Traditional topology optimization methods often suffer from the“dimension curse”problem,wherein the com-putation time increases exponentially with the degrees of freedom in the background grid.Overcoming this challe...Traditional topology optimization methods often suffer from the“dimension curse”problem,wherein the com-putation time increases exponentially with the degrees of freedom in the background grid.Overcoming this challenge,we introduce a real-time topology optimization approach leveraging Conditional Generative Adversarial Networks with Gradient Penalty(CGAN-GP).This innovative method allows for nearly instantaneous prediction of optimized structures.Given a specific boundary condition,the network can produce a unique optimized structure in a one-to-one manner.The process begins by establishing a dataset using simulation data generated through the Solid Isotropic Material with Penalization(SIMP)method.Subsequently,we design a conditional generative adversarial network and train it to generate optimized structures.To further enhance the quality of the optimized structures produced by CGAN-GP,we incorporate Pix2pixGAN.This augmentation results in sharper topologies,yielding structures with enhanced clarity,de-blurring,and edge smoothing.Our proposed method yields a significant reduction in computational time when compared to traditional topology optimization algorithms,all while maintaining an impressive accuracy rate of up to 85%,as demonstrated through numerical examples.展开更多
Structural damage in heterogeneousmaterials typically originates frommicrostructures where stress concentration occurs.Therefore,evaluating the magnitude and location of localized stress distributions within microstru...Structural damage in heterogeneousmaterials typically originates frommicrostructures where stress concentration occurs.Therefore,evaluating the magnitude and location of localized stress distributions within microstructures under external loading is crucial.Repeating unit cells(RUCs)are commonly used to represent microstructural details and homogenize the effective response of composites.This work develops a machine learning-based micromechanics tool to accurately predict the stress distributions of extracted RUCs.The locally exact homogenization theory efficiently generates the microstructural stresses of RUCs with a wide range of parameters,including volume fraction,fiber/matrix property ratio,fiber shapes,and loading direction.Subsequently,the conditional generative adversarial network(cGAN)is employed and constructed as a surrogate model to establish the statistical correlation between these parameters and the corresponding localized stresses.The stresses predicted by cGAN are validated against the remaining true data not used for training,showing good agreement.This work demonstrates that the cGAN-based micromechanics tool effectively captures the local responses of composite RUCs.It can be used for predicting potential crack initiations starting from microstructures and evaluating the effective behavior of periodic composites.展开更多
In underground mining,the belt is a critical component,as its state directly affects the safe and stable operation of the conveyor.Most of the existing non-contact detection methods based on machine vision can only de...In underground mining,the belt is a critical component,as its state directly affects the safe and stable operation of the conveyor.Most of the existing non-contact detection methods based on machine vision can only detect a single type of damage and they require pre-processing operations.This tends to cause a large amount of calculation and low detection precision.To solve these problems,in the work described in this paper a belt tear detection method based on a multi-class conditional deep convolutional generative adversarial network(CDCGAN)was designed.In the traditional DCGAN,the image generated by the generator has a certain degree of randomness.Here,a small number of labeled belt images are taken as conditions and added them to the generator and discriminator,so the generator can generate images with the characteristics of belt damage under the aforementioned conditions.Moreover,because the discriminator cannot identify multiple types of damage,the multi-class softmax function is used as the output function of the discriminator to output a vector of class probabilities,and it can accurately classify cracks,scratches,and tears.To avoid the features learned incompletely,skiplayer connection is adopted in the generator and discriminator.This not only can minimize the loss of features,but also improves the convergence speed.Compared with other algorithms,experimental results show that the loss value of the generator and discriminator is the least.Moreover,its convergence speed is faster,and the mean average precision of the proposed algorithm is up to 96.2%,which is at least 6%higher than that of other algorithms.展开更多
In this paper, a time-varying channel prediction method based on conditional generative adversarial network(CPcGAN) is proposed for time division duplexing/frequency division duplexing(TDD/FDD) systems. CPc GAN utiliz...In this paper, a time-varying channel prediction method based on conditional generative adversarial network(CPcGAN) is proposed for time division duplexing/frequency division duplexing(TDD/FDD) systems. CPc GAN utilizes a discriminator to calculate the divergence between the predicted downlink channel state information(CSI) and the real sample distributions under a conditional constraint that is previous uplink CSI. The generator of CPcGAN learns the function relationship between the conditional constraint and the predicted downlink CSI and reduces the divergence between predicted CSI and real CSI.The capability of CPcGAN fitting data distribution can capture the time-varying and multipath characteristics of the channel well. Considering the propagation characteristics of real channel, we further develop a channel prediction error indicator to determine whether the generator reaches the best state. Simulations show that the CPcGAN can obtain higher prediction accuracy and lower system bit error rate than the existing methods under the same user speeds.展开更多
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
The multimode fiber(MMF)has great potential to transmit high-resolution images with less invasive methods in endoscopy due to its large number of spatial modes and small core diameter.However,spatial modes crosstalk w...The multimode fiber(MMF)has great potential to transmit high-resolution images with less invasive methods in endoscopy due to its large number of spatial modes and small core diameter.However,spatial modes crosstalk will inevitably occur in MMFs,which makes the received images become speckles.A conditional generative adversarial network(GAN)composed of a generator and a discriminator was utilized to reconstruct the received speckles.We conduct an MMF imaging experimental system of transmitting over 1 m MMF with a 50μm core.Compared with the conventional method of U-net,this conditional GAN could reconstruct images with fewer training datasets to achieve the same performance and shows higher feature extraction capability.展开更多
Elastography is a non-invasive medical imaging technique to map the spatial variation of elastic properties of soft tissues.The quality of reconstruction results in elastography is highly sensitive to the noise induce...Elastography is a non-invasive medical imaging technique to map the spatial variation of elastic properties of soft tissues.The quality of reconstruction results in elastography is highly sensitive to the noise induced by imaging measurements and processing.To address this issue,we propose a deep learning(DL)model based on conditional Generative Adversarial Networks(cGANs)to improve the quality of nonhomogeneous shear modulus reconstruction.To train this model,we generated a synthetic displacement field with finite element simulation under known nonhomogeneous shear modulus distribution.Both the simulated and experimental displacement fields are used to validate the proposed method.The reconstructed results demonstrate that the DL model with synthetic training data is able to improve the quality of the reconstruction compared with the well-established optimization method.Moreover,we emphasize that our DL model is only trained on synthetic data.This might provide a way to alleviate the challenge of obtaining clinical or experimental data in elastography.Overall,this work addresses several fatal issues in applying the DL technique into elastography,and the proposed method has shown great potential in improving the accuracy of the disease diagnosis in clinical medicine.展开更多
In this paper,a new machine learning(ML)model combining conditional generative adversarial networks(CGANs)and active learning(AL)is proposed to predict the body-centered cubic(BCC)phase,face-centered cubic(FCC)phase,a...In this paper,a new machine learning(ML)model combining conditional generative adversarial networks(CGANs)and active learning(AL)is proposed to predict the body-centered cubic(BCC)phase,face-centered cubic(FCC)phase,and BCC+FCC phase of high-entropy alloys(HEAs).Considering the lack of data,CGANs are introduced for data augmentation,and AL can achieve high prediction accuracy under a small sample size owing to its special sample selection strategy.Therefore,we propose an ML framework combining CGAN and AL to predict the phase of HEAs.The arithmetic optimization algorithm(AOA)is introduced to improve the artificial neural network(ANN).AOA can overcome the problem of falling into the locally optimal solution for the ANN and reduce the number of training iterations.The AOA-optimized ANN model trained by the AL sample selection strategy achieved high prediction accuracy on the test set.To improve the performance and interpretability of the model,domain knowledge is incorporated into the feature selection.Additionally,considering that the proposed method can alleviate the problem caused by the shortage of experimental data,it can be applied to predictions based on small datasets in other fields.展开更多
Online traffic simulation that feeds from online information to simulate vehicle movement in real-time has recently seen substantial advancement in the development of intelligent transportation systems and urban traff...Online traffic simulation that feeds from online information to simulate vehicle movement in real-time has recently seen substantial advancement in the development of intelligent transportation systems and urban traffic management.It has been a challenging problem due to three aspects:1)The diversity of traffic patterns due to heterogeneous layouts of urban intersections;2)The nature of complex spatiotemporal correlations;3)The requirement of dynamically adjusting the parameters of traffic models in a real-time system.To cater to these challenges,this paper proposes an online traffic simulation framework called automated urban traffic operation simulation via meta-learning(AUTOSIM).In particular,simulation models with various intersection layouts are automatically generated using an open-source simulation tool based on static traffic geometry attributes.Through a meta-learning technique,AUTOSIM enables an automated learning process for dynamic model settings of traffic scenarios featured with different spatiotemporal correlations.Besides,AUTOSIM is capable of adapting traffic model parameters according to dynamic traffic information in real-time by using a meta-learner.Through computational experiments,we demonstrate the effectiveness of the meta-learningbased framework that is capable of providing reliable supports to real-time traffic simulation and dynamic traffic operations.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
The stress-life curve(S–N)and low-cycle strain-life curve(E–N)are the two primary representations used to characterize the fatigue behavior of a material.These material fatigue curves are essential for structural fa...The stress-life curve(S–N)and low-cycle strain-life curve(E–N)are the two primary representations used to characterize the fatigue behavior of a material.These material fatigue curves are essential for structural fatigue analysis.However,conducting material fatigue tests is expensive and time-intensive.To address the challenge of data limitations on ferrous metal materials,we propose a novel method that utilizes the Random Forest Algorithm and transfer learning to predict the S–N and E–N curves of ferrous materials.In addition,a data-augmentation framework is introduced using a conditional generative adversarial network(cGAN)to overcome data deficiencies.By incorporating the cGAN-generated data,the accuracy(R2)of the Random Forest Algorithm-trained model is improved by 0.3–0.6.It is proven that the cGAN can significantly enhance the prediction accuracy of the machine-learning model and balance the cost of obtaining fatigue data from the experiment.展开更多
The production of true color images requires observational data in the red,green,and blue(RGB)bands.The Advanced Geostationary Radiation Imager(AGRI)onboard China’s Fengyun-4(FY-4)series of geostationary satellites o...The production of true color images requires observational data in the red,green,and blue(RGB)bands.The Advanced Geostationary Radiation Imager(AGRI)onboard China’s Fengyun-4(FY-4)series of geostationary satellites only has blue and red bands,and we therefore have to synthesize a green band to produce RGB true color images.We used random forest regression and conditional generative adversarial networks to train the green band model using Himawari-8 Advanced Himawari Imager data.The model was then used to simulate the green channel reflectance of the FY-4 AGRI.A single-scattering radiative transfer model was used to eliminate the contribution of Rayleigh scattering from the atmosphere and a logarithmic enhancement was applied to process the true color image.The conditional generative adversarial network model was better than random forest regression for the green band model in terms of statistical significance(e.g.,a higher determination coefficient,peak signal-to-noise ratio,and structural similarity index).The sharpness of the images was significantly improved after applying a correction for Rayleigh scattering,and the images were able to show natural phenomena more vividly.The AGRI true color images could be used to monitor dust storms,forest fires,typhoons,volcanic eruptions,and other natural events.展开更多
Prediction of indoor airflow distribution often relies on high-fidelity,computationally intensive computational fluid dynamics(CFD)simulations.Artificial intelligence(Al)models trained by CFD data can be used for fast...Prediction of indoor airflow distribution often relies on high-fidelity,computationally intensive computational fluid dynamics(CFD)simulations.Artificial intelligence(Al)models trained by CFD data can be used for fast and accurate prediction of indoor airflow,but current methods have limitations,such as only predicting limited outputs rather than the entire flow field.Furthermore,conventional Al models are not always designed to predict different outputs based on a continuous input range,and instead make predictions for one or a few discrete inputs.This work addresses these gaps using a conditional generative adversarial network(CGAN)model approach,which is inspired by current state-of-the-art Al for synthetic image generation.We create a new Boundary Condition CGAN(BC-CGAN)model by extending the original CGAN model to generate 2D airflow distribution images based on a continuous input parameter,such as a boundary condition.Additionally,we design a novel feature-driven algorithm to strategically generate training data,with the goal of minimizing the amount of computationally expensive data while ensuring training quality of the Al model.The BC-CGAN model is evaluated for two benchmark airflow cases:an isothermal lid-driven cavity flow and a non-isothermal mixed convection flow with a heated box.We also investigate the performance of the BC-CGAN models when training is stopped based on different levels of validation error criteria.The results show that the trained BC-CGAN model can predict the 2D distribution of velocity and temperature with less than 5%relative error and up to about 75,ooo times faster when compared to reference CFD simulations.The proposed feature-driven algorithm shows potential for reducing the amount of data and epochs required to train the Al models while maintaining prediction accuracy,particularly when the flow changes non-linearlywith respectto an input.展开更多
Fluorescence microscopy technology uses fluorescent dyes to provide highly specific visualization of cell components,which plays an important role in understanding the subcellular structure.However,fluorescence micros...Fluorescence microscopy technology uses fluorescent dyes to provide highly specific visualization of cell components,which plays an important role in understanding the subcellular structure.However,fluorescence microscopy has some limitations such as the risk of non-specific cross labeling in multi-labeled fluorescent staining and limited number of fluo-rescence labels due to spectral overlap.This paper proposes a deep learning-based fluorescence to fluorescence[Flu0-Fluo]translation method,which uses a conditional generative adversarial network to predict a fluorescence image from another fluorescence image and further realizes the multi-label fluorescent staining.The cell types used include human motor neurons,human breast cancer cells,rat cortical neurons,and rat cardiomyocytes.The effectiveness of the method is verified by successfully generating virtual fluorescence images highly similar to the true fluorescence images.This study shows that a deep neural network can implement Fluo-Fluo translation and describe the localization relationship between subcellular structures labeled with different fluorescent markers.The proposed Fluo-Fluo method can avoid non-specific cross labeling in multi-label fluorescence staining and is free from spectral overlaps.In theory,an unlimited number of fluorescence images can be predicted from a single fluorescence image to characterize cells.展开更多
基金supported by the National Key Research and Development Projects (Grant Nos.2021YFB3300601,2021YFB3300603,2021YFB3300604)Fundamental Research Funds for the Central Universities (No.DUT22QN241).
文摘Traditional topology optimization methods often suffer from the“dimension curse”problem,wherein the com-putation time increases exponentially with the degrees of freedom in the background grid.Overcoming this challenge,we introduce a real-time topology optimization approach leveraging Conditional Generative Adversarial Networks with Gradient Penalty(CGAN-GP).This innovative method allows for nearly instantaneous prediction of optimized structures.Given a specific boundary condition,the network can produce a unique optimized structure in a one-to-one manner.The process begins by establishing a dataset using simulation data generated through the Solid Isotropic Material with Penalization(SIMP)method.Subsequently,we design a conditional generative adversarial network and train it to generate optimized structures.To further enhance the quality of the optimized structures produced by CGAN-GP,we incorporate Pix2pixGAN.This augmentation results in sharper topologies,yielding structures with enhanced clarity,de-blurring,and edge smoothing.Our proposed method yields a significant reduction in computational time when compared to traditional topology optimization algorithms,all while maintaining an impressive accuracy rate of up to 85%,as demonstrated through numerical examples.
基金the support from the National Key R&D Program of China underGrant(Grant No.2020YFA0711700)the National Natural Science Foundation of China(Grant Nos.52122801,11925206,51978609,U22A20254,and U23A20659)G.W.is supported by the National Natural Science Foundation of China(Nos.12002303,12192210 and 12192214).
文摘Structural damage in heterogeneousmaterials typically originates frommicrostructures where stress concentration occurs.Therefore,evaluating the magnitude and location of localized stress distributions within microstructures under external loading is crucial.Repeating unit cells(RUCs)are commonly used to represent microstructural details and homogenize the effective response of composites.This work develops a machine learning-based micromechanics tool to accurately predict the stress distributions of extracted RUCs.The locally exact homogenization theory efficiently generates the microstructural stresses of RUCs with a wide range of parameters,including volume fraction,fiber/matrix property ratio,fiber shapes,and loading direction.Subsequently,the conditional generative adversarial network(cGAN)is employed and constructed as a surrogate model to establish the statistical correlation between these parameters and the corresponding localized stresses.The stresses predicted by cGAN are validated against the remaining true data not used for training,showing good agreement.This work demonstrates that the cGAN-based micromechanics tool effectively captures the local responses of composite RUCs.It can be used for predicting potential crack initiations starting from microstructures and evaluating the effective behavior of periodic composites.
基金This work was supported by the Shanxi Province Applied Basic Research Project,China(Grant No.201901D111100).Xiaoli Hao received the grant,and the URL of the sponsors’website is http://kjt.shanxi.gov.cn/.
文摘In underground mining,the belt is a critical component,as its state directly affects the safe and stable operation of the conveyor.Most of the existing non-contact detection methods based on machine vision can only detect a single type of damage and they require pre-processing operations.This tends to cause a large amount of calculation and low detection precision.To solve these problems,in the work described in this paper a belt tear detection method based on a multi-class conditional deep convolutional generative adversarial network(CDCGAN)was designed.In the traditional DCGAN,the image generated by the generator has a certain degree of randomness.Here,a small number of labeled belt images are taken as conditions and added them to the generator and discriminator,so the generator can generate images with the characteristics of belt damage under the aforementioned conditions.Moreover,because the discriminator cannot identify multiple types of damage,the multi-class softmax function is used as the output function of the discriminator to output a vector of class probabilities,and it can accurately classify cracks,scratches,and tears.To avoid the features learned incompletely,skiplayer connection is adopted in the generator and discriminator.This not only can minimize the loss of features,but also improves the convergence speed.Compared with other algorithms,experimental results show that the loss value of the generator and discriminator is the least.Moreover,its convergence speed is faster,and the mean average precision of the proposed algorithm is up to 96.2%,which is at least 6%higher than that of other algorithms.
基金supported in part by the National Science Fund for Distinguished Young Scholars under Grant 61925102in part by the National Natural Science Foundation of China(62201087&92167202&62101069&62201086)in part by the Beijing University of Posts and Telecommunications-China Mobile Research Institute Joint Innovation Center。
文摘In this paper, a time-varying channel prediction method based on conditional generative adversarial network(CPcGAN) is proposed for time division duplexing/frequency division duplexing(TDD/FDD) systems. CPc GAN utilizes a discriminator to calculate the divergence between the predicted downlink channel state information(CSI) and the real sample distributions under a conditional constraint that is previous uplink CSI. The generator of CPcGAN learns the function relationship between the conditional constraint and the predicted downlink CSI and reduces the divergence between predicted CSI and real CSI.The capability of CPcGAN fitting data distribution can capture the time-varying and multipath characteristics of the channel well. Considering the propagation characteristics of real channel, we further develop a channel prediction error indicator to determine whether the generator reaches the best state. Simulations show that the CPcGAN can obtain higher prediction accuracy and lower system bit error rate than the existing methods under the same user speeds.
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 National Key R&D Program of China(No.2018YFB2201803)the National Natural Science Foundation of China(Nos.61821001,61901045,and 61625104)。
文摘The multimode fiber(MMF)has great potential to transmit high-resolution images with less invasive methods in endoscopy due to its large number of spatial modes and small core diameter.However,spatial modes crosstalk will inevitably occur in MMFs,which makes the received images become speckles.A conditional generative adversarial network(GAN)composed of a generator and a discriminator was utilized to reconstruct the received speckles.We conduct an MMF imaging experimental system of transmitting over 1 m MMF with a 50μm core.Compared with the conventional method of U-net,this conditional GAN could reconstruct images with fewer training datasets to achieve the same performance and shows higher feature extraction capability.
基金National Natural Science Foundation of China (12002075)National Key Research and Development Project (2021YFB3300601)Natural Science Foundation of Liaoning Province in China (2021-MS-128).
文摘Elastography is a non-invasive medical imaging technique to map the spatial variation of elastic properties of soft tissues.The quality of reconstruction results in elastography is highly sensitive to the noise induced by imaging measurements and processing.To address this issue,we propose a deep learning(DL)model based on conditional Generative Adversarial Networks(cGANs)to improve the quality of nonhomogeneous shear modulus reconstruction.To train this model,we generated a synthetic displacement field with finite element simulation under known nonhomogeneous shear modulus distribution.Both the simulated and experimental displacement fields are used to validate the proposed method.The reconstructed results demonstrate that the DL model with synthetic training data is able to improve the quality of the reconstruction compared with the well-established optimization method.Moreover,we emphasize that our DL model is only trained on synthetic data.This might provide a way to alleviate the challenge of obtaining clinical or experimental data in elastography.Overall,this work addresses several fatal issues in applying the DL technique into elastography,and the proposed method has shown great potential in improving the accuracy of the disease diagnosis in clinical medicine.
基金supported by the Key Scientific and Technological Project of Henan Province (Grant No.212102210112)the National Natural Science Foundation of China (Grant No.52071298)the Strategic Research and Consulting Project of Chinese Academy of Engineering (Grant No.2022HENYB05)。
文摘In this paper,a new machine learning(ML)model combining conditional generative adversarial networks(CGANs)and active learning(AL)is proposed to predict the body-centered cubic(BCC)phase,face-centered cubic(FCC)phase,and BCC+FCC phase of high-entropy alloys(HEAs).Considering the lack of data,CGANs are introduced for data augmentation,and AL can achieve high prediction accuracy under a small sample size owing to its special sample selection strategy.Therefore,we propose an ML framework combining CGAN and AL to predict the phase of HEAs.The arithmetic optimization algorithm(AOA)is introduced to improve the artificial neural network(ANN).AOA can overcome the problem of falling into the locally optimal solution for the ANN and reduce the number of training iterations.The AOA-optimized ANN model trained by the AL sample selection strategy achieved high prediction accuracy on the test set.To improve the performance and interpretability of the model,domain knowledge is incorporated into the feature selection.Additionally,considering that the proposed method can alleviate the problem caused by the shortage of experimental data,it can be applied to predictions based on small datasets in other fields.
基金supported by the National Natural Science Foundation of China(62173329)。
文摘Online traffic simulation that feeds from online information to simulate vehicle movement in real-time has recently seen substantial advancement in the development of intelligent transportation systems and urban traffic management.It has been a challenging problem due to three aspects:1)The diversity of traffic patterns due to heterogeneous layouts of urban intersections;2)The nature of complex spatiotemporal correlations;3)The requirement of dynamically adjusting the parameters of traffic models in a real-time system.To cater to these challenges,this paper proposes an online traffic simulation framework called automated urban traffic operation simulation via meta-learning(AUTOSIM).In particular,simulation models with various intersection layouts are automatically generated using an open-source simulation tool based on static traffic geometry attributes.Through a meta-learning technique,AUTOSIM enables an automated learning process for dynamic model settings of traffic scenarios featured with different spatiotemporal correlations.Besides,AUTOSIM is capable of adapting traffic model parameters according to dynamic traffic information in real-time by using a meta-learner.Through computational experiments,we demonstrate the effectiveness of the meta-learningbased framework that is capable of providing reliable supports to real-time traffic simulation and dynamic traffic operations.
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]
基金support provided by the Jiangsu Industrial Technology Research Institute and the Yangtze Delta Region Institute of Advanced Materialssupported by the National Natural Science Foundation of China(Grant No.52205377)+1 种基金the National Key Research and Development Program(Grant No.2022YFB4601804)the Key Basic Research Project of Suzhou(Grant Nos.#SJC2022029,#SJC2022031).
文摘The stress-life curve(S–N)and low-cycle strain-life curve(E–N)are the two primary representations used to characterize the fatigue behavior of a material.These material fatigue curves are essential for structural fatigue analysis.However,conducting material fatigue tests is expensive and time-intensive.To address the challenge of data limitations on ferrous metal materials,we propose a novel method that utilizes the Random Forest Algorithm and transfer learning to predict the S–N and E–N curves of ferrous materials.In addition,a data-augmentation framework is introduced using a conditional generative adversarial network(cGAN)to overcome data deficiencies.By incorporating the cGAN-generated data,the accuracy(R2)of the Random Forest Algorithm-trained model is improved by 0.3–0.6.It is proven that the cGAN can significantly enhance the prediction accuracy of the machine-learning model and balance the cost of obtaining fatigue data from the experiment.
基金Supported by the National Key Research and Development Program of China(2018YFC150650)National Satellite Meteorological Center Mountain Flood Geological Disaster Prevention Meteorological Guarantee Project 2020 Construction Project(IN_JS_202004)。
文摘The production of true color images requires observational data in the red,green,and blue(RGB)bands.The Advanced Geostationary Radiation Imager(AGRI)onboard China’s Fengyun-4(FY-4)series of geostationary satellites only has blue and red bands,and we therefore have to synthesize a green band to produce RGB true color images.We used random forest regression and conditional generative adversarial networks to train the green band model using Himawari-8 Advanced Himawari Imager data.The model was then used to simulate the green channel reflectance of the FY-4 AGRI.A single-scattering radiative transfer model was used to eliminate the contribution of Rayleigh scattering from the atmosphere and a logarithmic enhancement was applied to process the true color image.The conditional generative adversarial network model was better than random forest regression for the green band model in terms of statistical significance(e.g.,a higher determination coefficient,peak signal-to-noise ratio,and structural similarity index).The sharpness of the images was significantly improved after applying a correction for Rayleigh scattering,and the images were able to show natural phenomena more vividly.The AGRI true color images could be used to monitor dust storms,forest fires,typhoons,volcanic eruptions,and other natural events.
基金supported in part by the U.S.Defense Threat Reduction Agency and performed under U.S.Department of Energy Contract No.DE-AC02-05CH11231supported by the National Science Foundation under Awards No.IIS-1802017,CBET-2217410,CNS-2025377,CNS-2241361.
文摘Prediction of indoor airflow distribution often relies on high-fidelity,computationally intensive computational fluid dynamics(CFD)simulations.Artificial intelligence(Al)models trained by CFD data can be used for fast and accurate prediction of indoor airflow,but current methods have limitations,such as only predicting limited outputs rather than the entire flow field.Furthermore,conventional Al models are not always designed to predict different outputs based on a continuous input range,and instead make predictions for one or a few discrete inputs.This work addresses these gaps using a conditional generative adversarial network(CGAN)model approach,which is inspired by current state-of-the-art Al for synthetic image generation.We create a new Boundary Condition CGAN(BC-CGAN)model by extending the original CGAN model to generate 2D airflow distribution images based on a continuous input parameter,such as a boundary condition.Additionally,we design a novel feature-driven algorithm to strategically generate training data,with the goal of minimizing the amount of computationally expensive data while ensuring training quality of the Al model.The BC-CGAN model is evaluated for two benchmark airflow cases:an isothermal lid-driven cavity flow and a non-isothermal mixed convection flow with a heated box.We also investigate the performance of the BC-CGAN models when training is stopped based on different levels of validation error criteria.The results show that the trained BC-CGAN model can predict the 2D distribution of velocity and temperature with less than 5%relative error and up to about 75,ooo times faster when compared to reference CFD simulations.The proposed feature-driven algorithm shows potential for reducing the amount of data and epochs required to train the Al models while maintaining prediction accuracy,particularly when the flow changes non-linearlywith respectto an input.
基金This work was supported in part by the National Natural Science Foundation of China(Nos.61871263,12034005,and 11827808)the Natural Science Foundation of Shanghai(Nos.21ZR1405200 and 20S31901300).
文摘Fluorescence microscopy technology uses fluorescent dyes to provide highly specific visualization of cell components,which plays an important role in understanding the subcellular structure.However,fluorescence microscopy has some limitations such as the risk of non-specific cross labeling in multi-labeled fluorescent staining and limited number of fluo-rescence labels due to spectral overlap.This paper proposes a deep learning-based fluorescence to fluorescence[Flu0-Fluo]translation method,which uses a conditional generative adversarial network to predict a fluorescence image from another fluorescence image and further realizes the multi-label fluorescent staining.The cell types used include human motor neurons,human breast cancer cells,rat cortical neurons,and rat cardiomyocytes.The effectiveness of the method is verified by successfully generating virtual fluorescence images highly similar to the true fluorescence images.This study shows that a deep neural network can implement Fluo-Fluo translation and describe the localization relationship between subcellular structures labeled with different fluorescent markers.The proposed Fluo-Fluo method can avoid non-specific cross labeling in multi-label fluorescence staining and is free from spectral overlaps.In theory,an unlimited number of fluorescence images can be predicted from a single fluorescence image to characterize cells.
