The cavitation in axial piston pumps threatens the reliability and safety of the overall hydraulic system. Vibration signal can reflect the cavitation conditions in axial piston pumps and it has been ...combined with machine learning to detect the pump cavitation. However, the vibration signal usually contains noise in real working conditions, which raises concerns about accurate recognition of cavitation in noisy environment. This paper presents an intelligent method to recognise the cavitation in axial piston pumps in noisy environment. First, we train a convolutional neural network (CNN) using the spectrogram images transformed from raw vibration data under different cavitation conditions. Second, we employ the technique of gradient‐weighted class activation mapping (Grad‐CAM) to visualise class‐discriminative regions in the spectrogram image. Finally, we propose a novel image processing method based on Grad‐CAM heatmap to automatically remove entrained noise and enhance class features in the spectrogram image. The experimental results show that the proposed method greatly improves the diagnostic performance of the CNN model in noisy environments. The classification accuracy of cavitation conditions increases from 0.50 to 0.89 and from 0.80 to 0.92 at signal‐to‐noise ratios of 4 and 6 dB, respectively.
In this paper, we present a new static and time-dependent MagnetoHydroDynamic (MHD) equilibrium code, TokaMaker, for axisymmetric configurations of magnetized plasmas, based on the well-known ...Grad-Shafranov equation. This code utilizes finite element methods on an unstructured triangular grid to enable capturing accurate machine geometry and simple mesh generation from engineering-like descriptions of present and future devices. The new code is designed for ease of use without sacrificing capability and speed through a combination of Python, Fortran, and C/C++ components. A detailed description of the numerical methods of the code, including a novel formulation of the boundary conditions for free-boundary equilibria, and validation of the implementation of those methods using both analytic test cases and cross-code validation is shown. Results show expected convergence across tested polynomial degree for analytic and cross-code test cases.
•A developed CNN model proposed to predict the ETC of gradient porous ceramics.•Integrating self-attention mechanism into our model leads to a higher accuracy.•Grad-CAM applied to visually explain ...the optimization mechanism of our model.•Gradient QSGS developed to generate porous structure with gradient porosity.
Accurate and stable prediction of the effective thermal conductivity (ETC) of porous ceramic materials is of great significance for their application in areas such as optimizing the design of thermal barrier coatings and improving energy conversion efficiency. Porous ceramic materials exhibit complex porous structures with gradient porosity distributions that pose a great challenge for effective medium theory (EMT) and conventional convolutional neural networks (CNN) in attempting to accurately and stably predict the ETC of porous media. In this study, a CNN model that integrates self-attention and a multiscale feature-fusion mechanism is proposed to predict the ETC of porous media with greater accuracy and stability. The integration of the self-attention and multiscale feature-fusion mechanisms enhances the CNN's ability to learn long-range dependencies and preserve detailed information. The optimization of the CNN's accuracy and stability is visually illustrated using gradient-weighted class activation mapping (Grad-CAM) for ETC. Additionally, by employing the proposed gradient quartet structure generation set (QSGS), a gradient porous ceramic media dataset comprising 10 000 images was built to train the CNN model. Finally, the prediction results and relative error distribution of the ETC were compared across different models. Our model demonstrated improvements in statistical metrics, including a 33.7 % decrease in mean error, 25.2 % decrease in median error, and 59.6 % decrease in maximum error. The decreases in these metrics and Grad-CAM for the ETC strongly demonstrates that the model proposed in this work greatly improved the accuracy and stability of predicting the ETC of ceramic materials with gradient porosity distributions.
Display omitted
Myocardial infarction (MI) accounts for a high number of deaths globally. In acute MI, accurate electrocardiography (ECG) is important for timely diagnosis and intervention in the emergency setting. ...Machine learning is increasingly being explored for automated computer-aided ECG diagnosis of cardiovascular diseases. In this study, we have developed DenseNet and CNN models for the classification of healthy subjects and patients with ten classes of MI based on the location of myocardial involvement. ECG signals from the Physikalisch-Technische Bundesanstalt database were pre-processed, and the ECG beats were extracted using an R peak detection algorithm. The beats were then fed to the two models separately. While both models attained high classification accuracies (more than 95%), DenseNet is the preferred model for the classification task due to its low computational complexity and higher classification accuracy than the CNN model due to feature reusability. An enhanced class activation mapping (CAM) technique called Grad-CAM was subsequently applied to the outputs of both models to enable visualization of the specific ECG leads and portions of ECG waves that were most influential for the predictive decisions made by the models for the 11 classes. It was observed that Lead V4 was the most activated lead in both the DenseNet and CNN models. Furthermore, this study has also established the different leads and parts of the signal that get activated for each class. This is the first study to report features that influenced the classification decisions of deep models for multiclass classification of MI and healthy ECGs. Hence this study is crucial and contributes significantly to the medical field as with some level of visible explainability of the inner workings of the models, the developed DenseNet and CNN models may garner needed clinical acceptance and have the potential to be implemented for ECG triage of MI diagnosis in hospitals and remote out-of-hospital settings.
•This is the first study to explain the inner workings of the DenseNet and CNN models developed for MI detection.•DenseNet is a better model than CNN, for rapid classification of MI.•Model is developed with ten-fold cross-validation. Hence, it is robust and accurate.•Obtained high accuracy of 98.9% for the classification of ten MI classes with DenseNet model.
In this paper, in order to penalize for lack of divergence-free solution, we propose a sparse grad-div stabilized algorithm for the incompressible magnetohydrodynamics equations, which just adds a ...minimally intrusive module that implements grad-div stabilization with a sparse block structure matrix. Unconditional stability and error estimates of the proposed algorithm are provided and numerical tests are carried out. Compared to other grad-div stabilizations, the sparse grad-div stabilized algorithm is more efficient with some large values of grad-div parameters.
•A Fine-tuned light weight EfficientNet V2S model having state-of-the-art performance.•Exhaustive performance comparison on three different datasets with large variant of disease classes for ...cancerous and healthy brain cell classification.•Multigrade classification of tumor classes for the three datasets have 44 classes, 12 classes and 4 classes respectively.•Illustration of the results by explainable model through GradCam Visualisation.
Medical imaging plays a vital role in detecting and treating brain tumors. Malignant or non-malignant brain tissue’s abnormal growth causes long-term brain damage. It is crucial to detect and properly categorize the kind of brain tumor. Specialists normally use MRI to create high-contrast grayscale brain images to segment them. Convolutional neural networks (CNN) driven by deep learning (DL) have transformed computer-assisted testing systems by producing good results in a wide range of medical imaging analytics applications, including tumor diagnosis in the brain. The paper introduces a lightweight fine-tuned Convolutional Neural Network EfficientNet ’ECNN’ to detect brain tumors. In this study, we provide a transfer learning-based measurement strategy for grouping cerebrum growths in three distinct datasets with different classifications, such as meningioma, glioma, and pituitary growth, using fine-tuned EfficientNets. The findings of this research rely on Efficient Nets to classify brain tumors in three different types of datasets utilizing a fine-tuned transfer learning mechanism. With EfficientNetV2S as the system’s foundation, our proposed way of fine-tunned pre-trained EfficientNetV2S model outperformed for all datasets over state of the art methods. The effectiveness of the suggested model has been assessed using performance metrics, and outcomes were compared to those produced using state-of-the-art approaches. The average test accuracy, recall, precision, and sensitivity score are 98.48%, 98%, 98.5%, and 98.71%, respectively.
•Multimodal imaging was used to simultaneously extract morphological, compositional and structural information of tissues.•Rapid and accurate diagnosis of breast cancer was achieved by multimodal ...micro-imaging with deep learning.•Gradient-weighted Class Activation Mapping (Grad-CAM) was used to reveal the reliability of model performance.
Accurate and rapid diagnosis of breast cancer is particularly important since it becomes the primary malignant tumor threatening women's health. Although pathological diagnosis with H&E staining section is the gold standard in tumor diagnosis, it is hard to meet quick intraoperative inspection because of its complex procedures and hysteresis. This study adopts multimodal microscopic imaging technology (bright-field imaging, auto-fluorescence imaging and orthogonal polarization imaging) combined with deep learning to achieve rapid intelligent diagnosis of breast cancer by getting the rich information of tissue morphology, content and structure of collagen in tissue slices. By using both fusion classification models of multimodal images at pixel level and decision level, the AUC score and accuracy is 0.9366 and 89.01% for the pixel fusion classification, as well as 0.9421 and 87.53% for the decision fusion classification, respectively. The results suggest that the multimodal microscopic imaging technique proposed in this study has unique advantages in accuracy, speed and feasibility in clinic for breast cancer diagnosis, and has strong clinical potential and application prospects when combined with deep learning.
Display omitted
•Defect types of pine nut was identified using hyperspectral imaging at two spectral ranges.•1D CNN models using spectra as inputs obtained promising performances.•3D CNN models using ...hyperspectral images as input obtained equivalent performances.•1D CNN and 3D CNN models were visualized and interpreted by Grad-CAM++.
Pine nuts, as a highly nutritious and medicinally valuable food, are susceptible to various defects during their cultivation, harvesting, and transportation, which can reduce their quality. Therefore, rapid and accurate identification of pine nut defect types is of utmost importance to ensure the overall quality of the pine nuts. In this study, hyperspectral imaging (HSI) systems covering two spectral ranges (400–1000 nm and 900–1700 nm) were employed to capture hyperspectral images of healthy pine nuts and pine nuts with six types of defects. One-dimensional (1D) and three-dimensional (3D) Convolutional Neural Network (CNN) models with multi-head attention mechanisms were constructed using 1D spectra and 3D hyperspectral images, respectively. To validate the effectiveness of the proposed models, Support Vector Classifier (SVC) models were built using 1D spectra and used as a comparison. Overall, the proposed CNN models outperform traditional machine learning methods in two spectral ranges (400–1000 nm and 900–1700 nm). 1D CNN model in the near-infrared spectral range (900–1700 nm) achieved an accuracy of 90.23 % on the training set and 81.32 % on the validation set. Additionally, the Generalized Gradient-Weighted Class Activation Mapping (Grad-CAM++) visualization method was applied to conduct visual analysis on the 1D CNN and 3D CNN models, enabling the identification of important wavelength ranges and pixel regions in the models, thereby enhancing the interpretability of the decision-making process of the models. Overall, the results of this study demonstrated the feasibility of using a combination of hyperspectral imaging and convolutional neural networks for pine nut defects classification, and the visual analysis of the models provided new insights and understanding for pine nut defects identification.
PDF
