Search Results (2,340)

The rapid expansion of e-commerce has significantly influenced consumer purchasing behavior, making user reviews a critical source of product-related information. However, the large volume of low-quality and superficial reviews limits the ability to obtain reliable insights. This study aims to classify Turkish e-commerce reviews as either useful or useless, thereby highlighting high-quality content to support more informed consumer decisions. A dataset of 15,170 Turkish product reviews collected from major e-commerce platforms was analyzed using traditional machine learning approaches, including Support Vector Machines and Logistic Regression, and transformer-based models such as BERT and RoBERTa. In addition, a novel Multi-Transformer Fusion Framework (MTFF) was proposed by integrating BERT and RoBERTa representations through concatenation, weighted-sum, and attention-based fusion strategies. Experimental results demonstrated that the concatenation-based fusion model achieved the highest performance with an F1-score of 91.75%, outperforming all individual models. Among standalone models, Turkish BERT achieved the best performance (F1: 89.37%), while the BERT + Logistic Regression hybrid approach yielded an F1-score of 88.47%. The findings indicate that multi-transformer architectures substantially enhance classification performance, particularly for agglutinative languages such as Turkish. To improve the interpretability of the proposed framework, SHAP (SHapley Additive exPlanations) was employed to analyze feature contributions and provide transparent explanations for model predictions, revealing that the model primarily relies on experience-oriented and semantically meaningful linguistic cues. The proposed approach can support e-commerce platforms by automatically prioritizing high-quality and informative reviews, thereby improving user experience and decision-making processes. Full article

Grayscale-based Encryption-then-Compression (EtC) systems transform RGB images into the YCbCr color space, concatenate the components into a single grayscale image, and apply block permutation, block rotation/flipping, and block-wise negative–positive inversion. Because this pipeline separates color components and disrupts inter-channel statistics, existing extended jigsaw puzzle solvers (JPSs) have been regarded as ineffective, and grayscale-based EtC systems have been considered resistant to ciphertext-only visual reconstruction. In this paper, we present a practical ciphertext-only attack against grayscale-based EtC. The proposed attack introduces three key components: (i) Texture-Based Component Classification (TBCC) to distinguish luminance (Y) and chrominance (Cb/Cr) blocks and focus reconstruction on structure-rich regions; (ii) Regularized Single-Channel Edge Compatibility (R-SCEC), which applies Tikhonov regularization to a single-channel variant of the Mahalanobis Gradient Compatibility (MGC) measure to alleviate covariance rank-deficiency while maintaining robustness under inversion and geometric transforms; and (iii) Adaptive Pruning based on the TBCC-reduced search space that skips redundant boundary matching computations to further improve reconstruction efficiency. Experiments show that, in settings where existing extended JPS solvers fail, our method can still recover visually recognizable semantic content, revealing a potential vulnerability in grayscale-based EtC and calling for a re-evaluation of its security. Full article

Accurately predicting molten steel carbon content plays a crucial role in improving productivity and energy efficiency during the Basic Oxygen Furnace (BOF) steelmaking process. However, current data-driven methods primarily focus on endpoint carbon content prediction, while lacking sufficient investigation into real-time curve forecasting during the blowing process, which hinders real-time closed-loop BOF control. In this article, a novel Transformer-based framework is presented for real-time carbon content prediction. The contributions include three main aspects. First, the prediction paradigm is reconstructed by converting the regression task into a sequence classification task, which demonstrates superior robustness and accuracy compared to traditional regression methods. Second, the focus is shifted from traditional endpoint-only forecasting to long-term prediction by introducing a Transformer-based model for continuous, real-time prediction of carbon content. Last, spatial–temporal feature representation is enhanced by integrating an optical flow channel with the original RGB channels, and the resulting four-channel input tensor effectively captures the dynamic characteristics of the converter mouth flame. Experimental results on an independent test dataset demonstrate favorable performance of the proposed framework in predicting carbon content trajectories. The model achieves high accuracy, reaching 84% during the critical decarburization endpoint phase where carbon content decreases from 0.0829 to 0.0440, and delivers predictions with approximately 75% of errors within ±0.05. Such performance demonstrates the practical potential for supporting intelligent BOF steelmaking. Full article

This study evaluates the swelling potential in clayey soils of the Paleogene Brebi, Mera, and Moigrad formations in the Transylvanian Basin (Romania) by integrating direct free-swelling tests (FS; STAS 1913/12-88) with indirect index-property diagrams and semi-quantitative X-ray diffraction (XRD; RIR method). The indirect analysis combines three swelling-susceptibility classification charts—Seed et al. (AI–clay), Van der Merwe (PI–clay), and Dakshanamurthy and Raman (LL–PI)—with mineralogical trends from the Casagrande plasticity chart, complemented by Holtz and Kovacs’s clay-mineral reference fields and Skempton’s activity concept (AI = PI/% < 2 µm). The geotechnical dataset comprises 88 Brebi, 46 Mera, and 263 Moigrad specimens (with parameter counts varying by test), an XRD was performed on a representative subset. The free swell (FS) results indicate that Brebi soils range from low to active behavior (50–135%) without reaching the very active class; most Brebi specimens fall in the medium-activity range. Moigrad spans the full FS spectrum (20–190%) but is predominantly in the medium-to-active range. In contrast, Mera soils exhibit predominantly active behavior, covering the full range of activity classes (30–170%). The empirical classification charts diverge systematically: clay-sensitive schemes tend to assign higher swell susceptibility than the LL–PI approach, especially in carbonate-influenced soils. XRD results corroborate these patterns: Brebi is calcite-rich (mean ≈ 53.5 wt% CaCO₃) with minor expandable minerals (mean ≈ 3.1 wt%); Mera is feldspathic (orthoclase mean ≈ 55.3 wt%) with variable expandable phases; and Moigrad has a higher clay-mineral content (mean ≈ 38.8 wt%). Overall, swelling is controlled by the combined effects of clay-fraction reactivity, clay volume continuity, and carbonate-related microstructural constraints. Full article

Almonds are a highly valued nut due to their rich protein and nutritional content. However, they are vulnerable to aflatoxin B1 (AFB1) contamination in warm and humid environments. Consumption of AFB1-contaminated almonds can pose serious health risks, including kidney damage, and may lead to significant economic losses. Consequently, a rapid and non-destructive detection method is essential to ensure food safety by identifying and removing contaminated almonds from the supply chain. Hyperspectral imaging (HSI) and 3D deep learning provide a non-destructive, efficient alternative to current AFB1 detection methods. This study presents an attention-guided Inception ResNet 3D Network (AGIR-3DNet) for fast and precise detection of AFB1 contamination in almonds utilizing HSI. The proposed model integrates multi-scale feature extraction, residual learning, and attention mechanisms to enhance spatial-spectral feature representation, enabling more precise classification. The proposed 3D model was rigorously tested, and its performance was compared against 3D Inception and various conventional machine learning models. Compared to conventional machine learning models and deep learning architectures, AGIR-3DNet outperformed and achieved superior validation accuracy of 93.30%, an F1-score (harmonic mean of precision and recall) of 0.94, and an area under the receiver operating characteristic curve (AUC) value of 0.98. Furthermore, the model enhances processing efficiency, making it faster and more suitable for real-time industrial applications. Full article

Phishing and spam emails continue to pose a serious cybersecurity threat, leading to financial loss, information leakage, and reputational damage. Traditional email filtering approaches struggle to keep pace with increasingly sophisticated attack strategies, particularly those involving malicious content and deceptive attachments. This study proposes a dual-layer deep learning architecture designed to enhance email security by improving the detection of phishing and spam messages. The first layer employs deep learning models, including LSTM- and transformer-based classifiers, to analyze email content and structural features across legitimate, phishing, and spam emails. The second layer focuses on spam emails containing attachments and applies advanced transformer models, such as GPT-2 and XLM-RoBERTa, to assess contextual and semantic patterns associated with malicious attachments. By integrating textual analysis with attachment-level inspection, the proposed architecture overcomes limitations of single-layer approaches that rely solely on email body content. Experimental evaluation using accuracy and F1-score demonstrates that the dual-layer framework achieves a minimum F1-score of 98.75 percent in spam–ham classification and attains an attachment detection accuracy of up to 99.46 percent. These results indicate that the proposed approach offers a reliable and scalable solution for enhancing real-world email security systems. Full article

The main characteristics of the large number of coffee species are differences in aroma and caffeine content. Labeled blends of Coffea arabica (C. arabica) and Coffea canephora (C. canephora) are common to broaden the flavor profile or enhance the stimulating effect of the beverage. New emerging species such as Coffea liberica (C. liberica) further increase the variability in blends. However, significant price differences between coffee species increase the risk of unlabeled blends and thus influence food quality and safety for consumers. In this study, a prototypic hyphenation of trapped headspace-gas chromatography-ion mobility spectrometry-quadrupole mass spectrometry (THS-GC-IMS-QMS) was used for the detection of characteristic compounds of C. arabica, C. canephora, and C. liberica in green and roasted coffee samples. For the discrimination of coffee species with IMS data, multivariate resolution with multivariate curve resolution–alternating least squares (MCR-ALS) prior to partial least squares–discriminant analysis (PLS-DA) was evaluated. With this approach, the classification accuracy, as well as sensitivity and specificity, of the PLS-DA model was significantly improved from an overall accuracy of 87% without prior feature selection to 92%. As MCR-ALS preserves the physical and chemical properties of the original data, characteristic features were determined for subsequent substance identification. The simultaneously generated QMS data allowed for partial annotation of the characteristic volatile organic compounds (VOC) of roasted coffee. Full article

Depression represents a major global health challenge, yet traditional clinical diagnosis faces limitations, including high costs, limited coverage, and low patient willingness. Social media platforms provide new opportunities for early depression screening through user-generated content. However, existing methods often lack systematic integration of clinical knowledge and fail to leverage multi-modal information comprehensively. We propose a DSM-5-guided methodology that systematically maps clinical diagnostic criteria to computable social media features across three modalities: textual semantics (BERT-based deep semantic extraction), behavioral patterns (temporal activity analysis), and topic distributions (LDA-based cognitive bias identification). We design a hierarchical architecture integrating BERT, Bi-LSTM, hierarchical attention, and multi-task learning to capture both character-level and post-level importance while jointly optimizing depression classification, symptom recognition, and severity assessment. Experiments on the WU3D dataset (32,570 users, 2.19 million posts) demonstrate that our model achieves 91.8% F1-score, significantly outperforming baseline methods (BERT: 85.6%, TextCNN: 78.6%, and SVM: 72.1%) and large language models (GPT-4 few-shot: 86.9%). Ablation studies confirm that each component contributes meaningfully with synergistic effects. The model provides interpretable predictions through attention visualization and outputs fine-grained symptom assessments aligned with DSM-5 criteria. With low computational cost (~50 ms inference time), local deployability, and superior privacy protection, our approach offers significant practical value for large-scale mental health screening applications. This work demonstrates that domain-specialized methods with explicit clinical knowledge integration remain highly competitive in the era of general-purpose large language models. Full article

Crowdfunding has emerged as an alternative funding source among entrepreneurs, businesses, and industries. In recent years, research on machine learning-based project classification models has been conducted with the aim of predicting the success of crowdfunding campaigns, both for entrepreneurs and investors. However, most of the research has focused on classification approaches using non-content information such as project metadata, creators’ behavior, and social history, but there have been few attempts to use text content data per se, particularly in order to provide explanations and evidence for how the prediction decisions were made. To address this point, we propose to use a deep learning-based approach called Hierarchical Attention Network (HAN) to predict the success of crowdfunding campaigns and provide explanation and justification of the prediction decisions using attention weights. We collect publicly available data of crowdfunding campaigns and build our success prediction model with an accuracy of 86.38% and 87.29%, using an Updates section and backers’ comments in a Comments section, respectively. We also explore the feasibility of early success prediction during the funding period (up to 2 months), with as much as 80.99% accuracy in 1 to 2 months. Finally, we examine word and sentence attention weight scores to clarify key factors in predicting crowdfunding success. Full article

Generative models play a pivotal role in the field of medical imaging. This paper provides an extensive and scholarly review of the application of generative models in medical image creation and translation. In the creation aspect, the goal is to generate new images based on potential conditional variables, while in translation, the aim is to map images from one or more modalities to another, preserving semantic and informational content. The review begins with a thorough exploration of a diverse spectrum of generative models, including Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), Diffusion Models (DMs), and their respective variants. The paper then delves into an insightful analysis of the merits and demerits inherent to each model type. Subsequently, a comprehensive examination of tasks related to medical image creation and translation is undertaken. For the creation aspect, papers are classified based on downstream tasks such as image classification, segmentation, and others. In the translation facet, papers are classified according to the target modality. A chord diagram depicting medical image translation across modalities, including Magnetic Resonance Imaging (MRI), Computed Tomography (CT), Cone Beam CT (CBCT), X-ray radiography, Positron Emission Tomography (PET), and ultrasound imaging, is presented to illustrate the direction and relative quantity of previous studies. Additionally, the chord diagram of MRI image translation across contrast mechanisms is also provided. The final section offers a forward-looking perspective, outlining prospective avenues and implementation guidelines for future research endeavors. Full article

The construction industry is a major consumer of natural resources and a significant source of CO₂ emissions. Although numerous studies have addressed cement reduction through supplementary materials, the replacement of natural aggregates has received less attention despite its high environmental relevance. Practical application of recycled aggregate concrete remains limited due to complex classification and testing requirements. This study investigates the use of locally crushed construction and demolition waste as aggregate for new structural concrete with minimal on-site preparation. The goal was to maximize recycled material utilization while ensuring adequate performance. Demolition materials from normal- and high-strength concrete, 3D-printed concrete, and fired clay bricks were crushed using jaw and impact crushers, and the entire particle size curve was incorporated into new mixtures. Two compositions were tested: 50% and 75% recycled aggregate combined with natural quartz sand, without increasing cement content. Compressive strength and density were evaluated at 28 and 90 days. High-strength concrete waste provided strengths close to the reference mixture, while normal concrete and brick aggregates resulted in lower but still structural-grade concretes. The strengths achieved ranged between 35 MPa and 73 MPa, which is between 48% and 98% of the reference value, respectively. A linear relationship was found between density and compressive strength, enabling estimation from simple measurements. The results confirm that uncontaminated demolition waste can be efficiently reused on site with limited testing, supporting circular construction and reduced environmental impact. Full article

Ocular disorders such as keratitis, glaucoma, age-related macular degeneration (AMD), diabetic retinopathy (DR), and dry eye disease (DED) are highly prevalent worldwide and remain major causes of visual impairment and blindness. Conventional therapeutic approaches for ocular diseases, such as eye drops, surgery, and laser therapy, are frequently hampered by limited drug bioavailability, rapid clearance, and treatment-related complications, primarily due to the eye’s unique anatomical and physiological barriers. Hydrogels, characterized by their three-dimensional network structure, high water content, excellent biocompatibility, and tunable physicochemical properties, have emerged as promising platforms for ophthalmic drug delivery. This review summarizes the classification, fabrication strategies, and essential properties of hydrogels, and highlights recent advances in their application to ocular diseases, including keratitis management, corneal wound repair, intraocular pressure regulation and neuroprotection in glaucoma, sustained drug delivery for AMD and DR, vitreous substitutes for retinal detachment, and therapies for DED. In particular, we highlight recent advances in stimuli-responsive hydrogels that enable spatiotemporally controlled drug release in response to ocular cues such as temperature, pH, redox state, and enzyme activity, thereby enhancing therapeutic precision and efficacy. Furthermore, this review critically evaluates translational aspects, including long-term ocular safety, clinical feasibility, manufacturing scalability, and regulatory challenges, which are often underrepresented in existing reviews. By integrating material science, ocular pathology, and translational considerations, this review aims to provide a comprehensive framework for the rational design of next-generation hydrogel systems and to facilitate their clinical translation in ophthalmic therapy. Full article

The colored-leaf Osmanthus fragrans is a valuable ornamental tree species that integrates greenery, colorful leaves, and fragrance. At present, research on colored-leaf Osmanthus fragrans mainly focuses on cultivar breeding, classification and cultivation, and physiological resistance, while studies on leaf color variation remain limited. In this study, the colored-leaf Osmanthus cultivar ‘Jinyu Guihua’ and its female parent were used as materials. The leaf coloration mechanism was systematically investigated through a combined analysis of physiology, transcriptomics, and metabolomics. The results showed that compared with the female parent, the leaves of ‘Jinyu Guihua’ exhibited significantly reduced chlorophyll b and anthocyanin contents, fewer chloroplasts, and more plastoglobules. Transcriptomic analysis identified 3938 differentially expressed genes (DEGs), among which the key chlorophyll metabolism gene CAO was downregulated and NOL was upregulated; the key carotenoid synthesis gene PSY was downregulated and CYP97A3 was upregulated; the key anthocyanin synthesis gene ANS was downregulated; and the PetC2 gene in the photosynthesis-related Cytb6-f complex was upregulated. qRT-PCR validation results were consistent with the RNA-seq data. Metabolomic analysis detected 1290 metabolites, classified into 21 subcategories, with flavonoids being the most abundant (17.21%). Anthocyanin synthase (ANS) significantly downregulated the expression levels of cyanidin-3-O-rutinoside (Cy3R) and delphinidin-3-O-rutinoside (De3R). In conclusion, the leaf color variation in ‘Jinyu Guihua’ is closely related to changes in leaf pigment content and the regulation of key metabolic pathway gene expression. The findings of this study provide a theoretical basis for the molecular breeding of new colored-leaf Osmanthus varieties and serve as a reference for trait research in other ornamental plants. Full article

Deceptive and evolving conversations on online platforms threaten trust, security, and user safety, particularly when concept drift obscures malicious intent. Large Language Models (LLMs) offer strong natural language reasoning but remain unreliable in risk-sensitive scenarios due to contextual ambiguity and hallucinations. This article introduces a domain knowledge-enhanced Dual-LLM framework that integrates structured cues with pretrained models to improve fraud detection and drift classification. The proposed approach achieves 98% accuracy on benchmark datasets, significantly outperforming zero-shot LLMs and traditional classifiers. The results highlight how domain-grounded prompts enhance both accuracy and interpretability, offering a trustworthy path for applying LLMs in safety-critical applications. Beyond advancing the state of the art in fraud detection, this work has the potential to benefit domains such as cybersecurity, e-commerce, financial fraud prevention, and online content moderation. Full article

In this paper, we propose a source camera identification method based on disentangled feature modeling, aiming to achieve robust extraction of camera fingerprint features under complex imaging and post-processing conditions. To address the severe coupling between image content and camera fingerprint features in existing methods, which makes content interference difficult to suppress, we develop a dual-branch deep learning framework guided by imaging physics. By introducing physical consistency constraints, the proposed framework explicitly separates image content representations from device-related fingerprint features in the feature space, thereby enhancing the stability and robustness of source camera identification. The proposed method adopts two parallel branches: a content modeling branch and a fingerprint feature extraction branch. The content branch is built upon an improved U-Net architecture to reconstruct scene and color information, and further incorporates texture refinement and multi-scale feature fusion to reduce residual content interference in fingerprint modeling. The fingerprint branch employs ResNet-50 as the backbone network to learn discriminative global features associated with the camera imaging pipeline. Based on these branches, fingerprint information dominated by sensor noise is explicitly extracted by computing the residual between the input image and the reconstructed content, and is further encoded through noise analysis and feature fusion for joint camera model classification. Experimental results on multiple public-source camera forensics datasets demonstrate that the proposed method achieves stable and competitive identification performance in same-brand camera discrimination, complex imaging conditions, and post-processing scenarios, validating the effectiveness of the proposed disentangled modeling and physical consistency constraint strategy for source camera identification. Full article