Search Results (129)

Grinding surface texture is random and feature information is weak, so it is difficult to extract effective features by deep learning network. In addition, the existing deep learning methods mostly adopt a large parameter model in grinding surface roughness recognition task, and the cost of deployment in embedded end is high. In order to solve these problems, a new lightweight network model GE-MobileNet (Ghost-ECA-MobileNetV3) is proposed. Based on MobileNetV3, a feature extractor is introduced into the shallow network part of the model to enhance the ability of the network to extract and suppress the surface texture feature and noise. At the same time, SE (Squeeze-and-Excitation) attention mechanism is replaced with ECA (Efficient Channel) attention mechanism with stronger performance. Finally, the deep network layer is removed to reduce the model size. The experimental results show that the accuracy of GE-MobileNet-based grinding surface roughness measurement model on test set is 94.97%, which is better than other networks. This study proves the effectiveness of the roughness measurement method based on GE-MobileNet. Full article

Obstructive sleep apnea–hypopnea syndrome (OSAHS) is a prevalent sleep disorder strongly linked to increased cardiovascular and metabolic risk. While prior studies have explored snore-based analysis for OSAHS, they have largely focused on either detection or classification in isolation. Here, we present a two-stage framework that integrates precise snoring event detection with deep learning-based classification. In the first stage, we develop an Adaptive Multi-Feature Fusion Endpoint Detection algorithm (AMFF-ED), which leverages short-time energy, spectral entropy, zero-crossing rate, and spectral centroid to accurately isolate snore segments following spectral subtraction noise reduction. Through adaptive statistical thresholding, joint decision-making, and post-processing, our method achieves a segmentation accuracy of 96.4%. Building upon this, we construct a balanced dataset comprising 6830 normal and 6814 OSAHS-related snore samples, which are transformed into Mel spectrograms and input into ERBG-Net—a hybrid deep neural network combining ECA-enhanced ResNet18 with bidirectional GRUs. This architecture captures both spectral patterns and temporal dynamics of snoring sounds. The experimental results demonstrate a classification accuracy of 95.84% and an F1 score of 94.82% on the test set, highlighting the model’s robust performance and its potential as a foundation for automated, at-home OSAHS screening. Full article

On-road vision-based systems rely on object detection to ensure vehicle safety and efficiency, making it an essential component of autonomous driving. Deep learning methods show high performance; however, they often require special hardware due to their large sizes and computational complexity, which makes real-time deployment on edge devices expensive. This study proposes lightweight object detection models based on the YOLOv5s architecture, known for its speed and accuracy. The models integrate advanced channel attention strategies, specifically the ECA module and SE attention blocks, to enhance feature selection while minimizing computational overhead. Four models were developed and trained on the KITTI dataset. The models were analyzed using key evaluation metrics to assess their effectiveness in real-time autonomous driving scenarios, including precision, recall, and mean average precision (mAP). BaseECAx2 emerged as the most efficient model for edge devices, achieving the lowest GFLOPs (13) and smallest model size (9.1 MB) without sacrificing performance. The BaseSE-ECA model demonstrated outstanding accuracy in vehicle detection, reaching a precision of 96.69% and an mAP of 98.4%, making it ideal for high-precision autonomous driving scenarios. We also assessed the models’ robustness in more challenging environments by training and testing them on the BDD-100K dataset. While the models exhibited reduced performance in complex scenarios involving low-light conditions and motion blur, this evaluation highlights potential areas for improvement in challenging real-world driving conditions. This study bridges the gap between affordability and performance, presenting lightweight, cost-effective solutions for integration into real-time autonomous vehicle systems. Full article

In this paper, we propose a crossover operator for genetic algorithms with binary chromosomes populations based on the cellular automata ($\mathit{CGACell}$). After presenting the fundamental elements regarding cellular automata with specific examples for one- and two- dimensional cases, the the most widely used crossover operators in applications with genetic algorithms are described, and the crossover operator based on cellular automata is defined. Specific forms of the crossover operator based on the ECA and 2D CA cases are described and exemplified. The $\mathit{CGACell}$ crossover operator is used in the genetic structure to improved the KNN algorithm in terms of the parameter represented by the number of nearest neighbors selected by the data classification method. Validity and practical performance testing are performed on image data classification problems by optimizing the nearest-neighbors-based algorithm. The experimental study on the proposed crossover operator, by comparing a GA algorithm based on $\mathit{CGACell}$ with GA algorithms based on other crossover methods, including classical GAs and permutation-based, heuristic, and hybrid methods, attests to good qualitative performance in terms of correctness percentages in the recognition of new images, as well as in classification and recognition applications of facial image classes corresponding to several persons. Full article

Background/Objectives: Accurate visualization of the Achilles tendon enthesis is critical for distinguishing mechanical, degenerative, and inflammatory pathologies. Although ultrasonography is the first-line modality for suspected enthesis disease, recent technical advances may expand the role of magnetic resonance imaging (MRI). This study evaluated the utility of ultra-short echo time (UTE) and zero echo time (ZTE) sequences versus proton density-weighted imaging (PD-WI) for depicting the enthesis organ in healthy volunteers. Methods: In this institutional review board (IRB)-approved prospective single-center study, 50 asymptomatic adult volunteers underwent 3-Tesla hindfoot MRI with fat-suppressed PD-WI, UTE, and ZTE between 2018 and 2023. Four radiologists assessed image quality, signal-to-noise ratio, visibility, and abnormal high signal intensities (SIs) of the periost, sesamoid, and enthesis fibrocartilages (PCa, SCa, and ECa, respectively). Statistical tests included Chi-square, McNemar, paired Wilcoxon, and Benjamini–Hochberg adjustments for multiple comparisons. Results: The median age was 36 years (range: 20–51); 58% women were included. PD-WI and ZTE sequences were always available while UTE was unavailable in 24% of patients. PD-WI consistently failed to concomitantly visualize all fibrocartilages. ZTE and UTE visualized all fibrocartilages in 72% and 92.1% of volunteers, respectively, with significant differences favoring ZTE and UTE over PD-WI (p < 0.0001) and UTE over ZTE (p = 0.027). Inter-rater agreement exceeded 80% except for SCa on ZTE (68%, 95%CI: 53.2–80.1). Abnormal SCa findings in asymptomatic patients were more frequent with UTE (23.7%) and ZTE (34%) than with PD-WI (2%) (p = 0.0045). Conclusions: At 3-Tesla, UTE and ZTE sequences reliably depict the enthesis organ of the Achilles tendon, outperforming PD-WI. However, the high sensitivity of these sequences also presents challenges in interpretation. Full article

To meet the growing demand for secure and reliable image protection in digital communication, this paper proposes a novel image encryption framework that addresses the challenges of high plaintext sensitivity, resistance to statistical attacks, and key security. The method combines a two-dimensional dynamically coupled map lattice (2D DCML) with elementary cellular automata (ECA) to construct a heterogeneous chaotic system with strong spatiotemporal complexity. To further enhance nonlinearity and diffusion, a multi-source perturbation mechanism and adaptive DNA encoding strategy are introduced. These components work together to obscure the image structure, pixel correlations, and histogram characteristics. By embedding spatial and temporal symmetry into the coupled lattice evolution and perturbation processes, the proposed method ensures a more uniform and balanced transformation of image data. Meanwhile, the method enhances the confusion and diffusion effects by utilizing the principle of symmetric perturbation, thereby improving the overall security of the system. Experimental evaluations on standard images demonstrate that the proposed scheme achieves high encryption quality in terms of histogram uniformity, information entropy, NPCR, UACI, and key sensitivity tests. It also shows strong resistance to chosen plaintext attacks, confirming its robustness for secure image transmission. Full article

Background: Soybean is an important global crop in food security and agricultural economics. Accurate estimation of soybean pod counts is critical for yield prediction, breeding programs, precision farming, etc. Traditional methods, such as manual counting, are slow, labor-intensive, and prone to errors. With rapid advancements in artificial intelligence (AI), deep learning has enabled automatic pod number estimation in collaboration with unmanned aerial vehicles (UAVs). However, existing AI models are computationally demanding and require significant processing resources (e.g., memory). These resources are often not available in rural regions and small farms. Methods: To address these challenges, this study presents a set of lightweight, efficient AI models designed to overcome these limitations. By integrating model simplification, weight quantization, and squeeze-and-excitation (SE) self-attention blocks, we develop compact AI models capable of fast and accurate soybean pod count estimation. Results and Conclusions: Experimental results show a comparable estimation accuracy of 84–87%, while the AI model size is significantly reduced by a factor of 9–65, thus making them suitable for deployment in edge devices, such as Raspberry Pi. Compared to existing models such as YOLO POD and SoybeanNet, which rely on over 20 million parameters to achieve approximately 84% accuracy, our proposed lightweight models deliver a comparable or even higher accuracy (84.0–86.76%) while using fewer than 2 million parameters. In future work, we plan to expand the dataset by incorporating diverse soybean images to enhance model generalizability. Additionally, we aim to explore more advanced attention mechanisms—such as CBAM or ECA—to further improve feature extraction and model performance. Finally, we aim to implement the complete system in edge devices and conduct real-world testing in soybean fields. Full article

Objective: This study proposes a novel deep learning approach for enhancing low-dose bone scintigraphy images using an Enhanced Convolutional Autoencoder (ECAE), aiming to reduce patient radiation exposure while preserving diagnostic quality, as assessed by both expert-based quantitative image metrics and qualitative evaluation. Methods: A supervised learning framework was developed using real-world paired low- and full-dose images from 105 patients. Data were acquired using standard clinical gamma cameras at the Nuclear Medicine Department of the University General Hospital of Alexandroupolis. The ECAE architecture integrates multiscale feature extraction, channel attention mechanisms, and efficient residual blocks to reconstruct high-quality images from low-dose inputs. The model was trained and validated using quantitative metrics—Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM)—alongside qualitative assessments by nuclear medicine experts. Results: The model achieved significant improvements in both PSNR and SSIM across all tested dose levels, particularly between 30% and 70% of the full dose. Expert evaluation confirmed enhanced visibility of anatomical structures, noise reduction, and preservation of diagnostic detail in denoised images. In blinded evaluations, denoised images were preferred over the original full-dose scans in 66% of all cases, and in 61% of cases within the 30–70% dose range. Conclusion: The proposed ECAE model effectively reconstructs high-quality bone scintigraphy images from substantially reduced-dose acquisitions. This approach supports dose reduction in nuclear medicine imaging while maintaining—or even enhancing—diagnostic confidence, offering practical benefits in patient safety, workflow efficiency, and environmental impact. Full article

To address the issues of missed detections and false detections of small target missed detections caused by dense occlusion in complex traffic environments, a non-maximum suppression method, Bot-NMS, is proposed to achieve accurate prediction and localization of occluded targets. In the backbone network of YOLOv7, the Ghost module, the ECA attention mechanism, and the multi-scale feature detection structure are introduced to enhance the network’s capacity to learn small target features. The SCSTD and KITTI datasets were used to train and test the improved YOLOv7 target detection network model. The results demonstrate that the improved YOLOv7 method significantly enhances the recall rate and detection accuracy of various targets. A multi-target tracking method based on target re-identification (ReID) is proposed. Utilizing deep learning theory, a ReID model for target identification is constructed to comprehensively capture global and foreground target features. By establishing the correlation cost matrix of the cosine distance and IoU overlap, the correlation between target detection objects, the tracking trajectory, and ReID feature similarity is realized. The VERI-776 vehicle re-identification dataset and MARKET1501 pedestrian re-identification dataset were used to train the proposed ReID model, and multi-target tracking performance comparison experiments were conducted on the MOT16 dataset. The results show that the multi-target tracking method by introducing the ReID model and improving the cost matrix can better deal with the dense occlusion of the target, and can effectively and accurately track the road target in the realistic complex traffic environment. Full article

Background: Our study evaluated the correlation between internal carotid artery stenosis (ICAS) and retinal microvascular changes in patients with hypertensive retinopathy, dyslipidemia and ICAS. We analyzed vascular measurements provided by optical coherence tomography angiography (OCTA) and carotid Doppler ultrasonography (US) and linked OCTA parameters with carotid artery US measurements on the same side. Statistical differences in OCTA analysis among three groups (no stenosis, mild stenosis and moderate stenosis) were evaluated and correlated with carotid Doppler parameters. Our study aimed to evaluate whether OCTA can be proposed as a screening method in patients diagnosed with mild and moderate ICAS in order to improve the early detection of carotid changes, thus potentially reducing the rate of cardiovascular and cerebral complications of ICAS. Methods: We conducted a study on hypertensive patients with ICAS using six OCTA parameters in the analysis of the retinal vasculature and carotid Doppler US velocities of three carotid arteries and the vertebral artery (VA). Kruskal–Wallis and Dunn’s post hoc tests were used to determine whether there were statistically significant differences between the normal, mild and moderate stenosis groups. Spearman and Pearson correlation were used to obtain correlations among OCTA parameters such as the foveal avascular zone (FAZ), non-flow area (NFA), vascular flow area (VFA) and blood flow velocity on carotid Doppler US. Results: In the final analysis, 49 patients were included and 3 groups of stenosis were obtained, comprising 21 subjects with no stenosis, 19 with mild stenosis and 9 with moderate stenosis. Right eye and left eye groups were formed. In the right eye group with right ICAS, we found statistically significant results for FAZ circularity when comparing the normal stenosis group to the mild stenosis group (p = 0.025) and the mild stenosis group to the moderate stenosis group (p = 0.006). Statistically significant results were also observed for NFA when comparing the normal stenosis group to the moderate stenosis group (p = 0.004) and the mild stenosis group to the moderate stenosis group (p = 0.011). When comparing the FAZ area (p = 0.016) and VFA (p = 0.037) for the normal and moderate groups, statistically significant values were obtained. When comparing the normal and moderate stenosis groups with regard to the left eye, we found statistically significant results for VFA (p = 0.041), NFA (p = 0.045) and VFA (p = 0.029). When comparing the mild and moderate carotid artery stenosis groups, we obtained statistically significant results for NFA (p = 0.001), FAZ area (p = 0.007) and VFA (p = 0.013). In the right eye group, correlations between internal carotid artery (ICA) peak systolic velocity (PSV) and VFA (rho = −0.286), ICA end-diastolic velocity (EDV) and NFA (r = 0.365), external carotid artery (ECA) PSV and VFA (r = −0.288; rho = −0.317), common carotid artery (CCA) PSV and NFA (rho = −0.345), CCA EDV and NFA (rho = −0.292) and VA PSV and VFA (r = −0.327; rho = −0.379) were found. When analyzing OCTA parameters, we found statistically significant results for NFA and VFA (r = −0.374; rho = −0.288). Correlations were also found in the left eye group between ICA PSV and NFA (r = −0.351; rho = −0.313), ICA EDV and VFA (r = −0.421; rho = −0.314), ECA PSV and NFA (r = −0.412; rho = −0.457), CCA PSV and NFA (p = −0.288; rho = −0.339), and CCA EDV and NFA (r = −0.404; rho = −0.417). Conclusions: Our study found correlations between carotid Doppler velocities and OCTA vascular flow parameters; thus, OCTA may be used as a tool for monitoring the microvascular changes associated with carotid stenosis. OCTA can provide insights concerning the overall vascular condition of the patient, since it provides subjective data on vessel density and flow; therefore, by monitoring hypertensive patients with both OCTA and carotid Doppler US, we may be able to increase efficiency in screening and diagnosing patients with IACS. Full article

In rolling bearing fault diagnosis, when an unknown fault is present, the Closed-Set Recognition (CSR) method tends to misclassify it as a known fault. To address this issue, an Open-Set Recognition (OSR) framework is proposed for rolling bearing fault diagnosis in this study. The framework is built upon a serial multi-scale convolutional prototype learning (SMCPL) network, enhanced with an efficient channel attention (ECA) mechanism to extract the most critical fault features. The extracted features are fed into the Density Peak Clustering (DPC) module, which identifies known and unknown classes based on the computed local densities and relative distances. Finally, validation is performed on the Case Western Reserve University (CWRU) dataset, the Xi’an Jiaotong University rolling bearing accelerated life test dataset (XJTU-SY), and the Paderborn University bearing dataset (PU), Germany, and the framework is comprehensively evaluated in terms of several evaluation metrics, such as normalization accuracy and feature visualization. The experimental results show that SMCPL-ECA-DPC outperforms the comparative methods of SMCPL, CPL, ANEDL, CNN, and OpenMax and has high diagnostic performance in the identification of unknown faults. Full article

Seed potatoes without sprouts usually need to be manually selected in mechanized production, which has been the bottleneck of efficiency. A fast and efficient object recognition algorithm is required for the additional removal process to identify unqualified seed potatoes. In this paper, a lightweight deep learning algorithm, YOLOv8_EBG, is proposed to both improve the detection performance and reduce the model parameters. The ECA attention mechanism was introduced in the backbone and neck of the model to more accurately extract and fuse sprouting features. To further reduce the model parameters, Ghost convolution and C3ghost were introduced to replace the normal convolution and C2f blocks in vanilla YOLOv8n. In addition, a bi-directional feature pyramid network is integrated in the neck part for multi-scale feature fusion to enhance the detection accuracy. The experimental results from an isolated test dataset show that the proposed algorithm performs better in detecting sprouts under natural light conditions, achieving an mAP_0.5 of 95.7% and 91.9% AP for bud recognition. Compared to the YOLOv8n model, the improved model showed a 6.5% increase in mAP_0.5, a 12.9% increase in AP_0.5 for bud recognition, and a 5.6% decrease in the number of parameters. Additionally, the improved algorithm was applied and tested on mechanized sorting equipment, and the accuracy of seed potato detection was as high as 92.5%, which was sufficient to identify and select sprouted potatoes, an indispensable step since only sprouted potatoes can be used as seed potatoes. The results of the study can provide technical support for subsequent potato planting intelligence. Full article

The welding quality of industrial pipelines directly impacts structural safety. X-ray non-destructive testing (NDT), known for its non-invasive and efficient characteristics, is widely used for weld defect detection. However, challenges such as low contrast between defects and background, as well as large variations in defect scales, reduce the accuracy of existing object detection models. To address these, an optimized detection model based on You Only Look Once (YOLO) v5 is proposed. Firstly, the Efficient Multi-Scale Attention (EMA) attention mechanism is integrated into the first Cross Stage Partial (C3) module of the backbone to enhance the model’s receptive field and the initial feature extraction. Secondly, the Efficient Channel Attention (ECA) attention mechanism is embedded before the Spatial Pyramaid Pooling Fast (SPPF) layer to enhance the model’s ability to extract small targets and key features. Finally, the Complete Intersection over Union (CIoU) loss is replaced with Wise Intersection over Union (WIoU) to improve localization accuracy and multi-scale detection performance. The experimental results show that the optimized model achieves a precision of 94.1%, a recall of 89.2%, and an mAP@0.5 of 94.6%, representing improvements by 11.5%, 5.4%, and 6.9%, respectively, over the original YOLOv5. The optimized model also outperforms several mainstream object detection models in weld defect detection. In terms of mAP@0.5, the optimized YOLOv5 model shows improvements of 14.89%, 13.02%, 6.1%, 19.37%, 7.1%, 7.5%, and 10.7% compared with the Faster-RCNN, SSD, RT-DETR, YOLOv3, YOLOv8, YOLOv9, and YOLOv10 models, respectively. This optimized model significantly enhances X-ray weld defect detection accuracy, meeting industrial application requirements and offering another high-precision solution for weld defect detection. Full article

Many bearing fault diagnosis methods often struggle to balance between adequate feature extraction and lightweight property, which makes it somewhat difficult to fulfill the accuracy and efficiency required for practical applications. To address this issue, this study describes the development of a multiscale lightweight deep learning model for accurate bearing fault diagnosis. Specifically, the Gaussian pyramid method, which can create a series of images at different scales, is employed to express the Gramian angular field (GAF) matrix images generated by transforming the bearing vibration signals to avoid the common problem of insufficient feature extraction of a single-scale image. At the same time, the dependencies between feature channels are extracted using a lightweight attention mechanism utilized in deep learning, known as Efficient Channel Attention (ECA), to improve the capability of feature representation. This approach effectively improves the learning ability of bearing fault characteristics and greatly increases the accuracy of fault diagnosis. Considering the problem related to the lightweight level of the method, a Ghost module, a type of convolution neural network system, is also employed to generate more features by using fewer parameters, thereby improving the overall calculation efficiency. Here we have developed a residual module based on the Ghost module and ECA, which can be easily integrated into most bearing fault diagnosis backbone networks. Based on our experimental tests, the developed system can clearly achieve high accuracy precision of bearing fault diagnosis to fulfill the needs of practical engineering while maintaining light weight. Specifically, the test accuracy of the proposed method using two bearing fault datasets exceeds 99.4%, and the giga floating-point operations (GFLOPs) is only 1.99, which can fully meet the needs of practical engineering. Full article

Objectives: Carotid geometry and cardiovascular risk factors play a significant role in the development of carotid atherosclerotic plaques. This study aimed to investigate the correlation between carotid plaque formation and carotid artery geometry characteristics. Methods: A retrospective cross-sectional analysis was performed on 1227 patients, categorized into a normal group (n = 685) and carotid plaque groups causing either mild stenosis (<50% stenosis based on NASCET criteria, n = 385) or moderate-to-severe stenosis (>50%, n = 232). The left and right carotid were evaluated individually for each group. Patient data, including cardiovascular risk factors and laboratory test results, were collected. Carotid geometric measurements were obtained from 3D models reconstructed from cranio-cervical computed tomography angiography (CTA) using semi-automated software (MIMICS). The geometric variables analyzed included the vascular diameter and sectional area of the common carotid artery (CCA), internal carotid artery (ICA), external carotid artery (ECA), and carotid artery bifurcation (CAB), as well as the carotid bifurcation angles and carotid tortuosity. Results: Compared to the normal group, in both the right and left carotid arteries, patients with carotid plaques exhibited a significantly higher age (p < 0.001) and a greater prevalence of hypertension (p < 0.001) and diabetes mellitus (p < 0.001). Additionally, they demonstrated a larger CCA and a smaller carotid bifurcation dimension (p < 0.05). In the analysis of the left carotid artery, patients with carotid plaques also had a significantly smaller ICA dimension (p < 0.05) than the normal group. Conclusions: This study found that patients with carotid plaques were older and had a higher prevalence of hypertension and diabetes, larger CCAs, and smaller carotid bifurcations. The plaque-positive left ICA was significantly smaller than that of the plaque-negative group, suggesting a side-specific vulnerability. These findings highlight the role of carotid geometry in plaque formation and its potential clinical implications for personalized risk assessment and targeted interventions. Full article