Search Results (36,916)

This paper proposes an interpretable machine learning approach for predicting the splitting strength of asphalt concrete and supporting data-driven mixture design. A database consisting of 296 samples was constructed, and 14 input variables related to asphalt properties, aggregate gradation, and fiber characteristics were selected for modeling. Eight machine learning models, namely TabPFN, ANN, SVR, RF, XGBoost, LightGBM, FLAML, and FT-Transformer, were developed and compared. The results show that all eight models achieved satisfactory predictive capability, whereas TabPFN overall achieved the best performance in the Monte Carlo cross-validation, with the lowest average RMSE of 0.34 ± 0.10, the lowest average MAE of 0.21 ± 0.02, a relatively low average MAD of 0.14 ± 0.03, the highest average R² of 0.85 ± 0.08, and the highest composite score of 0.81. SHAP analysis further indicated that splitting strength prediction was mainly governed by a limited number of dominant variables, among which Ag9.5, AC, Du, FT, and Ag4.75 were the most effective parameters. In addition, favorable parameter ranges for improving splitting strength were quantified, such as Ag9.5 < 66.8%, AC < 5.4 wt.%, Du > 134.7 cm and Ag4.75 < 45.0%. Finally, a graphic user interface platform integrating prediction and SHapley Additive exPlanations-based interpretation was developed to improve the accessibility and practical applicability of the proposed framework. Full article

The detection technology for metal surface defects plays a crucial role in improving metal product quality and production efficiency in various manufacturing and 3-D printing factories. Metal defect detection faces scale variation and irregular shapes, which limit the adaptability of general object detection models in industrial scenarios. Deep learning-based methods are widely used for metal surface defect detection due to their strong adaptability and high automation. Yet, their existing studies pay limited attention to adaptability, evaluation, and recommendations across different detection methods for metal surface defects. This work mainly discusses YOLO, R-CNN, and transformers, as well as FPN, and analyzes their applications in metal surface defect detection according to their respective characteristics, to provide guidance for future research. YOLO has advantages in real-time industrial online detection, while R-CNN and transformer models show potential advantages in handling complex defect cases. Additionally, this work summarizes commonly used datasets and evaluation metrics for metal surface defect detection and analyzes the benchmark performance of different types of detection methods. It also discusses future research directions, including the current status and improvement paths of different models in terms of accuracy, real-time performance, and adaptability. Future models should focus on balancing accuracy and real-time performance, exploring new hybrid architectures, and improving adaptability to different metal surface defects to support further development in this field. Full article

This study investigates how a network’s structural and relational capabilities condition the influence of social CRM capabilities on innovation novelty, highlighting a deeper network paradox. Drawing on survey evidence from social enterprises, the analyses indicate that social CRM capabilities meaningfully contribute to the generation of novel innovations. Yet the two network capabilities move in opposite directions: structural capability amplifies the innovative gains derived from social CRM, whereas relational capability tends to dilute them. These divergent effects reflect the simultaneous pull of structural-hole and network-closure mechanisms within the same organizational setting. The results suggest that organizations aiming to translate social CRM investments into innovation may benefit more from structurally expansive network positions than from tightly embedded relational ties. Future work could employ longitudinal and cross-institutional designs to strengthen causal insight and broaden the study’s applicability. Full article

Partial agricultural production loads exhibit significant temporality. The concentrated access of temporary loads can easily trigger operational challenges in distribution networks, such as heavy overload, terminal voltage violations, and increased network losses. To address these issues, this paper proposes a coordinated dispatch strategy for multiple flexible resources to cope with temporary loads. First, combining the operational characteristics of motor-pumped well loads, a refined model for motor-pumped well loads is constructed to fully exploit their regulation potential as flexible loads. Second, considering the supporting role of mobile energy storage systems (MESS) for heavy overload distribution networks, a spatiotemporal dispatch model for MESS is established. Then, aiming to minimize the total system operating cost, an economic dispatch model coordinating multiple flexible resources, including MESS, distributed generators (DG), and flexible loads, is developed. The original non-convex problem is transformed into a mixed-integer second-order cone programming problem using Second-Order Cone Relaxation (SOCR) method for efficient solution. Finally, the effectiveness of the proposed strategy is verified on an improved IEEE 33-bus system. Full article

Accurate ecological prediction is critical for sustainable environmental management and carbon cycle assessment, yet model development is often constrained by limited datasets and inconsistent preprocessing practices. Reliable litterfall prediction plays a key role in understanding nutrient cycling and supporting sustainable forest ecosystem management. Although gradient boosting models have shown promising performance in ecological applications, structured evaluations integrating preprocessing strategies with synthetic data augmentation remain limited under data-scarce conditions. This study proposes the Hybrid Preprocessing and Augmented Boosting Framework (HPABF), which combines multi-stage preprocessing—including MICE imputation, log transformation, and feature engineering—with synthetic data augmentation to enhance predictive robustness. The framework was evaluated across eight machine learning models using a 968-sample forest ecological dataset. To mitigate data scarcity, 5000 synthetic samples were generated while preserving the statistical distribution and multivariate structure of the original data (91% fidelity). Fractal dimension analysis was further introduced as a geometric validation metric to assess prediction structure and stability beyond conventional performance measures. Within the HPABF, gradient boosting models achieved a 7% improvement over baseline performance (R² = 0.96, MAE = 0.06) under cross-validation strategies designed to reduce overfitting. Training with synthetic data further improved predictive accuracy (R² = 0.98), demonstrating the framework’s effectiveness for data-scarce ecological applications. By improving prediction reliability under limited data conditions, the proposed framework supports more accurate environmental monitoring, informed decision-making, and sustainable management of forest ecosystems. Full article

The physical characteristics of a heated non-Newtonian Eyring–Powell fluid in a conduit with sinusoidally moving ciliated walls are highlighted in this analytical study. The impact of mass transmission is considered in this model. The dimensional form of the governing equations is simplified using the long-wavelength estimation and suitable transformations to produce a set of dimensionless partial differential equations with pertinent boundary conditions. To solve it, the perturbation technique is utilized applying polynomial solutions. The solutions of temperature, concentrations, and velocity profiles are obtained, and then are further analyzed through graphical results. An accurate mathematical solution for the pressure gradient is achieved by integrating the velocity profile over the elliptic cross-section. The non-Newtonian Eyring–Powell fluid flows quicker through this vertical ciliated elliptic duct than the Newtonian fluid. Moreover, the cilia elliptic movement eccentricity and the wave number for metachronal wave have a dual effect on the velocity profile. Increasing the dimensionless flow rate and occlusion leads to an increase in closed contour size, as seen in the streamline description. Full article

CRISPR technologies are transforming cardiovascular therapy development by creating an increasingly seamless pipeline from potential target discovery to clinical translation. What began as a genome-editing tool has evolved into a versatile platform that enables researchers to precisely interrogate and modulate cardiac biology with tools such as base- and prime-editors, and CRISPR inhibition and activation. In this review, we follow the use of CRISPR across the stages of biomedical research through to bench-to-bedside application. This review begins by addressing how genome-wide and focused CRISPR screens discover developmental regulators, disease drivers, and drug-response pathways, making the first steps in identifying therapeutic targets. We then explore how CRISPR engineering creates progressively more relevant disease model systems to validate mechanisms of disease and test interventions, helping bridge the translational gaps between the lab and the clinic. Finally, we consider how CRISPR technologies are beginning to enter cardiovascular clinical trials, while highlighting the key challenges that still limit this translation. By linking the latest advances of modern CRISPR platforms to the stages of therapeutic development, this review highlights how CRISPR technology is reshaping the pipeline from molecular insight to clinical innovation in cardiac disease. Full article

High-strength bolts are critical structural components that are highly susceptible to corrosion in complex environments, posing significant threats to structural safety and reliability. Although acoustic emission (AE) technology has been widely applied in structural health monitoring, existing studies mainly focus on damage mode identification or source localization, while the identification of corrosion evolution stages based on AE signals remains insufficient. This study develops an intelligent corrosion diagnosis framework for high-strength bolts by integrating multimodal feature fusion and optimized machine learning. AE signals are first collected from the near-end and far-end of bolts using a wireless sensor network and then transformed into time–frequency representations via continuous wavelet transform (CWT). The resulting time–frequency images are fed into a modified ResNet-18 network to extract deep features, while statistical features are simultaneously extracted from the raw signals to preserve global information. These heterogeneous features are subsequently fused to form a comprehensive representation of corrosion characteristics. Furthermore, an artificial protozoa optimizer (APO) is introduced to adaptively optimize the hyperparameters of the XGBoost model. The results demonstrate that AE signals generated by hammering bolts with different corrosion levels can be successfully distinguished. The proposed method achieves high accuracy in corrosion stage classification and outperforms conventional approaches. Even when evaluated on an additional M30 bolt dataset, the proposed method maintains robust performance, demonstrating excellent generalization capability across different bolt sizes. These results demonstrate the practical potential of the proposed method for intelligent bolt corrosion diagnosis. Full article

This article addresses recent critiques of secularisation as a linear explanatory model for religious change in European societies, proposing that contemporary artistic creation is a fertile site for observing new interrelations between the secular and the religious. Focusing on João Madureira’s Missa de Pentecostes (2010), composed for the ensemble ‘Sete Lágrimas’ and part of a cultural project by the Roman Catholic community of ‘Capela do Rato’ (Lisbon), the study analyses how this work creatively reconfigures the traditional Mass form. By juxtaposing the Ordinary sections (e.g., Kyrie, Gloria) with the Proper sections (e.g., Introitus, Sequentia), which incorporate non-canonical Portuguese poetic texts, the composition creates a hybrid space in which ritual and artistic modes interact and mutually re-legitimise each other. Using a heterological interpretative framework inspired by Michel de Certeau, the article highlights the tensions and exchanges between ritual and aesthetic logics. The analysis draws on key theoretical concepts including Jean Rancière’s notions of consensus and dissensus, Pierre Bourdieu’s theory of ritual and habitus, Paul Ricoeur’s philosophy of translation as hospitality, and Pierre Lévy’s concept of universalism without totality. The findings suggest that Madureira’s work enacts a process of poetic re-signification of religious memory, opening new possibilities for hybrid ritual–artistic practices. These practices transform ritual time-space into an interface that fosters plural and non-totalising forms of spiritual belonging. Full article

Kolmogorov–Arnold Networks (KANs) have recently gained increasing attention as an alternative to conventional neural architectures, mainly because they replace fixed activation functions with learnable univariate mappings defined along network edges. This design not only increases modeling flexibility but also makes it easier to interpret how inputs are transformed within the network while maintaining parameter efficiency. KANs are particularly well suited for sensor-driven systems where transparency, robustness, and computational constraints are critical. This study provides a survey of KAN-based approaches for processing sensor data. A literature review conducted from 2024 to 2026 examined the deployment of KAN models in industrial and mechanical sensing, medical and biomedical sensing, and remote sensing and environmental monitoring, utilizing a Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)-based methodology. We first revisit the theoretical foundations of KANs and their main architectural variants, including spline-based, polynomial-based, monotonic, and hybrid formulations, to structure the discussion. From a practical standpoint, we then examine how KAN modules are integrated into modern deep learning pipelines, such as convolutional, recurrent, transformer-based, graph-based, and physics-informed architectures. KAN-based models demonstrate comparable predictive performance as conventional machine learning models, while having fewer parameters and more interpretable representations. Several limitations persist, including computational overhead, sensitivity to noisy signals, and resource-constrained device deployment challenges. Real-world sensor systems encounter significant challenges in adopting KAN-based models, including scalability in large-scale sensor networks, integration with hardware architectures, automated model development, resilience to out-of-distribution conditions, and the need for standardized evaluation metrics. Collectively, these observations provide a clearer understanding of the current and potential limitations of KAN-based models, offering practical guidance on the development of interpretable and efficient learning systems for future sensor equipment applications. Full article

Adversarial examples reveal critical vulnerabilities in deep neural networks, posing significant risks in real-world deployment. In black-box settings, transferable targeted attacks rely on surrogate models but often suffer from low success rates. We argue that this limitation arises not only from surrogate-boundary overfitting but also from insufficient alignment with the target semantic space, which restricts the ability of adversarial examples to encode target-specific characteristics. To address this issue, we propose Cosine-Based Logit Alignment (CBLA), a unified framework for transferable targeted attacks. CBLA replaces the conventional cross-entropy loss with a cosine similarity objective to enhance directional alignment in logit space and alleviate gradient saturation. In addition, a semantic-invariant transformation strategy is introduced to improve structural consistency and cross-model generalization. Experiments on the ImageNet validation set demonstrate that CBLA consistently improves targeted attack success rates, achieving an average gain of 4.55% over strong baselines across multiple architectures. Full article

Physical coupling, nonlinearity and uncertainty degrade the dynamic performance of electro-hydraulic servo systems, particularly under conditions involving input delays, leading to reduced trajectory tracking accuracy or even system instability. These factors often fail to meet the high-precision requirements of engineering applications. To effectively address these difficulties, this paper proposes a novel adaptive control protocol for networked electro-hydraulic servo systems. For the minimal communication delay problem of networked electro-hydraulic servo systems, Laplace transform algorithm together with Padé approximation is adopted in this study to remove the delay term from the mathematical system model. Moreover, the matched modeling parametric uncertainty of systems is estimated and compensated by the neural network adaptive method to improve the dynamical performance of the system during the steady state. The controller is designed on the basis of recursive backstepping strategy and the finite-time stability theorem, which can handle system nonlinearity and guarantee transient response. The validity of the proposed theoretical results is proved by Lyapunov stability and the feasibility and superiority are verified via physical simulation. Full article

The need for Arabic Aspect-Based Sentiment Analysis (ABSA) has grown steadily alongside the expansion of digital content, while the linguistic complexity of Modern Standard Arabic and its diverse dialects introduces significant challenges. However, progress in the field remains constrained by methodological fragmentation, inconsistent task definitions, heterogeneous datasets, and non-standardized evaluation practices. Based on a systematic analysis of 57 studies, this work presents an analytical and interpretive review that moves beyond performance-oriented surveys to examine the methodological foundations of Arabic ABSA research. The review follows a rigorous and transparent study selection process and applies a structured analytical framework to analyze task formulations, dataset characteristics, modeling approaches and evaluation strategies. Our findings reveal persistent challenges, including ambiguous aspect definitions, insufficiently documented annotation protocols, structural annotation biases, and limited robustness across domains and dialects. A heavy reliance on Transformer-based architectures and new Arabic foundation models can create an illusion of progress. Researchers often evaluate these models on small and homogeneous datasets. Consequently, strong in-domain performance obscures limited cross-domain and cross-dialectal generalizability. This study concludes by outlining actionable research directions, emphasizing clearer task standardization, more rigorous annotation guidelines, unified evaluation, and broader dialectal coverage to enhance reproducibility and scalability in Arabic ABSA systems. Full article

Image-based AI offers a low-cost alternative to traditional turbidity sensors in farm ponds, yet the prevailing shift toward Vision Transformers (ViTs) critically overlooks two field realities: the chronic scarcity of annotated data (Small Data) and the strict computational limits of edge hardware. This study presents a frugal computer vision framework that challenges the need for complex architectures in environmental screening. By systematically benchmarking six deep learning models across a calibrated high-turbidity dataset (200–800 NTU, 700 images) under standardized capture conditions, we demonstrate that traditional Convolutional Neural Networks (CNNs) possess a crucial inductive bias for this task. Specifically, ResNet-50 significantly outperformed modern ViTs in both accuracy (96.3% vs. 80.0%) and data efficiency, effectively capturing spatial scattering patterns without the massive data requirements that hindered transformer convergence. Deployed on a resource-constrained Raspberry Pi 4, the CNN-based system achieved an inference latency of 46 ms, demonstrated in an initial hardware-in-the-loop field proof-of-concept (82.4% agreement under baseline, calm-weather conditions, $n=17$). This edge-native approach not only provides actionable spatial turbidity maps to guide on-farm filtration and livestock management decisions but also establishes a critical architectural baseline: under controlled capture protocols, mature CNNs consistently outperform ViTs, establishing them as the optimal architecture for frugal, small-data agricultural Internet of Things (IoT) deployments. Full article

This paper introduces a q-deformed extension of the Lindley distribution. This extension is obtained by replacing the classical exponential with the q-exponential function from Tsallis non-extensive statistical techniques. This transformation offers more control over the tail behavior of the distribution, providing a transition between exponential and power-law decay patterns. Such flexibility is particularly useful when modeling right-skewed data with excess kurtosis, where classical models may not adequately describe heavy-tailed and highly skewed data. We derive several key properties, including the quantile function, expressed by the Lambert–Tsallis function $W_q$, the raw and incomplete moments, the probability-weighted moments, and the Tsallis entropy. The distribution of order statistics is also investigated. For parameter estimation, we employ several frequentist methods and conduct extensive Monte Carlo simulation studies to assess and compare their performance. Finally, applications to real-world datasets show that the q-deformed Lindley model is practically superior and more flexible than the classical Lindley distribution and other well-known models. Full article