selection.