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
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
针对实际应用中基于动态工况下电池状态参数的片段数据进行电池健康状态(state of health,SOH)实时估计的问题,提出基于动态工况下锂离子电池状态参数(电压、电流、温度)实测数据二维特征图像和深度学习的锂离子电池容量估计算法。首先...针对实际应用中基于动态工况下电池状态参数的片段数据进行电池健康状态(state of health,SOH)实时估计的问题,提出基于动态工况下锂离子电池状态参数(电压、电流、温度)实测数据二维特征图像和深度学习的锂离子电池容量估计算法。首先,将动态工况下电池状态参数监测量(电压、电流和温度)的片段数据转化为二维特征图像。其次,提出基于残差卷积神经网络(residual convolutional neural network,Res-CNN)和门控循环单元(gate recurrent unit,GRU)网络结合的多通道深度学习模型Res-CNN-GRU,以构建动态工况下电池状态参数特征图像和SOH之间的复杂非线性关系,其中电压、电流和温度的二维特征图像以三通道的方式输入到Res-CNN-GRU模型中,模型输出为对应电池的相邻参考充放电循环实验所获得容量的差值。研究结果表明:此方法在锂电池随机充放电工况下对电池健康状态估计效果更佳,且Res-CNN-GRU模型的泛化性和全局特征提取能力较强。论文研究为现实工况下电池健康状态估计的进一步深入研究提供了参考。展开更多
The health monitoring and fault diagnosis of heavy-duty engines are increasingly important for energy storage ecosystem. During operation, vibration characters corresponding to the specific fault need to be extracted ...The health monitoring and fault diagnosis of heavy-duty engines are increasingly important for energy storage ecosystem. During operation, vibration characters corresponding to the specific fault need to be extracted from the overall system vibration. Faulty characteristics emanating from one single cylinder are also mixed with those from other cylinders. Besides, the change of working condition brings strong nonlinearities in surface vibration. To solve these problems, an improved deep residual shrinkage network (IDRSN) is developed for detecting diverse engine faults at various degrees using single channel surface vibration signal. Within IDRSN, a wide convolution kernel is utilized in first convolution layer to capture the long-term fault-related impacts and eliminate the short-time random impact. The residual network module is adopted to enhance the focus the relevant components of vibration signals. Mini-batch training strategy is used to improve the model stability. Meanwhile, Gradient-weighted class activation map is adopted to assess the consistency between the learned knowledge and the fault-related information. The IDRSN is implemented to diagnosing a diesel engine under various faults, faulty degrees and operating speeds. Comparisons with existing models are analyzed in terms of hyper-parameters, training samples, noise resistance, and visualization. Results demonstrate the proposed IDRSN's superior performance on fault diagnosis accuracy, stability, anti-noise performance, and anti-interference performance. An average accuracy rate of 98.38 % was achieved by the proposed IDRSN, in comparison to 96.64 % and 93.56 % achieved by the DRSN and the wide-kernel deep convolutional neural network respectively. These results highlight the proposed IDRSN's superiority in diagnosing multiple faults under various working conditions, offering a low-cost, highly effective, and applicable approach for complex fault diagnosis tasks.展开更多
Slippery road conditions,such as snowy,icy or slushy pavements,are one of the major threats to road safety in winter.The U.S.Department of Transportation(USDOT)spends over 20%of its maintenance budget on pavement main...Slippery road conditions,such as snowy,icy or slushy pavements,are one of the major threats to road safety in winter.The U.S.Department of Transportation(USDOT)spends over 20%of its maintenance budget on pavement maintenance in winter.However,despite extensive research,it remains a challenging task to monitor pavement conditions and detect slippery roadways in real time.Most existing studies have mainly explored indirect estimates based on pavement images and weather forecasts.The emerging connected vehicle(CV)technology offers the opportunity to map slippery road conditions in real time.This study proposes a CV-based slippery detection system that uses vehicles to acquire data and implements deep learning algorithms to predict pavements’slippery conditions.The system classifies pavement conditions into three major categories:dry,snowy and icy.Different pavement conditions reflect different levels of slipperiness:dry surface corresponds to the least slippery condition,and icy surface to the most slippery condition.In practice,more attention should be paid to the detected icy and snowy pavements when driving or implementing pavement maintenance and road operation in winter.The classification algorithm adopted in this study is Long Short-Term Memory(LSTM),which is an artificial Recurrent Neural Network(RNN).The LSTM model is trained with simulated CV data in VISSIM and optimized with a Bayesian algorithm.The system can achieve 100%,99.06%and 98.02%prediction accuracy for dry pavement,snowy pavement and icy pavement,respectively.In addition,it is observed that potential accidents can be reduced by more than 90%if CVs can adjust their driving speed and maintain a greater distance from the leading vehicle after receiving a warning signal.Simulation results indicate that the proposed slippery detection system and the information sharing function based on the CV technology and deep learning algorithm(i.e.,the LSTM network implemented in this study)are expected to deliver real-time detec-tion of slippery pavement conditions,thus significantly eliminating the potential risk of accidents.展开更多
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.
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funded by the National Key R&D Program of China(Grant No.2021YFD2000303)Tianjin Research Innovation Project for Postgraduate Students in China(Grant No.2021YJSB182)Weichai Power Co.,Ltd.in China(Grant No.WCDL-GH-2023-0147).
文摘The health monitoring and fault diagnosis of heavy-duty engines are increasingly important for energy storage ecosystem. During operation, vibration characters corresponding to the specific fault need to be extracted from the overall system vibration. Faulty characteristics emanating from one single cylinder are also mixed with those from other cylinders. Besides, the change of working condition brings strong nonlinearities in surface vibration. To solve these problems, an improved deep residual shrinkage network (IDRSN) is developed for detecting diverse engine faults at various degrees using single channel surface vibration signal. Within IDRSN, a wide convolution kernel is utilized in first convolution layer to capture the long-term fault-related impacts and eliminate the short-time random impact. The residual network module is adopted to enhance the focus the relevant components of vibration signals. Mini-batch training strategy is used to improve the model stability. Meanwhile, Gradient-weighted class activation map is adopted to assess the consistency between the learned knowledge and the fault-related information. The IDRSN is implemented to diagnosing a diesel engine under various faults, faulty degrees and operating speeds. Comparisons with existing models are analyzed in terms of hyper-parameters, training samples, noise resistance, and visualization. Results demonstrate the proposed IDRSN's superior performance on fault diagnosis accuracy, stability, anti-noise performance, and anti-interference performance. An average accuracy rate of 98.38 % was achieved by the proposed IDRSN, in comparison to 96.64 % and 93.56 % achieved by the DRSN and the wide-kernel deep convolutional neural network respectively. These results highlight the proposed IDRSN's superiority in diagnosing multiple faults under various working conditions, offering a low-cost, highly effective, and applicable approach for complex fault diagnosis tasks.
文摘Slippery road conditions,such as snowy,icy or slushy pavements,are one of the major threats to road safety in winter.The U.S.Department of Transportation(USDOT)spends over 20%of its maintenance budget on pavement maintenance in winter.However,despite extensive research,it remains a challenging task to monitor pavement conditions and detect slippery roadways in real time.Most existing studies have mainly explored indirect estimates based on pavement images and weather forecasts.The emerging connected vehicle(CV)technology offers the opportunity to map slippery road conditions in real time.This study proposes a CV-based slippery detection system that uses vehicles to acquire data and implements deep learning algorithms to predict pavements’slippery conditions.The system classifies pavement conditions into three major categories:dry,snowy and icy.Different pavement conditions reflect different levels of slipperiness:dry surface corresponds to the least slippery condition,and icy surface to the most slippery condition.In practice,more attention should be paid to the detected icy and snowy pavements when driving or implementing pavement maintenance and road operation in winter.The classification algorithm adopted in this study is Long Short-Term Memory(LSTM),which is an artificial Recurrent Neural Network(RNN).The LSTM model is trained with simulated CV data in VISSIM and optimized with a Bayesian algorithm.The system can achieve 100%,99.06%and 98.02%prediction accuracy for dry pavement,snowy pavement and icy pavement,respectively.In addition,it is observed that potential accidents can be reduced by more than 90%if CVs can adjust their driving speed and maintain a greater distance from the leading vehicle after receiving a warning signal.Simulation results indicate that the proposed slippery detection system and the information sharing function based on the CV technology and deep learning algorithm(i.e.,the LSTM network implemented in this study)are expected to deliver real-time detec-tion of slippery pavement conditions,thus significantly eliminating the potential risk of accidents.
