Search Results (221)

Accurate millet appearance quality assessment is critical for fair procurement pricing. Traditional manual inspection is time-consuming and subjective, necessitating an automated solution. This study proposes a machine-vision-based approach using deep learning for dense-scene millet detection and quality evaluation. High-resolution images of standardized millet samples were collected via smartphone and annotated into seven categories covering impurities, high-quality grains, and various defects. To address the challenges with small object detection and feature loss, the YOLO11s model with an overlap-partitioning strategy were introduced, dividing the high-resolution images into smaller patches for improved object representation. The experimental results show that the optimized model achieved a mean average precision (mAP) of 94.8%, significantly outperforming traditional whole-image detection with a mAP of 15.9%. The optimized model was deployed in a custom-developed mobile application, enabling low-cost, real-time millet inspection directly on smartphones. It can process full-resolution images (4608 × 3456 pixels) containing over 5000 kernels within 6.8 s. This work provides a practical solution for on-site quality evaluation in procurement and contributes to real-time agricultural inspection systems. Full article

Federated learning (FL), as a distributed machine learning framework, enables multiple participants to jointly train models without sharing data, thereby ensuring data privacy and security. However, FL systems still struggle to escape the typical poisoning threat launched by Byzantine nodes. The current defence measures almost all rely on the anomaly detection of local gradients in a plaintext state, which not only weakens privacy protection but also allows malicious clients to upload malicious ciphertext gradients once they are encrypted, which thus easily evade existing screenings. At the same time, mainstream aggregation algorithms are generally based on the premise that “each client’s data satisfy an independent and identically distributed (IID)”, which is obviously difficult to achieve in real scenarios where large-scale terminal devices hold their own data. Symmetry in data distribution and model updates across clients is crucial for achieving robust and fair aggregation, yet non-IID data and adversarial attacks disrupt this balance. To address these challenges, we propose FedOPCS, an optimized poisoning countermeasure for non-IID FL algorithms with privacy-preserving stability by introducing three key innovations: Conditional Generative Adversarial Network (CGAN)-based data augmentation with conditional variables to simulate global distribution, a dynamic weight adjustment mechanism with homomorphic encryption, and two-stage anomaly detection combining gradient analysis and model performance evaluation. Extensive experiments on MNIST and CIFAR-10 show that, in the model poisoning and mixed poisoning environments, FedOPCS outperforms the baseline methods by 11.4% and 4.7%, respectively, while maintaining the same efficiency as FedAvg. FedOPCS therefore offers a privacy-preserving, Byzantine-robust, and communication-efficient solution for future heterogeneous FL deployments. Full article

This review paper presents a comprehensive analysis of the evolving landscape of data exchange, with a particular focus on the transformative role of emerging technologies such as blockchain, field-programmable gate arrays (FPGAs), and artificial intelligence (AI). We explore how the integration of these technologies into data management systems enhances operational efficiency, precision, and security through intelligent automation and advanced machine learning techniques. The paper also critically examines the key challenges facing data exchange today, including issues of interoperability, the demand for real-time processing, and the stringent requirements of regulatory compliance. Furthermore, it underscores the urgent need for robust ethical frameworks to guide the responsible use of AI and to protect data privacy. In addressing these challenges, the paper calls for innovative research aimed at overcoming current limitations in scalability and security. It advocates for interdisciplinary approaches that harmonize technological innovation with legal and ethical considerations. Ultimately, this review highlights the pivotal role of collaboration among researchers, industry stakeholders, and policymakers in fostering a digitally inclusive future—one that strengthens data exchange practices while upholding global standards of fairness, transparency, and accountability. Full article

Credit risk assessment plays a critical role in financial risk management, focusing on predicting borrower default to minimize losses and ensure compliance. This study systematically reviews 23 empirical articles published between 2019 and 2023, highlighting the integration of machine learning and optimization techniques, particularly bio-inspired metaheuristics, for feature selection in individual credit risk assessment. These nature-inspired algorithms, derived from biological and ecological processes, align with bio-inspired principles by mimicking natural intelligence to solve complex problems in high-dimensional feature spaces. Unlike prior reviews that adopt broader scopes combining corporate, sovereign, and individual contexts, this work focuses exclusively on methodological strategies for individual credit risk. It categorizes the use of machine learning algorithms, feature selection methods, and metaheuristic optimization techniques, including genetic algorithms, particle swarm optimization, and biogeography-based optimization. To strengthen transparency and comparability, this review also synthesizes classification performance metrics—such as accuracy, AUC, F1-score, and recall—reported across benchmark datasets. Although no unified experimental comparison was conducted due to heterogeneity in study protocols, this structured summary reveals consistent trends in algorithm effectiveness and evaluation practices. The review concludes with practical recommendations and outlines future research directions to improve fairness, scalability, and real-time application in credit risk modeling. Full article

Background: Cardiotocography (CTG) is widely used in obstetrics to monitor fetal heart rate and uterine contractions. It helps detect early signs of fetal distress. However, manual interpretation of CTG can be time-consuming and may vary between clinicians. Recent advances in machine learning provide more efficient and consistent alternatives for analyzing CTG data. Objectives: This study aims to investigate the classification of fetal health using various machine learning models to facilitate early detection of fetal health conditions. Methods: This study utilized a tabular dataset comprising 2126 patient records and 21 features. To classify fetal health outcomes, various machine learning algorithms were employed, including CatBoost, Decision Tree, ExtraTrees, Gradient Boosting, KNN, LightGBM, Random Forest, SVM, ANN and DNN. To address class imbalance and enhance model performance, the Synthetic Minority Oversampling Technique (SMOTE) was employed. Results: Among the tested models, the LightGBM algorithm achieved the highest performance, boasting a classification accuracy of 90.73% and, more notably, a balanced accuracy of 91.34%. This superior balanced accuracy highlights LightGBM’s effectiveness in handling imbalanced datasets, outperforming other models in ensuring fair classification across all classes. Conclusions: This study highlights the potential of machine learning models as reliable tools for fetal health classification. The findings emphasize the transformative impact of such technologies on medical diagnostics. Additionally, the use of SMOTE effectively addressed dataset imbalance, further enhancing the reliability and applicability of the proposed approach. Full article

Riparian vegetation reduces the conveyance capacity and increases the likelihood of floods. Studies that consider vegetation in flow modeling rely on unmanned aerial vehicle (UAV) data, which restrict the covered area. In contrast, this study explores advances in remote sensing and machine learning techniques to obtain vegetation data for an entire river by relying solely on satellite data, superior to UAVs in terms of spatial coverage, temporal frequency, and cost effectiveness. This study proposes a machine learning method to obtain key vegetation parameters at a resolution of 10 m. The goal was to evaluate the applicability of remotely sensed vegetation data using the proposed method on a dynamic roughness distributed runoff model in the Abukuma River to assess the effect of vegetation on the typhoon Hagibis flood (12 October 2019). Two machine learning models were trained to obtain vegetation height and density using different satellite sources, and the parameters were mapped in the river floodplains with 10 m resolution based on Sentinel-2 imagery. The vegetation parameters were successfully estimated, with the vegetation height overestimated in the urban areas, particularly in the downstream part of the river, then integrated into a dynamic roughness calculation routine and patched into the RRI model. The simulations with and without vegetation were also compared. The machine learning models for density and height obtained fair results, with an R² of 0.62 and 0.55, respectively, and a slight overestimation of height. The results showed a considerable increase in water depth (up to 17.7% at the Fushiguro station) and a decrease in discharge (28.1% at the Tateyama station) when vegetation was considered. Full article

Ensuring fairness in machine learning models applied to educational data is crucial for mitigating biases that can reinforce systemic inequities. This paper compares various fairness-enhancing algorithms across preprocessing, in-processing, and post-processing stages. Preprocessing methods such as Reweighting, Learning Fair Representations, and Disparate Impact Remover aim to adjust training data to reduce bias before model learning. In-processing techniques, including Adversarial Debiasing and Prejudice Remover, intervene during model training to directly minimize discrimination. Post-processing approaches, such as Equalized Odds Post-Processing, Calibrated Equalized Odds Post-Processing, and Reject Option Classification, adjust model predictions to improve fairness without altering the underlying model. We evaluate these methods on educational datasets, examining their effectiveness in reducing disparate impact while maintaining predictive performance. Our findings highlight tradeoffs between fairness and accuracy, as well as the suitability of different techniques for various educational applications. Full article

With the growing demand for diverse and high-volume manufacturing of composite material parts in aerospace applications, traditional machining methods have faced significant challenges due to their low efficiency and inconsistent quality. To address these challenges, digital twin (DT) technology offers a promising solution for developing automated production systems by enabling optimal configuration of manufacturing parameters. However, despite its potential, the widespread adoption of DT in complex manufacturing systems remains hindered by inherent limitations in adaptability and inter-system collaboration. This paper proposes an integrated framework that combines Model-Based Systems Engineering (MBSE) with deep learning (DL) to develop a digital twin system capable of adaptive machining. The proposed system employs three core components: machine vision-based process quality inspection, cognition-driven reasoning mechanisms, and adaptive optimization modules. By emulating human-like cognitive error correction and learning capabilities, this system enables real-time adaptive optimization of aerospace manufacturing processes. Experimental validation demonstrates that the cognition-driven DT framework achieves a defect recognition accuracy of 99.59% in aircraft cable fairing machining tasks. The system autonomously adapts to dynamic manufacturing conditions with minimal human intervention, significantly outperforming conventional processes in both efficiency and quality consistency. This work underscores the potential of integrating MBSE with DL to enhance the adaptability and robustness of digital twin systems in complex manufacturing environments. Full article

In forest operations, traditional ergonomic studies have been carried out by assessing body posture manually, but such assessments may suffer in terms of efficiency and reliability. Advancements in machine learning provided the opportunity to overcome many of the limitations of the manual approach. This study evaluated the intra- and inter-reliability of postural assessments in manual and motor-manual forest operations using the Ovako Working Posture Analysing System (OWAS)—which is one of the most used methods in forest operations ergonomics—by considering the predictions of a deep learning model as reference data and the rating inputs of three raters done in two replicates, over 100 images. The results indicated moderate to almost perfect intra-rater agreement (Cohen’s kappa = 0.48–1.00) and slight to substantial agreement (Cohen’s kappa = 0.02–0.64) among human raters. Inter-rater agreement between pairwise human-model datasets ranged from poor to fair (Cohen’s kappa = −0.03–0.34) and from fair to moderate when integrating all the human ratings with those of the model (Fleiss’ kappa = 0.28–0.49). The deep learning (DL) model highly outperformed human raters in assessment speed, requiring just one second per image, which, on average, was 19 to 53 times faster compared to human ratings. These findings highlight the efficiency and potential of integrating DL algorithms into OWAS assessments, offering a rapid and resource-efficient alternative while maintaining comparable reliability. However, challenges remain regarding subjective interpretations of complex postures. Future research should focus on refining algorithm parameters, enhancing human rater training, and expanding annotated datasets to improve alignment between model outputs and human assessments, advancing postural assessments in forest operations. Full article

Background/Objectives: Food banks and pantries play a critical role in improving food security through allocating essential resources to households that lack consistent access to sufficient and nutritious food. However, these organizations encounter significant operational challenges, including variability in food donations, volunteer shortages, and difficulties in matching supply with demand. Artificial intelligence (AI) has become increasingly prevalent in various sectors of the food industry and related services, highlighting its potential applicability in addressing these operational complexities. Methods: This study systematically reviewed empirical evidence on AI applications in food banks and pantry services published before 15 April 2025. The review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A comprehensive keyword and reference search was conducted in 11 electronic bibliographic databases: PubMed, Web of Science, Scopus, MEDLINE, APA PsycArticles, APA PsycInfo, CINAHL Plus, EconLit with Full Text, Applied Science & Technology Full Text (H.W. Wilson), Family & Society Studies Worldwide, and SocINDEX. Results: We identified five peer-reviewed papers published from 2015 to 2024, four of which utilized structured data machine learning algorithms, including neural networks, K-means clustering, random forests, and Bayesian additive regression trees. The remaining study employed text-based topic modeling to analyze food bank and pantry services. Of the five papers, three focused on the food donation process, and two examined food collection and distribution. Discussion: Collectively, these studies show the emerging potential for AI applications to enhance food bank and pantry operations. However, notable limitations were identified, including the scarcity of studies on this topic, restricted geographic scopes, and methodological challenges such as the insufficient discussion of data representativeness and statistical power. None of the studies addressed AI ethics, including model bias and fairness, or discussed intervention and policy implications in depth. Further studies should investigate innovative AI-driven solutions within food banks and pantries to help alleviate food insecurity. Full article

The increasing adoption of artificial intelligence algorithms is redefining decision-making across various industries. In the financial sector, where automated credit granting has undergone profound changes, this transformation raises concerns about biases perpetuated or introduced by AI systems. This study investigates the methods used to identify and mitigate biases in AI models applied to credit granting. We conducted a systematic literature review using the IEEE, Scopus, Web of Science, and Science Direct databases, covering the period from 1 January 2013 to 1 October 2024. From the 414 identified articles, 34 were selected for detailed analysis. Most studies are empirical and quantitative, focusing on fairness in outcomes and biases present in datasets. Preprocessing techniques dominated as the approach for bias mitigation, often relying on public academic datasets. Gender and race were the most studied sensitive attributes, with statistical parity being the most commonly used fairness metric. The findings reveal a maturing research landscape that prioritizes fairness in model outcomes and the mitigation of biases embedded in historical data. However, only a quarter of the papers report more than one fairness metric, limiting comparability across approaches. The literature remains largely focused on a narrow set of sensitive attributes, with little attention to intersectionality or alternative sources of bias. Furthermore, no study employed causal inference techniques to identify proxy discrimination. Despite some promising results—where fairness gains exceed 30% with minimal accuracy loss—significant methodological gaps persist, including the lack of standardized metrics, overreliance on legacy data, and insufficient transparency in model pipelines. Future work should prioritize developing advanced bias mitigation methods, exploring sensitive attributes, standardizing fairness metrics, improving model explainability, reducing computational complexity, enhancing synthetic data generation, and addressing the legal and ethical challenges of algorithms. Full article

The reciprocal relationship between Large Language Models (LLMs) and Knowledge Graphs (KGs) highlights their synergistic potential in enhancing artificial intelligence (AI) applications. LLMs, with their natural language understanding and generative capabilities, support the automation of KG construction through entity recognition, relation extraction, and schema generation. Conversely, KGs serve as structured and interpretable data sources that improve the transparency, factual consistency and reliability of LLM-based applications, mitigating challenges such as hallucinations and lack of explainability. This study conducts a systematic literature review of 77 studies to examine AI methodologies supporting LLM–KG integration, including symbolic AI, machine learning, and hybrid approaches. The research explores diverse applications spanning healthcare, finance, justice, and industrial automation, revealing the transformative potential of this synergy. Through in-depth analysis, this study identifies key limitations in current approaches, including challenges in scalability with maintaining dynamic and real-time Knowledge Graphs, difficulty in adapting general-purpose LLMs to specialized domains, limited explainability in tracing model outputs to interpretable reasoning, and ethical concerns surrounding bias, fairness, and transparency. In response, the study highlights potential strategies to optimize LLM–KG synergy. The findings from this study provide actionable insights for researchers and practitioners aiming for robust, transparent, and adaptive AI systems to enhance knowledge-driven AI applications through LLM–KG integration, further advancing generative AI and explainable AI (XAI) applications. Full article

This paper examines the uptake of AI-driven fraud detection systems among financial institutions in the UAE and Qatar, with a special focus on trust, transparency, and perceptions of fairness. Despite the promise of AI operations in identifying financial anomalies, unclear decision-making processes and algorithmic bias constrain its extensive acceptance, especially in regulation-driven banking sectors. This study uses a quantitative strategy based on Partial Least Squares Structural Equation Modeling (PLS-SEM) and Multi-Group Analysis (MGA) of survey responses from 409 bank professionals, such as auditors and compliance officers. This study shows that transparency greatly enhances trust, which is the leading predictor of AI uptake. Fairness perception mediates the negative impacts of algorithmic bias, emphasizing its important role in establishing system credibility. The analysis of subgroups shows differential regional and professional variations in trust and fairness sensitivity, where internal auditors and highly AI-exposed subjects are found to exhibit higher adoption preparedness. Compliance with regulations also emerges as a positive enabler of adoption. This paper concludes with suggestions for practical implementation by banks, developers, and regulators to align AI deployment with ethical and regulatory aspirations. It recommends transparent, explainable, and fairness-sensitive AI tools as essential for promoting adoption in regulation-driven sectors. The findings provide a guide for promoting responsible, trust-driven AI implementation in fraud detection. Full article

Fairness is becoming indispensable for ethical machine learning (ML) applications. However, it remains a challenge to identify unfairness if there are changes in the distribution of underlying features among different groups and machine learning outputs. This paper proposes a novel fairness metric framework considering multiple attributes, including ML outputs and feature variations for bias detection. The framework comprises two principal components, comparison and aggregation functions, which collectively ensure fairness metrics with high adaptability across various contexts and scenarios. The comparison function evaluates individual variations in the attribute across different groups to generate a fairness score for an individual attribute, while the aggregation function combines individual fairness scores of single or multiple attributes for the overall fairness understanding. Both the comparison and aggregation functions can be customized based on the context for the optimized fairness evaluations. Three innovative comparison–aggregation function pairs are proposed to demonstrate the effectiveness and robustness of the novel framework. The novel framework underscores the importance of dynamic fairness, where ML systems are designed to adapt to changing societal norms and population demographics. The new metric can monitor bias as a dynamic fairness indicator for robustness in ML systems. Full article

Machine learning algorithms have become essential tools in modern physics experiments, enabling the precise and efficient analysis of large-scale experimental data. The Compressed Baryonic Matter (CBM) experiment at the Facility for Antiproton and Ion Research (FAIR) demands innovative methods for processing the vast data volumes generated at high collision rates of up to 10 MHz. This study presents a deep-learning-based approach to enhance the signal/background (S/B) ratio for $\Lambda$ particles within the Kalman Filter (KF) Particle Finder framework. Using the Artificial Neural Networks for First Level Event Selection (ANN4FLES) package of CBM, a multi-layer perceptron model was designed and trained on simulated data to classify $\Lambda$ particle candidates as signal or background. The model achieved over 98% classification accuracy, enabling significant reductions in background—in particular, a strong suppression of the combinatorial background that lacks physical meaning—while preserving almost the whole $\Lambda$ particle signal. This approach improved the S/B ratio by a factor of 10.97, demonstrating the potential of deep learning to complement existing particle reconstruction techniques and contribute to the advancement of data analysis methods in heavy-ion physics. Full article