Search Results (596)

Rotating machinery is a core component of modern industry, and its operational state directly affects system safety and reliability. In order to achieve intelligent fault diagnosis of bearings under complex working conditions, the health management of bearings has become an important issue. Although deep learning has shown remarkable advantages, its performance still relies on the assumption that the training and testing data share the same distribution, which often deteriorates in real applications due to variations in load and rotational speed. This study focused on the scenario of domain generalization (DG) and proposed a Meta-Learning with Gradient Alignment and Data Augmentation (MGADA) method for cross-domain bearing fault diagnosis. Within the meta-learning framework, Mixup-based data augmentation was performed on the support set in the inner loop to alleviate overfitting under small-sample conditions and enhanced task-level data diversity. In the outer loop optimization stage, an arithmetic gradient alignment constraint was introduced to ensure consistent update directions across different source domains, thereby reducing cross-domain optimization conflicts. Meanwhile, a centroid convergence constraint was incorporated to enforce samples of the same class from different domains to converge to a shared centroid in the feature space, thus enhancing intra-class compactness and semantic consistency. Cross-working-condition experiments conducted on the Case Western Reserve University (CWRU) bearing dataset demonstrate that the proposed method achieves high classification accuracy across different target domains, with an average accuracy of 98.89%. Furthermore, ablation studies confirm the necessity of each module (Mixup, gradient alignment, and centroid convergence), while t-SNE and confusion matrix visualizations further illustrate that the proposed approach effectively achieves cross-domain feature alignment and intra-class aggregation. The proposed method provides an efficient and robust solution for bearing fault diagnosis under complex working conditions and offers new insights and theoretical references for promoting domain generalization in practical industrial applications. Full article

Machine learning and deep learning techniques integrated with advanced sensing technologies have revolutionized agricultural engineering, addressing complex challenges in food production, quality assessment, and environmental monitoring. This survey presents a systematic review and meta-analysis of recent developments by examining the peer-reviewed literature from 2015 to 2024. The analysis reveals computational approaches ranging from traditional algorithms like support vector machines and random forests to deep learning architectures, including convolutional and recurrent neural networks. Deep learning models often demonstrate superior performance, showing 5–10% accuracy improvements over traditional methods and achieving 93–99% accuracy in image-based applications. Three primary application domains are identified: agricultural product quality assessment using hyperspectral imaging, crop and field management through precision optimization, and agricultural automation with machine vision systems. Dataset taxonomy shows spectral data predominating at 42.1%, followed by image data at 26.2%, indicating preference for non-destructive approaches. Current challenges include data limitations, model interpretability issues, and computational complexity. Future trends emphasize lightweight model development, ensemble learning, and expanding applications. This analysis provides a comprehensive understanding of current capabilities and future directions for machine learning in agricultural engineering, supporting the development of efficient and sustainable agricultural systems for global food security. Full article

We propose a nested ensemble learning framework that utilizes Topological Data Analysis (TDA) to extract and integrate topological features from graph data, with the goal of improving performance on classification and regression tasks. Our approach computes persistence diagrams (PDs) using lower-star filtrations induced by three filter functions: closeness, betweenness, and degree 2 centrality. To overcome the limitation of relying on a single filter, these PDs are integrated through a data-driven, three-level architecture. At Level-0, diverse base models are independently trained on the topological features extracted for each filter function. At Level-1, a meta-learner combines the predictions of these base models for each filter to form filter-specific ensembles. Finally, at Level-2, a meta-learner integrates the outputs of these filter-specific ensembles to produce the final prediction. We evaluate our method on both simulated and real-world graph datasets. Experimental results demonstrate that our framework consistently outperforms base models and standard stacking methods, achieving higher classification accuracy and lower regression error. It also surpasses existing state-of-the-art approaches, ranking among the top three models across all benchmarks. Full article

Background: Artificial Intelligence (AI) is increasingly applied in endurance sports to optimize performance, enhance recovery, and personalize nutrition and supplementation. This review synthesizes current knowledge on AI applications in endurance sports, emphasizing implications for metabolic health, nutritional strategies, and recovery optimization, while also addressing ethical considerations and future directions. Methods: A narrative review was conducted using targeted searches of PubMed, Scopus, and Web of Science with cross-referencing. Extracted items included sport/context, data sources, AI methods including machine learning (ML), validation type (internal vs. external/field), performance metrics, comparators, and key limitations to support a structured synthesis; no formal risk-of-bias assessment or meta-analysis was undertaken due to heterogeneity. Results: AI systems effectively integrate multimodal physiological, environmental, and behavioral data to enhance metabolic health monitoring, predict recovery states, and personalize nutrition. Continuous glucose monitoring combined with AI algorithms allows precise carbohydrate management during prolonged events, improving performance outcomes. AI-driven supplementation strategies, informed by genetic polymorphisms and individual metabolic responses, have demonstrated enhanced ergogenic effectiveness. However, significant challenges persist, including measurement validity and reliability of sensor-derived signals and overall dataset quality (e.g., noise, missingness, labeling error), model performance and generalizability, algorithmic transparency, and equitable access. Furthermore, limited generalizability due to homogenous training datasets restricts widespread applicability across diverse athletic populations. Conclusions: The integration of AI in endurance sports offers substantial promise for improving performance, recovery, and nutritional strategies through personalized approaches. Realizing this potential requires addressing existing limitations in model performance and generalizability, ethical transparency, and equitable accessibility. Future research should prioritize diverse, representative, multi-site data collection across sex/gender, age, and race/ethnicity. Coverage should include performance level (elite to recreational), sport discipline, environmental conditions (e.g., heat, altitude), and device platforms (multi-vendor/multi-sensor). Equally important are rigorous external and field validation, transparent and explainable deployment with appropriate governance, and equitable access to ensure scientifically robust, ethically sound, and practically relevant AI solutions. Full article

Industrial image anomaly detection (IAD) is crucial for quality control, but its performance often degrades when training data contain label noise. To circumvent the reliance on potentially flawed labels, unsupervised methods that learn from the data distribution itself have become a mainstream approach. Among various unsupervised techniques, student–teacher frameworks have emerged as a highly effective paradigm. Student–Teacher Feature Pyramid Matching (STPM) is a powerful method within this paradigm, yet it is susceptible to such noise. Inspired by STPM and aiming to solve this issue, this paper introduces Meta-Learning Guided STPM (MLG-STPM), a novel framework that enhances STPM’s robustness by incorporating a guidance mechanism inspired by meta-learning. This guidance is achieved through an Evolving Meta-Set (EMS), which dynamically maintains a small high-confidence subset of training samples identified by their low disagreement between student and teacher networks. By training the student network on a combination of the current batch and the EMS, MLG-STPM effectively mitigates the impact of noisy labels without requiring an external clean dataset or complex re-weighting schemes. Comprehensive experiments on the MVTec AD and VisA benchmark datasets with synthetic label noise (0% to 20%) demonstrate that MLG-STPM significantly improves anomaly detection and localization performance compared to the original STPM, especially under higher noise conditions, and achieves competitive results against other relevant approaches. Full article

Background: Neuroimaging-based diagnostic approaches are of critical importance for the accurate diagnosis and treatment of major depressive disorder (MDD). However, multisite neuroimaging data often exhibit substantial heterogeneity in terms of scanner protocols and population characteristics. Moreover, concerns over data ownership, security, and privacy make raw MRI datasets from multiple sites inaccessible, posing significant challenges to the development of robust diagnostic models. Federated learning (FL) offers a privacy-preserving solution to facilitate collaborative model training across sites without sharing raw data. Methods: In this study, we propose the personalized Federated Gradient Matching and Contrastive Optimization (pF-GMCO) algorithm to address domain shift and support scalable MDD classification using multimodal MRI. Our method incorporates gradient matching based on cosine similarity to weight contributions from different sites adaptively, contrastive learning to promote client-specific model optimization, and multimodal compact bilinear (MCB) pooling to effectively integrate structural MRI (sMRI) and functional MRI (fMRI) features. Results and Conclusions: Evaluated on the Rest-Meta-MDD dataset with 2293 subjects from 23 sites, pF-GMCO achieved accuracy of 79.07%, demonstrating superior performance and interpretability. This work provides an effective and privacy-aware framework for multisite MDD diagnosis using federated learning. Full article

In the face of ever-evolving cyber threats, modern intrusion detection systems (IDS) must achieve long-term adaptability without sacrificing performance on previously encountered attacks. Traditional IDS approaches often rely on static training assumptions, making them prone to forgetting old patterns, underperforming in label-scarce conditions, and struggling with imbalanced class distributions as new attacks emerge. To overcome these limitations, we present a continual learning framework tailored for adaptive intrusion detection. Unlike prior methods, our approach is designed to operate under real-world network conditions characterized by high-dimensional, sparse traffic data and task-agnostic learning sequences. The framework combines three core components: a clustering-based memory strategy that selectively retains informative historical samples using DP-Means; multi-level knowledge distillation that aligns current and previous model states at output and intermediate feature levels; and a meta-learning-driven class reweighting mechanism that dynamically adjusts to shifting attack distributions. Empirical evaluations on benchmark intrusion detection datasets demonstrate the framework’s ability to maintain high detection accuracy while effectively mitigating forgetting. Notably, it delivers reliable performance in continually changing environments where the availability of labeled data is limited, making it well-suited for real-world cybersecurity systems. Full article

Swarm Robotics (SR) is a relatively new field, inspired by the collective intelligence of social insects. It involves using local rules to control and coordinate large groups (swarms) of relatively simple physical robots. Important tasks that robot swarms can handle include demining, search, rescue, and cleaning up toxic spills. Over the past decade, the research effort in the field of Swarm Robotics has intensified significantly in terms of hardware, software, and systems integrated developments, yet significant challenges remain, particularly regarding standardization, scalability, and cost-effective deployment. To contextualize the state of Swarm Robotics technologies, this paper provides a systematic literature review (SLR) of Swarm Robotic technologies published from 2014 to 2024, with an emphasis on how hardware and software subsystems have co-evolved. This work provides an overview of 40 studies in peer-reviewed journals along with a well-defined and replicable systematic review protocol. The protocol describes criteria for including and excluding studies and outlines a data extraction approach. We explored trends in sensor hardware, actuation methods, communication devices, and energy systems, as well as an examination of software platforms to produce swarm behavior, covering meta-heuristic algorithms and generic middleware platforms such as ROS. Our results demonstrate how dependent hardware and software are to achieve Swarm Intelligence, the lack of uniform standards for their design, and the pragmatic limits which hinder scalability and deployment. We conclude by noting ongoing challenges and proposing future directions for developing interoperable, energy-efficient Swarm Robotics (SR) systems incorporating machine learning (ML). Full article

Long Range Wide Area Network (LoRaWAN) has become an attractive option for maritime communication because it is low-cost, long-range, and energy-efficient. Yet its performance at sea is often limited by fading, interference, and the strict energy budgets of maritime Internet of Things (IoT) devices. This review, prepared in line with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines, examines 23 peer-reviewed studies published between 2019 and 2025 that explore adaptive antenna solutions for LoRaWAN in marine environments. The work covered four main categories: switched-beam, phased array, reconfigurable, and Artificial Intelligence or Machine Learning (AI/ML)-enabled antennas. Results across studies show that adaptive approaches improve gain, beam agility, and signal reliability even under unstable conditions. Switched-beam antennas dominate the literature (45%), followed by phased arrays (30%), reconfigurable designs (20%), and AI/ML-enabled systems (5%). Unlike previous reviews, this study emphasizes maritime propagation, environmental resilience, and energy use. Despite encouraging results in signal-to-noise ratio (SNR), packet delivery, and coverage range, clear gaps remain in protocol-level integration, lightweight AI for constrained nodes, and large-scale trials at sea. Research on reconfigurable intelligent surfaces (RIS) in maritime environments remains limited. However, these technologies could play an important role in enhancing spectral efficiency, coverage, and the scalability of maritime IoT networks. Full article

Road traffic crashes (RTCs) have emerged as a major global cause of fatalities, with the number of accident-related deaths rising rapidly each day. To mitigate this issue, it is essential to develop early prediction methods that help drivers and riders understand accident statistics relevant to their region. These methods should consider key factors such as speed limits, compliance with traffic signs and signals, pedestrian crossings, right-of-way rules, weather conditions, driver negligence, fatigue, and the impact of excessive speed on RTC occurrences. Raising awareness of these factors enables individuals to exercise greater caution, thereby contributing to accident prevention. A promising approach to improving road traffic accident severity classification is the stacking ensemble method, which leverages multiple machine learning models. This technique addresses challenges such as imbalanced datasets and high-dimensional features by combining predictions from various base models into a meta-model, ultimately enhancing classification accuracy. The ensemble approach exploits the diverse strengths of different models, capturing multiple aspects of the data to improve predictive performance. The effectiveness of stacking depends on the careful selection of base models with complementary strengths, ensuring robust and reliable predictions. Additionally, advanced feature engineering and selection techniques can further optimize the model’s performance. Within the field of artificial intelligence, various machine learning (ML) techniques have been explored to support decision making in tackling RTC-related issues. These methods aim to generate precise reports and insights. However, the stacking method has demonstrated significantly superior performance compared to existing approaches, making it a valuable tool for improving road safety. Full article

Few-shot object detection methods perform well in natural scenes, where meta-learners can effectively extract target features from limited support data. However, PCB defect detection faces unique challenges: scarce defect samples, low-resolution targets, and severe overfitting risks. Additionally, PCBs’ dense circuitry creates low-contrast defects that blend into background noise, while traditional meta-learning struggles to generate realistic synthetic defects under actual manufacturing constraints. To overcome these limitations, we propose SM-FSOD, a second-order meta-learning model featuring a defect-aware prototype network. Unlike conventional approaches, it dynamically emphasizes critical defect features when constructing class prototypes from few-shot samples. Our extensive few-shot experiments on the DeepPCB and DsPCBSD+ datasets demonstrate the performance of the SM-FSOD model. Comparative tests on the DeepPCB dataset show that, compared with the strong Meta-RCNN baseline, our model achieves a maximum performance improvement of 14.0% under the challenging five-shot setting, while still attaining a 7.6% accuracy gain in the more relaxed 50-shot setting. Similarly, evaluation on the DsPCBSD+ dataset reveals that our proposed method maintains an average accuracy improvement of 2.3% to 9.6% compared to the competitive DeFRCN model in complex scenarios, indicating the strong adaptability of SM-FSOD across various application environments. Ablation studies further demonstrate that incorporating the improved MOMP and DGPT modules individually yields average accuracy gains of 3.6% and 4.5%, respectively, under the five-shot setting compared to the baseline, confirming that these enhancements can orthogonally improve the detection precision in few-shot PCB scenarios. Full article

Abdominal fat is a key indicator of chicken meat quality. Excessive deposition not only reduces meat quality but also decreases feed conversion efficiency, making the breeding of low-abdominal-fat strains economically important. Genomic selection (GS) uses information from genome-wide association studies (GWASs) and high-throughput sequencing data. It estimates genomic breeding values (GEBVs) from genotypes, which enables early and precise selection. Given that abdominal fat is a polygenic trait controlled by numerous small-effect loci, this study combined population genetic analyses with machine learning (ML)-based feature selection. Relevant single-nucleotide polymorphisms (SNPs) were first identified using a combined GWAS and linkage disequilibrium (LD) approach, followed by a two-stage feature selection process—Lasso for dimensionality reduction and recursive feature elimination (RFE) for refinement—to generate the model input set. We evaluated multiple machine learning models for predicting genomic estimated breeding values (GEBVs). The results showed that linear models and certain nonlinear models achieved higher accuracy and were well suited as base learners for ensemble methods. Building on these findings, we developed a Dynamic Adaptive Weighted Stacking Ensemble Learning Framework (DAWSELF), which applies dynamic weighting and voting to heterogeneous base learners and integrates them layer by layer, with Ridge serving as the meta-learner. In three independent validation populations, DAWSELF consistently outperformed individual models and conventional stacking frameworks in prediction accuracy. This work establishes an efficient GEBV prediction framework for complex traits such as chicken abdominal fat and provides a reusable SNP feature selection strategy, offering practical value for enhancing the precision of poultry breeding and improving product quality. Full article

Soil nutrient monitoring plays a vital role in advancing sustainable agriculture by maintaining soil health, optimizing crop productivity, and minimizing environmental impacts. This study addresses gaps in unified definitions and standard methodologies by systematically analyzing 93 articles using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework. The results highlight five major monitoring approaches: traditional methods, Remote Sensing (RS), Internet of Things (IoT) and smart systems, in situ sensors, and Artificial Intelligence (AI)-based models, each contributing uniquely to nutrient assessment. A noticeable trend toward integrating machine learning and deep learning with sensor technologies underscores the advancement toward real-time, data-driven precision agriculture. The study also explores spatial and temporal publication trends, criteria for site selection, and the validation techniques used to assess monitoring accuracy. A synthesized definition of soil nutrient monitoring is proposed to support future research and standardization. This review highlights the crucial role of soil nutrient monitoring technologies in sustainable agriculture, crop optimization, and environmental management. It provides a comprehensive overview of the techniques employed in monitoring soil nutrients for precision soil management. Full article

Background/Objectives: The limited availability of labeled data, particularly in the medical domain, poses a significant challenge for training accurate diagnostic models. While deep learning techniques have demonstrated notable efficacy in image-based tasks, they require large annotated datasets. In data-scarce scenarios—especially involving rare diseases—their performance deteriorates significantly. Meta-learning offers a promising alternative by enabling models to adapt quickly to new tasks using prior knowledge and only a few labeled examples. This study aims to evaluate the effectiveness of representative meta-learning models for thoracic disease classification in chest X-rays. Methods: We conduct a comparative evaluation of four meta-learning models: Prototypical Networks, Relation Networks, MAML, and FoMAML. First, we assess five backbone architectures (ConvNeXt, DenseNet-121, ResNet-50, MobileNetV2, and ViT) using a Prototypical Network. The best-performing backbone is then used across all meta-learning models for fair comparison. Experiments are performed on the ChestX-ray14 dataset under a 2-way setting with multiple k-shot configurations. Results: Prototypical Networks combined with DenseNet-121 achieved the best performance, with a recall of 68.1%, an F1-score of 67.4%, and a precision of 0.693 in the 2-way, 10-shot configuration. In a disease-specific analysis, Hernia obtains the best classification results. Furthermore, Prototypical and Relation Networks demonstrate significantly higher computational efficiency, requiring fewer FLOPs and shorter execution times than MAML and FoMAML. Conclusions: Prototype-based meta-learning, particularly with DenseNet-121, proves to be a robust and computationally efficient approach for few-shot chest X-ray disease classification. These findings highlight its potential for real-world clinical applications, especially in scenarios with limited annotated medical data. Full article

Background: Customer churn significantly impacts business revenues. Machine Learning (ML) and Deep Learning (DL) methods are increasingly adopted to predict churn, yet a systematic synthesis of recent advancements is lacking. Objectives: This systematic review evaluates ML and DL approaches for churn prediction, identifying trends, challenges, and research gaps from 2020 to 2024. Data Sources: Six databases (Springer, IEEE, Elsevier, MDPI, ACM, Wiley) were searched via Lens.org for studies published between January 2020 and December 2024. Study Eligibility Criteria: Peer-reviewed original studies applying ML/DL techniques for churn prediction were included. Reviews, preprints, and non-peer-reviewed works were excluded. Methods: Screening followed PRISMA 2020 guidelines. A two-phase strategy identified 240 studies for bibliometric analysis and 61 for detailed qualitative synthesis. Results: Ensemble methods (e.g., XGBoost, LightGBM) remain dominant in ML, while DL approaches (e.g., LSTM, CNN) are increasingly applied to complex data. Challenges include class imbalance, interpretability, concept drift, and limited use of profit-oriented metrics. Explainable AI and adaptive learning show potential but limited real-world adoption. Limitations: No formal risk of bias or certainty assessments were conducted. Study heterogeneity prevented meta-analysis. Conclusions: ML and DL methods have matured as key tools for churn prediction, yet gaps remain in interpretability, real-world deployment, and business-aligned evaluation. Systematic Review Registration: Registered retrospectively in OSF. Full article