High-accuracy gas dispersion models are necessary for predicting toxic gas movement, and for reducing the damage caused by toxic gas release accidents in chemical processes. In urban areas, where obstacles are large a...
详细信息
High-accuracy gas dispersion models are necessary for predicting toxic gas movement, and for reducing the damage caused by toxic gas release accidents in chemical processes. In urban areas, where obstacles are large and abundant, computational fluid dynamics (CFD) would be the best choice for simulating and analyzing scenarios of accidental release of toxic chemicals. However, owing to the large computation time required for CFD simulation, it is inappropriate in emergency situations and in real-time alarm systems. In this study, a non-linear surrogate model based on deep learning is proposed using a variational autoencoder with deep convolutional layers and a deep neural network with batch normalization (VAEDC-DNN) for real-time analysis of the probability of death (P-death). VAEDC can extract representation features of the Pdeath contour with complicated urban geometry in the latent space, and DNN maps the variable space into the latent space for the Pdeath image data. The chlorine gas leak accident in the Mipo complex (city of Ulsan, Republic of Korea) is used for verification of the model. The proposed model predicts the Pdeath image within a mean squared error of 0.00246, and compared with other models, it exhibits superior performance. Furthermore, through the smoothness of image transition in the variable space, it is confirmed that image generation is not overfitting by data memorization. (C) 2018 Elsevier Ltd. All rights reserved.
Supervised representation learning based on the teacher-student framework can extract quality-related features for soft sensors, in which the teacher network extracts representation information for the student network...
详细信息
Supervised representation learning based on the teacher-student framework can extract quality-related features for soft sensors, in which the teacher network extracts representation information for the student network as supervision information. In traditional applications, the teacher network is heavy and is difficult to train, so the teacher network is conventionally pre-trained. However, the pre-training of the teacher network is unnecessary if the training process is not complicated so that it is meaningful to joint optimize the teacher-student network. In our application, the teacher-student framework is used to extract quality-related representation information for soft sensors. The objective is to maximize the mutual information of representation information and supervision information, in which the inconsistency of distributions between observed information and supervisory information is modeled as isotropic Gaussian noise. The objective is decoupled through analysis under some approximate assumptions so that the alternative iteration method can be used to update the parameters of the model. The proposed quality-related feature extraction method is applied to soft sensors combined with a traditional just-in-time learning method. Our experiments show that the prediction performance of our representation extraction method is better than other existing representation extraction algorithms. (C) 2022 Published by Elsevier Inc.
In this study, we propose a deep learning related framework to analyze S&P500 stocks using bi-dimensional histogram and autoencoder. The bi-dimensional histogram consisting of daily returns of stock price and stoc...
详细信息
In this study, we propose a deep learning related framework to analyze S&P500 stocks using bi-dimensional histogram and autoencoder. The bi-dimensional histogram consisting of daily returns of stock price and stock trading volume is plotted for each stock. autoencoder is applied to the bi-dimensional histogram to reduce data dimension and extract meaningful features of a stock. The histogram distance matrix for stocks are made of the extracted features of stocks, and stock market network is built by applying Planar Maximally Filtered Graph(PMFG) algorithm to the histogram distance matrix. The constructed stock market network represents the latent space of bi-dimensional histogram, and network analysis is performed to investigate the structural properties of the stock market. we discover that the structural properties of stock market network are related to the dispersion of bi-dimensional histogram. Also, we confirm that the autoencoder is effective in extracting the latent feature of the bi-dimensional histogram. Portfolios using the features of bi-dimensional histogram network are constructed and their investment performance is evaluated in comparison with other benchmark portfolios. We observe that the portfolio consisting of stocks corresponding to the peripheral nodes of bi-dimensional histogram network shows better investment performance than other benchmark stock portfolios.
Emerging recently as a novel concept in communication system design, end-to-end learning introduces deep neural networks (NNs) to represent the transmitter and receiver functions. Consequently, the whole system can be...
详细信息
Emerging recently as a novel concept in communication system design, end-to-end learning introduces deep neural networks (NNs) to represent the transmitter and receiver functions. Consequently, the whole system can be interpreted as an autoencoder (AE), which can be optimized from a holistic approach through a data-driven training method. Until now, the AE technique is mainly developed for point-to-point communication scenarios. In this paper, we aim to develop a novel NN-based AE scheme for relay-assisted cooperative communication systems. Specifically, three NN components are constructed to learn the behavior of the transmitter, relay node, and receiver, respectively. As the conventional end-to-end training is inapplicable, a novel two-stage training approach is proposed to indirectly solve the end-to-end training problem. The implicit approximations involved are analytically expressed based on information theory, offering insights on the achievable performance with the proposed training method. The proposed AE model eliminates the need for channel state information and noise variance of any link, and is adaptive to the variation in the input block length. Simulation results verify its advantages over the conventional decode-and-forward (DF) and amplify-and-forward (AF) schemes in various scenarios.
In multi-label learning, in order to improve the accuracy of classification, many scholars have considered the relationship between features and features, features and labels or labels and labels, but how to combine t...
详细信息
In multi-label learning, in order to improve the accuracy of classification, many scholars have considered the relationship between features and features, features and labels or labels and labels, but how to combine the correlation among them is rarely studied. Based on this, this paper proposes a multi-label learning algorithm with kernel extreme learning machine autoencoder. Firstly, the label space is reconstructed by using the non-equilibrium labels completion method in the label space. Then, the non-equilibrium labels space information is added to the input node of the kernel extreme learning machine autoencoder network, and the input features are output as the target. Finally, the kernel extreme learning machine is used for classification. Our method implements the information fusion between features and features, between labels and features, and between labels and labels. Compared with the traditional autoencoder network, the extreme learning machine autoencoder has no iterative process, which reduces the network training time and improves the classification accuracy. The experimental results of the proposed algorithm in the opening benchmark multi-label data sets show that the KELM-AE algorithm has some advantages over other comparative multi-label learning algorithms and the statistical hypothesis testing and stability analysis further illustrate the effectiveness of the proposed algorithm. (C) 2019 Elsevier B.V. All rights reserved.
The use of deep learning methods for modeling fluid flow has drawn a lot of attention in the past few years. Here we present a data-driven reduced-order model (ROM) for predicting flow fields in a bed configuration of...
详细信息
The use of deep learning methods for modeling fluid flow has drawn a lot of attention in the past few years. Here we present a data-driven reduced-order model (ROM) for predicting flow fields in a bed configuration of hot particles. The ROM consists of a parametric spatio-temporal convolutional autoencoder. The neural network architecture comprises two main components. The first part resolves the spatial and temporal dependencies present in the input sequence, while the second part of the architecture is responsible for predicting the solution at the subsequent timestep based on the information gathered from the preceding part. We also propose the utilization of a post-processing non-trainable output layer following the decoding path to incorporate the physical knowledge, e.g. no-slip condition, into the prediction. The ROM is evaluated by comparing its predicted solution with the high-fidelity counterpart. In addition, proper orthogonal decomposition (POD) is employed to systematically analyze and compare the dominant structures present in both sets of solutions. The assessment of the ROM for a bed configuration with variable particle temperature showed accurate results at a fraction of the computational cost required by traditional numerical simulation methods.
Zero-shot learning (ZSL) aims to recognize the novel object categories using the semantic representation of categories, and the key idea is to explore the knowledge of how the novel class is semantically related to th...
详细信息
Zero-shot learning (ZSL) aims to recognize the novel object categories using the semantic representation of categories, and the key idea is to explore the knowledge of how the novel class is semantically related to the familiar classes. Some typical models are to learn the proper embedding between the image feature space and the semantic space, whilst it is important to learn discriminative features and comprise the coarse-to-fine image feature and semantic information. In this paper, we propose a discriminative embedding autoencoder with a regressor feedback (DEARF) model for ZSL. The encoder learns a mapping from the image feature space to the discriminative embedding space, which regulates both inter-class and intra-class distances between the learned features by a margin, making the learned features be discriminative for object recognition. The regressor feedback learns to map the reconstructed samples back to the the discriminative embedding and the semantic embedding, assisting the decoder to improve the quality of the samples and provide a generalization to the unseen classes. The DEARF model is validated extensively on the benchmark datasets, and the experiment results show that the DEARF model outperforms the state-of-the-art models, and especially in the generalized zero-shot learning (GZSL), significant improvements are achieved.
Existing fault diagnosis methods usually assume that there are balanced training data for every machine health ***,the collection of fault signals is very difficult and expensive,resulting in the problem of imbalanced...
详细信息
Existing fault diagnosis methods usually assume that there are balanced training data for every machine health ***,the collection of fault signals is very difficult and expensive,resulting in the problem of imbalanced training *** will degrade the performance of fault diagnosis methods *** address this problem,an imbalanced fault diagnosis of rotating machinery using autoencoder-based SuperGraph feature learning is proposed in this *** autoencoder is firstly used to compress every monitoring signal into a low-dimensional vector as the node attribute in the *** the edge connections in the graph depend on the relationship between *** the basis,graph convolution is performed on the constructed SuperGraph to achieve imbalanced training dataset fault diagnosis for rotating *** experiments are conducted on a benchmarking publicized dataset and a practical experimental platform,and the results show that the proposed method can effectively achieve rotating machinery fault diagnosis towards imbalanced training dataset through graph feature learning.
Although researchers have applied many methods to history matching, such as Monte Carlo methods, ensemble-based methods, and optimization algorithms, history matching fractured reservoirs is still challenging. The key...
详细信息
Although researchers have applied many methods to history matching, such as Monte Carlo methods, ensemble-based methods, and optimization algorithms, history matching fractured reservoirs is still challenging. The key challenges are effectively representing the fracture network and coping with large amounts of reservoir-model parameters. With increasing numbers of fractures, the dimension becomes larger, resulting in heavy computational work in the inversion of fractures. This paper proposes a new characterization method for the multiscale fracture network, and a powerful dimensionality-reduction method by means of an autoencoder for model parameters. The characterization method of the fracture network is dependent on the length, orientation, and position of fractures, including largescale and small-scale fractures. To significantly reduce the dimension of parameters, the deep sparse autoencoder (DSAE) transforms the input to the low-dimensional latent variables through encoding and decoding. Integrated with the greedy layer-wise algorithm, we set up a DSAE and then take the latent variables as optimization variables. The performance of the DSAE with fewer activating nodes is excellent because it reduces the redundant information of the input and avoids overfitting. Then, we adopt the ensemble smoother (ES) with multiple data assimilation (ES-MDA) to solve this minimization problem. We test our proposed method in three synthetic reservoir history-matching problems, compared with the no-dimensionality-reduction method and the principal-component analysis (PCA). The numerical results show that the characterization method integrated with the DSAE could simplify the fracture network, preserve the distribution of fractures during the update, and improve the quality of history matching naturally fractured reservoirs.
As a commonly used model for anomaly detection, the autoencoder model for anomaly detection does not train the objective for extracted features, which is a downside of autoencoder model. In addition, it is well known ...
详细信息
As a commonly used model for anomaly detection, the autoencoder model for anomaly detection does not train the objective for extracted features, which is a downside of autoencoder model. In addition, it is well known that the autoencoder model has over-prominent reconstruction ability for anomalous data, leading to high false-negative rate. On the other hand, the deep support vector data description (SVDD) model first extracts features through deep neural network, and then map the extracted features into a hypersphere. However, the deep SVDD model has disadvantages such as feature information loss and feature collapse during training process, leading to a decrease in anomaly detection accuracy. To alleviate such drawbacks mentioned above, in this article, we propose a novel model, called improved autoencoder with memory module (IAEMM). Specifically, this model jointly learns deep SVDD model and autoencoder model to minimize the overall loss of deep SVDD error and reconstruction error, and add a memory module after encoder to amplify the difference of reconstruction error between normal and abnormal data. The proposed model can well identify abnormal hidden features and mitigate the problem of feature collapse. Experimental results on several datasets confirm the effectiveness and stability of our proposed method.
暂无评论