Search Results (90,748)

Adversarial attacks in Natural Language Processing (NLP) present a critical challenge, particularly in sentiment analysis, where subtle input modifications can significantly alter model predictions. In search of more robust defenses against adversarial attacks on sentimental analysis, this research work introduces two novel defense mechanisms: the Lexicon-Based Random Substitute Model (LRSM) and the Word-Variant Voting Model (WVVM). LRSM employs randomized substitutions from a dataset-specific lexicon to generate diverse input variations, disrupting adversarial strategies by introducing unpredictability. Unlike traditional defenses requiring synonym dictionaries or precomputed semantic relationships, LRSM directly substitutes words with random lexicon alternatives, reducing overhead while maintaining robustness. Notably, LRSM not only neutralizes adversarial perturbations but occasionally surpasses the original accuracy by correcting inherent model misclassifications. Building on LRSM, WVVM integrates LRSM, Frequency-Guided Word Substitution (FGWS), and Synonym Random Substitution and Voting (RS&V) in an ensemble framework that adaptively combines their outputs. Logistic Regression (LR) emerged as the optimal ensemble configuration, leveraging its regularization parameters to balance the contributions of individual defenses. WVVM consistently outperformed standalone defenses, demonstrating superior restored accuracy and F1 scores across adversarial scenarios. The proposed defenses were evaluated on two well-known sentiment analysis benchmarks: the IMDB Sentiment Dataset and the Yelp Polarity Dataset. The IMDB dataset, comprising 50,000 labeled movie reviews, and the Yelp Polarity dataset, containing labeled business reviews, provided diverse linguistic challenges for assessing adversarial robustness. Both datasets were tested using 4000 adversarial examples generated by established attacks, including Probability Weighted Word Saliency, TextFooler, and BERT-based Adversarial Examples. WVVM and LRSM demonstrated superior performance in restoring accuracy and F1 scores across both datasets, with WVVM excelling through its ensemble learning framework. LRSM improved restored accuracy from 75.66% to 83.7% when compared to the second-best individual model, RS&V, while the Support Vector Classifier WVVM variation further improved restored accuracy to 93.17%. Logistic Regression WVVM achieved an F1 score of 86.26% compared to 76.80% for RS&V. These findings establish LRSM and WVVM as robust frameworks for defending against adversarial text attacks in sentiment analysis. Full article

This paper introduces a novel fractional-order model using the Caputo derivative operator to investigate the virus dynamics of adaptive immune responses. Two infection routes, namely cell-to-cell and virus-to-cell transmissions, are incorporated into the dynamics. Our research establishes the existence and uniqueness of positive and bounded solutions through the application of the generalized mean-value theorem and Banach fixed-point theory methods. The fractional-order model is shown to be Ulam–Hyers stable, ensuring the model’s resilience to small errors. By employing the normalized forward sensitivity method, we identify critical parameters that profoundly influence the transmission dynamics of the fractional-order virus model. Additionally, the framework of optimal control theory is used to explore the characterization of optimal adaptive immune responses, encompassing antibodies and cytotoxic T lymphocytes (CTL). To assess the influence of memory effects, we utilize the generalized forward–backward sweep technique to simulate the fractional-order virus dynamics. This study contributes to the existing body of knowledge by providing insights into how the interaction between virus-to-cell and cell-to-cell dynamics within the host is affected by memory effects in the presence of optimal control, reinforcing the invaluable synergy between fractional calculus and optimal control theory in modeling within-host virus dynamics, and paving the way for potential control strategies rooted in adaptive immunity and fractional-order modeling. Full article

Research highlights a growing demand for active, experiential learning methods in higher education, especially in teacher education. While the benefits of parental involvement (PI) are well-documented, Hungary lacks tools to effectively prepare teacher trainees for fostering family–school cooperation. This study addresses this gap by introducing a custom-designed board game as an innovative teaching tool. The game simulates real-world challenges in PI through a cooperative, scenario-based framework. Exercises are grounded in international and national research, ensuring their relevance and evidence-based design. Tested with 110 students, the game’s educational value was assessed via post-gameplay questionnaires. Participants emphasized the strengths of its cooperative structure, realistic scenarios, and integration of humor. Many reported gaining new insights into parental roles and strategies for effective home–school partnerships. Practical applications include integrating the game into teacher education curricula and adapting it for other educational contexts. This study demonstrates how board games can bridge theory and practice, offering an engaging, effective medium to prepare future teachers for the challenges of PI. Full article

Data annotation serves as a critical foundation for artificial intelligence (AI) and machine learning (ML). Recently, AI agents powered by large language models (LLMs) have emerged as effective solutions to longstanding challenges in data annotation, such as scalability, consistency, cost, and limitations in domain expertise. These agents facilitate intelligent automation and adaptive decision-making, thereby enhancing the efficiency and reliability of annotation workflows across various fields. Despite the growing interest in this area, a systematic understanding of the role and capabilities of AI agents in annotation is still underexplored. This paper seeks to fill that gap by providing a comprehensive review of how LLM-driven agents support advanced reasoning strategies, adaptive learning, and collaborative annotation efforts. We analyze agent architectures, integration patterns within workflows, and evaluation methods, along with real-world applications in sectors such as healthcare, finance, technology, and media. Furthermore, we evaluate current tools and platforms that support agent-based annotation, addressing key challenges such as quality assurance, bias mitigation, transparency, and scalability. Lastly, we outline future research directions, highlighting the importance of federated learning, cross-modal reasoning, and responsible system design to advance the development of next-generation annotation ecosystems. Full article

Community detection in complex networks plays a pivotal role in modern scientific research, including in social network analysis and protein structure analysis. Traditional community detection methods face challenges in integrating heterogeneous multi-source information, capturing global semantic relationships, and adapting to dynamic network evolution. This paper proposes a novel unsupervised multimodal community detection algorithm (UMM) based on fractal iteration. The core idea is to design a dual-channel encoder that comprehensively considers node semantic features and network topological structures. Initially, node representation vectors are derived from structural information (using feature vectors when available, or singular value decomposition to obtain feature vectors for nodes without attributes). Subsequently, a parameter-free graph convolutional encoder (PFGC) is developed based on fractal iteration principles to extract high-order semantic representations from structural encodings without requiring any training process. Furthermore, a semantic–structural dual-channel encoder (DC-SSE) is designed, which integrates semantic encodings—reduced in dimensionality via UMAP—with structural features extracted by PFGC to obtain the final node embeddings. These embeddings are then clustered using the K-means algorithm to achieve community partitioning. Experimental results demonstrate that the UMM outperforms existing methods on multiple real-world network datasets. Full article

The low-cost Strapdown Inertial Navigation System (SINS)/Global Navigation Satellite System (GNSS) is widely used in autonomous vehicles for positioning and navigation. Initial alignment is a critical stage for SINS operations, and the alignment time and accuracy directly affect the SINS navigation performance. To address the issue that low-cost SINS/GNSS cannot effectively achieve rapid and high-accuracy alignment in complex environments that contain noise and external interference, an adaptive multiple backtracking robust alignment method is proposed. The sliding window that constructs observation and reference vectors is established, which effectively avoids the accumulation of sensor errors during the full integration process. A new observation vector based on the magnitude matching is then constructed to effectively reduce the effect of outliers on the alignment process. An adaptive multiple backtracking method is designed in which the window size can be dynamically adjusted based on the innovation gradient; thus, the alignment time can be significantly shortened. Furthermore, the modified variational Bayesian Kalman filter (VBKF) that accurately adjusts the measurement noise covariance matrix is proposed, and the Expectation–Maximization (EM) algorithm is employed to refine the prior parameter of the predicted error covariance matrix. Simulation and experimental results demonstrate that the proposed method significantly reduces alignment time and improves alignment accuracy. Taking heading error as the critical evaluation indicator, the proposed method achieves rapid alignment within 120 s and maintains a stable error below 1.2° after 80 s, yielding an improvement of over 63% compared to the backtracking-based Kalman filter (BKF) method and over 57% compared to the fuzzy adaptive KF (FAKF) method. Full article

Leptospirosis is a globally significant zoonosis affecting animal health, productivity, and the environment. While typically associated with tropical climates, its persistence in semi-arid regions such as La Laguna, Mexico—characterized by low humidity, high temperatures, and limited water sources—remains poorly understood. Although these adverse environmental conditions theoretically limit the survival of Leptospira, high livestock density and synanthropic reservoirs (e.g., rodents) may compensate, facilitating transmission. In this cross-sectional study, blood sera from 445 dairy cows (28 herds: 12 intensive [MI], 16 semi-intensive [MSI] systems) were analyzed via microscopic agglutination testing (MAT) against 10 pathogenic serovars. Urine samples were cultured for active Leptospira detection. Risk factors were assessed through epidemiological surveys and multivariable analysis. This study revealed an overall apparent seroprevalence of 27.0% (95% CI: 22.8–31.1), with significantly higher rates in MSI (54.1%) versus MI (12.2%) herds (p < 0.001) and an estimated true seroprevalence of 56.3% (95% CI: 50.2–62.1) in MSI and 13.1% (95% CI: 8.5–18.7) in MI herds (p < 0.001). The Sejroe serogroup was isolated from urine in both systems, confirming active circulation. In MI herds, rodent presence (OR: 3.6; 95% CI: 1.6–7.9) was identified as a risk factor for Leptospira seropositivity, while first-trimester abortions (OR:10.1; 95% CI: 4.2–24.2) were significantly associated with infection. In MSI herds, risk factors associated with Leptospira seropositivity included co-occurrence with hens (OR: 2.8; 95% CI: 1.5–5.3) and natural breeding (OR: 2.0; 95% CI: 1.1–3.9), whereas mastitis/agalactiae (OR: 2.8; 95% CI: 1.5–5.2) represented a clinical outcome associated with seropositivity. Despite semi-arid conditions, Leptospira maintains transmission in La Laguna, particularly in semi-intensive systems. The coexistence of adapted (Sejroe) and incidental serogroups underscores the need for targeted interventions, such as rodent control in MI systems and poultry management in MSI systems, to mitigate both zoonotic and economic impacts. Full article

Hydrogels, characterized by their high water content, tunable mechanical properties, and excellent biocompatibility, have emerged as a promising material platform for the preservation of cultural heritage. Their unique physicochemical features enable non-invasive and adaptable solutions for environmental regulation, structural stabilization, and antifungal protection. This review provides a comprehensive overview of recent progress in hydrogel-based strategies specifically developed for the conservation of cultural relics, with a particular focus on antifungal performance—an essential factor in preventing biodeterioration. Current hydrogel systems, composed of natural or synthetic polymer networks integrated with antifungal agents, demonstrate the ability to suppress fungal growth, regulate humidity, alleviate mechanical stress, and ensure minimal damage to artifacts during application. This review also highlights future research directions, such as the application prospects of novel materials, including stimuli-responsive hydrogels and self-dissolving hydrogels. As an early exploration of the use of hydrogels in antifungal protection and broader cultural heritage conservation, this work is expected to promote the wider application of this emerging technology, contributing to the effective preservation and long-term transmission of cultural heritage worldwide. Full article

The design and planning of Western-style constructions during the early Qing Dynasty in China constituted a significant multicultural encounter that fused technological advancement with aesthetic innovation. This cultural interplay is particularly evident in the imperial garden and pavilion projects commissioned by the Qing court, which served as physical and symbolic sites of cross-cultural dialogue. Influenced by the intellectual and artistic movements of the European Renaissance, Western architectural concepts gradually found their way into the spatial and visual language of Chinese architecture, especially within the royal gardens and aristocratic buildings of the time. These structures were not simply imitative but rather represented a selective adaptation of Western ideas to suit Chinese imperial tastes and principles. This article examines the architectural language that emerged from this encounter between Chinese and European cultures, analysing symbolic motifs, spatial design, ornamental aesthetics, the application of linear perspective, and the integration of foreign architectural forms. These elements collectively functioned as tools to construct a unique visual discourse that communicated both political authority and cultural hybridity. The findings underscore that this architectural phenomenon was not merely stylistic imitation, but rather a dynamic convergence of technological knowledge and artistic vision across cultural boundaries. Full article

As a core device in low-voltage distribution networks, the distribution zone transformer (DZT) is influenced by short circuits, overloads, and unbalanced loads, which cause thermal aging, mechanical stress, and eventually deformation of the winding, resulting in parameter deviations from nameplate values and impairing system operation. However, existing identification methods typically require synchronized high- and low-voltage data and are limited to symmetric three-phase conditions, which limits their application in practical distribution systems. To address these challenges, this paper proposes a parameter identification method for DZTs under three-phase unbalanced conditions. Firstly, based on the transformer’s T-equivalent circuit considering the load, the power flow equations are derived without involving the synchronization issue of high-voltage and low-voltage side data, and the sum of the impedances on both sides is treated as an independent parameter. Then, a novel power flow equation under three-phase unbalanced conditions is established, and an adaptive recursive least squares (ARLS) solution method is constructed using the measurement data sequence provided by the smart meter of the intelligent transformer terminal unit (TTU) to achieve online identification of the transformer winding parameters. The effectiveness and robustness of the method are verified through practical case studies. Full article

To address the limitations of the existing cotton seedling growth prediction methods in field environments, specifically, poor representation of spatiotemporal features and low visual fidelity in texture rendering, this paper proposes an algorithm for the prediction of cotton seedling growth from images based on FCA-STNet. The model leverages historical sequences of cotton seedling RGB images to generate an image of the predicted growth at time t + 1 and extracts 37 phenotypic traits from the predicted image. A novel STNet structure is designed to enhance the representation of spatiotemporal dependencies, while an Adaptive Fine-Grained Channel Attention (FCA) module is integrated to capture both global and local feature information. This attention mechanism focuses on individual cotton plants and their textural characteristics, effectively reducing the interference from common field-related challenges such as insufficient lighting, leaf fluttering, and wind disturbances. The experimental results demonstrate that the predicted images achieved an MSE of 0.0086, MAE of 0.0321, SSIM of 0.8339, and PSNR of 20.7011 on the test set, representing improvements of 2.27%, 0.31%, 4.73%, and 11.20%, respectively, over the baseline STNet. The method outperforms several mainstream spatiotemporal prediction models. Furthermore, the majority of the predicted phenotypic traits exhibited correlations with actual measurements with coefficients above 0.8, indicating high prediction accuracy. The proposed FCA-STNet model enables visually realistic prediction of cotton seedling growth in open-field conditions, offering a new perspective for research in growth prediction. Full article

In this study, we propose a bidirectional chemical sensor platform based on a reconfigurable ion-sensitive field-effect transistor (R-ISFET) architecture. The device incorporates Ni-silicide Schottky barrier source/drain (S/D) contacts, enabling ambipolar conduction and bidirectional turn-on behavior for both p-type and n-type configurations. Channel polarity is dynamically controlled via the program gate (PG), while the control gate (CG) suppresses leakage current, enhancing operational stability and energy efficiency. A dual-control-gate (DCG) structure enhances capacitive coupling, enabling sensitivity beyond the Nernst limit without external amplification. The extended-gate (EG) architecture physically separates the transistor and sensing regions, improving durability and long-term reliability. Electrical characteristics were evaluated through transfer and output curves, and carrier transport mechanisms were analyzed using band diagrams. Sensor performance—including sensitivity, hysteresis, and drift—was assessed under various pH conditions and external noise up to 5 V_pp (i.e., peak-to-peak voltage). The n-type configuration exhibited high mobility and fast response, while the p-type configuration demonstrated excellent noise immunity and low drift. Both modes showed consistent sensitivity trends, confirming the feasibility of complementary sensing. These results indicate that the proposed R-ISFET sensor enables selective mode switching for high sensitivity and robust operation, offering strong potential for next-generation biosensing and chemical detection. Full article

Rapid urbanization and demographic shifts present significant challenges to spatial justice in green space provision. Traditional static assessments have become increasingly inadequate for guiding park planning, which now requires a dynamic, future-oriented analytical approach. To address this gap, this study incorporates population dynamics into urban park planning by developing a dynamic evaluation framework for park accessibility. Building on the Gaussian-based two-step floating catchment area (Ga2SFCA) method, we propose the human-population-projection-Ga2SFCA (HPP-Ga2SFCA) model, which integrates population forecasts to assess park service efficiency under future demographic pressures. Using neighborhood-committee-level census data from 2000 to 2020 and detailed park spatial data, we identified five types of population change and forecast demographic distributions for both short- and long-term scenarios. Our findings indicate population decline in the urban core and outer suburbs, with growth concentrated in the transitional inner-suburban zones. Long-term projections suggest that 66% of communities will experience population growth, whereas short-term forecasts indicate a decline in 52%. Static models overestimate park accessibility by approximately 40%. In contrast, our dynamic model reveals that accessibility is overestimated in 71% and underestimated in 7% of the city, highlighting a potential mismatch between future population demand and current park supply. This study offers a forward-looking planning framework that enhances the responsiveness of park systems to demographic change and supports the development of more equitable, adaptive green space strategies. Full article

Ensuring software quality during development requires effective regression testing. However, test suites in open-source libraries often grow large, redundant, and difficult to maintain. Most traditional test suite optimization methods treat test cases as atomic units, without analyzing the utility of individual instructions. This paper presents an intelligent method for test case synthesis using a Q-learning agent. The agent learns to construct compact test cases by interacting with an execution environment and receives rewards based on branch coverage improvements and simultaneous reductions in test case length. The training process includes a pretraining phase that transfers knowledge from the original test suite, followed by adaptive learning episodes on individual test cases. As a result, the method requires no formal documentation or API specifications and uses only execution traces of the original test cases. An explicit synthesis algorithm constructs new test cases by selecting API calls from a learned policy encoded in a Q-table. Experiments were conducted on two open-source C++ libraries of differing API complexity and original test suite size. The results show that the proposed method can reach up to 67% test suite reduction while preserving branch coverage, confirming its effectiveness for regression test suite minimization in resource-constrained or specification-limited environments. Full article

To improve the sampling efficiency of Markov Chain Monte Carlo in complex parameter spaces, this paper proposes an adaptive sampling method that integrates a swarm intelligence mechanism called the BeeSwarm-MH algorithm. The method combines global exploration by scout bees with local exploitation by worker bees. It employs multi-stage perturbation intensities and adaptive step-size tuning to enable efficient posterior sampling. Focusing on Bayesian inference for parameter estimation in the soliton solutions of the two-dimensional complex Ginzburg–Landau equation, we design a dedicated inference framework to systematically compare the performance of BeeSwarm-MH with the classical Metropolis–Hastings algorithm. Experimental results demonstrate that BeeSwarm-MH achieves comparable estimation accuracy while significantly reducing the required number of iterations and total computation time for convergence. Moreover, it exhibits superior global search capabilities and adaptive features, offering a practical approach for efficient Bayesian inference in complex physical models. Full article