Search Results (26,838)

With the escalating global cyber threats, Distributed Denial of Service (DDoS) attacks have become one of the most disruptive and prevalent network attacks. Traditional DDoS detection systems face significant challenges due to the unpredictable nature, diverse protocols, and coupled behavioral patterns of attack traffic. To address this issue, this paper proposes a novel approach for DDoS attack detection by leveraging the Transformer architecture to model both temporal dependencies and behavioral patterns, significantly improving detection accuracy. We utilize the global attention mechanism of the Transformer to effectively capture long-range temporal correlations in network traffic, and the model’s ability to process multiple traffic features simultaneously enables it to identify nonlinear interactions. By reconstructing the CIC-DDoS2019 dataset, we strengthen the representation of attack behaviors, enabling the model to capture dynamic attack patterns and subtle traffic anomalies. This approach represents a key contribution by applying Transformer-based self-attention mechanisms to accurately model DDoS attack traffic, particularly in handling complex and dynamic attack patterns. Experimental results demonstrate that the proposed method achieves 99.9% accuracy, with 100% precision, recall, and F1 score, showcasing its potential for high-precision, low-false-alarm automated DDoS attack detection. This study provides a new solution for real-time DDoS detection and holds significant practical implications for cybersecurity systems. Full article

The proposed study explores the consistency of the geometrical character of surfaces under scaling, rotation and translation. In addition to its mathematical significance, it also exhibits advantages over image processing and economic applications. In this paper, the authors used partition-based principal component analysis similar to two-dimensional Sub-Image Principal Component Analysis (SIMPCA), along with a suitably modified atypical wavelet transform in the classification of 2D images. The proposed framework is further extended to three-dimensional objects using machine learning classifiers. To strengthen fairness, we benchmarked against both Random Forest (RF) and Support Vector Machine (SVM) classifiers using nested cross-validation, showing consistent gains when TIFV is included. In addition, we carried out a robustness analysis by introducing Gaussian noise to the intensity channel, confirming that TIFV degrades much more gracefully compared to traditional descriptors. Experimental results demonstrate that the method achieves improved performance compared to traditional hand-crafted descriptors such as measured values and histogram of oriented gradients. In addition, it is found to be useful that this proposed algorithm is capable of establishing consistency locally, which is never possible without partition. However, a reasonable amount of computational complexity is reduced. We note that comparisons with deep learning baselines are beyond the scope of this study, and our contribution is positioned within the domain of interpretable, affine-invariant descriptors that enhance classical machine learning pipelines. Full article

Accelerated artificial aging of zinc oxide (ZnO)-based acrylic artists’ paint, filled with calcium carbonate (CaCO₃) as an extender, was carried out for a total of 1963 h (~8 × 10⁷ lux·h), with assessments at specific intervals. The total color difference ΔE* was <2 (CIELab-76 system) over 1725 h of aging, while the human eye notices color change at ΔE* > 2. Oxidative degradation of organic components in the paint to form volatile products was revealed by attenuated total reflectance–Fourier transform infrared (ATR-FTIR) spectroscopy, micro-Raman spectroscopy, and scanning electron microscopy with energy-dispersive X-ray spectroscopy (SEM-EDS). It appears that deep oxidation of organic intermediates and volatilization of organic matter may be responsible for the relatively small value of ΔE* color difference during aging of the samples. To elucidate the degradation pathways, principal component analysis (PCA) was applied to the spectral data, revealing: (1) the catalytic role of ZnO in accelerating photodegradation, (2) the Kolbe photoreaction, (3) the decomposition of the binder to form volatile degradation products, and (4) the relative photoinactivity of CaCO₃ compared with ZnO, showing slower degradation in areas with a higher CaCO₃ content compared with those dominated by ZnO. These results provide fundamental insights into formulation-specific degradation processes, offering practical guidance for the development of more durable artist paints and conservation strategies for acrylic artworks. Full article

To address the fragmentation and weak correlation of knowledge in the design method domain, this paper proposes a framework for constructing a knowledge graph driven by multi-source heterogeneous data. The process involves collecting multi-source heterogeneous data and subsequently utilizing text mining and natural language processing techniques to extract design themes and method elements. A “theme–stage–attribute” three-dimensional mapping model is established to achieve semantic coupling of knowledge. The BERT-BiLSTM-CRF (Bidirectional Encoder Representations from Transformers-Bidirectional Long Short-Term Memory-Conditional Random Field) model is employed for entity recognition and relation extraction, while the Sentence-BERT (Sentence Bidirectional Encoder Representations from Transformers) model is used to perform multi-source knowledge fusion. The Neo4j graph database facilitates knowledge storage, visualization, and querying, forming the basis for developing a prototype of a design method recommendation system. The framework’s effectiveness was validated through experiments on extraction performance and knowledge graph quality. The results demonstrate that the framework achieves an F1 score of 91.2% for knowledge extraction, and an 8.44% improvement over the baseline. The resulting graph’s node and relation coverage reached 94.1% and 91.2%, respectively. In complex semantic query tasks, the framework shows a significant advantage over traditional classification systems, achieving a maximum F1 score of 0.97. It can effectively integrate dispersed knowledge in the field of design methods and support method matching throughout the entire design process. This research is of significant value for advancing knowledge management and application in innovative product design. Full article

Efficient routing optimization remains a pivotal challenge in Electronic Design Automation (EDA), as it profoundly influences circuit performance, power consumption, and manufacturing cost. The Rectilinear Steiner Minimum Tree (RSMT) problem plays a crucial role in this process by minimizing the routing length through the introduction of Steiner points. This paper proposes a reinforcement learning-driven RSMT construction model that incorporates a novel Selective Kernel Transformer Network (SKTNet) encoder to enhance feature representation. SKTNet integrates a Selective Kernel Convolution (SKConv) and an improved Macaron Transformer to improve multi-scale feature extraction and global topology modeling. Additionally, Self-Critical Sequence Training (SCST) is employed to optimize the policy by leveraging a greedy-decoded baseline sequence for the advantage computation. Experimental results demonstrate superior performance over state-of-the-art methods in wirelength optimization. Ablation studies further validate the contribution of this model, highlighting its effectiveness and scalability for routing. Full article

This paper presents a comprehensive study on automated defect detection in complex structures using phased array ultrasonic testing data, focusing on both traditional signal processing and advanced deep learning methods. As a non-AI baseline, the well-known signal-to-noise ratio algorithm was improved by introducing automatic depth gate calculation using derivative analysis and eliminated the need for manual parameter tuning. Even though this method demonstrates robust flaw indication, it faces difficulties for automatic defect detection in highly noisy data or in cases with large pore zones. Considering this, multiple DL architectures—including fully connected networks, convolutional neural networks, and a novel Convolutional Attention Temporal Transformer for Sequences—are developed and trained on diverse datasets comprising simulated CIVA data and real-world data files from welded and composite specimens. Experimental results show that while the FCN architecture is limited in its ability to model dependencies, the CNN achieves a strong performance with a test accuracy of 94.9%, effectively capturing local features from PAUT signals. The CATT-S model, which integrates a convolutional feature extractor with a self-attention mechanism, consistently outperforms the other baselines by effectively modeling both fine-grained signal morphology and long-range inter-beam dependencies. Achieving a remarkable accuracy of 99.4% and a strong F1-score of 0.905 on experimental data, this integrated approach demonstrates significant practical potential for improving the reliability and efficiency of NDT in complex, heterogeneous materials. Full article

Rural landscapes are changing rapidly, yet many assessments remain descriptive and weakly connected to planning instruments. This study connects rural landscape analysis with planning and management by examining post-earthquake transformations in Topaktaş (Tuşba, Van), a village redesigned and relocated after the 2011 events. Using ArcGIS 10.8 and the Analytic Hierarchy Process (AHP), we integrate DEM, slope, aspect, CORINE land cover Plus, surface-water presence/seasonality, and proximity to hazards (active and surface-rupture faults) and infrastructure (Karasu Stream, highways, village roads). A risk overlay is treated as a hard constraint. We produce suitability maps for settlement, agriculture, recreation, and industry; derive a composite optimum land-use surface; and translate outputs into decision rules (e.g., a 0–100 m fault no-build setback, riparian buffers, and slope thresholds) with an outline for implementation and monitoring. Key findings show legacy footprints at lower elevations, while new footprints cluster near the upper elevation band (DEM range 1642–1735 m). Most of the area exhibits 0–3% slopes, supporting low-impact access where hazards are manageable; however, several newly designated settlement tracts conflict with risk and water-service conditions. Although limited to a single case and available data resolutions, the workflow is transferable: it moves beyond mapping to actionable planning instruments—zoning overlays, buffers, thresholds, and phased management—supporting sustainable, culturally informed post-earthquake reconstruction. Full article

Artificial intelligence-based image processing is critical for sensor fusion and image transformation in mobility systems. Advanced driver assistance functions such as forward monitoring and digital side mirrors are essential for driving safety. Degradation due to raindrops, fog, and high-dynamic range (HDR) imbalance caused by lighting changes impairs visibility and reduces object recognition and distance estimation accuracy. This paper proposes a diffusion framework to enhance visibility under multi-degradation conditions. The denoising diffusion probabilistic model (DDPM) offers more stable training and high-resolution restoration than the generative adversarial networks. The DDPM relies on large-scale paired datasets, which are difficult to obtain in raindrop scenarios. This framework applies the Palette diffusion model, comprising data augmentation and raindrop-removal modules. The data augmentation module generates raindrop image masks and learns inpainting-based raindrop synthesis. Synthetic masks simulate raindrop patterns and HDR imbalance scenarios. The raindrop-removal module reconfigures the Palette architecture for image-to-image translation, incorporating the augmented synthetic dataset for raindrop removal learning. Loss functions and normalization strategies improve restoration stability and removal performance. During inference, the framework operates with a single conditional input, and an efficient sampling strategy is introduced to significantly accelerate the process. In post-processing, tone adjustment and chroma compensation enhance visual consistency. The proposed method preserves fine structural details and outperforms existing approaches in visual quality, improving the robustness of vision systems under adverse conditions. Full article

This study aims to address the problem that traditional helical gears generate significant axial forces during transmission and innovatively proposes a design scheme of double helical face gears (DHFG). An accurate mathematical model of the tooth surface is established using spatial meshing theory and coordinate transformation. A systematic investigation using the orthogonal test method is then conducted to analyze the influence of key parameters, such as the pinion tooth number, transmission ratio, and helix angle, on gear performance. The finite element analysis results show that the overlap degree of this double helical tooth surface gear pair in actual transmission can reach 2–3, demonstrating excellent transmission smoothness. More importantly, its unique symmetrical tooth surface structure successfully achieves the self-balancing effect of axial force. Simulation verification shows that the axial force is reduced by approximately 70% compared to traditional helical tooth surface gears, significantly reducing the load on the bearing. Finally, the prototype gear is successfully trial-produced through a five-axis machining center. Experimental tests confirmed that the contact impressions are highly consistent with the simulation results, verifying the feasibility of the design theory and manufacturing process. Full article

High-quality development highlights the importance of environmental protection and green low-carbon development. The high-quality development of the manufacturing industry is not only the key content for achieving green transformation, but also an important cornerstone for building a modern national industrial system. Current research focuses on companies and governments, ignoring the important value of suppliers and consumers. As a result, existing mechanisms have failed to deliver the desired results. This paper constructs an evolutionary game model involving manufacturing enterprises, local governments, suppliers, and consumers, and systematically analyzes the strategy selection process of the four participating populations. On this basis, the impact of exogenous and endogenous factors on the evolutionarily stable strategy is studied at the microscopic level using numerical simulation methods. The results show that (1) increasing any of the endogenous factors, such as innovative capability, organization building, and industrial resources, can accelerate the evolution of manufacturing enterprises evolve to smart upgrade strategy. (2) Increasing any one of the exogenous factors, such as policy environment, industrial cooperation, and market demand, can accelerate the rate at which manufacturing enterprises choose to adopt the strategy of smart upgrade. The purpose of this paper is to provide a theoretical reference for the behavioral strategies of manufacturing enterprises, and to provide a realistic reference for local governments to build a mechanism to promote the high-quality development of the manufacturing industry. Full article

To investigate the influence of surface films on the material removal mechanism of single-crystal silicon during nanogrinding, molecular dynamics (MD) simulations were performed under different surface-film conditions. The simulations examined atomic displacements, grinding forces, radial distribution functions (RDF), phase transformations, temperature distributions, and residual stress distributions to elucidate the damage mechanisms at the surface and subsurface on the nanoscale. In this study, boron nitride (BN) and graphene films were applied to the surface of single-crystal silicon workpieces for nanogrinding simulations. The results reveal that both BN and graphene films effectively suppress chip formation, thereby improving the surface quality of the workpiece, with graphene showing a stronger inhibitory effect on atomic displacements. Both films reduce tangential forces and mitigate grinding force fluctuations, while increasing normal forces; the increase in normal force is smaller with BN. Although both films enlarge the subsurface damage layer (SDL) thickness and exhibit limited suppression of crystalline phase transformations, they help to alleviate surface stress release. In addition, the films reduce the surface and subsurface temperatures, with graphene yielding a lower temperature. Residual stresses beneath the abrasive grain are also reduced when either film is applied. Overall, BN and graphene films can enhance the machined surface quality, but further optimization is required to minimize subsurface damage (SSD), providing useful insights for the optimization of single-crystal silicon nanogrinding processes. Full article

Pineapple leaf fibers (PALFs), obtained from abundant yet underutilized pineapple leaf residues, represent a promising feedstock for producing fibrillated cellulose. In this work, cellulosic fibers were isolated and characterized by Fiber Quality Analysis (FQA), showing lengths between 0.33 and 0.47 mm and widths of 12.2 µm after organosolv pulping using ethanol and acetic acid as a catalyst, followed by hydrogen peroxide bleaching with diethylenetriaminepentaacetic acid as a chelating agent. The cellulosic fibers were then subjected to TEMPO-mediated oxidation and subsequently disintegrated by microfluidization to produce micro-/nanofibrillated cellulose (MNFC) with a carboxylate content of 0.85 and 1.00 mmol COO⁻/g, zeta potential of −41 and −53 mV, and average widths of 15 and 12 nm for unbleached and bleached nanofibrils, respectively. The nanofibrillation yields were 73% and 68% for the bleached and unbleached MNFC samples, indicating the presence of some non-fibrillated or partially fibrillated fractions. X-ray diffraction analysis confirmed preservation of cellulose type I crystalline structure, with increased crystallinity, reaching 85% in the bleached MNFC. These findings demonstrate the feasibility of a sequential process, combining organosolv pulping, hydrogen peroxide bleaching, TEMPO-mediated oxidation, and microfluidization, for preparing MNFC from pineapple leaf fibers. Overall, this study highlights pineapple leaf residues as a sustainable source of MNFC, supporting strategies to transform agricultural waste into valuable bio-based materials. Full article

In this article, we present a novel reinforcement learning-based framework in the discrete cosine transform to achieve better image steganography. First, the input image is divided into several blocks to extract semantic and structural features, evaluating their suitability for data embedding. Second, the Proximal Policy Optimization algorithm (PPO) is introduced in the block selection process to learn adaptive embedding policies, which effectively balances image fidelity and steganographic security. Moreover, the Deep Q-network (DQN) is used for adaptively adjusting the weights of the peak signal-to-noise ratio, structural similarity index, and detection accuracy in the reward formulation. Experimental results on the BOSSBase dataset confirm the superiority of our framework, achieving both lower detection rates and higher visual quality across a range of embedding payloads, particularly under low-bpp conditions. Full article

Photocatalytic membrane reactors (PMRs), which combine photocatalysis with membrane separation, represent a pivotal technology for sustainable water treatment and resource recovery. Although extensive research has documented various configurations of photocatalytic-membrane hybrid processes and their potential in water treatment applications, a comprehensive analysis of the interrelationships among reactor architectures, intrinsic physicochemical mechanisms, and overall process efficiency remains inadequately explored. This knowledge gap hinders the rational design of highly efficient and stable reactor systems—a shortcoming that this review seeks to remedy. Here, we critically examine the connections between reactor configurations, design principles, and cutting-edge applications to outline future research directions. We analyze the evolution of reactor architectures, relevant reaction kinetics, and key operational parameters that inform rational design, linking these fundamentals to recent advances in solar-driven hydrogen production, CO₂ conversion, and industrial scaling. Our analysis reveals a significant disconnect between the mechanistic understanding of reactor operation and the system-level performance required for innovative applications. This gap between theory and practice is particularly evident in efforts to translate laboratory success into robust and economically feasible industrial-scale operations. We believe that PMRs will realize their transformative potential in sustainable energy and environmental applications in future. Full article

This study presents a sustainable upcycling strategy to convert “Pit,” a carbon-rich coke oven by-product from steel manufacturing, into high-purity graphite for use as an anode material in lithium-ion batteries. Despite its high carbon content, raw Pit contains significant impurities and has irregular particle morphology, which limits its direct application in batteries. We employed a multi-step, additive-free refinement process—including jet milling, spheroidization, and high-temperature graphitization—to enhance carbon purity and structural properties. The processed Pit-derived graphite showed a much-improved particle size distribution (D50 reduced from 25.3 μm to 14.8 μm & Span reduced from 1.72 to 1.23), increased tap density (from 0.54 to 0.80 g/cm³), and reduced BET surface area, making it suitable for high-performance lithium-ion batteries anodes. Structural characterization by XRD and TEM confirmed dramatically enhanced crystallinity after graphitization (graphitization degree increasing from ~13 for raw Pit to 95.7% for graphitized Pit at 3000 °C). The fully processed graphite (denoted S_Pit3000) delivered a reversible discharge capacity of 346.7 mAh/g with an initial Coulombic efficiency of 93.5% in half-cell tests—comparable to commercial artificial graphite. Furthermore, when composited with silicon oxide to form a hybrid anode, the material achieved an even higher capacity of 418.0 mAh/g under high mass loading conditions. These results highlight the feasibility of transforming industrial coke waste into value-added electrode materials through environmentally friendly physical processes. The upcycled graphite anode meets industrial performance standards, demonstrating a promising route toward circular economy solutions in both the steel and battery industries. Full article