An automatic iterative optimization and inverse design method for photonic crystal fiber (PCF) is proposed based on convolutional adversarial autoencoder (CAAE) and forward prediction convolutional neural network (PCN...
详细信息
An automatic iterative optimization and inverse design method for photonic crystal fiber (PCF) is proposed based on convolutional adversarial autoencoder (CAAE) and forward prediction convolutional neural network (PCNN). This method takes the two-dimensional (2D) material refractive index distribution of the fiber cross-section as the structural parameter space and can achieve automatic generation and optimization of PCFs in the 2D parameter space. The automatic generation is based on CAAE, which can compress the 2D fiber structural parameter matrix into a 36-dimensional hyperparameter space with Gaussian distribution, and the Gaussian hyperparameters can be restored to the original 2D structural matrix through the decoder. The decoder can work independently and generate random PCFs after inputting Gaussian hyperparameters. Then, the forward PCNN is constructed to evaluate the optical property of the PCFs generated from the decoder. By combining the PCNN and CAAE networks, automatic generation and optimization of 2D PCF structures can be achieved. The structural variables generated and optimized are the refractive index distribution of the fiber cross-section, which is more flexible and can be applied to different types of PCFs. We also propose a transfer learning method for the random generation of different PCFs, which only needs a small amount of data to train the autoencoder, and efficient and accurate random generation of other PCFs with different lattice arrangements can be achieved. The proposed automatic generation and optimization method is flexible and efficient, which provide a new approach for the optimization and reverse design of PCF structures in 2D parameter space.
Based on brain magnetic resonance imaging (MRI), multiple variations ranging from MRI scanners to center-specific parameter settings, imaging protocols, and brain region-of-interest (ROI) definitions pose a big challe...
详细信息
Based on brain magnetic resonance imaging (MRI), multiple variations ranging from MRI scanners to center-specific parameter settings, imaging protocols, and brain region-of-interest (ROI) definitions pose a big challenge for multi-center Alzheimer's disease characterization and classification. Existing approaches to reduce such variations require intricate multi-step, often manual preprocessing pipelines, including skull stripping, segmentation, registration, cortical reconstruction, and ROI outlining. Such procedures are time-consuming, and more importantly, tend to be user biased. Contrasting costly and biased preprocessing pipelines, the question arises whether we can design a deep learning model to automatically reduce these variations from multiple centers for Alzheimer's disease classification? In this study, we used T1 and T2-weighted structural MRI from Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset based on three groups with 375 subjects, respectively: patients with Alzheimer's disease (AD) dementia, with mild cognitive impairment (MCI), and healthy controls (HC);to test our approach, we defined AD classification as classifying an individual's structural image to one of the three group labels. We first introduced a convolutional adversarial autoencoder (CAAE) to reduce the variations existing in multi-center raw MRI scans by automatically registering them into a common aligned space. Afterward, a convolutional residual soft attention network (CRAT) was further proposed for AD classification. Canonical classification procedures demonstrated that our model achieved classification accuracies of 91.8%, 90.05%, and 88.10% for the 2-way classification tasks using the RAW aligned MRI scans, including AD vs. HC, AD vs. MCI, and MCI vs. HC, respectively. Thus, our automated approach achieves comparable or even better classification performance by comparing it with many baselines with dedicated conventional preprocessing pipelines. Furthermore, the uncove
In recent years, researchers have extensively explored the application of drive -by inspection technology for bridge damage assessment. This approach involves using the response of a sensing vehicle to identify damage...
详细信息
In recent years, researchers have extensively explored the application of drive -by inspection technology for bridge damage assessment. This approach involves using the response of a sensing vehicle to identify damage. However, many existing methods rely on data collected from both healthy and damaged bridge conditions, which may not always be available. Therefore, this study introduces a fully unsupervised computer vision -based methodology for bridge structural health monitoring (BSHM) using drive -by inspection. It analyzes the time-frequency domain of a two -axle vehicle's response by deriving a novel formulation for the contact point response from vehicle axles. The axles signals are then processed through subtraction, filtering, and decomposition using empirical Fourier decomposition with an improved segmentation approach based on the Savitzky-Golay filter (SGEFD). Relevant Intrinsic Mode Functions (IMF) are extracted as features representing damage, and the Wavelet Synchro-squeezed transform (WSST) is obtained from these features and used as input for the damage assessment algorithm. The performance of two state-of-the-art unsupervised generative machine learning methods, namely convolutional variational autoencoders (CVAE) and convolutional adversarial autoencoders (CAAE), is compared for the damage assessment task. These methods are trained solely with the residual WSST obtained from the vehicle responses when traversing a bridge in its reference state. A damage index (DI) is defined based on the measured error between the original and reconstructed images, and a damage threshold is calculated from the DI distribution of samples from the benchmark bridge state. During testing, the error between the original and reconstructed WSST is compared to the damage threshold, enabling the classification of new samples as healthy or damaged. The methodology is evaluated using both numerical and experimental vehicle-bridge interaction (VBI) models, considering various
Network traffic classification (NTC) has attracted great attention in many applications such as secure communications, intrusion detection systems. The existing NTC methods based on supervised learning rely on suffici...
详细信息
Network traffic classification (NTC) has attracted great attention in many applications such as secure communications, intrusion detection systems. The existing NTC methods based on supervised learning rely on sufficient labeled datasets in the training phase, but for most traffic datasets, it is difficult to obtain label information in practical applications. Although unsupervised learning does not rely on labels, its classification accuracy is not high, and the number of data classes is difficult to determine. This paper proposes an unsupervised NTC method based on adversarial training and deep clustering with improved network traffic classification (NTC) and lower computational complexity in comparison with the traditional clustering algorithms. Here, the training process does not require data labels, which greatly reduce the computational complexity of the network traffic classification through pretraining. In the pretraining stage, an autoencoder (AE) is used to reduce the dimension of features and reduce the complexity of the initial high-dimensional network traffic data features. Moreover, we employ the adversarial training model and a deep clustering structure to further optimize the extracted features. The experimental results show that our proposed method has robust performance, with a multiclassification accuracy of 92.2%, which is suitable for classification with a large number of unlabeled data in actual application scenarios. This paper only focuses on breakthroughs in the algorithm stage, and future work can be focused on the deployment and adaptation in practical environments.
暂无评论