Pneumonia ranks as a leading cause of mortality, particularly in children aged five and under. Detecting this disease typically requires radiologists to examine chest X-rays and report their findings to physicians, a ...Pneumonia ranks as a leading cause of mortality, particularly in children aged five and under. Detecting this disease typically requires radiologists to examine chest X-rays and report their findings to physicians, a task susceptible to human error. The application of Deep Transfer Learning (DTL) for the identification of pneumonia through chest X-rays is hindered by a shortage of available images, which has led to less than optimal DTL performance and issues with overfitting. Overfitting is characterized by a model’s learning that is too closely fitted to the training data, reducing its effectiveness on unseen data. The problem of overfitting is especially prevalent in medical image processing due to the high costs and extensive time required for image annotation, as well as the challenge of collecting substantial datasets that also respect patient privacy concerning infectious diseases such as pneumonia. To mitigate these challenges, this paper introduces the use of conditional generative adversarial networks (CGAN) to enrich the pneumonia dataset with 2690 synthesized X-ray images of the minority class, aiming to even out the dataset distribution for improved diagnostic performance. Subsequently, we applied four modified lightweight deep transfer learning models such as Xception, MobileNetV2, MobileNet, and EfficientNetB0. These models have been fine-tuned and evaluated, demonstrating remarkable detection accuracies of 99.26%, 98.23%, 97.06%, and 94.55%, respectively, across fifty epochs. The experimental results validate that the models we have proposed achieve high detection accuracy rates, with the best model reaching up to 99.26% effectiveness, outperforming other models in the diagnosis of pneumonia from X-ray images.展开更多
Under complex flight conditions,such as obstacle avoidance and extreme sea state,wing-in-ground(WIG)effect aircraft need to ascend to higher altitudes,resulting in the disappearance of the ground effect.A design of hi...Under complex flight conditions,such as obstacle avoidance and extreme sea state,wing-in-ground(WIG)effect aircraft need to ascend to higher altitudes,resulting in the disappearance of the ground effect.A design of high-speed WIG airfoil considering non-ground effect is carried out by a novel two-step inverse airfoil design method that combines conditional generative adversarial network(CGAN)and artificial neural network(ANN).The CGAN model is employed to generate a variety of airfoil designs that satisfy the desired lift-drag ratios in both ground effect and non-ground effect conditions.Subsequently,the ANN model is utilized to forecast aerodynamic parameters of the generated airfoils.The results indicate that the CGAN model contributes to a high accuracy rate for airfoil design and enables the creation of novel airfoil designs.Furthermore,it demonstrates high accuracy in predicting aerodynamic parameters of these airfoils due to the ANN model.This method eliminates the necessity for numerical simulations and experimental testing through the design procedure,showcasing notable efficiency.The analysis of airfoils generated by the CGAN model shows that airfoils exhibiting high lift-drag ratios under both flight conditions typically have cambers of among[0.08c,0.105c],with the positions of maximum camber occurring among[0.35c,0.5c]of the chord length,and the leading-edge radiuses of these airfoils primarily cluster among[0.008c,0.025c]展开更多
目的遥感图像建筑物分割是图像处理中的一项重要应用,卷积神经网络在遥感图像建筑物分割中展现出优秀性能,但仍存在建筑物漏分、错分,尤其是小建筑物漏分以及建筑物边缘不平滑等问题。针对上述问题,本文提出一种含多级通道注意力机制的...目的遥感图像建筑物分割是图像处理中的一项重要应用,卷积神经网络在遥感图像建筑物分割中展现出优秀性能,但仍存在建筑物漏分、错分,尤其是小建筑物漏分以及建筑物边缘不平滑等问题。针对上述问题,本文提出一种含多级通道注意力机制的条件生成对抗网络(conditional generative adversarial network,CGAN)模型Ra-CGAN,用于分割遥感图像建筑物。方法首先构建一个具有多级通道注意力机制的生成模型G,通过融合包含注意力机制的深层语义与浅层细节信息,使网络提取丰富的上下文信息,更好地应对建筑物的尺度变化,改善小建筑物漏分问题。其次,构建一个判别网络D,通过矫正真实标签图与生成模型生成的分割图之间的差异来改善分割结果。最后,通过带有条件约束的G和D之间的对抗训练,学习高阶数据分布特征,使建筑物空间连续性更强,提升分割结果的边界准确性及平滑性。结果在WHU Building Dataset和Satellite Dataset II数据集上进行实验,并与优秀方法对比。在WHU数据集中,分割性能相对于未加入通道注意力机制和对抗训练的模型明显提高,且在复杂建筑物的空间连续性、小建筑物完整性以及建筑物边缘准确和平滑性上表现更好;相比性能第2的模型,交并比(intersection over union,IOU)值提高了1.1%,F1-score提高了1.1%。在Satellite数据集中,相比其他模型,准确率更高,尤其是在数据样本不充足的条件下,得益于生成对抗训练,分割效果得到了大幅提升;相比性能第2的模型,IOU值提高了1.7%,F1-score提高了1.6%。结论本文提出的含多级通道注意力机制的CGAN遥感图像建筑物分割模型,综合了多级通道注意力机制生成模型与条件生成对抗网络的优点,在不同数据集上均获得了更精确的遥感图像建筑物分割结果。展开更多
文摘Pneumonia ranks as a leading cause of mortality, particularly in children aged five and under. Detecting this disease typically requires radiologists to examine chest X-rays and report their findings to physicians, a task susceptible to human error. The application of Deep Transfer Learning (DTL) for the identification of pneumonia through chest X-rays is hindered by a shortage of available images, which has led to less than optimal DTL performance and issues with overfitting. Overfitting is characterized by a model’s learning that is too closely fitted to the training data, reducing its effectiveness on unseen data. The problem of overfitting is especially prevalent in medical image processing due to the high costs and extensive time required for image annotation, as well as the challenge of collecting substantial datasets that also respect patient privacy concerning infectious diseases such as pneumonia. To mitigate these challenges, this paper introduces the use of conditional generative adversarial networks (CGAN) to enrich the pneumonia dataset with 2690 synthesized X-ray images of the minority class, aiming to even out the dataset distribution for improved diagnostic performance. Subsequently, we applied four modified lightweight deep transfer learning models such as Xception, MobileNetV2, MobileNet, and EfficientNetB0. These models have been fine-tuned and evaluated, demonstrating remarkable detection accuracies of 99.26%, 98.23%, 97.06%, and 94.55%, respectively, across fifty epochs. The experimental results validate that the models we have proposed achieve high detection accuracy rates, with the best model reaching up to 99.26% effectiveness, outperforming other models in the diagnosis of pneumonia from X-ray images.
基金supported by the Priority Academic Program Development of Jiangsu Higher Education Institutions,the Fundamental Research Funds for the Central Universities(No.ILA220101A23)CARDC Fundamental and Frontier Technology Research Fund(No.PJD20200210)the Aeronautical Science Foundation of China(No.20200023052002).
文摘Under complex flight conditions,such as obstacle avoidance and extreme sea state,wing-in-ground(WIG)effect aircraft need to ascend to higher altitudes,resulting in the disappearance of the ground effect.A design of high-speed WIG airfoil considering non-ground effect is carried out by a novel two-step inverse airfoil design method that combines conditional generative adversarial network(CGAN)and artificial neural network(ANN).The CGAN model is employed to generate a variety of airfoil designs that satisfy the desired lift-drag ratios in both ground effect and non-ground effect conditions.Subsequently,the ANN model is utilized to forecast aerodynamic parameters of the generated airfoils.The results indicate that the CGAN model contributes to a high accuracy rate for airfoil design and enables the creation of novel airfoil designs.Furthermore,it demonstrates high accuracy in predicting aerodynamic parameters of these airfoils due to the ANN model.This method eliminates the necessity for numerical simulations and experimental testing through the design procedure,showcasing notable efficiency.The analysis of airfoils generated by the CGAN model shows that airfoils exhibiting high lift-drag ratios under both flight conditions typically have cambers of among[0.08c,0.105c],with the positions of maximum camber occurring among[0.35c,0.5c]of the chord length,and the leading-edge radiuses of these airfoils primarily cluster among[0.008c,0.025c]
文摘目的遥感图像建筑物分割是图像处理中的一项重要应用,卷积神经网络在遥感图像建筑物分割中展现出优秀性能,但仍存在建筑物漏分、错分,尤其是小建筑物漏分以及建筑物边缘不平滑等问题。针对上述问题,本文提出一种含多级通道注意力机制的条件生成对抗网络(conditional generative adversarial network,CGAN)模型Ra-CGAN,用于分割遥感图像建筑物。方法首先构建一个具有多级通道注意力机制的生成模型G,通过融合包含注意力机制的深层语义与浅层细节信息,使网络提取丰富的上下文信息,更好地应对建筑物的尺度变化,改善小建筑物漏分问题。其次,构建一个判别网络D,通过矫正真实标签图与生成模型生成的分割图之间的差异来改善分割结果。最后,通过带有条件约束的G和D之间的对抗训练,学习高阶数据分布特征,使建筑物空间连续性更强,提升分割结果的边界准确性及平滑性。结果在WHU Building Dataset和Satellite Dataset II数据集上进行实验,并与优秀方法对比。在WHU数据集中,分割性能相对于未加入通道注意力机制和对抗训练的模型明显提高,且在复杂建筑物的空间连续性、小建筑物完整性以及建筑物边缘准确和平滑性上表现更好;相比性能第2的模型,交并比(intersection over union,IOU)值提高了1.1%,F1-score提高了1.1%。在Satellite数据集中,相比其他模型,准确率更高,尤其是在数据样本不充足的条件下,得益于生成对抗训练,分割效果得到了大幅提升;相比性能第2的模型,IOU值提高了1.7%,F1-score提高了1.6%。结论本文提出的含多级通道注意力机制的CGAN遥感图像建筑物分割模型,综合了多级通道注意力机制生成模型与条件生成对抗网络的优点,在不同数据集上均获得了更精确的遥感图像建筑物分割结果。
