Search Results (688)

Metallographic microstructure analysis is essential for understanding the evolution of steel microstructures during heat treatment and mechanical processing. However, accurate analysis of optical micrographs remains difficult because of blurred grain boundaries, grayscale inhomogeneity within grains, and irregular grain morphologies. To address these issues, this work proposes an automated metallographic image-processing method based on superpixels, DPSS (dual-phase steel segmentation), with the main contribution focused on microstructure segmentation. First, image contrast and boundary visibility are enhanced by edge detection and sharpening. Then, superpixel segmentation is combined with extracted edge information to improve boundary localization and preserve irregular grain morphology, enabling more complete extraction of grain or particle regions from optical images. The proposed method is validated on optical micrographs of Mn-Si low-alloy steel, and the results show that it provides more accurate and complete segmentation than conventional ImageJ (Version: 1.54f)-based processing. Based on the segmented regions, a lightweight neural network is further used for phase identification. The final classification recognition accuracy can reach 99.91%. This classification result serves to demonstrate that the improved segmentation results can provide more reliable inputs for subsequent microstructure recognition. Overall, the proposed method offers an effective and automated solution for metallographic image segmentation and supports more accurate downstream phase analysis. Full article

From the perspective of applied surface science, heritage textiles from the Kashgar region can be regarded as fragile fibrous surface systems in which stains, abrasion, yarn breakage, yarn shedding, holes, and color fading represent measurable surface-degradation phenomena. However, manual inspection of these complex, woven, embroidered, and aged surfaces is time-consuming and difficult to standardize. To support non-contact surface-condition documentation, this study proposes an improved YOLOv8-based framework, YOLOv8-MABFT, for surface defect detection and condition-level assessment of Kashgar heritage textiles. The model integrates the C2f-Faster-EMA module and an RT-DETR-informed decoder head to improve the detection of weak-boundary and fine-grained surface defects. A dataset of 8247 high-resolution annotated images was constructed, covering six surface-degradation categories: stains, broken yarn, yarn shedding, holes, abrasion, and color fading. Experimental results show that YOLOv8-MABFT achieves an F1-score of 94.6%, a precision of 91.4%, a recall of 98.0%, and an mAP@0.5 of 94.0%, outperforming Faster R-CNN, SSD, YOLOv5n, YOLOv7n, and YOLOv8n while maintaining lightweight computational characteristics. CAM-based visualizations indicate that the improved model focuses more consistently on defect-related surface regions rather than surrounding decorative textures. Based on detected defects, seven surface-condition variables were constructed and input into a Random Forest classifier for four-level condition prediction. SHAP analysis shows that Distribution and Severity are the main contributors to condition classification. Overall, the proposed framework provides an applied surface-science tool for non-contact surface defect detection, surface-condition documentation, and preliminary condition-level assessment of fragile textile substrates. Full article

We study a minimal quantum pre-processing filter for image feature extraction built from angle embeddings and two Control-NOT (CNOT) gates. Our goal is to assess whether such a lightweight quantum front-end can benefit classical classifiers and to investigate whether its induced entanglement—measured via average single-qubit von Neumann entropy—relates to predictive performance. The circuit admits three spatially symmetric layouts (diagonal, vertical, and horizontal), each producing distinct feature transformations. Experiments show that the filter can provide modest gains in shallow learning settings, but it does not consistently outperform strong classical baselines. Notably, we find no reliable relationship between entanglement and classification accuracy: variations in average entropy fail to consistently track performance. These results suggest that the utility of simple quantum filters is determined more by dataset structure and model capacity than by entanglement magnitude, offering practical guidance for the design of hybrid quantum–classical learning pipelines. Full article

Plant disease recognition models trained under laboratory conditions often degrade markedly after cross-domain transfer because of the pronounced distribution gap between source and target domains and the scarcity of labeled target-domain samples. To address the transfer task from PlantVillage (PV_100) to PlantDoc, this study develops and evaluates a lightweight cross-domain few-shot plant disease recognition method under a strict PlantVillage-to-PlantDoc protocol. The method integrates EfficientNet-B0 feature extraction, cosine-similarity-based prototypical classification, and training-time target-domain BN adaptation (TBA). During training, unlabeled target-domain images are used only for BN statistical calibration, whereas inference is limited to feature extraction and prototype matching, without gradient updates or iterative optimization. Under a unified experimental protocol, the proposed method achieved cross-split mean accuracies of 42.69 ± 0.62% for one-shot and 54.24 ± 0.72% for five-shot, where ± denotes the standard deviation across three strict data splits; it outperformed ProtoNet by 7.44 and 9.43 percentage points, respectively. Ablation results indicate that TBA is the main source of performance improvement, whereas more complex adaptation strategies do not yield stable additional gains. The core encoder can be executed entirely on the NPU, with an estimated single-sample inference latency as low as 0.658 ms, indicating strong potential for encoder-level mobile deployment. Full article

Atmospheric turbulence originates from random fluctuations in the refractive index of the propagation medium that induce wavefront distortions and intensity scintillation. In application scenarios such as adaptive optics, rapid and accurate characterization of turbulence conditions is of critical importance. Existing turbulence-sensing approaches predominantly rely on intensity statistical analysis, wavefront measurements, and parameter estimation inferred from imaging degradation. However, these methods typically require complex reconstruction procedures, leading to increased system complexity and substantial computational overhead, which limits their applicability in scenarios demanding low-latency lightweight architectures, such as adaptive optics and ground-to-satellite laser communications. In this work, turbulence perception is reformulated from a conventional wavefront reconstruction problem into a measurement-operator design problem. We propose an all-optical turbulence perception framework based on a multilayer diffractive processor. The proposed approach maps the phase statistical characteristics induced by atmospheric turbulence into discriminative intensity-domain features, enabling direct perception of turbulence strength. The perception process is performed exclusively in the optical domain, without the need for numerical reconstruction. Numerical results demonstrate that the proposed diffractive processor can robustly distinguish different turbulence strength levels, with an overall classification accuracy of 79.50%, indicating its effectiveness as a new technological pathway for atmospheric turbulence perception. Full article

Background: Chest radiography is widely used in clinical workflows; however, exploratory image-level classification across multiple public-dataset categories remains less studied than single-disease classification tasks. We aimed to develop and internally evaluate a compact SqueezeNet-based pipeline for nine-class chest radiograph classification within a public dataset. Low-computational-footprint approaches may be relevant for future research prototypes in resource-constrained settings, particularly when offline operation is desirable; however, no real-world clinical deployment or triage validation was assessed in the present study. Methods: Using a public dataset of 6743 frontal radiographs spanning normal anatomy and eight pathology categories, we extracted 512-dimensional embeddings from a pre-trained SqueezeNet-1.0 (features module with global average pooling) and trained a scikit-learn MLP with a single hidden layer. Performance was assessed with stratified 5-fold cross-validation using accuracy and class-wise precision, recall, and F1; interpretability was examined via confusion matrices and dimensionality reduction techniques (t-SNE, and MDS). Results: The model achieved a mean accuracy of 98.83% across folds, with per-class precision, recall, and F1 generally ≥0.96 and a weighted F1 of 0.99; confusion matrices showed minimal off-diagonal errors, and embedding visualizations revealed well-separated, class-consistent clusters. Conclusions: Compact CNN features coupled with a simple MLP demonstrated strong internal performance for multi-class CXR classification within the evaluated dataset. However, the absence of external validation, the use of synthetically augmented data, and the lack of patient-level provenance metadata substantially limit conclusions regarding generalizability and clinical applicability. Full article

Lightweight devices are becoming a crucial part of networked systems, including Internet of Things environments. These devices usually have constraints, such as limited computational power, which have directed researchers to develop lightweight crypto algorithms to secure the data generated by these devices. Therefore, an efficient but secure crypto algorithm for these devices is required. In this paper, we thoroughly evaluate well-known SPN-based algorithms, namely AES, LED, PRESENT, ASCON-128, and ASCON-128a, based on the success rates of statistical randomness tests, including the Frequency, Runs, Discrete Fourier Transform, and Cumulative Sum tests. With these tests, the assessment measures the algorithms’ ability to produce unpredictable text. To ensure thorough evaluation, the experiments included approximately 19,000 image files of varying sizes up to 2560 KB. The extensive experimental results show that the ASCON family achieved high success rates above 98% in all tests, particularly for small file sizes, while AES achieved higher success rates for larger file sizes, and LED showed limited performance for the varied file sizes. The results confirm that ASCON-128 and ASCON-128a offer the needed trade-off between computation and randomness validation. Based on this evaluation, we propose an adaptive encryption framework based on file size, data classification, and device computational power. Full article

Background: Accurate and efficient analysis of mitotic figures in whole-slide images (WSIs) is essential for tumor grading and prognosis. Methods: In this work, we present a three-stage pipeline for WSI-scale mitosis analysis that balances accuracy with clinical throughput: (1) a YOLOv11-based detector to propose mitosis candidates; (2) an ultra-lightweight classifier to refine detections and suppress false positives; and (3) a downstream classifier to distinguish atypical from normal mitoses for deeper biological insight. Results: In benchmark datasets, the two-stage detector improves F1 over detection-only baselines, while the atypical/normal module achieves strong accuracy, demonstrating cross-domain generalization. We further perform a proof-of-concept survival analysis on early-stage (I–II) cases from the TCGA-BRCA cohort, suggesting that mitosis-derived features may provide modest incremental prognostic information beyond the clinical baseline and nuclei features. Conclusions: Overall, the method delivers accurate detection, robust atypical mitosis classification, and high efficiency, processing gigapixel WSIs in minutes on a single GPU, positioning it for large-scale translational studies and future clinical workflow validation. Full article

Diabetic retinopathy (DR) and diabetic macular oedema (DME) are two of the most significant preventable contributors to blindness in the adult population worldwide, yet current automated screening systems typically address each condition in isolation and rely on a single imaging modality. In this study, we propose a deep learning model that simultaneously grades DR severity and detects DME by fusing paired colour fundus and optical coherence tomography (OCT) images acquired from the same eye during the same clinical visit. Our architecture employs two parallel EfficientNet-B0 backbones pre-trained on ImageNet, one for each modality, whose 1280-dimensional feature vectors are concatenated into a 2560-dimensional joint representation. This fused representation passes through a shared fully connected block before branching into a three-class DR classification head and a binary DME detection head. We train and evaluate the model on a private dataset of 425 paired fundus and OCT eye images (850 images). The proposed architecture adopts feature-level fusion, in which modality-specific deep features are independently extracted from fundus and OCT images using separate convolutional backbones and subsequently concatenated to form a joint representation for multi-task learning. On the held-out test set (n= 85), the fusion model achieves 82.4% DR accuracy (area under the receiver operating characteristic curve [AUC] = 0.929, macro sensitivity = 0.81, macro specificity = 0.905) and 97.6% DME accuracy (AUC = 0.999, sensitivity = 0.833, specificity = 1.000). The fusion model detects 10 of 12 DME-positive eyes compared with only 7 of 12 for either the fundus-only or OCT-only baselines, representing a 43% relative improvement in DME sensitivity. Stratified five-fold cross-validation (n = 425 aggregated predictions) corroborates these findings, with the fusion model reaching 87.1% DR accuracy (AUC = 0.978) and 99.1% DME accuracy (AUC = 1.000). Gradient-weighted class activation mapping visualisations confirm that the fundus branch attends to clinically relevant macular lesions, whereas the OCT branch highlights retinal layer disruptions and subretinal fluid, providing interpretability. To the best of our knowledge, the proposed MultiRetNet is the first lightweight, task-specific multimodal architecture to jointly grade DR severity and detect DME from paired same-eye, same-visit fundus and OCT images through explicit feature-level fusion within a single end-to-end multi-task framework, distinct from recent generalist ophthalmic foundation models, supporting the value of multimodal fusion for comprehensive diabetic eye screening pending external validation. Full article

Cardiovascular diseases (CVDs) are the leading cause of global mortality, highlighting the need for efficient and reliable automated electrocardiogram (ECG) analysis. While deep learning methods have achieved high classification accuracy, their large model sizes and computational demands limit clinical deployment. This study proposes a lightweight multiscale framework, the FPN–ECA–ELM, integrating a feature pyramid network (FPN), efficient channel attention (ECA), and an extreme learning machine (ELM) for automated CVD classification using standard 12-lead ECG images. The FPN enables efficient multiscale feature fusion by combining feature maps from different network depths to generate high-resolution semantically enriched representations. ECA performs channel-wise feature recalibration, and the ELM replaces conventional fully connected layers, further reducing computational cost. Under an inter-patient evaluation protocol, the model achieved 87.08% accuracy and 87.07% weighted F1-score for binary classification, and 78.06% accuracy and 78.34% weighted F1-score for five-class classification, demonstrating competitive classification performance. The model contains only 1.73 million parameters, with a size of 6.59 MB, requiring 0.21 GFLOPs, and achieves an inference time of 0.69 ms per sample. These results illustrate a favorable balance between accuracy and efficiency, supporting practical deployment in resource-constrained clinical and edge-computing environments. Full article

With the rapid increase in urban waste, efficient and accurate garbage classification has become pivotal for sustainable development. However, existing methods often grapple with high computational complexity, limited adaptability to diverse waste types, and challenges in deploying on resource-constrained devices. To address these issues, this study proposes GMamba, a lightweight garbage classification model based on the Mamba architecture. GMamba employs a hierarchical structure, integrating two modules, the GML Block for efficient local–global feature fusion and the GMC Block for fine-grained spatial dependency modeling, achieving robust feature aggregation while minimizing computational redundancy. Evaluations on the Huawei Cloud Garbage Classification dataset and the custom MixTrash dataset demonstrate that GMamba, with only 17.18 M parameters, achieves Top-1 accuracies of 92.75% and 92.58%, respectively. While scaling evaluations indicate that VMamba maintains a marginal lead in absolute Top-1 accuracy, the proposed GMamba delivers a substantially superior balance between accuracy and computational efficiency, reducing parameter count by 45% and FLOPs by 47.3%, thus demonstrating promising deployment potential for resource-constrained edge systems. Full article

Early and reliable detection of plant diseases is critical for sustaining agricultural productivity and reducing economic losses. In olive cultivation, peacock eye disease poses a significant threat by adversely affecting leaf health and crop yield. While deep learning models have demonstrated strong performance in plant disease detection, their reliance on high-dimensional feature representations often leads to increased computational cost and limited deployability in real-world agricultural settings. This study proposes an efficient and robust olive leaf disease classification framework that integrates deep feature extraction, devised composite filter-based feature selection, and ensemble learning. Deep features are extracted from olive leaf images using transfer learning with ResNet101 and MobileNet architectures. To address feature redundancy and computational inefficiency, multiple filter-based selection strategies—including mutual information, Chi-square, F-score, and five devised composite selectors (score fusion, union, intersection, hybrid, and class-wise filtering)—are employed to generate compact and informative feature subsets of fixed sizes (32, 64, and 128 features). The selected features are evaluated using k-NN, SVM, and LightGBM classifiers under stratified 5-fold cross-validation. Experimental results demonstrate that competitive and near-baseline performance can be achieved with substantially reduced feature dimensionality. In particular, using only 128 selected features, the proposed approach attains up to 0.988 accuracy and 0.976 MCC, closely matching the performance obtained with full deep feature vectors. Furthermore, voting-based ensemble strategies, including iterative majority voting and hybrid GA–BO fusion, further enhance robustness, achieving the highest mean accuracy of 0.9916 among the evaluated ensemble configurations. These findings highlight the effectiveness of the proposed composite filter-based selection and ensemble framework as a practical, lightweight, and accurate solution for olive leaf disease detection, suitable for deployment in precision agriculture and resource-constrained environments. Full article

Fatigue driving causes 20–30% of global traffic accidents. To address limitations in feature fusion and real-time performance, this study proposes an improved You Only Look Once version 8 (YOLOv8)-Long Short-Term Memory (LSTM) model with symmetry-aware spatiotemporal feature learning. In the spatial phase, Group Shuffle Convolution (GSConv) and Slim Neck structures are introduced to enhance facial feature detection while reducing parameters by 32.3%. In the temporal phase, an improved Inverted Transformer(iTransformer) with differential attention is integrated with an LSTM-Feed-Forward Network (FFN) architecture, achieving a 90.1% prediction accuracy and an 84.6% noise suppression rate. A standardized dataset of 13,200 images was constructed using a four-level classification system. By implementing TensorRT acceleration and multi-process parallel frameworks, the system optimizes single-frame latency to 38 ms—a 9.5× efficiency gain—while maintaining an overall detection accuracy of 92.4%. These results demonstrate that the proposed framework effectively balances model lightweighting with high precision, providing a robust and efficient solution for real-time driver monitoring in complex driving scenarios. Full article

Tomato (Solanum lycopersicum) cultivation is highly vulnerable to fungal, bacterial, and viral leaf diseases that can significantly reduce crop yield and fruit quality when not detected at early stages. Although recent deep learning approaches have achieved remarkable performance in plant disease classification, many state-of-the-art architectures remain computationally expensive and therefore difficult to deploy on resource-constrained edge devices commonly used in smart agriculture environments. To address this challenge, this paper introduces EcoTomHybridNet, an adaptive resource-aware CNN–Transformer framework designed for efficient tomato leaf disease classification under edge-computing constraints. The proposed architecture combines a lightweight convolutional backbone with a dual-branch inference mechanism composed of a fast convolutional branch for computationally efficient prediction and a Transformer-enhanced branch with local self-attention for richer contextual feature extraction. Unlike conventional lightweight hybrid models relying on static inference pipelines, EcoTomHybridNet integrates a lightweight policy-guided routing mechanism that dynamically allocates inputs between the fast convolutional branch and the Transformer-enhanced branch according to input complexity. This adaptive inference strategy dynamically reduces unnecessary Transformer computations for simpler samples while preserving strong predictive performance on more challenging inputs through policy-guided branch allocation. To further improve representation capability without significantly increasing computational complexity, the proposed student network is trained using knowledge distillation from a ViT-Tiny teacher model. Experimental results on the PlantVillage tomato dataset demonstrate that EcoTomHybridNet achieves 99.42% test accuracy and 99.0% validation accuracy under the full hybrid inference configuration. Additional validation strategies, including 5-fold cross-validation and robustness evaluation under Gaussian noise and motion blur perturbations, indicate stable performance across different data splits and moderate image degradations, suggesting improved generalization capability beyond simple dataset memorization. Furthermore, adaptive routing experiments using a lightweight threshold-based policy mechanism achieved 99.20% test accuracy while reducing computational complexity from 0.36 GFLOPs to 0.25 GFLOPs per image, corresponding to approximately 30% computational savings. These results demonstrate the effectiveness of policy-guided adaptive inference for balancing predictive performance and computational efficiency in edge-oriented plant disease classification. Overall, EcoTomHybridNet provides an efficient and adaptive framework for intelligent plant disease monitoring in IoT-enabled smart agriculture systems. Full article

In this work, we propose ARTEMIS, a novel and highly interpretable deep learning pipeline for the automatic classification of Chest X-ray (CXR) and Computed Tomography (CT) images into different categories related to important clinical outcomes: COVID-19 infection, Community-Acquired Pneumonia (CAP) cases, and Normal cases. Unlike existing models based on the static feature enhancement step, ARTEMIS proposes a learnable preprocessing component that dynamically adapts the image contrast and sharpness in training mode, facilitating adaptive optimization. Our hybrid network combines EfficientNet-B0 backbone with built-in SE attention with the optional lightweight Transformer encoder block to jointly learn local radiological features and global relationships between pixels. Comprehensive experiments have been conducted on five different datasets, which comprise four publicly available ones and one novel CT dataset annotated by radiologists, including X-ray and CT modalities. Experimental results show strong robustness and generalization with macro F1-scores greater than 96% on public datasets and 99.39% accuracy on our new CT dataset. To interpret the decision-making process, Grad-CAM++ is employed to generate class-discriminative saliency maps; the highlighted regions are systematically validated against established radiological criteria by a board-certified radiologist, confirming that model decisions are grounded in clinically meaningful pulmonary findings rather than imaging artifacts. Full article