Search Results (140)

State-level health resource systems need precise and timely prediction models, but they are plagued by the ongoing problem of deteriorating model performance because of constantly shifting data distributions (data drift). Predicting uncommon but important events like sickle cell crisis is a classification task where this problem is most noticeable. This paper presents the Evolving AI-Driven Ensemble Learning Framework, which blends novelty detection using the F1-score with sophisticated ensemble approaches (stacking XGBoost, Deep Neural Network, and Random Forest with a meta-learner). Complex, high-dimensional health data are handled using sophisticated feature engineering techniques, such as automated feature selection via evolutionary algorithms and meta-learning (MAML). We empirically assessed a reactive retraining technique that was improved by ensemble stacking and simulated real-time data drift. After five retraining cycles, the improved ensemble and feature engineering showed significant performance improvements over the initial model, achieving substantial improvements: F1-score improved from 0.1250 to 0.9734 (an absolute increase of 0.8484, representing a 678.7% relative improvement), recall from 0.0714 to 0.9767 (an absolute increase of 0.9053), and precision from 0.5000 to 0.9702 (an absolute increase of 0.4702). The framework maintained high specificity (0.9700) and demonstrated outstanding discriminative performance with an AUC-ROC of 0.9909 (an 8.5% improvement). The model’s strong predictive capacity was confirmed by improvements in the Matthews Correlation Coefficient from 0.1000 to 0.9467 (846.7% improvement) and Cohen’s Kappa from 0.0800 to 0.9467 (1083.3% improvement). Model transparency in pipeline development is now made possible by a fixed runtime issued in the SHAP explainability layer. The efficiency of the framework is empirically validated by this study, showing that automated feature engineering and optimized ensemble learning greatly increase model stability and preserve remarkable accuracy for minority classes in complicated data contexts. Full article

This paper introduces an integrated multi-objective evolutionary framework for synthesis of heterogeneous regression ensembles featuring localized, learner-specific feature selection. Rather than enforcing global feature spaces, the proposed paradigm simultaneously optimizes base estimator activation patterns, customized variable subsets tailored to each active learner, and continuous voting weights within a unified mixed-variable optimization process. The evolutionary pipeline minimizes two conflicting axes: predictive error, quantified via Root Mean Squared Error, and structural complexity, modeled as the average cardinality of selected features across active estimators. To prevent data leakage, the framework is validated under a rigorous nested cross-validation architecture using five real-world application benchmarks and comprehensively evaluated against 16 baseline configurations, including standalone learners, static voting ensembles, and isolated wrapper multi-objective feature selection pipelines. The empirical findings demonstrate that our joint evolved-weight variant achieves the dominant global predictive ranking across both non-parametric Wilcoxon and absolute mean trajectories. Concurrently, it maintains exceptional structural parsimony by yielding competitive dimensionality reductions, effectively balancing execution runtimes against Pareto-optimal generalization. Furthermore, a systematic ablation analysis isolates the continuous weighting mechanism as a pivotal driver for discovering significantly more compact ensemble topologies. Full article

Search-based software engineering (SBSE) tackles critical optimization problems in software engineering, including the next release problem (NRP) and feature selection problem (FSP). Traditional heuristic approaches and integer linear programming (ILP) methods work well for small- to medium-scale problems but face growing computational cost as instances scale up. We investigate quantum annealing (QA) as an optimization subroutine for multi-objective SBSE problems. We propose two QA-based algorithms tailored to different problem scales. For small-scale problems, we reformulate multi-objective optimization (MOO) as single-objective optimization (SOO) using penalty-based mappings for quantum processing. For large-scale problems that exceed current hardware capacity, we employ a decomposition strategy guided by maximum energy impact (MEI) that partitions the problem into smaller sub-QUBOs, integrating QA with a steepest-descent method for local search. Applied to NRP and FSP, our approaches are benchmarked against the heuristic NSGA-II, IBEA, and MOEA/D, as well as the ILP-based $ϵ$-constraint method. The experimental results reveal that while our methods produce fewer non-dominated solutions than $ϵ$-constraint, they achieve substantial reductions in execution time. Compared to the evolutionary baselines, our methods achieve competitive solution quality with lower runtime on the instances that they can encode. The penalty-based QUBO formulation fails to reach feasible regions on constraint-dense FSP instances, limiting the current applicability of the approach. QA is a promising but still hardware-limited component for multi-objective SBSE workflows, rather than a wholesale replacement for classical solvers. Full article

Wearable inertial sensing and markerless vision are increasingly integrated to enable objective assessment of locomotor and postural function for sports telerehabilitation, intelligent physiotherapy, and athlete performance monitoring. Before such multimodal systems can be translated to clinical practice, their fusion, optimization, and temporal modeling strategies require validation under controlled conditions with reliable ground truth. This study presents a unified multimodal framework that hierarchically integrates inertial measurement unit (IMU) signals and RGB visual information through kernelized representation learning, adaptive multimodal fusion, evolutionary feature optimization, and deep temporal classification. The IMU branch employs Kernelized Extreme Learning Machine (KELM) denoising, Kernelized Canonical Correlation Fusion (KCCF), entropy-guided adaptive windowing, and complementary time-series descriptors (MINIROCKET, TS-CHIEF, and r-STSF). Concurrently, the RGB branch combines anisotropic diffusion filtering, HRNet-based silhouette extraction, DensePose R-CNN, Mesh Graphormer, and Multi-Model Pose-Flow Fusion (MPFF) to learn robust visual representations. Both modalities are integrated through Weighted Canonical Feature Fusion (WCFF) and optimized using a Genetic Algorithm for feature selection and adaptive modality weighting before temporal modeling with cluster-based alignment, Gaussian Process Sequence Modeling, and DeepConvLSTM. As the selected benchmarks do not provide complete inertial recordings, the inertial modality is established according to the adopted experimental protocol to support multimodal fusion analysis. Under 5-fold subject-independent cross-validation, the framework achieves accuracies of 86.56 ± 0.31% on SoccerDiffusion and 88.04 ± 0.25% on HumanoidRobotPose. Although evaluated on humanoid robotic benchmarks, the proposed framework provides a methodological basis for future wearable-enabled clinical movement assessment, remote rehabilitation, and athlete monitoring, while validation on synchronized human inertial-visual datasets remains an important direction for future research. Full article

This paper makes a contribution to smart-grid cybersecurity by proposing an application of our approach, previously published in this journal, to design—from smart-grid data—transparent, interpretable, and accurate systems for detection and classification of cyber-attacks, natural-event-related disturbances, and regular operation of the smart grid. The collection of 15 open-source simulated smart-grid data sets provided by Mississippi State University, USA, in collaboration with Oak Ridge National Laboratories, USA, is used in our experiments. To address this problem, we use our knowledge-based data-mining/machine-learning approach which ultimately generates a set of fuzzy rule-based classifiers—each with a different trade-off between its accuracy and the interpretability of its knowledge base (both are the subjects of maximization in a multi-objective optimization process using evolutionary algorithms). The paper also contributes an extensive cross-validation-based experiment showing that while our approach is not as accurate as alternative and inherently accuracy-oriented “black boxes,” it surpasses them in terms of transparency and interpretability of the generated classification decisions, while ensuring acceptable accuracy of these decisions. Therefore, it can act as a second cybersecurity layer that uses transparent rules to help SCADA operators instantly verify and explain alerts triggered by accurate, fast “black-box” detectors. This paper also provides a contribution to a more general and important area of the automatic and effective selection of input variables (features) that are essential in a given decision-making problem (such as smart-grid contingency classification considered in this work). Full article

Background/Objectives: The precise identification of Alzheimer’s disease (AD) stages through clinical data is crucial for early diagnosis and suitable therapy. This classification remains troublesome due to overlap in cognitive profiles across different phases of illness progression. This study presents a comprehensive and advanced diagnostic system, termed FLAME, featuring an enhanced federated learning architecture for privacy-preserving multi-institutional implementation. It provides a systematic review of machine learning (ML) and deep learning (DL) models for the classification of five stages of Alzheimer’s disease (AD). The models include cognitively normal (CN), subjective memory complaints (SMC), early mild cognitive impairment (EMCI), late mild cognitive impairment (LMCI), and Alzheimer’s disease (AD). Methods: Sixteen traditional machine learning models and eleven deep learning architectures—including FT-Transformer and NODE—were evaluated using a structured clinical dataset comprising 362 features. A hybrid ensemble was created at the probability level by combining the two top-performing models, LightGBM and a five-layer DNN. The weights of this ensemble were automatically optimised using a Genetic Algorithm (GA) with Macro-F1 as the fitness criterion, confirmed stable across 30 independent runs ($w^{★}=0.5024\pm 0.0001$). A federated learning architecture was then established, deploying the DNN across non-IID clients while keeping LightGBM centralised. We examine four distinct aggregation algorithms: FedAvg, FedProx, FedNova, and SCAFFOLD. Results: Among all deep learning architectures, FT-Transformer achieved the highest standalone performance (accuracy = 0.7810, $\kappa$ = 0.7081). The five-layer deep neural network (DNN) was selected as the DL representative for the hybrid ensemble. LightGBM attained superior machine learning performance (accuracy = 0.8156, $\kappa$ = 0.7537), confirmed deterministic across 10 seeds. The LightGBM vs. XGBoost difference is not statistically significant (McNemar $p=0.4227$). The GA-optimised hybrid ensemble (w = 0.685) surpassed both individual baselines across all evaluation metrics. The FedNova hybrid design achieved superior overall performance in federated configurations, surpassing all centralised arrangements in accuracy (accuracy = 0.8213, $\kappa$ 0.7614). Conclusions: Evolutionary ensemble optimisation combined with federated learning provides a robust, scalable, and privacy-preserving solution for AD stage classification, offering a clinically viable framework for real-world multi-institutional decision-support systems. However, the AD class remains severely under-recalled across all configurations (F1 ≤ 0.21), identifying this as the primary open challenge for clinical translation. Full article

With the rapid growth of Chinese social media data, many language-driven analytical tasks, such as sentiment analysis and malicious account detection, are increasingly formulated as computationally expensive optimization problems, particularly in the context of hyperparameter tuning for deep learning models. Due to the intrinsic characteristics of Chinese text, including implicit word boundaries, strong context dependency, and high linguistic variability, the resulting feature representations are often high-dimensional, sparse, and heterogeneously distributed. From an optimization perspective, these properties induce highly irregular, non-smooth, and multimodal objective landscapes, posing significant challenges to conventional surrogate-assisted data-driven evolutionary algorithms (DDEAs). To address this problem, this paper proposes a Normal Selection-based data-driven evolutionary algorithm (NSEA) for improving surrogate-assisted optimization under complex conditions. Specifically, a Normal distribution-based selection strategy (NSS) is developed to enable probabilistic selection of surrogate models, balancing exploitation of high-performing models and exploration of alternative candidates, thereby alleviating premature convergence in multimodal search spaces. In addition, an exponential weighting ensemble (EWE) method is introduced to aggregate surrogate models based on their relative ranking performance, which enhances the stability and generalization capability of fitness approximation across different regions of the search space. Extensive experiments on benchmark functions demonstrate that the proposed NSEA consistently outperforms several state-of-the-art DDEAs in terms of optimization accuracy and robustness. Furthermore, a real-world application of cheating official account (COA) detection on Chinese social media is conducted, in which the hyperparameter optimization of a heterogeneous graph transformer (HGT) model is formulated as an EOP. The results further prove the effectiveness and practical applicability of the NSEA in complex data-driven scenarios. Overall, this study provides an effective optimization framework for handling EOPs with complex and multimodal characteristics and offers a feasible computational approach for tasks associated with large-scale Chinese textual data. Full article

As the rapid development of the industrial Internet of Things (IIoT) progresses, some data in the IIoT start to present the following characteristics: huge volume, high dimensions, distributed storage across multiple devices, and restricted data sharing due to privacy protection concerns. Such data presents a significant challenge to existing data processing methods. To this end, this work proposes an intelligent distributed-data processing method with privacy protection for IIoT (I2DPM). In this method, a federated feature integrator is first designed to capture the global feature subset of the distributed data under privacy protection. Based on the captured feature subset, a many-objective feature selection model is constructed by including the feature number, feature cost, cross-entropy, accuracy, and recall as the five objectives, where these five objectives represent the key factors influencing the feature selection performance. Then, an feedback-assisted information clustering many-objective evolutionary algorithm (MaOEA-IFC) is developed to solve the constructed model and thus obtain the optimal feature subsets, which fully utilizes the ideas of feedforward and feedback control. Finally, MaOEA-IFC is first compared with five state-of-the-art methods on two benchmark test suites to validate its ability to obtain reliable experimental results, and then our method is tested on eight datasets. Extensive results demonstrate that MaOEA-IFC is highly competitive, and our method can obtain the feature subsets with good comprehensive performance on the premise of protecting data privacy. In summary, this work provides a method for processing the data with the above characteristics in IIoT. Full article

High-dimensional small-sample data are widely encountered in medical diagnosis, bioinformatics, and industrial inspection, where traditional feature selection methods often suffer from premature convergence and local optima. To address these issues, this paper proposes a Hybrid Breeding-based Co-evolutionary Ant Colony Optimization method (HBACO) for feature selection. Inspired by the principle of hybrid breeding, in which individuals with distinct traits produce superior offspring through cross recombination, inheritance of desirable genes and continuous evolution, the proposed algorithm establishes a three-population collaborative framework. It consists of an ACO-based search population, an HRO-based evolutionary population and a cooperative feedback population that evolve iteratively together. Furthermore, we devise a heuristic strategy integrating correlation and genetic characteristics to help mine high-value feature subsets. Meanwhile, a collaborative pheromone updating mechanism is adopted to realize efficient knowledge sharing among populations. Experiments conducted on 13 high-dimensional datasets, including Colon and Lung, demonstrate that HBACO achieves superior classification accuracy, feature reduction performance, and convergence behavior compared with 10 representative algorithms. Specifically, HBACO improves the average classification accuracy by 3.9% and achieves an average feature dimensionality reduction rate of 91.4%. Statistical tests further confirm the significance of the proposed method. The results indicate that HBACO provides an effective and robust solution for high-dimensional feature selection problems. Full article

Background/Objectives: Typhoid fever remains a major public health challenge in many low-income countries, where overlapping clinical symptoms and the limited reliability of conventional diagnostic procedures hinder accurate diagnosis. This study aims to develop a reliable and efficient diagnostic framework that automates typhoid fever detection from clinical data while preserving patient privacy. Methods: To achieve this objective, we propose a hybrid framework combining genetic algorithm (GA)–based feature selection, a Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) deep learning classifier, and federated learning. The GA identifies the most informative clinical features, reducing redundancy and computational complexity. The selected features are then used to train a CNN–LSTM model in a federated learning setup using the Federated Averaging (FedAvg) algorithm, enabling collaborative model training across multiple clients without sharing raw patient data. Results: Experimental results show that the proposed framework achieves 92% accuracy, with a strong F1-score and satisfactory sensitivity. Compared to models trained on the full feature set, the proposed approach requires less memory and shorter training time, while maintaining balanced performance under class imbalance. Conclusions: These results demonstrate that integrating evolutionary feature selection, deep sequential learning, and federated training provides an effective and privacy-aware solution for multi-class typhoid fever diagnosis. The proposed framework is particularly suitable for clinical environments with limited data access and constrained resources. Full article

Metaheuristic algorithms, including evolutionary approaches, are vital for solving non-trivial and non-convex optimization problems. However, real-world engineering often involves high-dimensional, expensive problems that deteriorate performance due to the substantial amount of required fitness evaluations. To address this, a growing trend utilizes evolutionary algorithms assisted by surrogate models, which limit the computational burden by providing alternatives to expensive evaluations. Leveraging the exploration capabilities of the recently developed Slime Mould Algorithm—a metaheuristic with only one tuning parameter that ignores personal best information—this work develops its surrogate-assisted counterpart: the Surrogate-Assisted Slime Mould Algorithm (SASMA). This new approach features an original database management strategy and surrogate building mechanism. To confirm its effectiveness and versatility, SASMA is tested on benchmark mathematical functions for 30 and 100 dimensions, as well as a classical truss design problem, against several surrogate-assisted and metaheuristic algorithms. The proposed SASMA achieved statistically significant improvements in both case studies, outperforming the selected benchmark algorithms on most test functions. Full article

To address the high-dimensional design optimization of an adaptive cycle fan (ACF), this paper proposes a new multi-objective optimization (MOO) method based on explainable artificial intelligence (XAI)-driven feature selection. The proposed method integrates a neural network surrogate model, Shapley additive explanation (SHAP) analysis, and a genetic algorithm. By considering Pareto front quality, surrogate model accuracy, and optimization preference, a composite evaluation metric, Q, is defined to guide a bidirectional feature selection process based on SHAP analysis, thereby establishing a dynamic, closed-loop process of simultaneous feature selection and MOO. The results indicate that the proposed method significantly enhances global search capability, accurately identifying 66 optimal features from 119 initial features. A further comparison with results without forward selection confirms the necessity of dynamically adjusting the feature space during optimization. Under the same condition, the optimal design increases the core pressure ratio from 2.71 to 2.81 and core efficiency from 80.80% to 82.92%. The flow mechanism analysis reveals that the performance gains mainly result from the reconstruction of shock structures and the suppression of shock–boundary layer interactions and secondary flows. The XAI-enhanced surrogate-assisted evolutionary algorithm (SAEA) proposed in this paper provides a promising methodology for high-dimensional MOO of aeroengines and other complex systems. Full article

Cotton spider mites pose a significant threat to cotton production, while traditional manual investigation and blanket pesticide application are inefficient for precision pest management in large-scale cotton fields. To address this challenge, this study developed an integrated UAV multispectral remote sensing system for spider mite monitoring and precision spraying. Multispectral imagery was acquired from cotton fields in Shaya County, Xinjiang using UAV-mounted cameras, and vegetation indices including RDVI, MSAVI, SAVI, and OSAVI were selected through feature optimization. Comparative evaluation of three machine learning models (Logistic Regression, Random Forest, and Support Vector Machine) and two deep learning models (1D-CNN and MobileNetV2) was conducted. Considering classification performance and computational efficiency for real-time UAV deployment, Random Forest was identified as optimal, achieving 85.47% accuracy, an 85.24% F1-score, and an AUC of 0.912. The model generated centimeter-level spatial distribution maps for precise spray zone delineation. An improved NSGA-III multi-objective path optimization algorithm was proposed, incorporating PCA-based heuristic initialization, differential evolution operators, and co-evolutionary dual population strategies to optimize deadheading distance, energy consumption, operation time, turning frequency, and load balancing. Ablation study validated the effectiveness of each component, with the fully improved algorithm reducing IGD by 59.94% and increasing HV by 5.90% compared to standard NSGA-III. Field validation showed 98.5% coverage of infested areas with only 3.6% path repetition, effectively minimizing pesticide waste and phytotoxicity risks. This study established a complete technical pipeline from monitoring to application, providing a valuable reference for precision pest control in large-scale cotton production systems. The framework demonstrated robust performance across multiple field sites, though its generalization is currently limited to one geographic region and growth stage. Future work will extend its application to additional cotton varieties, growth stages, and geographic regions. Full article

As the number of feature dimensions increases, the decision-making space exhibits extensive and discrete characteristics, which poses a severe challenge to multi-objective (MO) evolutionary algorithms when searching for the optimal feature subset. Many existing algorithms face the difficulty of slow convergence speed and may fall into local optimal solutions. This study proposes AF-NSGA-II (an adaptive filtering-nondominated sorting genetic algorithm II), an improved MO evolutionary algorithm for high-dimensional feature selection, in which a novel sparse generation scheme for the solution set and an innovative adaptive crossover mechanism are introduced. This sparse initialization strategy, based on three distinct filter feature selection methods, produces initial solutions closer to the optimal Pareto solution set, which is beneficial for convergence. The adaptive crossover mechanism dynamically selects between geometric crossover operators (fostering convergence) and non-geometric crossover operators (enhancing diversity) based on parent similarity, effectively balancing both aspects and helping the algorithm to escape local optima. The algorithm is compared against six renowned multi-objective evolutionary algorithms across ten complex and publicly available datasets. The comparison results demonstrate the superiority of AF-NSGA-II over other algorithms, as well as its effectiveness in identifying the optimal feature subset. Full article

In machine learning, feature selection (FS) is crucial for simplifying data while preserving the variables that most influence predictive performance. Although FS has been extensively studied, addressing it in an unsupervised setting remains challenging. Without class labels, optimization is more prone to slow convergence and the local optima. In particular, unsupervised text FS has received comparatively little attention, and its effectiveness is often limited by the underlying search strategy. To address this issue, we propose a hybrid breeding cooperative whale optimization algorithm (HBCWOA) tailored to unsupervised text FS. HBCWOA combines the cooperative evolutionary mechanism of hybrid breeding optimization with the global search capability of the whale optimization algorithm. The population is partitioned into three lines that evolve independently, while high-quality candidates are periodically exchanged among them to maintain diversity and promote stable, progressive convergence. Moreover, we design an adaptive dynamic accurate probabilistic transfer function (ADAPTF) to balance exploration and exploitation. By integrating the refinement ability of S-shaped transfer functions with the broader search ability of V-shaped ones, ADAPTF adaptively adjusts the exploration depth, reduces redundancy, and improves the convergence stability. After FS, K-means clustering is employed to assess how well the selected features structure document groups. Experiments on the CEC2022 benchmark functions and eight text datasets, under multiple evaluation metrics, show that HBCWOA attains faster convergence, more effective search exploration, and higher clustering accuracy than its S-shaped and V-shaped variants as well as several competitive text FS methods. Full article