Search Results (83)

Copy-move forgery detection (CMFD) is a crucial image forensics analysis technique. The rapid development of deep learning algorithms has led to impressive advancements in CMFD. However, existing models suffer from two key limitations: Their feature fusion modules insufficiently exploit the complementary nature of features from the RGB domain and noise domain, resulting in suboptimal feature representations. During decoding, they simply classify pixels as authentic or forged, without aggregating cross-layer information or integrating local and global attention mechanisms, leading to unsatisfactory detection precision. To overcome these limitations, a robust detection and localization approach to image copy-move forgery using multi-feature fusion is proposed. Firstly, a Multi-Feature Fusion Network (MFFNet) was designed. Within its feature fusion module, features from both the RGB domain and noise domain were fused to enable mutual complementarity between distinct characteristics, yielding richer feature information. Then, a Lightweight Multi-layer Perceptron Decoder (LMPD) was developed for image reconstruction and forgery localization map generation. Finally, by aggregating information from different layers and combining local and global attention mechanisms, more accurate prediction masks were obtained. The experimental results demonstrate that the proposed MFFNet model exhibits enhanced robustness and superior detection and localization performance compared to existing methods when faced with JPEG compression, noise addition, and resizing operations. Full article

This article explores Vsevolod Meyerhold’s biomechanics as an avant-garde theatrical and anthropotechnical method developed to forge new subjectivity and redefine roles in post-revolutionary society. It delves into early Soviet avant-garde theatre’s emphasis on movement as a core expressive tool and the transformation of the actor’s body into a precise instrument for calibrated gestures. Methodologically, the research is based on cultural studies examining relations between art processes and the functioning of social institutions. The article also analyzes a significant corpus of recently published archival materials related to Meyerhold’s development of biomechanical elements and details the structure of Meyerhold’s exercises and their role in enhancing motor skills and expressiveness on stage. The purpose of this article is to interpret biomechanics in the socio-cultural context of early Soviet times, while also examining it as a complex system transcending mere theatrical training. The key finding of the article is that the development of biomechanics encompassed not only theatrical, scientific, and social aspects but also proved close to the ideas of philosophy of Russian anthropocosmism. Full article

Semantic segmentation of workpieces and die cavities is critical for intelligent process monitoring and quality control in hammer die-forging. However, the field of 3D point cloud segmentation currently faces prominent limitations in forging scenario adaptation: existing state-of-the-art (SOTA) methods are predominantly optimized for road driving or indoor scenes, where targets have stable poses and regular surfaces. They lack dedicated designs for capturing the fine-grained deformation characteristics of forging workpieces and alleviating multi-scale feature misalignment caused by large pose variations—key pain points in forging segmentation. Consequently, these methods fail to balance segmentation accuracy and real-time efficiency required for practical forging applications. To address this gap, this paper proposes a novel semantic segmentation framework fusing 3D point cloud and bird’s-eye-view (BEV) representations for complex die-forging scenes. Specifically, a Star-based encoding module is designed in the BEV encoding stage to enhance capture of fine-grained workpiece deformation characteristics. A hierarchical feature-offset alignment mechanism is developed in decoding to alleviate multi-scale spatial and semantic misalignment, facilitating efficient cross-layer fusion. Additionally, a weighted adaptive fusion module enables complementary information interaction between point cloud and BEV modalities to improve precision.We evaluate the proposed method on our self-constructed simulated and real die-forging point cloud datasets. The results show that when trained solely on simulated data and tested directly in real-world scenarios, our method achieves an mIoU that surpasses RPVNet by $1.1\%$. After fine-tuning with a small amount of real data, the mIoU further improves by $5\%$, reaching optimal performance. Full article

This study investigates a hybrid processing route that integrates localized fusion-based additive manufacturing and hot forging for the production of complex-shaped components, with emphasis on metallurgical integrity and mechanical performance. The DIN 8555 E6-UM-60 alloy, traditionally classified as martensitic and applied under severe wear conditions, exhibited atypical metallurgical behavior during hybrid processing, notably the consistent formation of chromium carbides under specific thermomechanical conditions. Metallographic analyses, microhardness measurements, thermographic monitoring, hot tensile tests, and room-temperature tensile tests were performed to establish correlations between microstructure, thermal history, and mechanical response. Specimens produced by additive manufacturing and subsequently hot forged showed a significant reduction in porosity, improved microstructural homogeneity, and partial retention of hardening phases, enabling discussion of recrystallization mechanisms, phase stabilization, and precipitation phenomena in martensitic alloys processed by additive manufacturing. Hot tensile tests revealed limited hot workability of the alloy, while room-temperature tensile tests led to premature fracture, with failure consistently initiating at pre-existing microcracks formed during the forging stage. Although detrimental, these microcracks provide valuable insight into critical processing conditions and ductility limits of the material. Overall, the hybrid route demonstrates strong potential for industrial applications, highlighting the importance of precise thermomechanical cycle control to mitigate defects and enhance structural reliability. Full article

Detecting surface defects in forgings is crucial for ensuring the reliability of automotive components such as steering knuckles. In fluorescent magnetic particle inspection (FDMPI) images, normal forging surfaces generally exhibit locally symmetric texture patterns, whereas cracks and other flaws appear as locally asymmetric regions. Traditional FDMPI inspection relies on manual visual judgement, which is inefficient and error-prone. This paper introduces SDDNet, a symmetry-aware deep learning model for surface defect detection in FDMPI images. A dedicated FDMPI dataset is constructed and further expanded using a denoising diffusion probabilistic model (DDPM) to improve training robustness. To better separate symmetric background textures from asymmetric defect cues, SDDNet integrates a UPerNet-based segmentation layer for background suppression and a Scale-Variant Inception Module (SVIM) within an RTMDet framework for multi-scale feature extraction. Experiments show that SDDNet effectively suppresses background noise and significantly improves detection accuracy, achieving a mean average precision (mAP) of 45.5% on the FDMPI dataset, 19% higher than the baseline, and 71.5% mAP on the NEU-DET dataset, outperforming existing methods by up to 8.1%. Full article

The quantity, size, and distribution of non-metallic inclusions in High-Strength Low-Alloy (HSLA) steel critically influence its service performance. Conventional detection methods often fail to adequately characterize extreme inclusion distributions in large-section components. This study developed an integrated full-process inclusion analysis system combining high-precision motion control, parallel optical imaging, and laser spectral analysis technologies to achieve rapid and automated identification and compositional analysis of inclusions in meter-scale samples. Through systematic investigation across the industrial process chain—from a dia. 740 mm consumable electrode to a dia. 810 mm electroslag remelting (ESR) ingot and finally to a dia. 400 mm forged billet—key process-specific insights were obtained. The results revealed the effective removal of Type D (globular oxides) inclusions during ESR, with their counts reducing from over 8000 in the electrode to approximately 4000–7000 in the ingot. Concurrently, the mechanism underlying the pronounced enrichment of Type C (silicates) in the ingot tail was elucidated, showing a nearly fourfold increase to 1767 compared to the ingot head, attributed to terminal solidification segregation and flotation dynamics. Subsequent forging further demonstrated exceptional refinement and dispersion of all inclusion types. The billet tail achieved exceptionally high purity, with counts of all inclusion types dropping to extremely low levels (e.g., Types A, B, and C were nearly eliminated), representing a reduction of approximately one order of magnitude. Based on these findings, enhanced process strategies were proposed, including shallow molten pool control, slag system optimization, and multi-dimensional quality monitoring. An intelligent analysis framework integrating a YOLOv11 detection model with spectral feedback was also established. This work provides crucial process knowledge and technological support for achieving the quality control objective of “known and controllable defects” in HSLA steel. Full article

The critical shortage of donor organs remains the foremost challenge in transplantation medicine. Nevertheless, advancements in robotic-assisted surgery (RAS), artificial intelligence (AI)-enhanced donor–recipient matching, and bioengineering—particularly 3D bioprinting—are revolutionizing the field. Today, RAS has evolved from an innovative technique into a reliable clinical tool, with evidence indicating that it enhances surgical precision and results in better patient outcomes. Meanwhile, AI and machine learning are advancing donor–recipient matching and allocation, producing models that offer superior predictive accuracy for graft survival compared to traditional methods. Additionally, bioengineering strategies, especially 3D bioprinting and tissue engineering, are progressing from the creation of acellular scaffolds to the development of vascularized constructs, marking a significant milestone toward functional organ replacement. Despite persistent challenges such as high costs, regulatory obstacles, new structured formation programs, and the necessity for effective vascularization in engineered tissues, the integration of these disciplines is forging a new paradigm in regenerative medicine. The primary objective of this review is to synthesize multidisciplinary innovations by leveraging clinical studies and technological assessments to delineate future directions in regenerative medicine and organ transplantation. Full article

This paper addresses the critical challenge of detecting content-aware image manipulations, specifically focusing on seam carving forgery. While deep learning models, particularly Convolutional Neural Networks (CNNs), have shown promise in this area, their black-box nature limits their trustworthiness in high-stakes domains like digital forensics. To address this gap, we propose and validate a framework for interpretable forgery detection, termed E-XAI (Ensemble Explainable AI). Conceptually inspired by Ensemble Learning, our framework’s novelty lies not in combining predictive models, but in integrating a multi-perspective ensemble of explainability techniques. Specifically, we combine SHAP for fine-grained, pixel-level feature attribution with Grad-CAM for region-level localization to create a more robust and holistic interpretation of a single, custom-trained CNN’s decisions. Our approach is validated on a purpose-built, balanced, binary-class dataset of 10,300 images. The results demonstrate high classification performance on an unseen test set, with a 95% accuracy and a 99% precision for the forged class. Furthermore, we analyze the model’s robustness against JPEG compression, a common real-world perturbation. More importantly, the application of the E-XAI framework reveals how the model identifies subtle forgery artifacts, providing transparent, visual evidence for its decisions. This work contributes a robust end-to-end pipeline for interpretable image forgery detection, enhancing the trust and reliability of AI systems in information security. Full article

With the widespread use of audio editing software and artificial intelligence, it has become very easy to forge audio files. One type of these forgeries is copy-move forgery, which is achieved by copying a segment from an audio file and placing it in a different place in the same file, where the aim is to take the speech content out of its context and alter its meaning. In practice, forged recordings are often disguised through post-processing steps such as lossy compression, additive noise, or median filtering. This distorts acoustic features and makes forgery detection more difficult. This study introduces a robust keypoint-based approach that analyzes Mel-spectrograms, which are visual time-frequency representations of audio. Instead of processing the raw waveform for forgery detection, the proposed method focuses on identifying duplicate regions by extracting distinctive visual patterns from the spectrogram image. We tested this approach on two speech datasets (Arabic and Turkish) under various real-world attack conditions. Experimental results show that the method outperforms existing techniques and achieves high accuracy, precision, recall, and F1-scores. These findings highlight the potential of visual-domain analysis to increase the reliability of audio forgery detection in forensic and communication contexts. Full article

Voice phishing has emerged as a critical security threat, exploiting both linguistic manipulation and advances in synthetic speech technologies. Traditional keyword-based approaches often fail to capture contextual patterns or detect forged audio, limiting their effectiveness in real-world scenarios. To address this gap, we propose a multimodal voice phishing detection system that integrates text and audio analysis. The text module employs a KoBERT-based transformer classifier with self-attention interpretation, while the audio module leverages MFCC features and a CNN–BiLSTM classifier to identify synthetic speech. A fusion mechanism combines the outputs of both modalities, with experiments conducted on real-world call transcripts, phishing datasets, and synthetic voice corpora. The results demonstrate that the proposed system consistently achieves high values regarding the accuracy, precision, recall, and F1-score on validation data while maintaining robust performance in noisy and diverse real-call scenarios. Furthermore, attention-based interpretability enhances trustworthiness by revealing cross-token and discourse-level interaction patterns specific to phishing contexts. These findings highlight the potential of the proposed system as a reliable, explainable, and deployable solution for preventing the financial and social damage caused by voice phishing. Unlike prior studies limited to single-modality or shallow fusion, our work presents a fully integrated text–audio detection pipeline optimized for Korean real-world datasets and robust to noisy, multi-speaker conditions. Full article

The growing demand for precision and consistency in the forging industry has heightened the need for predictive simulation tools. While extensive research has focused on parameters such as flow stress, die wear, billet fracture, and residual stresses, the phenomenon of billet buckling, especially during cold upset forging, remains underexplored. Most existing models address only elastic buckling for slender billets using classical approaches like Euler and Rankine-Gordon formulae, which are not suitable for inelastic deformation in shorter billets. This study presents a numerical model developed to analyze inelastic buckling during cold forging and to determine associated stresses and deflection characteristics. The model was validated through finite element simulations across a range of billet geometries (10–40 mm diameter, 120 mm length), materials (aluminum, stainless steel, and copper), and friction coefficients (µ = 0.12, 0.16, and 0.35). Stress distributions were evaluated against die stroke, with particular emphasis on the influence of strain hardening and geometry. The results showed that billet geometry and strain-hardening exponent significantly affect buckling behavior, whereas friction had a secondary effect, mainly altering overall stress levels. A nonlinear regression approach incorporating material properties, geometric parameters, and friction was used to formulate the numerical model. The developed model effectively estimated buckling stresses across various conditions but could not precisely predict buckling points based on stress differentials. This work contributes a novel framework for integrating material, geometric, and process variables into stress prediction during forging, advancing defect control strategies in industrial metal forming. Full article

With the rapid advancement of image processing techniques, digital image forgery detection has emerged as a critical research area in information forensics. This paper proposes a novel deep learning model based on Multi-view Multi-dimensional Forgery Detection Networks (MMFD-Net), designed to simultaneously determine whether an image has been tampered with and precisely localize the forged regions. By integrating a Multi-stream Edge Feature Learning module with a Multi-dimensional Information Fusion module, MMFD-Net employs joint supervised learning to extract semantics-agnostic forgery features, thereby enhancing both detection performance and model generalization. Extensive experiments demonstrate that MMFD-Net achieves state-of-the-art results on multiple public datasets, excelling in both pixel-level localization and image-level classification tasks, while maintaining robust performance in complex scenarios. Full article

Diabetes mellitus is a chronic metabolic disorder characterised by impaired glucose regulation, leading to severe complications affecting multiple organ systems. Current diagnostic approaches primarily rely on glucose monitoring, which, while being effective, fails to capture the underlying molecular changes associated with disease progression. Emerging biomarkers such as microRNAs (miRNAs) and adipokines offer new insights into diabetes pathophysiology, providing potential diagnostic and prognostic value beyond traditional methods. Given this, precise monitoring of the altered levels of miRNAs and adipokines can forge a path towards early diabetes diagnosis and improved disease management. Biosensors have revolutionised diabetes diagnostics, with glucose biosensors dominating the market for decades. However, recent advancements in nanobiosensors have expanded their scope beyond glucose detection, enabling highly sensitive and selective monitoring of biomolecular markers like miRNAs and adipokines. These nanotechnology-driven platforms offer rapid, inexpensive, and minimally invasive detection strategies, paving the way for improved disease management. This review provides an overview of diabetes, along with its pathogenesis, complications, and demographics, and explores the clinical relevance of miRNAs and adipokines as emerging biomarkers. It further examines the evolution of biosensor technologies, highlights recent developments in nanobiosensors for biomarker detection, and critically analyses the challenges and future directions in this growing field. Full article

To address the challenges of short allowable motion windows and complex motion planning inherent in dual forging manipulator systems, this study proposes a coordinated motion pattern tailored to dual-manipulator operations, focusing on forging deformation behavior and press control characteristics. First, six representative long-shaft forging materials were classified based on typical industrial applications. Using DEFORM-3D (V11.0) software, the deformation process during the elongation operation was analyzed, and the velocity and displacement characteristics at both ends of the forgings were extracted to clarify the compliant motion requirements of the grippers. Next, a segmented computation method for manipulator allowable motion time was developed based on the motion–time curve of the hydraulic press, significantly improving the time utilization efficiency for coordinated control. Furthermore, experimental tests were carried out to verify the dynamic response performance and motion accuracy of the dual-manipulator system. Finally, the dual-manipulator forging cycle was systematically divided into four stages—pre-forging adjustment, inter-pass compliance, execution phase, and forging completion—resulting in a structured and implementable coordination control framework. This research provides both a theoretical foundation and practical pathway for achieving efficient and precise coordinated motion control in dual forging manipulator systems, offering strong potential for engineering application and industrial deployment. Full article

A novel stainless steel with high Mn and Mo content (much higher than traditional stainless steel), designated CH241SS, was developed as a potential replacement for Cr-Mo-V alloy steel in the cold forging applications of precision industry. Through carbon reduction in an environmentally friendly manner and a two-stage heat treatment process, the hardness of as-cast CH241 was tailored from HRC 37 to HRC 29, thereby meeting the industrial specifications of cold-forged steel (≤HRC 30). X-ray diffraction analysis of the as-cast microstructure revealed the presence of a small amount of ferrite, martensite, austenite, and alloy carbides. After heat treatment, CH241 exhibited a dual-phase microstructure consisting of ferrite and martensite with dispersed Cr(Ni-Mo) alloy carbides. The CH241 alloy demonstrated excellent high-temperature stability. No noticeable softening occurred after 72 h for the second-stage heat treatment. Based on the mechanical and room-temperature tensile fatigue properties of CH241-F (forging material) and CH241-ST (soft-tough heat treatment), it was demonstrated that the CH241 stainless steel was superior to the traditional stainless steel 4xx in terms of strength and fatigue life. Therefore, CH241 stainless steel can be introduced into cold forging and can be used in precision fatigue application. The relevant data include composition design and heat treatment properties. This study is an important milestone in assisting the upgrading of the vehicle and aerospace industries. Full article