Search Results (10,814)

This paper proposes a novel method for synthesizing a discrete optimization algorithm based on the moth–flame paradigm for application to the architecture of deceptive systems incorporating decoys and traps. Unlike existing approaches that primarily rely on continuous search spaces or static deception strategies, the proposed method enables the formation of a discrete search space with a coordinate-based representation of deception objects and system states. A spiral search trajectory is synthesized by modeling the dynamic interaction between moths and flames, which allows the algorithm to balance exploration and exploitation effectively and to mitigate premature convergence to local optima. The problem of selecting subsequent operational steps of a deceptive system, which includes the control and reconfiguration of decoys and traps in response to detected events, is formulated as a discrete optimization problem. The objective of this optimization is to increase the effectiveness of cyberattack and malware detection in corporate network environments. The decision variables include the sequence of deception actions, process models, and architectural characteristics of the system, while the constraints are defined by the operational conditions, resource limitations, and structural features of corporate networks. The proposed method supports the identification of an optimal sequence of deception actions under dynamically changing conditions and provides mechanisms for operational adaptation to attacker behavior in real time. This adaptability enables the creation of deceptive systems capable of long-term autonomous operation without continuous administrative intervention, while simultaneously increasing their resistance to adversarial reconnaissance and reverse engineering of their operational principles. The experimental results confirm the feasibility and effectiveness of the proposed approach and demonstrate the potential of integrating population-based optimization algorithms into deceptive system architectures. Comparative analysis shows that the proposed method outperforms its closest competitor, the genetic algorithm, achieving an improvement of 4.82% in terms of the objective function value. Future research directions include deeper integration of population-based optimization methods into decoy-and-trap architectures and the development of a comprehensive framework for organizing their operation in accordance with the proposed conceptual model. Overall, the results contribute to enhancing the cyber-resilience of corporate networks through intelligent, adaptive, and autonomous systems for countering modern cyberattacks and malware. Full article

Covalent organic frameworks (COFs) stand at the forefront of reticular chemistry, weaving crystalline porosity with unparalleled designability and functional tunability. Their expansive channels and modular architectures have driven rapid advances in photocatalytic organic transformations, providing a platform for sunlight-driven reactions with high selectivity and sustainability. This review spotlights the rational engineering of metal-free COFs—from pore-size orchestration to chromophore integration—as versatile platforms for selective C–H activation, cross-coupling, and beyond. We survey landmark advances since 2016, dissecting the structure–activity relationships that drive efficiency under visible light, while unveiling challenges such as charge recombination and scalability issues. By establishing in-depth correlations between the structure of metal-free COFs and their photocatalytic performance, this work offers new opportunities to forge ahead in synthetic chemistry. Full article

(WMoTaNb)SiN refractory high-entropy nitride films were deposited via magnetron cosputtering, and the Si content was systematically regulated by varying the Si target power to investigate its influence on the microstructure, mechanical properties, oxidation resistance, and oxyhydrogen-flame ablation behavior. All the films exhibited dense columnar architectures with a distinct FCC + BCC dual-phase structure, whereas increasing the Si target power led to a gradual increase in the deposition rate and Si incorporation. The mechanical properties displayed a non-monotonic relationship with the Si target power, with film applied at an intermediate level of Si target power showing the highest hardness, approximately 28.5 GPa, and improved elastic recovery. Tribological evaluations using a GCr15 steel ball revealed that this film exhibited the lowest wear rate of 4.1 × 10⁻⁶ mm³·N⁻¹·m⁻¹ and a narrower wear track, which was attributed to reduced plastic deformation and the development of an oxygen-enriched tribofilm during sliding. High-temperature oxidation at 1000 °C in air revealed that Si incorporation significantly modified oxide-scale evolution by refining the oxidation products and altering the scale architecture, while the protection of the scale was governed by its continuity and compactness rather than its thickness alone. Oxyhydrogen-flame ablation tests revealed that the degradation behavior was primarily driven by the competition between oxidation-induced mass increase and ablation-induced material loss, with localized film disruption and substrate exposure playing a decisive role. In summary, the findings illustrate that an optimal Si target power establishes a favorable equilibrium between mechanical strength, tribological efficiency, oxidation resistance, and ablation performance, underscoring the potential of (WMoTaNb)SiN films for protective applications in complex mechanical and extreme thermal environments. Full article

Accurate crop yield forecasting is critical for securing food supplies, addressing climate-related risks, and enhancing agricultural production planning. Current predictive models often have drawbacks, including cumbersome architectures, heavy computational load, and insufficient feature mining. To resolve these issues, this study develops a lightweight prediction model designed to reduce structural complexity and computational load while maintaining high accuracy based on a symmetric dual-branch attention mechanism. This model adopts a two-branch symmetric structure: the spatial branch processes remote sensing images and geospatial data via convolutional neural networks to capture crop growth-related spatial patterns effectively. The temporal branch analyzes meteorological and yield time-series data using long short-term memory (LSTM) networks to capture temporal variation trends precisely. The outputs of the two branches are deeply integrated through feature concatenation and an adaptive weighting strategy. To test the model’s performance, this study uses county-level yield records, long-term time series, and meteorological datasets from 1980 to 2018 from major U.S. soybean-producing states as experimental inputs. This dataset is then compared with leading models like AMAP. Results show that in single-year forecasting, the model reduces RMSE by 4.1762% and boosts R² by 3.4458%—demonstrating strong short-term prediction capability. For five-year long-term forecasting, it reduces the RMSE by 3.2914% and increases the R² by 4.7537%. This effectively mitigates the performance decline of traditional models in long time-series scenarios, fully leveraging the value of in-depth mining for long-term time-series data. Full article

As deep learning models become increasingly integrated into critical decision-making systems, the need for xAI has grown paramount to ensure transparency, accountability, and trust.Post hocexplainability methods, which analyse trained models to interpret their predictions without modifying the underlying architecture, have become increasingly important, especially in fields such as healthcare and finance. Modern xAI techniques often produce feature importance rankings that fail to capture the true causal influence of features, particularly in transformer-based models. Recent quantitative metrics, such as Symmetric Relevance Gain (SRG), which measures the area between the feature corruption performance curves of the Most Important Feature (MIF) and the Least Important Feature (LIF), provide a more rigorous basis for evaluating explanation fidelity. In this study, we first show that existing xAI methods exhibit consistently poor performance under the SRG criterion when explaining transformer-based text classifiers. To address these limitations, we introduceEvoDropX, a novel framework that formulates explanation as an optimisation problem. EvoDropX leverages Grammatical Evolution (GE) to evolve sequences of feature corruption with the explicit objective of maximising SRG, thereby identifying features that most strongly influence model predictions. EvoDropX provides interventional, input–output (behavioural) explanations and does not attempt to infer or interpret internal model mechanisms. Through comprehensive experiments across multiple datasets (IMDB, Stanford Sentiment Treebank (SST-2), Amazon Polarity (AP)), multiple transformer models (BERT, roberta, distilbert), and multiple metrics (SRG, MIF, LIF, Counterfactual Conciseness (CFC)), we demonstrate that EvoDropX significantly outperforms all state-of-the-art (SOTA) xAI baselines including Attention-Aware Layer-Wise Relevance Propagation for Transformers (AttnLRP), SHapley Additive exPlanations (SHAP), and Local Interpretable Model-agnostic Explanations (LIME), when evaluated using intervention-based faithfulness criteria. Notably, EvoDropX achieves $74.77\%$ improvement in SRG than the best-performing baseline on the IMDB dataset with the BERT model, with consistent improvements observed across all dataset-model pairs. Finally, qualitative and linguistic analyses reveal that EvoDropX captures both sentiment-bearing terms and their structural relationships within sentences, yielding explanations that are both faithful and interpretable. Full article

Mixers are integral components in RF circuits for frequency conversion and are present in almost all RF front-ends. The relentless advancement of mobile communication standards, particularly towards 5G-Advanced and 6G, imposes ever more stringent and multi-dimensional performance requirements on mixer design. While previous surveys have capably summarized mixer technologies, this review distinguishes itself by providing a comprehensive and critical examination of millimeter-wave and sub-THz silicon-based integrated mixers, with explicit coverage extended from core RF bands to beyond 170 GHz. We place particular emphasis on the unique challenges and trade-offs inherent to silicon (CMOS and SiGe BiCMOS) platforms at these high frequencies. This work first summarizes the structural frameworks and underlying principles of mixers, examines multiple mixer variants, and performs an in-depth analysis of their key performance characteristics, encompassing conversion gain, noise figure (with distinctions between single-sideband (SSB) and double-sideband (DSB) definitions), isolation, and related metrics. Then, it compares and discusses the design of several mixers, especially analyzing their innovative points and key technologies, while critically evaluating their inherent limitations and trade-offs. Furthermore, a dedicated section synthesizes the most recent research trends, including heterogeneous integration, AI/ML-assisted design, and mixer architectures for integrated sensing and communication (ISAC), thereby addressing a notable gap in the current literature. Finally, it concludes with an outlook on future challenges and opportunities for mixers in next-generation communication systems. Full article

Accurate segmentation of breast cancer regions in histopathological images is critical for advancing computer-aided diagnostic systems, yet challenges persist due to heterogeneous tissue structures, staining variations, and the need to capture features across multiple scales. This study introduces MSB-UNet, a novel Multi-Scale Bifurcated U-Net architecture designed to address these challenges through a dual-pathway encoder–decoder framework that processes images at multiple resolutions simultaneously. By integrating a bifurcated encoder with a Feature Fusion Module, MSB-UNet effectively captures fine-grained cellular details and broader tissue-level patterns. MSB-UNet is formulated as a binary segmentation framework (tumor vs. outside region of interest), producing a two-channel probability map via a channel-wise Softmax output. Evaluated on a publicly available breast cancer histopathology dataset, MSB-UNet achieves a Dice Similarity Coefficient (DSC) of 91.3% and a mean Intersection over Union (mIoU) of 84.4%, outperforming state-of-the-art segmentation models. The architecture demonstrates better results compared to other baseline methods and has the potential to enhance automated diagnostic tools for breast cancer histopathology. Full article

Mn-based layered oxide cathodes are pivotal for advancing sodium-ion batteries, yet their practical deployment is hindered by structural instability and complex phase transformations during cycling. This review provides a systematic overview of recent strategies aimed at rational design and performance enhancement of these materials. It begins with fundamental thermodynamic principles governing phase formation, particularly P2/O3 structural dichotomy, and highlights the critical roles of sodium content, transition metal chemistry, and ionic potential in determining crystal stability. The emergence of high-entropy engineering is examined as a powerful approach to suppress detrimental phase transitions through configurational entropy stabilization, lattice distortion, and synergistic multi-element interactions. Furthermore, the integration of machine learning with multidimensional descriptors including electronegativity-weighted entropy and cationic potential enables more accurate predictions of phase behavior in complex compositional spaces. The review also highlights the decisive influence of synthesis protocols, where precise control over calcination conditions, atmosphere, and local elemental distribution enables the formation of targeted phase architectures, such as P2/O3 intergrowth, which exhibit superior electrochemical robustness. Collectively, these advances illustrate a shift from empirical trial and error toward a theory-guided, data-informed framework for designing high-performance layered oxide cathodes. Full article

Facial expression recognition (FER) in naturalistic settings is constrained by label ambiguity and variability in stimulus–response alignment. Adopting a data-centric perspective, this study examined whether emotional intelligence (EI)-stratified training data influence FER performance by treating EI as a qualitative factor associated with affective data consistency. Naturally elicited facial expressions were collected in a controlled emotion induction experiment with subjective arousal and valence ratings. Using response-driven labeling, neutral ratings were retained as indicators of ambiguity. Participants were grouped into High and Low EI based on the alignment between subjective evaluations and outputs from a pretrained affect estimator. Identical binary classifiers for arousal and valence recognition were trained while varying only the training data composition and evaluated across baseline, unambiguous, and ambiguous test sets using independent training repetitions with repetition-level statistical aggregation. EI-stratified training was associated with statistically detectable, context-dependent performance differences: group effects were observed primarily under baseline conditions and, to a lesser extent, under ambiguous conditions, whereas no reliable differences emerged under unambiguous conditions. Pooled discrimination differences were modest, but item-level analyses identified significant differences in classification correctness in specific task–condition combinations. Comparable patterns were observed across alternative backbone architectures. These findings indicate that FER performance in naturalistic contexts is influenced not only by model architecture but also by the statistical structure and internal coherence of the training data, supporting EI-informed data selection in ambiguity-prone scenarios. Full article

Network intrusion detection is a core component of modern cybersecurity, but it remains challenging due to highly imbalanced traffic, heterogeneous feature types, and a presence of short-term temporal dependencies in network flows. Traditional machine learning models often rely on handcrafted features and struggle with complex attack patterns, while deep learning approaches may become overly complex or difficult to interpret. In this paper, we propose a neural intrusion detection method that combines structured feature preprocessing with a compact hybrid architecture. Numerical and categorical traffic features are processed separately using robust normalisation and trainable embeddings, and then merged into an unified representation. The proposed model builds on a multi-scale feature interaction block, followed by channel-wise attention and a single bidirectional gated recurrent unit layer with attention pooling to capture short-term temporal behavior. The method is evaluated on two widely used benchmark datasets, i.e., the CIC-IDS2017 and CSE-CIC-IDS2018 dataset. Experimental results show that the proposed approach consistently outperforms the classical machine learning baselines and achieves competitive or superior performance compared to the recent deep learning methods proposed in the literature. The results confirm that the proposed architectural choices effectively capture both feature interactions and temporal patterns in network traffic. Full article

In bulk heterojunction (BHJ) organic solar cells (OSCs) employing perylene diimide (PDI)-based non-fullerene acceptors, excessive intermolecular interactions among PDI units lead to severe aggregation and pronounced donor–acceptor phase separation, both of which critically limit device performance. To address these issues, numerous structurally engineered PDI derivatives have been developed. In particular, twisted multi-PDI architectures designed to suppress intermolecular aggregation have shown improved morphological control; however, such twisted structures are often highly amorphous, which reduces electron-transport efficiency and constrains OSC performance. In this work, we introduce a mixed-acceptor strategy combining a twisted PDI dimer (SF-PDI₂) with a planar monomeric PDI (m-PDI) to balance aggregation and morphological uniformity. Ternary blend OSCs consisting of PTB7-Th as the donor and these two PDI acceptors exhibit systematic performance variations depending on their relative ratios. At the optimized composition (SF-PDI₂:m-PDI = 90:10 by weight), the device outperforms single-acceptor systems, which is attributed to controlled aggregation arising from the complementary structural features of the two PDI acceptors. This study demonstrates that combining mixed PDI acceptors with similar molecular moieties enables precise control of aggregation, improving both morphology and photovoltaic performance. Full article

Remote sensing semantic segmentation is fundamental for fine-grained urban scene understanding, which in turn provides pixel-level semantic insights for urban development and environmental surveillance. However, existing hybrid segmentation architectures fail to incorporate intrinsic geometric and physical priors, inevitably leading to structural fragmentation, boundary ambiguity, and spatial misalignment of heterogeneous features. Therefore, we propose a Superpixel-Tokenized and Frequency-Modulated Hybrid CNN–Transformer network (SFCT-Net) for remote sensing semantic segmentation. The proposed network integrates superpixel tokens and high-frequency constraints to preserve structural integrity and boundary precision. First, our Superpixel-Tokenized Linear Position Attention (STLPA) module replaces rigid window tokens with semantic superpixels to ensure object integrity with linear computational complexity. Second, we construct a Frequency-Modulated Deformable Edge Refinement (FMDER) module that leverages high-frequency spectral priors to modulate deformable sampling, achieving robust boundary recovery. Finally, we develop the Spatial–Semantic Feature Coupling (SSFC) module, which employs a dual-branch strategy to correct spatial drift and align deep semantic features with shallow details. Experiments conducted on our self-built Taiyuan Satellite Remote Sensing Dataset (TSRSD) along with the ISPRS Vaihingen and Potsdam benchmark datasets demonstrate that our proposed SFCT-Net delivers state-of-the-art performance and efficiency by fusing superpixel and frequency priors for robust structural and boundary recovery. Full article

Current Facial expression recognition methods typically extract facial features indiscriminately, incorporating expression-irrelevant information that compromises recognition accuracy. To overcome this, we propose Multi-stage Feature Sparse Constraints (MFSC), a novel model that integrates a Multi-scale Attention-based Sparse Window Selection (MSAWS) mechanism with key region graph learning. Notably, MFSC operates without dependence on pre-extracted facial landmarks, enabling more flexible deployment. The MSAWS mechanism progressively filters redundant features through multi-stage sparse attention, adaptively selecting the most discriminative facial patches. The selected tokens are structured into a dynamic graph to model regional relationships via graph neural networks (GNNs). Critically, our framework further introduces a global-guided fusion module, which effectively integrates fine-grained local features from an IR50 backbone with the global topological features from the GNN through cross-attention. This integration enables complementary strengths, where local details are enhanced by global semantic context. Comprehensive experiments on RAF-DB, FER2013, and AffectNet-7 datasets demonstrate MFSC’s superior performance, achieving state-of-the-art accuracy of 92.31%, 76.21%, and 67.35%, respectively. These results validate the effectiveness of our approach in focusing computational resources on expression-salient regions while maintaining a lightweight and efficient architecture. Full article

We develop and evaluate a deep contextual bandit framework for multivariate off-policy evaluation within a controlled simulation-based validation setting. Using real covariate distributions from the Adult, Boston Housing, and Wine Quality datasets, we construct synthetic treatment assignments and multivariate potential outcomes to enable rigorous benchmarking under known data-generating processes. We compare CNN-LSTM, LSTM, and Feed-forward Neural Network (FNN) architectures as nonlinear action-value estimators. To examine representation learning under structured dependence, an $AR\left(1\right)$ feature augmentation scheme is employed, while multivariate outcomes are standardized using empirical copula transformations to preserve cross-dimensional dependence. Policy values are estimated using Stabilized Importance Sampling (SIPS) and doubly robust (DR) estimators with bootstrap inference. Although the decision problem is strictly one-step, empirical results indicate that CNN-LSTM architectures provide competitive action-value calibration under temporal augmentation. Across all datasets, the DR estimator demonstrates substantially lower variance and greater stability than SIPS, consistent with its theoretical variance-reduction properties. Diagnostic analyses—including propensity overlap assessment, cumulative oracle regret (with oracle values known by construction), calibration evaluation, and sensitivity analysis—support the reliability of the proposed evaluation framework. Overall, the results demonstrate that combining copula-normalized multivariate outcomes with doubly robust off-policy evaluation yields a statistically principled and variance-efficient approach for offline policy learning in high-dimensional simulated environments. Full article

In complex traffic environments, image degradation caused by haze, low illumination, and occlusion significantly undermines the reliability of vehicle and pedestrian detection. To address these challenges, this paper proposes an aerial vision framework that tightly couples multi-level image enhancement with a lightweight detection architecture. At the image preprocessing stage, a cascaded “dehazing + enhancement” module is constructed, where a learning-based dehazing method is employed to restore long-range details affected by scattering artifacts. Additionally, structural fidelity is enhanced in low-light regions, while global brightness consistency is achieved. On the detection side, a lightweight yet robust detection architecture, termed GDEIM-SF, is designed. It adopts GoldYOLO as the lightweight backbone and integrates D-FINE as an anchor-free decoder. Moreover, two key modules, CAPR and ASF, are incorporated to enhance high-frequency edge modeling and multi-scale semantic alignment. Through evaluation on the VisDrone dataset, the proposed method achieves improvements of approximately 2.5 to 2.7 percentage points in core metrics such as mAP@50-90 compared to similar lightweight models, while maintaining a low parameter count and computational overhead. This ensures a balanced trade-off among detection accuracy, inference efficiency, and deployment adaptability, providing a practical and efficient solution for UAV-based visual perception tasks under challenging imaging conditions. Full article