Optimal Selection Algorithm Research Articles

Transfer function adaptation for effective feature selection with the side-blotched lizard algorithm

AbstractFeature selection is a crucial preprocessing step in data mining and machine learning, enhancing model performance and computational efficiency. This paper investigates the effectiveness of the Side-Blotched Lizard Optimization Algorithm (SBLA) for feature selection by developing six novel variants: Sbla-s1, Sbla-s2, Sbla-s3, Sbla-v1, Sbla-v2, and Sbla-v3, each employing distinct S-shaped or V-shaped transfer functions to convert the continuous search space to a binary format. These variants were rigorously evaluated on nineteen benchmark datasets from the UCI repository, comparing their performance based on average classification accuracy, average number of selected features, and average fitness value. The results demonstrated the superiority of Sbla-s3, achieving an average classification accuracy of 92.8% across all datasets, a mean number of selected features of 20, and an average fitness value of 0.08. Furthermore, Sbla-s3 consistently outperformed six other state-of-the-art metaheuristic algorithms, achieving the highest average accuracy on sixteen out of nineteen datasets. These findings establish Sbla-s3 as a promising and effective approach for feature selection, capable of identifying relevant features while maintaining high classification accuracy, potentially leading to improved model performance in various machine learning applications.

Path Optimization of Two-Posture Manipulator of Apple Packing Robots

Automated packing is urgently needed in apple production. This paper proposes an improved genetic algorithm fused with an optimal parameter selection algorithm to optimize the two-posture manipulator working path of packing robots. First, the structure and working principle of the packing robot were designed. Second, the kinematics and packing paths of the two-posture manipulator were analyzed. Finally, the path optimization method for the two-posture manipulator was introduced. The method was based on the improved genetic algorithm by using a two-level coding and region crossover operator. The parameter values can be automatically determined by the optimal parameter selection algorithm. Ten repeated comparative tests show that the total packing time is 23.86 s under the working conditions of four grasping points and fourteen placing points. The optimal performance of the proposed algorithm is better than that of the traditional genetic algorithm, and the average optimization amplitudes are 14.63%, 15.42%, 16.24%, and 13.82% for 9-groove, 12-groove, 14-groove, and 16-groove trays, respectively. The proposed algorithm can effectively prevent the premature convergence problem of the traditional genetic algorithm and the optimization process instability problem, improve the range of optimization, and reduce the manipulator working time during packing.

An efficient water quality index forecasting and categorization using optimized Deep Capsule Crystal Edge Graph neural network.

The world's freshwater supply, predominantly sourced from rivers, faces significant contamination from various economic activities, confirming that the quality of river water is critical for public health, environmental sustainability, and effective pollution control. This research addresses the urgent need for accurate and reliable water quality monitoring by introducing a novel method for estimating the water quality index (WQI). The proposed approach combines cutting-edge optimization techniques with Deep Capsule Crystal Edge Graph neural networks, marking a significant advancement in the field. The innovation lies in the integration of a Hybrid Crested Porcupine Genghis Khan Shark Optimization Algorithm for precise feature selection, ensuring that the most relevant indicators of water quality (WQ) are utilized. Furthermore, the use of the Greylag Goose Optimization Algorithm to fine-tune the neural network's weight parameters enhances the model's predictive accuracy. This dual optimization framework significantly improves WQI prediction, achieving a remarkable mean squared error (MSE) of 6.7 and an accuracy of 99%. By providing a robust and highly accurate method for WQ assessment, this research offers a powerful tool for environmental authorities to proactively manage river WQ, prevent pollution, and evaluate the success of restoration efforts. PRACTITIONER POINTS: Novel method combines optimization and Deep Capsule Crystal Edge Graph for WQI estimation. Preprocessing includes data cleanup and feature selection using advanced algorithms. Deep Capsule Crystal Edge Graph neural network predicts WQI with high accuracy. Greylag Goose Optimization fine-tunes network parameters for precise forecasts. Proposed method achieves low MSE of 6.7 and high accuracy of 99%.

Comparative analysis of selected optimization algorithms for mobile agents’ migration pattern

Comparative analysis of selected optimization algorithms for mobile agents’ migration pattern

A Novel Hybrid Intrusion Detection Framework Leveraging Machine Learning and Flower Pollination Optimization

The exponential growth in technologies such as cloud computing, smart devices, virtualization, and the Internet of Things (IoT) has generated over four hundred zettabytes of network traffic data annually. This surge necessitates robust cybersecurity strategies to protect information from intrusions, which can result in significant financial losses. Reducing security risks requires the use of data analytics and machine learning to derive insights and make informed decisions based on network data. This study introduces the Flower Pollination Optimization (FPO) algorithm for feature selection to enhance the performance of several classifiers on the UNSW-NB15 dataset. We evaluated four classifiers: Linear Discriminant Analysis (LDA), Multi-Layer Perceptron (MLP), Quadratic Discriminant Analysis (QDA), and K-Nearest Neighbors (KNN) in two scenarios: without feature selection and with FPO-based feature selection. The results demonstrate significant improvements in classifier performance with FPO, with QDA achieving the highest accuracy of 99.16%. Comparative analysis with recent studies highlights the superior performance of our approach, setting a new benchmark in intrusion detection. This research underscores the essential role of effective feature selection in improving the accuracy and reliability of Intrusion Detection Systems (IDS), particularly in IoT environments.

Augmented electric eel foraging optimization algorithm for feature selection with high-dimensional biological and medical diagnosis

Augmented electric eel foraging optimization algorithm for feature selection with high-dimensional biological and medical diagnosis

Enhancing deep learning-based slope stability classification using a novel metaheuristic optimization algorithm for feature selection

The evaluation of slope stability is of crucial importance in geotechnical engineering and has significant implications for infrastructure safety, natural hazard mitigation, and environmental protection. This study aimed to identify the most influential factors affecting slope stability and evaluate the performance of various machine learning models for classifying slope stability. Through correlation analysis and feature importance evaluation using a random forest regressor, cohesion, unit weight, slope height, and friction angle were identified as the most critical parameters influencing slope stability. This research assessed the effectiveness of machine learning techniques combined with modern feature selection algorithms and conventional feature analysis methods. The performance of deep learning models, including recurrent neural networks (RNNs), long short-term memory (LSTM) networks, and generative adversarial networks (GANs), in slope stability classification was evaluated. The GAN model demonstrated superior performance, achieving the highest overall accuracy of 0.913 and the highest area under the ROC curve (AUC) of 0.9285. Integration of the binary bGGO technique for feature selection with the GAN model led to significant improvements in classification performance, with the bGGO-GAN model showing enhanced sensitivity, positive predictive value, negative predictive value, and F1 score compared to the classical GAN model. The bGGO-GAN model achieved 95% accuracy on a substantial dataset of 627 samples, demonstrating competitive performance against other models in the literature while offering strong generalizability. This study highlights the potential of advanced machine learning techniques and feature selection methods for improving slope stability classification and provides valuable insights for geotechnical engineering applications.

PDSMV3-DCRNN: A novel ensemble deep learning framework for enhancing phishing detection and URL extraction

Phishing is a cyber-attack that exploits victims' technical ignorance or naivety and commonly involves a Uniform Resources Locator (URL). As a result, it is beneficial to examine URLs before accessing them to spot a phishing assault. Several algorithms based on machine learning have been presented to detect phishing attempts. However, these approaches often suffer from lower performance outcomes, such as lower accuracy, longer response times, and higher false positive rates. Furthermore, many existing methods rely heavily on predefined feature sets, which may limit their adaptability and robustness. In contrast, our proposed method leverages a more dynamic feature selection process, which includes the Conditional Wasserstein Generative Adversarial Network (CWGAN) for addressing data imbalance and the Binary Grey Goose Optimization Algorithm (BGGOA) for optimal feature selection. This dynamic approach enhances the model's ability to adapt to varying data characteristics, improving detection performance. The proposed solution is divided into two stages: pre-deployment and deployment. During the pre-deployment stage, the dataset is preprocessed, including data transformation, handling irrelevant and redundant data, and ensuring data balancing. Minority samples are increased using CWGAN to avoid class imbalance. Features are then selected using BGGOA, resulting in a feature-reduced dataset used for training and testing ensemble deep learning classifiers, specifically the Novel Pyramid Depth-wise Separable-MobileNetV3 (PyDS-MV3) and Deformable Convolutional Residual Neural Network (DCRNN), termed PDSMV3-DCRNN. During the deployment phase, the Boosted ConvNeXt approach extracts URL features fed into the trained classifier to predict "phishing" or "benign". According to experimental findings, the proposed solution outperforms all other tested approaches, displaying a faster training time of 0.11 s and achieving an optimal accuracy of 99.21%.

A holistic approach to software fault prediction with dynamic classification

Software Fault Prediction is a critical domain in machine learning aimed at pre-emptively identifying and mitigating software faults. This study addresses challenges related to imbalanced datasets and feature selection, significantly enhancing the effectiveness of fault prediction models. We mitigate class imbalance in the Unified Dataset using the Random-Over Sampling technique, resulting in superior accuracy for minority-class predictions. Additionally, we employ the innovative Ant-Colony Optimization algorithm (ACO) for feature selection, extracting pertinent features to amplify model performance. Recognizing the limitations of individual machine learning models, we introduce the Dynamic Classifier, a ground-breaking ensemble that combines predictions from multiple algorithms, elevating fault prediction precision. Model parameters are fine-tuned using the Grid-Search Method, achieving an accuracy of 94.129% and superior overall performance compared to random forest, decision tree and other standard machine learning algorithms. The core contribution of this study lies in the comparative analysis, pitting our Dynamic Classifier against Standard Algorithms using diverse performance metrics. The results unequivocally establish the Dynamic Classifier as a frontrunner, highlighting its prowess in fault prediction. In conclusion, this research introduces a comprehensive and innovative approach to software fault prediction. It pioneers the resolution of class imbalance, employs cutting-edge feature selection, and introduces dynamic ensemble classifiers. The proposed methodology, showcasing a significant advancement in performance over existing methods, illuminates the path toward developing more accurate and efficient fault prediction models.

Application of LSTM neural network in the research of cyclical industries: taking the automotive industry as an illustrative case

Anticipating future developmental trends within an industry stands as one of the paramount responsibilities for industry researchers. Nevertheless, owing to the intricate and subjective nature inherent in industry research, coupled with researchers usually having to rely on their own subjective judgments when making predictions, the forecasting outcomes frequently prove unsatisfactory. In order to address this issue, this study introduces deep learning technology into the industry research field and employs Long & Short-Term Memory (LSTM) networks to forecast a typical cyclical industry - the automotive industry. In the specific experiment, Adam optimization algorithm is employed to enhance model training speed, followed by utilization of the grid search algorithm for optimal parameter selection. Subsequently, the obtained optimal model is utilized for LSTM multivariate sequence prediction in order to forecast the future development trend of the automotive industry over the next six months. The ultimate outcome demonstrates that the LSTM model accurately anticipated the forthcoming U-shaped rebound trend in the automotive industry, albeit with some limitations in predicting precise numerical values and timing. Nevertheless, it aligns closely with the actual developmental trajectory. This investigation represents a constructive application of deep learning technology in industrial research, and its final findings hold significant implications for future industry research endeavors.

Chronological wild geese optimization algorithm for cluster head selection and routing in wireless sensor network

Chronological wild geese optimization algorithm for cluster head selection and routing in wireless sensor network

MOHCOA: Multi-objective hermit crab optimization algorithm for feature selection in sentiment analysis of Covid-19 Twitter datasets

MOHCOA: Multi-objective hermit crab optimization algorithm for feature selection in sentiment analysis of Covid-19 Twitter datasets

Enhancing anomaly detection: A comprehensive approach with MTBO feature selection and TVETBO[sbnd]Optimized Quad-LSTM classification

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.

Hybrid Predictive Machine Learning Model for the Prediction of Immunodominant Peptides of Respiratory Syncytial Virus.

Respiratory syncytial virus (RSV) is a common respiratory pathogen that infects the human lungs and respiratory tract, often causing symptoms similar to the common cold. Vaccination is the most effective strategy for managing viral outbreaks. Currently, extensive efforts are focused on developing a vaccine for RSV. Traditional vaccine design typically involves using an attenuated form of the pathogen to elicit an immune response. In contrast, peptide-based vaccines (PBVs) aim to identify and chemically synthesize specific immunodominant peptides (IPs), known as T-cell epitopes (TCEs), to induce a targeted immune response. Despite their potential for enhancing vaccine safety and immunogenicity, PBVs have received comparatively less attention. Identifying IPs for PBV design through conventional wet-lab experiments is challenging, costly, and time-consuming. Machine learning (ML) techniques offer a promising alternative, accurately predicting TCEs and significantly reducing the time and cost of vaccine development. This study proposes the development and evaluation of eight hybrid ML predictive models created through the permutations and combinations of two classification methods, two feature weighting techniques, and two feature selection algorithms, all aimed at predicting the TCEs of RSV. The models were trained using the experimentally determined TCEs and non-TCE sequences acquired from the Bacterial and Viral Bioinformatics Resource Center (BV-BRC) repository. The hybrid model composed of the XGBoost (XGB) classifier, chi-squared (ChST) weighting technique, and backward search (BST) as the optimal feature selection algorithm (ChST-BST-XGB) was identified as the best model, achieving an accuracy, sensitivity, specificity, F1 score, AUC, precision, and MCC of 97.10%, 0.98, 0.97, 0.98, 0.99, 0.99, and 0.96, respectively. Additionally, K-fold cross-validation (KFCV) was performed to ensure the model's reliability and an average accuracy of 97.21% was recorded for the ChST-BST-XGB model. The results indicate that the hybrid XGBoost model consistently outperforms other hybrid approaches. The epitopes predicted by the proposed model may serve as promising vaccine candidates for RSV, subject to in vitro and in vivo scientific assessments. This model can assist the scientific community in expediting the screening of active TCE candidates for RSV, ultimately saving time and resources in vaccine development.

Enhanced Filtrate Feature Selection Algorithm for Feature Subset Generation

Objectives: In the bioinformatics field feature selection plays a vital role in selecting relevant features for making better decisions and assessment of disease diagnosis. Brain Tumour (BT) is the second leading disease in the world. Most of the BT detection techniques are based on Magnetic Resonance (MR) images. Methods: In this paper, medical reports are used in the detection of BT to increase the surveillance of patients. To improve the accuracy of predictive models, a new adaptive technique called Enhanced Filtrate Feature Selection (EFFS) algorithm for optimal feature selection is proposed. Initially, the EFFS algorithm finds the dependency of each attribute and feature score by using Mutual Information Gain, Chi-Square, Correlation, and Fishore score filter methods. Afterward, the occurrence rate of each top-ranked attribute is filtered by applying threshold value and obtaining the optimal feature by using the Pareto principle. Findings: The performance of the selected optimal features is evaluated by time complexity, number of features selected, and accuracy. The efficiency of the proposed algorithm is measured and analyzed in a high-quality optimal subset based on a Random Forest classifier integrated with the ranking of attributes. The EFFS algorithm selects 39 out of 46 significant and relevant features with minimum selection time and shows 99.31 % of accuracy for BT, 29 features with 99.47% of accuracy for Breast Cancer, 15 features with 94.61% of accuracy for Lung Cancer, 15 features with 98.84% of accuracy for Diabetes and 43 features with 90% of accuracy for Covid-19 dataset. Novelty: To decrease the processing time and improve the performance of a model feature selection process will be done at the initial stages for the betterment of the classification task. Thus, the proposed EFFS algorithm is applied to different datasets based on medical reports and EFFS outperforms with greater performance measurements and time. The appropriate feature selection techniques help to diagnose diseases in the prior phase and increase the survival of human beings. Keywords: Bioinformatics, Brain Tumour, Chi­Square, Correlation, EFFS, Feature Selection, Fishore Score, Information Gain, Optimal Features, Random Forest

Research on Multi-Source Data Fusion and Satellite Selection Algorithm Optimization in Tightly Coupled GNSS/INS Navigation Systems

With the increase in the number of Global Navigation Satellite System (GNSS) satellites and their operating frequencies, richer observation data are provided for the tightly coupled Global Navigation Satellite System/Inertial Navigation System (GNSS/INS). In this paper, we propose an efficient and robust combined navigation scheme to address the key issues of system accuracy, robustness, and computational efficiency. The tightly combined system fuses multi-source data such as the pseudo-range, the pseudo-range rate, and dual-antenna observations from the GNSS and the horizontal attitude angle from the vertical gyro (VG) in order to realize robust navigation in a sparse satellite observation environment. In addition, to cope with the high computational load faced by the system when the satellite observation conditions are good, we propose a weighted quasi-optimal satellite selection algorithm that reduces the computational burden of the navigation system by screening the observable satellites while ensuring the accuracy of the observation data. Finally, we comprehensively evaluate the proposed system through simulation experiments. The results show that, compared with the loosely coupled navigation system, our system has a significant improvement in state estimation accuracy and still provides reliable attitude estimation in regions with poor satellite observation conditions. In addition, in comparison experiments with the optimal satellite selection algorithm, our proposed satellite selection algorithm demonstrates greater advantages in terms of computational efficiency and engineering practicability.

Research on the algorithm for optimal selection of detection modes for rail crack detection

In the application of ultrasonic guided wave testing for rail crack detection, it is necessary to select a guided wave mode that is more sensitive to cracks as the detection mode. However, ultrasonic guided waves have multi-mode and dispersive characteristics. In order to extract mode information from complex signals, this paper proposes an optimal detection mode selection method based on the sensitivity of guided wave modes to cracks. This method is different from the traditional method of determining mode types by calculating the mode velocity through the arrival time of wave packets in the time domain signal. Based on the dispersion characteristics and mode features of guided wave modes, this paper establishes a crack sensitivity evaluation index. In a wide frequency band and among numerous modes, the guided wave modes suitable for detecting cracks in different regions of the full cross-section of rails are accurately selected. Experimental results show that the guided wave modes selected by the mode selection method proposed in this paper, based on the crack area energy and crack reflection intensity evaluation indexes, can accurately identify rail cracks, laying a foundation for the research on rail crack detection and localization methods.

Social coevolution and Sine chaotic opposition learning Chimp Optimization Algorithm for feature selection

Feature selection is a hot problem in machine learning. Swarm intelligence algorithms play an essential role in feature selection due to their excellent optimisation ability. The Chimp Optimisation Algorithm (CHoA) is a new type of swarm intelligence algorithm. It has quickly won widespread attention in the academic community due to its fast convergence speed and easy implementation. However, CHoA has specific challenges in balancing local and global search, limiting its optimisation accuracy and leading to premature convergence, thus affecting the algorithm’s performance on feature selection tasks. This study proposes Social coevolution and Sine chaotic opposition learning Chimp Optimization Algorithm (SOSCHoA). SOSCHoA enhances inter-population interaction through social coevolution, improving local search. Additionally, it introduces sine chaotic opposition learning to increase population diversity and prevent local optima. Extensive experiments on 12 high-dimensional classification datasets demonstrate that SOSCHoA outperforms existing algorithms in classification accuracy, convergence, and stability. Although SOSCHoA shows advantages in handling high-dimensional datasets, there is room for future research and optimization, particularly concerning feature dimensionality reduction.

Fuzzy Bipolar Hypersoft Sets: A Novel Approach for Decision-Making Applications

This article presents a pioneering mathematical model, fuzzy bipolar hypersoft (FBHS) sets, which combines the bipolarity of parameters with the fuzziness of data. Motivated by the need for a comprehensive framework capable of addressing uncertainty and variability in complex phenomena, our approach introduces a novel method for representing both the presence and absence of parameters through FBHS sets. By employing two mappings to estimate positive and negative fuzziness levels, we bridge the gap between bipolarity, fuzziness, and parameterization, allowing for more realistic simulations of multifaceted scenarios. Compared to existing models like bipolar fuzzy hypersoft (BFHS) sets, FBHS sets offer a more intuitive and user-friendly approach to modeling phenomena involving bipolarity, fuzziness, and parameterization. This advantage is underscored by a detailed comparison and a practical example illustrating FBHS sets’ superiority in modeling such phenomena. Additionally, this paper provides an in-depth exploration of fundamental FBHS set operations, highlighting their robustness and applicability in various contexts. Finally, we demonstrate the practical utility of FBHS sets in problem-solving and introduce an algorithm for optimal object selection based on available information sets, further emphasizing the advantages of our proposed framework.

ОЦЕНКА РЕЗУЛЬТАТОВ ПРИМЕНЕНИЯ АЛГОРИТМА ВЫБОРА ОПТИМАЛЬНОГО ХИРУРГИЧЕСКОГО ДОСТУПА К ЗАБРЮШИННОМУ ПРОСТРАНСТВУ У ПАЦИЕНТОВ С РАЗЛИЧНЫМИ ПАРАМЕТРАМИ КОНСТИТУЦИИ.

Relevance. Despite the rapid development and predominance of endovideosurgical techniques in the treatment of pathologies of organs and structures of the retroperitoneal space, the implementation of transperitoneal or retroperitoneal approaches for open surgical interventions remains a routine activity. Surgical treatment of various pathologies of retroperitoneal localization leads to the development of nonspecific life-threatening complications in 23.8% - 30% of clinical observations, and associated mortality - 7.2% - 11% of cases. Previously, our works presented the results of comparing the number of this type of complications when using laparotomy or retroperitoneal access, depending on the constitutional parameters of the patient. An assessment was made of the significance of the influence of constitutional parameters on the development of nonspecific life-threatening complications, on the basis of which an algorithm for choosing the optimal surgical access to the structures of the retroperitoneal space was developed [patent application No. 2024113445 dated May 17, 2024]. Purpose of the study. To evaluate the effectiveness of using an algorithm for selecting the optimal surgical approach in the surgical treatment of pathologies of organs and structures of retroperitoneal localization. Materials and methods. Comparative analysis of the results of surgical treatment of patients with various surgical pathologies of the retroperitoneal space. Group I (n = 167), where the choice of surgical approach was determined using the “optimal surgical approach selection algorithm.” Group II (n = 284), in which the choice of access to the structures of the retroperitoneal space was not unified and was chosen without taking into account the constitutional parameters of the patient. In the perioperative period, the duration of surgical intervention, the volume of intraoperative blood loss, the number of days of stay in the intensive care unit, the time of postoperative respiratory support, the duration of postoperative intestinal paresis and the number of postoperative bed days were assessed. Criteria assessed in the postoperative period: development of myocardial infarction, acute cardiovascular failure, ARDS with the development of respiratory failure, acute kidney injury; cases of development of ischemic colitis and small intestinal obstruction, requiring repeated interventions, as well as the phenomenon of multiple organ failure. Wound complications included failure of retroperitoneal and laparotomy wounds, including eventration. To calculate quantitative characteristics, the median (Me) and percentiles (Q0.25 - Q0.75) were determined. Calculation of statistical significance between groups was performed using the Mann-Whitney U test**, for comparison of qualitative indicators - the Chi-square test* in IBM SPSS Statistics 25 software. Results. In group I, compared with group II, there was a shorter surgical intervention time [140.8 vs 179.5] min, p = 0.031**, a smaller volume of intraoperative blood loss [280.4 vs 413.3] ml, p = 0.024* *; postoperative respiratory support [4.5 vs 8.5] hours, p = 0.041**; length of stay in the intensive care unit [1.8 vs 3.4] days, p = 0.021**; postoperative intestinal paresis [1.2 vs 4.8] days p = 0.024**; and duration of total postoperative hospital stay [9.1 vs 16.4] days p = 0.003**. The number of postoperative nonspecific life-threatening and wound complications in group I was 24 (14.4%), and in group II - 64 (22.5%) cases (p = 0.023*). The number of complications-related deaths in group I was 9 (5.4%); in group II - 32 (11.26%) cases (p = 0.037*). Conclusion. The use of an algorithm for selecting the optimal surgical approach for surgical treatment of pathologies of organs and structures of the retroperitoneal localization of the access leads to a reduction in the number of nonspecific life-threatening complications to 14.4%, and associated deaths to 5.4%.