Search Results (415)

Strawberries are highly perishable fruits prone to postharvest losses due to defects, diseases, and uneven ripening. This study proposes a deep learning-based approach for automated quality assessment using the YOLOv8n object detection model. A custom dataset of 5663 annotated strawberry images was compiled, covering eight quality categories, including anthracnose, gray mold, powdery mildew, uneven ripening, and physical defects. Data augmentation techniques, such as rotation and Gaussian blur, were applied to enhance model generalization and robustness. The model was trained over 100 and 200 epochs, and its performance was evaluated using standard metrics: Precision, Recall, and mean Average Precision (mAP). The 200-epoch model achieved the best results, with a mAP50 of 0.79 and an inference time of 1 ms per image, demonstrating suitability for real-time applications. Classes with distinct visual features, such as anthracnose and gray mold, were accurately classified. In contrast, visually similar categories, such as ‘Good Quality’ and ‘Unripe’ strawberries, presented classification challenges. Full article

The Generalized Hough Transform (GHT) is a powerful method for rigid shape detection under rotation, scaling, translation, and partial occlusion conditions, but its four-dimensional accumulator incurs prohibitive computational and memory demands that prevent real-time deployment. To address this, we propose a framework that compresses the 4-D search space into a concise 2-D voting scheme by combining two-level sparse point-pair screening with an accelerated lookup. In the offline stage, template edges are extracted using an adaptive Canny operator with Otsu-determined thresholds, and gradient-direction differences for all point pairs are quantized to retain only those in the dominant bin, yielding rotation- and scale-invariant descriptors that populate a compact 2-D reference table. During the online stage, an adaptive grid selects only the highest-gradient pixels per cell as a base points, while a precomputed gradient-direction bucket table enables constant-time retrieval of compatible subpoints. Each valid base–subpoint pair is mapped to indices in the lookup table, and “fuzzy” votes are cast over a 3 × 3 neighborhood in the 2-D accumulator, whose global peak determines the object center. Evaluation on 200 real industrial parts—augmented to 1000 samples with noise, blur, occlusion, and nonlinear illumination—demonstrates that our method maintains over 90% localization accuracy, matches the classical GHT, and achieves a ten-fold speedup, outperforming IGHT and LI-GHT variants by 2–3×, thereby delivering a robust, real-time solution for industrial rigid object localization. Full article

Span-wise homogeneous supersonic cavity flows display complicated structures due to shear layer breakdown, flow acoustic resonance, and even non-linear hydrodynamic-acoustic interactions. In practical applications, such as aircraft bays, the cavity is of finite width and has doors, both of which introduce distinctive phenomena that couple with the shear layer at the cavity lip, further modulating shear layer bifurcations and tonal mechanisms. In particular, asymmetric states manifest as ‘tornado’ vortices with significant practical consequences on the design and operation. Both inward- and outward-facing leading-wedge doors, resulting in leading edge shocks directed into and away from the cavity, are examined at select opening angles ranging from $22.5°$ to $90°$ (fully open) at Mach 1.6. The computational approach utilizes the Reynolds-Averaged Navier–Stokes equations with a one-equation model and is augmented by experimental observations of cavity floor pressure and surface oil-flow patterns. For the no-doors configuration, the asymmetric results are consistent with a long-time series DDES simulation, previously validated with two experimental databases. When fully open, outer wedge doors (OWD) yield an asymmetric flow, while inner wedge doors (IWD) display only mildly asymmetric behavior. At lower door angles (partially closed cavity), both types of doors display a successive bifurcation of the shear layer, ultimately resulting in a symmetric flow. IWD tend to promote symmetry for all angles observed, with the shear layer experiencing a pitchfork bifurcation at the ‘critical angle’ ($67.5°$). This is also true for the OWD at the ‘critical angle’ ($45°$), though an entirely different symmetric flow field is established. The first observation of pitchfork bifurcations (‘critical angle’) for the IWD is at $67.5°$ and for the OWD, $45°$, complementing experimental observations. The back wall signature of the bifurcated shear layer (impingement preference) was found to be indicative of the 3D cavity dynamics and may be used to establish a correspondence between 3D cavity dynamics and the shear layer. Below the critical angle, the symmetric flow field is comprised of counter-rotating vortex pairs at the front and back wall corners. The existence of a critical angle and the process of door opening versus closing indicate the possibility of hysteresis, a preliminary discussion of which is presented. Full article

Background: Pharmaceutical compounds frequently co-occur in environmental waters, but studies on their combined effects on animals and humans remain limited. The present study investigated the individual and combined short-term effects of ketoprofen (Kp, a nonsteroidal anti-inflammatory drug inhibiting cyclooxygenase-2), valproic acid (VPA, an anticonvulsant acting as a voltage-gated sodium channel modulator), and meropenem (Mp, a β-lactam antibiotic) at environmentally relevant concentrations on zebrafish behavior, acetylcholinesterase (AChE) activity, and oxidative status. Methods: Adult zebrafish were exposed for 4 days to Kp, VPA, Mp, and their binary and ternary mixtures. Behavioral effects were assessed using 3D novel tank and social behavior tests, while the oxidative stress response was assessed through malondialdehyde (MDA) content, superoxide dismutase (SOD), and glutathione peroxidase (GPx) activities. Results: Zebrafish exposed to Mp showed a notable increase in immobility, whereas those exposed to VPA and Mp + Kp exhibited a significant augmentation of average velocity and counter-clockwise rotations. All treated groups exhibited a notable increase in the time spent near the walls (thigmotaxis), and except for the control and Mp-exposed zebrafish, the other groups mostly stayed in the bottom tank zone (geotaxis). Kp, VPA + Kp, and VPA + Mp + Kp treatments impaired social behavior, with zebrafish displaying less interest in conspecifics. Biochemical analysis demonstrated that both the individual drugs and their combination caused oxidative stress, characterized by decreased GPx activity and increased SOD activity and MDA levels. Moreover, AChE activity was more strongly inhibited in zebrafish exposed to the binary and ternary mixtures than to individual drugs. Conclusions: The results indicate that acute exposure to individual and/or combined pharmaceuticals induces behavioral changes, oxidative damage, and AChE inhibition in zebrafish, highlighting the need to assess the effects of pharmaceutical mixtures for comprehensive ecosystem risks evaluation. Full article

The accurate identification of wood patterns is critical for optimizing the use of sustainable wood building materials, promoting resource efficiency, and reducing waste in construction. This study presents a deep learning-based approach for enhanced wood material recognition, combining EfficientNet architecture with advanced data augmentation techniques to achieve robust classification. The augmentation strategy incorporates geometric transformations (flips, shifts, and rotations) and photometric adjustments (brightness and contrast) to improve dataset diversity while preserving discriminative wood grain features. Validation was performed using a controlled augmentation pipeline to ensure realistic performance assessment. Experimental results demonstrate the model’s effectiveness, achieving 88.9% accuracy (eight out of nine correct predictions), with further improvements from targeted image preprocessing. The approach provides valuable support for preliminary sustainable building material classification, and can be deployed through user-friendly interfaces without requiring specialized AI expertise. The system retains critical wood pattern characteristics while enhancing adaptability to real-world variability, supporting reliable material classification in sustainable construction. This study highlights the potential of integrating optimized neural networks with tailored preprocessing to advance AI-driven sustainability in building material recognition, contributing to circular economy practices and resource-efficient construction. Full article

The construction of large-scale, dynamic datasets for specialized domain models often suffers with problems of low efficiency and poor consistency. This paper proposes a method that integrates multi-role collaboration with automated annotation to address these issues. The framework introduces two new roles, data augmentation specialists and automatic annotation operators, to establish a closed-loop process that includes dynamic classification adjustment, data augmentation, and intelligent annotation. Two supporting tools were developed: an image classification modification tool that automatically adapts to changes in categories and an automatic annotation tool with rotation-angle perception based on the rotation matrix algorithm. Experimental results show that this method increases annotation efficiency by 40% compared to traditional approaches, while achieving 100% annotation consistency after classification modifications. The method’s effectiveness was validated using the WATER-DET dataset, a collection of 1500 annotated images from the water conservancy engineering field. A model trained on this dataset achieved an F1-score of 0.9 for identifying water environment problems in rivers and lakes. This research offers an efficient framework for dynamic dataset construction, and the developed methods and tools are expected to promote the application of artificial intelligence in specialized domains. Full article

Accurate preoperative distinction between in situ and invasive Breast Cancer (BC) is critical for clinical decision-making and treatment planning. Radiomics and Machine Learning (ML) have shown promise in enhancing diagnostic performance from breast MRI, yet their application to this specific task remains underexplored. The aim of this study was to evaluate the performance of several ML classifiers, trained on radiomic features extracted from DCE–MRI and supported by basic clinical information, for the classification of in situ versus invasive BC lesions. In this study, we retrospectively analysed 71 post-contrast DCE–MRI scans (24 in situ, 47 invasive cases). Radiomic features were extracted from manually segmented tumour regions using the PyRadiomics library, and a limited set of basic clinical variables was also included. Several ML classifiers were evaluated in a Leave-One-Out Cross-Validation (LOOCV) scheme. Feature selection was performed using two different strategies: Minimum Redundancy Maximum Relevance (MRMR), mutual information. Axial 3D rotation was used for data augmentation. Support Vector Machine (SVM), K Nearest Neighbors (KNN), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) were the best-performing models, with an Area Under the Curve (AUC) ranging from 0.77 to 0.81. Notably, KNN achieved the best balance between sensitivity and specificity without the need for data augmentation. Our findings confirm that radiomic features extracted from DCE–MRI, combined with well-validated ML models, can effectively support the differentiation of in situ vs. invasive breast cancer. This approach is quite robust even in small datasets and may aid in improving preoperative planning. Further validation on larger cohorts and integration with additional imaging or clinical data are recommended. Full article

In the field of music notation recognition, while the recognition technology for common notation systems such as staff notation has become quite mature, the recognition techniques for traditional Chinese notation systems like guqin tablature (jianzipu) and Kunqu opera gongchepu remain relatively underdeveloped. As an important carrier of China’s thousand-year musical culture, the digital preservation and inheritance of Kunqu opera’s Gongche notation hold significant cultural value and practical significance. By addressing the unique characteristics of Gongche notation, this study overcomes the limitations of Western staff notation recognition technologies. By constructing a deep learning model adapted to the morphology of Chinese character-style notation symbols, it provides technical support for establishing an intelligent processing system for Chinese musical documents, thereby promoting the innovative development and inheritance of traditional music in the era of artificial intelligence. This paper has constructed the LGRC2024 (Gong-che notation based on Lilu Qu Pu) dataset. It has also employed data augmentation operations such as image translation, rotation, and noise processing to enhance the diversity of the dataset. For the recognition of Gong-che notation, the YOLOv8 model was adopted, and the network performances of its lightweight (n) and medium-weight (m) versions were compared and analyzed. The superior-performing YOLOv8m was selected as the basic model. To further improve the model’s performance, SimAM, Triplet Attention, and Multi-scale Convolutional Attention Module (MSCAM) were introduced to optimize the model. The experimental results show that the accuracy of the basic YOLOv8m model increased from 65.9% to 78.2%. The improved models based on YOLOv8m achieved recognition accuracies of 80.4%, 81.8%, and 83.6%, respectively. Among them, the improved model with the MSCAM module demonstrated the best performance in all aspects. Full article

With the rapid expansion of railway networks and increasing operational complexity, intelligent rail damage detection has become crucial for ensuring safety and improving maintenance efficiency. Traditional physical inspection methods (e.g., ultrasonic testing, magnetic flux leakage) are limited in terms of efficiency and environmental adaptability. This study proposes a machine vision-based approach leveraging deep learning to identify four primary types of rail damages: corrugations, spalls, cracks, and scratches. A self-developed acquisition device collected 298 field images from the Chongqing Metro system, which were expanded into 1556 samples through data augmentation techniques (including rotation, translation, shearing, and mirroring). This study systematically evaluated three object detection models—YOLOv8, SSD, and Faster R-CNN—in terms of detection accuracy (mAP), missed detection rate (mAR), and training efficiency. The results indicate that YOLOv8 outperformed the other models, achieving an mAP of 0.79, an mAR of 0.69, and a shortest training time of 0.28 h. To further enhance performance, this study integrated the Multi-Head Self-Attention (MHSA) module into YOLO, creating MHSA-YOLOv8. The optimized model achieved a significant improvement in mAP by 10% (to 0.89), increased mAR by 20%, and reduced training time by 50% (to 0.14 h). These findings demonstrate the effectiveness of MHSA-YOLO for accurate and efficient rail damage detection in complex environments, offering a robust solution for intelligent railway maintenance. Full article

Artificial intelligence (AI)-based techniques have become increasingly prevalent in the classification of medical images. However, the effectiveness of such methods is often constrained by the limited availability of annotated medical data. To address this challenge, data augmentation is frequently employed. This study investigates the impact of a novel augmentation approach on the classification performance of malignant lymphoma histopathological images. The proposed method involves slicing high-resolution images (1388 × 1040 pixels) into smaller segments (224 × 224 pixels) before applying standard augmentation techniques such as flipping and rotation. The original dataset consists of 374 images, comprising 32.6% mantle cell lymphoma, 30.2% chronic lymphocytic leukemia, and 37.2% follicular lymphoma. Through slicing, the dataset was expanded to 8976 images, and further augmented to 53,856 images. The visual geometry group with 16 layers (VGG16) convolutional neural network (CNN) was trained and evaluated on three datasets: the original, the sliced, and the sliced with augmentation. Performance was assessed using accuracy, AUC, precision, sensitivity, specificity, and F1 score. The results demonstrate a substantial improvement in classification performance when slicing was employed, with additional, albeit smaller, gains achieved through subsequent augmentation. Full article

The accuracy of pedicle screw insertion in pediatric scoliosis correction surgery using augmented reality technology in combination with a conventional navigation system was evaluated, and its usefulness was verified. A retrospective study of patients who underwent mixed reality technology-assisted posterior scoliosis correction and fixation was conducted. In total, 361 pedicle screws inserted with a mixed reality technology-assisted navigation system were analyzed; 25 pedicle screws (6.9%) showed Rao Classification Grade 1 deviation, whereas 0.83% showed Rao Classification Grade 2.3 deviation, which is a clinical deviation. In terms of the relationship between the rotation of the vertebral body and the deviation of the pedicle screw, the pedicle screw tended to deviate more easily when it was necessary to insert the pedicle screw in a more strongly oblique position due to the rotation of the vertebral body. The results suggest that the pedicle screw insertion accuracy with augmented reality technology may be superior to that with conventional navigation alone in scoliosis correction and fusion surgery for scoliosis in children. This system is expected to become a standard support tool for spine surgery and will contribute to improving the success rate of surgery and reducing the burden on the surgeon. Full article

Background: Coagulopathy in severe burn injury is associated with complications and mortality. Methods: We compared 3 tests (EXTEM, INTEM, FIBTEM) of rotational thromboelastometry (ROTEM), a viscoelastic coagulation assay (VCA), with conventional coagulation assays (CCAs), fibrinogen, d-dimers and coagulation factors during the five post-burn days in survivors and non-survivors with severe burn injury, in order to correlate the results with burn coagulopathy and prognosis. Results: Seventeen survivors and ten non-survivors, with mean total burn surface area of 33.78% were included. CCAs measurements were abnormal, but unable to detect coagulopathy. At day 2, D-dimers and fibrinogen levels were statistically augmented for non-survivors. Regarding VCAs, FIBTEM MCF increased for non-survivors at day 2 and remained increased for the whole post-burn period. Furthermore, FIBTEM A10 and A20 at day 2 and EXTEM A10, EXTEM A20, EXTEM MCF, and EXTEM CFT at day 5 took abnormal values for the same group (p < 0.05). These changes were underlined through abnormal measurements of coagulation factors. Conclusions:CCAs are poor indicators of coagulation status in burn injury, whereas VCAs are more sensitive markers, demonstrating coagulopathy and patients at greater risk of mortality. Full article

This research addresses the critical need for an efficient and precise identification of Capsicum spp. fruit varieties within the post-harvest contexts to enhance quality control and ensure consumer satisfaction. Employing the YOLOv8m convolutional neural network, the study identified eight distinct pepper varieties: Pimento, Bode, Cambuci, Chilli, Fidalga, Habanero, Jalapeno, and Scotch Bonnet. A dataset comprising 1476 annotated images was utilized and significantly expanded through data augmentation techniques, including rotation, flipping, and contrast adjustments. Comparative analysis reveals that training with the augmented dataset yielded significant improvements across key performance indicators, particularly in box precision, recall, and mean average precision (mAP50 and mAP95), underscoring the effectiveness of data augmentation. These findings underscore the considerable potential of CNNs to advance the AgriFood sector through increased automation and efficiency. While acknowledging the constraints of a controlled image dataset, subsequent research should prioritize expanding the dataset and conducting real-world testing to confirm the model’s robustness across various environmental factors. This study contributes to the field by illustrating the application of deep learning methodologies to enhance agricultural productivity and inform decision-making. Full article

As the most basic mechanical components, bearing troubleshooting is essential to ensure the safe and reliable operation of rotating machinery. Bearing fault diagnosis is challenging due to the scarcity of bearing fault diagnosis samples and the susceptibility of fault signals to external noise. To address these issues, a ResNet-CACNN-BiGRU-SDPA bearing fault diagnosis method based on time–frequency bi-domain and feature fusion is proposed. First, the model takes the augmented time-domain signals as inputs and reconstructs them into frequency-domain signals using FFT, which gives the signals a bi-directional time–frequency domain receptive field. Second, the long sequence time-domain signal is processed by a ResNet residual block structure, and a CACNN method is proposed to realize local feature extraction of the frequency-domain signal. Then, the extracted time–frequency domain long sequence features are fed into a two-layer BiGRU for bidirectional deep global feature mining. Finally, the long-range feature dependencies are dynamically captured by SDPA, while the global dual-domain features are spliced and passed into Softmax to obtain the model output. In order to verify the model performance, experiments were carried out on the CWRU and JNU bearing datasets, and the results showed that the method had high accuracy under both small sample size and noise perturbation conditions, which verified the model’s good fault-feature-learning capability and noise immunity performance. Full article

The morphology of blood vessels in retinal fundus images is a key biomarker for diagnosing conditions such as glaucoma, hypertension, and diabetic retinopathy. This study introduces a deep learning-based method for automatic blood vessel segmentation, trained from scratch on 44 clinician-annotated images. The proposed architecture integrates Bidirectional Long Short-Term Memory (Bi-LSTM) layers with dropout to mitigate overfitting. A distinguishing feature of this approach is the column-wise processing, which improves feature extraction and segmentation accuracy. Additionally, a custom data augmentation technique tailored for retinal images is implemented to improve training performance. The results are presented in their raw form—without post-processing—to objectively assess the method’s effectiveness and limitations. Further refinements, including pre- and post-processing and the use of image rotations to combine multiple segmentation outputs, could significantly boost performance. Overall, this work offers a novel and effective approach to the still unresolved task of retinal vessel segmentation, contributing to more reliable automated analysis in ophthalmic diagnostics. Full article