As modern industries increase in scale and integration, the industrial process data show more complex dynamic time variability. To solve the dynamic time-varying problem of industrial process data, a novel multiscale ...
详细信息
As modern industries increase in scale and integration, the industrial process data show more complex dynamic time variability. To solve the dynamic time-varying problem of industrial process data, a novel multiscale variational autoencoder (MSVAE) based Regressor (REG) (MSVAE-REG) is proposed for production prediction and energy saving. The encoder of the MSVAE is constructed by multiscale convolutional neural network (MSCNN) to extract the multiscale temporal dynamic features, including the overall and local trend features in the Gaussian latent space. Then, the decoder of the MSVAE recovers the input data to enhance the dynamic adaptability of multiscale features. Moreover, the REG utilizes the gated recurrent unit (GRU) to build a dynamic relationship between multiscale temporal dynamic features and the predicted output. Finally, the proposed model is verified on the propylene and ethylene production datasets. Compared with the back propagation (BP) network, the extreme learning machine (ELM), the radial basis function (RBF), the convolutional neural network (CNN) and the variational autoencoder (VAE), the MSVAE-REG achieves state-of-the-art results, with the prediction accuracy respectively reaching about 95% and 96%, providing a new judgment basis for optimizing the production process and saving energy.
variational autoencoder (VAE) has been extended as a representative nonlinear method for collaborative filtering. However, the bottleneck of VAE lies in the softmax computation over all items, such that it takes linea...
详细信息
ISBN:
(纸本)9781450390965
variational autoencoder (VAE) has been extended as a representative nonlinear method for collaborative filtering. However, the bottleneck of VAE lies in the softmax computation over all items, such that it takes linear costs in the number of items to compute the loss and gradient for optimization. This hinders the practical use due to millions of items in real-world scenarios. Importance sampling is an effective approximation method, based on which the sampled softmax has been derived. However, existing methods usually exploit the uniform or popularity sampler as proposal distributions, leading to a large bias of gradient estimation. To this end, we propose to decompose the inner-product-based softmax probability based on the inverted multi-index, leading to sublinear-time and highly accurate sampling. Based on the proposed proposals, we develop a fast variational autoencoder (FastVAE) for collaborative filtering. FastVAE can outperform the state-of-the-art baselines in terms of both sampling quality and efficiency according to the experiments on three real-world datasets.
As a powerful tool for machine learning on the graph, network embedding, which projects nodes into low-dimensional spaces, has a variety of applications on complex networks. Most current methods and models are not sui...
详细信息
As a powerful tool for machine learning on the graph, network embedding, which projects nodes into low-dimensional spaces, has a variety of applications on complex networks. Most current methods and models are not suitable for bipartite networks, which have two different types of nodes and there are no links between nodes of the same type. Furthermore, the only existing methods for bipartite network embedding ignore the internal mechanism and highly nonlinear structures of links. Therefore, in this paper, we propose a new deep learning method to learn the node embedding for bipartite networks based on the widely used autoencoder framework. Moreover, we carefully devise a node-level triplet including two types of nodes to assign the embedding by integrating the local and global structures. Meanwhile, we apply the variational autoencoder (VAE), a deep generation model with natural advantages in data generation and reconstruction, to enhance the node embedding for the highly nonlinear relationships between nodes and complex features. Experiments on some widely used datasets show the effectiveness of the proposed model and corresponding algorithm compared with some baseline network (and bipartite) embedding techniques. (C) 2020 Elsevier Inc. All rights reserved.
The latent variable prior of the variational autoencoder (VAE) often utilizes a standard Gaussian distribution because of the convenience in calculation, but has an underfitting problem. This paper proposes a variatio...
详细信息
The latent variable prior of the variational autoencoder (VAE) often utilizes a standard Gaussian distribution because of the convenience in calculation, but has an underfitting problem. This paper proposes a variational autoencoder with optimizing Gaussian mixture model priors. This method utilizes a Gaussian mixture model to construct prior distribution, and utilizes the Kullback-Leibler (KL) distance between posterior and prior distribution to implement an iterative optimization of the prior distribution based on the data. The greedy algorithm is used to solve the KL distance for defining the approximate variational lower bound solution of the loss function, and for realizing the VAE with optimizing Gaussian mixture model priors. Compared with the standard VAE method, the proposed method obtains state-of-the-art results on MNIST, Omniglot, and Frey Face datasets, which shows that the VAE with optimizing Gaussian mixture model priors can learn a better model.
Air Traffic Management aims at ensuring safety during aircraft operations, particularly within Terminal Manoeuvring Areas where traffic density is high. The challenge lies in balancing safety and efficiency by closely...
详细信息
Air Traffic Management aims at ensuring safety during aircraft operations, particularly within Terminal Manoeuvring Areas where traffic density is high. The challenge lies in balancing safety and efficiency by closely managing the likelihood of mid-air collisions regarding the airport movements. Traditional models like the Reich and Anderson -Hsu models have been influential, but they fall short in representing the complex reality of Terminal Manoeuvring Areas. Data -driven approaches are emerging, with Monte Carlo simulations offering a more flexible methodology for collision risk estimation. This paper introduces a framework for assessing Mid -Air Collision likelihood resulting from Terminal Manoeuvring Area procedures by combining the field of Deep Generative Modelling using a variational autoencoder with the domain of rare event statistics through Subset Simulation. By incorporating disentanglement into the variational autoencoders model, we create a latent space that aligns dimensions with distinctive trajectory traits. Then, Subset Simulation is employed to gauge Mid -Air Collision probability, utilizing latent representations as input. Finally, sensitivity analysis reveals pivotal factors influencing collision risk, correlated with trajectory attributes via disentanglement. The methodology is applied to traffic around Zurich Airport: it evaluates the risk arising from go -around and take -off procedures using Automatic Dependent Surveillance -Broadcast data.
Breast cancer continues to be a major health concern worldwide. Early and accurate prediction is crucial for effective treatment and improving survival rates. Computer Aided Diagnosis system serves as an invaluable to...
详细信息
Breast cancer continues to be a major health concern worldwide. Early and accurate prediction is crucial for effective treatment and improving survival rates. Computer Aided Diagnosis system serves as an invaluable tool for radiologists, aiming to reduce diagnostic errors and enhance the accuracy of diagnosis. These systems incorporate various processing techniques, including pre-processing, segmentation, feature extraction, and classification. Moreover, deep learning methods frequently suffer from sub optimal performance and demand substantial computational resources. This study focuses on developing an automated classification model for mammography images to aid in breast cancer diagnosis. Our proposed model initiates with noise removal using median filters, followed by the removal of the pectoral muscle in images through the Canny-edge detection method. On these preprocessed images, we applied data augmentation using a two-point crossover technique, addressing issues of small datasets and class imbalances common in medical image analysis. The images then undergo multi-scale representation via the fourth-order complex diffusion algorithm. Feature extraction is conducted on these multi-scaled images using a Hierarchical variational Auto-encoders and then classified using a Support Vector Machine. Employing fourth-order complex diffusion for initial multi-scale representation significantly enhances the accuracy of feature extraction resulting in robust classification performance. The training process involves two different datasets like MIAS and the KAU-BCMD. Test results for the KAU-BCMD dataset include: accuracy of 99.80%, Area Under the Curve of 99.30%, F1-score of 99.20%, balanced accuracy of 99.80%, and Matthews correlation coefficient of 99.20%. For the MIAS dataset, test results show accuracy of 99.30%, Area Under the Curve of 99.10%, F1-score of 98.30%, balanced accuracy of 99.00%, and Matthews correlation coefficient of 99.00%. Our validation results clearl
Latent Dirichlet allocation model (LDA) has been widely used in topic modeling. Recent works have shown the effectiveness of integrating neural network mechanisms with this generative model for learning text represent...
详细信息
Latent Dirichlet allocation model (LDA) has been widely used in topic modeling. Recent works have shown the effectiveness of integrating neural network mechanisms with this generative model for learning text representation. However, one of the significant setbacks of LDA is that it is based on a Dirichlet prior that has a restrictive covariance structure. All its variables are considered to be negatively correlated, which makes the model restrictive. In a practical sense, topics can be positively or negatively correlated. To address this problem, we proposed a generalized Dirichlet variational autoencoder (GD-VAE) for topic modeling. The Generalized Dirichlet (GD) distribution has a more general covariance structure than the Dirichlet distribution because it takes into account both positively and negatively correlated topics in the corpus. Our proposed model leverages rejection sampling variational inference using a reparameterization trick for effective training. GDVAE compares favorably to recent works on topic models on several benchmark corpora. Experiments show that accounting for topics' positive and negative correlations results in better performance. We further validate the superiority of our proposed framework on two image data sets. GD-VAE demonstrates its significance as an integral part of a classification architecture. For reproducibility and further research purposes, code for this work can be found at https://***/hormone03/GD-VAE.
High -dimensional data such as natural images or speech signals exhibit some form of regularity, preventing their dimensions from varying independently. This suggests that there exists a lower dimensional latent repre...
详细信息
High -dimensional data such as natural images or speech signals exhibit some form of regularity, preventing their dimensions from varying independently. This suggests that there exists a lower dimensional latent representation from which the high -dimensional observed data were generated. Uncovering the hidden explanatory features of complex data is the goal of representation learning, and deep latent variable generative models have emerged as promising unsupervised approaches. In particular, the variational autoencoder (VAE) which is equipped with both a generative and an inference model allows for the analysis, transformation, and generation of various types of data. Over the past few years, the VAE has been extended to deal with data that are either multimodal or dynamical (i.e., sequential). In this paper, we present a multimodal and dynamical VAE (MDVAE) applied to unsupervised audiovisual speech representation learning. The latent space is structured to dissociate the latent dynamical factors that are shared between the modalities from those that are specific to each modality. A static latent variable is also introduced to encode the information that is constant over time within an audiovisual speech sequence. The model is trained in an unsupervised manner on an audiovisual emotional speech dataset, in two stages. In the first stage, a vector quantized VAE (VQ-VAE) is learned independently for each modality, without temporal modeling. The second stage consists in learning the MDVAE model on the intermediate representation of the VQ-VAEs before quantization. The disentanglement between static versus dynamical and modality -specific versus modality -common information occurs during this second training stage. Extensive experiments are conducted to investigate how audiovisual speech latent factors are encoded in the latent space of MDVAE. These experiments include manipulating audiovisual speech, audiovisual facial image denoising, and audiovisual speech emotion
Deep learning (DL)-based approaches have demonstrated remarkable performance in predicting the remaining useful life (RUL) of complex systems, which is beneficial for making timely maintenance decisions. However, the ...
详细信息
Deep learning (DL)-based approaches have demonstrated remarkable performance in predicting the remaining useful life (RUL) of complex systems, which is beneficial for making timely maintenance decisions. However, the majority of these DL methods suffer from a lack of interpretability, and it is difficult to mine the degradation features in the presence of significant measurement noises. To remedy the deficiency, a multi-channel fusion variational autoencoder (MCFVAE)-based approach is proposed. A feature fusion module is designed to capture and fuse the multi-channel features, which facilitates the disclosure of the degradation information from the multi-sensor data. A variational inference module is further introduced to generate the compressive representations and project them into a latent space as an interpretable component, which can display the degradation degree of the multi-sensor systems. A regressor module is finally utilized to establish the relationship between the compressive representations and the RUL. The superior feature fusion and distribution characteristics learning abilities of the MCFVAE contribute to achieving robust and interpretable RUL prediction. The effectiveness and superiority of the proposed method are experimentally validated through a publicly available Commercial modular aero propulsion system simulation dataset and compared with the existing methods.
In the advent of the Industry 4.0 paradigm, intelligent manufacturing has gained prominence with the integration of advanced Artificial Intelligence (AI) technologies aimed at augmenting production efficiency and miti...
详细信息
In the advent of the Industry 4.0 paradigm, intelligent manufacturing has gained prominence with the integration of advanced Artificial Intelligence (AI) technologies aimed at augmenting production efficiency and mitigating operational costs. Particularly, in process industries such as cement manufacturing, the efficacy of production is intrinsically tied to the manifold process elements involved. The underlying complexity is further accentuated by the fact that the production chain is typified by a multi-variate, time -variant, and non-linear system. Such characteristics exacerbate the challenges associated with predicting the quality of final goods, especially considering the intricate physical-chemical reactions that persist even in steady states, which will reflect to the data representation. Additionally, prevailing prediction systems are impeded by their inability to assimilate ancillary spatiotemporal information, rendering their predictive accuracies suboptimal for practical production demands. Addressing these issues, this study introduces an innovative approach for online prediction of final production quality by employing a Spatiotemporal Neural Network. The core attributes of this technique encompass the extraction of latent spatial information and the effective handling of extensive temporal sequences within two main components by a variational autoencoder framework. In the variational autoencoder, it is achieved through the strategic application of learnable convolutional neural layers, supplemented by gated recurrent layers with self -attention. In a novel approach, these two fundamental components are seamlessly integrated within a single end -to -end optimization framework. Empirical evidence derived from a real -world dataset serves to substantiate the superior performance of our proposed methodology in contrast to extant machine learning algorithms. The findings are indicative of the potential that deep learning architectures harbor in addressing
暂无评论