Geo-cellar models contain millions of gridblocks and are very time-consuming to simulate. This challenge necessitates upscaling geo-cellular models to obtain fit-for-purpose models for simulation. Simulation-based ups...
详细信息
Geo-cellar models contain millions of gridblocks and are very time-consuming to simulate. This challenge necessitates upscaling geo-cellular models to obtain fit-for-purpose models for simulation. Simulation-based upscaling methods are computationally demanding, especially if there is a large number of geological realizations. On the other hand, static methods do not take into account the dynamics of the flow. In this paper, a novel hybrid deep learning-based upscaling method is proposed that can handle highly channelized and layered reservoir models. The proposed method combines the ConvLSTM network with the fast marching method (FMM), which is a computationally efficient method to get the dynamic response of the reservoir without the need for full-physics flow simulation. Since reservoir models have deposited during different geological periods, they have a temporal distribution along the third dimension. ConvLSTM layers can simultaneously extract spatiotemporal dependencies that other networks in the literature were not able to do so. The proposed method follows a twostep training process. In the first step, a variational autoencoder with ConvLSTM blocks (ConvLSTM-VAE) is trained and validated unsupervised using 10,000 permeability realizations. This network learns the datagenerating distribution of the realizations and improves the overall upscaling process. Then, the acquired weights are used to initialize the ConvLSTM-FMM network, which is fine-tuned by the particle swarm optimization to accomplish the upscaling task by minimizing the difference between the pressure drop of the fine-scale and upscaled realizations calculated by the FMM. Validity of the FMM to estimate the BHP drop of the wells was verified on the utilized reservoir model. The advantage of the proposed data-driven method is that it can be trained once and used to upscale new realizations, contrary to conventional simulation-based methods that require running the entire process whenever the fine
Generating 3D point cloud directly from latent prior (e.g., Gaussian distribution) plays a vital role in the representation learning and data augmentation in 3D vision tasks. Since point cloud is formed by irregu-lar ...
详细信息
Generating 3D point cloud directly from latent prior (e.g., Gaussian distribution) plays a vital role in the representation learning and data augmentation in 3D vision tasks. Since point cloud is formed by irregu-lar points, the generation process of point cloud requires rich semantic information, yet few studies are devoted to it. In this paper, we recast this generation task as a progressive learning problem to model the two-level hierarchy of distributions and address it by proposing a novel model called hierarchical consis-tency variational autoencoder (HC-VAE). This framework introduces a hierarchical consistent mechanism (HCM) to model the shape consistency and the pointwise representation consistency in a complementary manner. Specifically, we propose a stackable encoder-decoder framework and constrain the generation quality progressively to ensure that the underlying shape and fine-grained parts can be reconstructed with high fidelity. Additionally, given the progressively generated intermediate point cloud instances, a hierarchical-positive contrastive loss is introduced to learn the point-distribution-free instance represen-tations to avoid explicitly parametrizing the distribution of points in a shape. In this way, our model suffices to generate diverse, high-resolution, and uniform point cloud instances. Extensive experimental results demonstrate that the proposed method achieves state-of-the-art performance in point cloud gen-eration.(c) 2022 Elsevier Ltd. All rights reserved.
Porous membranes have been utilized intensively in a wide range of fields due to their special characteristics and a rigorous characterization of their microstructures is crucial for understanding their properties and...
详细信息
Porous membranes have been utilized intensively in a wide range of fields due to their special characteristics and a rigorous characterization of their microstructures is crucial for understanding their properties and improving the performance for target applications. A promising method for the quantitative analysis of porous structures leverages the physics-based generation of porous structures at the pore scale, which can be validated against real experimental microstructures, followed by building the process-structure-property relationships with data-driven algorithms such as artificial neural networks. In this study, a variational autoencoder (VAE) neural network model is used to characterize the 3D structural information of porous materials and to represent them with low-dimensional latent variables, which further model the structure-property relationship and solve the inverse problem of process-structure linkage combined with the Bayesian optimization method. Our methods provide a quantitative way to learn structural descriptors in an unsupervised manner which can characterize porous microstructures robustly.
Accurate prediction of the future motion of surrounding vehicles is crucial for ensuring the safety of motion planning in autonomous vehicles. However, it is challenging to perform because of the complex interactions ...
详细信息
Accurate prediction of the future motion of surrounding vehicles is crucial for ensuring the safety of motion planning in autonomous vehicles. However, it is challenging to perform because of the complex interactions between vehicles. In this study, we propose a novel multi-modal vehicle trajectory prediction framework that utilizes a coarse-to-fine approach by first generating initial trajectory proposals with a conditional variational autoencoder (CVAE) and then refining them using the conditional diffusion model. We first address the problems of data sparsity and irregularity by converting the trajectory coordinates to the Frenet coordinate system. To enable the model to better distinguish between different features, we employ a temporal encoder to extract trajectory features and a long short-term memory (LSTM) network to extract lane features. The target lane evaluator is utilized to calculate the attention weights for each lane candidate, thereby generating more deterministic future trajectories. We then use the CVAE to generate initial multiple trajectory proposals based on the surrounding scene context and the trajectory features of the target vehicle. Finally, we formulate the trajectory refinement task as a reverse process of the conditional diffusion model, which effectively enhances the multi-modal trajectory proposals. Experiments conducted on Argoverse and nuScenes demonstrate that our method outperforms state-of-the-art methods in some evaluation metrics while achieving the optimal trade-off between predictive accuracy and efficiency. Field experiments conducted in urban environments further validate the effectiveness of the proposed approach. (c) 2023 Elsevier B.V. All rights reserved.
variational autoencoder (VAE) is an unsupervised learning that represents high dimensional input data into normally distributed latent space. Multi-channel physiological signals, namely EEG and peripherals are mostly ...
详细信息
variational autoencoder (VAE) is an unsupervised learning that represents high dimensional input data into normally distributed latent space. Multi-channel physiological signals, namely EEG and peripherals are mostly preferred for affective computing. The DEAP dataset is converted into multimodal latent dataset for emotion recognition in this study. 40-ch recordings of 32 participants are encoded to different modalities of peripherals and 32-ch EEG. First, short-time Fourier transform (STFT) is used to extract time-frequency (TF) distribution for training VAE. Thus, the localized components in the each channel of the modalities is converted to 100 -dimensional space using VAE. The proposed method is applied to each participant's recordings to obtain new latent encoded dataset. Within and between subject classification results using latent dataset are compared to the original data for peripheral, 32ch EEG and peripheral with EEG modalities. Naive Bayes (NB) classifier is used to evaluate the encoding performance of the 100-dimensional modalities, and compared to original results. The error rates of leave-one participant-out cross-validation (LOPO CV) 0.3322 and 0.3327 are yielded for high/low arousal and valence states while the originals are 0.349 and 0.382.
In the context of burgeoning industrial advancement, there is an increasing trend towards the integration of intelligence and precision in mechanical equipment. Central to the functionality of such equipment is the ro...
详细信息
In the context of burgeoning industrial advancement, there is an increasing trend towards the integration of intelligence and precision in mechanical equipment. Central to the functionality of such equipment is the rolling bearing, whose operational integrity significantly impacts the overall performance of the machinery. This underscores the imperative for reliable fault diagnosis mechanisms in the continuous monitoring of rolling bearing conditions within industrial production environments. Vibration signals are primarily used for fault diagnosis in mechanical equipment because they provide comprehensive information about the equipment's condition. However, fault data often contain high noise levels, high-frequency variations, and irregularities, along with a significant amount of redundant information, like duplication, overlap, and unnecessary information during signal transmission. These characteristics present considerable challenges for effective fault feature extraction and diagnosis, reducing the accuracy and reliability of traditional fault detection methods. This research introduces an innovative fault diagnosis methodology for rolling bearings using deep convolutional neural networks (CNNs) enhanced with variational autoencoders (VAEs). This deep learning approach aims to precisely identify and classify faults by extracting detailed vibration signal features. The VAE enhances noise robustness, while the CNN improves signal data expressiveness, addressing issues like gradient vanishing and explosion. The model employs the reparameterization trick for unsupervised learning of latent features and further trains with the CNN. The system incorporates adaptive threshold methods, the "3/5" strategy, and Dropout methods. The diagnosis accuracy of the VAE-CNN model for different fault types at different rotational speeds typically reaches more than 90 %, and it achieves a generally acceptable diagnosis result. Meanwhile, the VAE-CNN augmented fault diagnosis mode
Background Lung cancer is one of the most malignant tumors, causing over 1,000,000 deaths each year worldwide. Deep learning has brought success in many domains in recent years. DNA methylation, an epigenetic factor, ...
详细信息
Background Lung cancer is one of the most malignant tumors, causing over 1,000,000 deaths each year worldwide. Deep learning has brought success in many domains in recent years. DNA methylation, an epigenetic factor, is used for model training in many studies. There is an opportunity for deep learning methods to analyze the lung cancer epigenetic data to determine their subtypes for appropriate treatment. Results Here, we employ variational autoencoders (VAEs), an unsupervised deep learning framework, on 450K DNA methylation data of TCGA-LUAD and TCGA-LUSC to learn latent representations of the DNA methylation landscape. We extract a biologically relevant latent space of LUAD and LUSC samples. It is showed that the bivariate classifiers on the further compressed latent features could classify the subtypes accurately. Through clustering of methylation-based latent space features, we demonstrate that the VAEs can capture differential methylation patterns about subtypes of lung cancer. Conclusions VAEs can distinguish the original subtypes from manually mixed methylation data frame with the encoded features of latent space. Further applications about VAEs should focus on fine-grained subtypes identification for precision medicine.
To ensure the safety and reliability of complex industrial processes are very ***,extracting multiple features of data effectively is a great significance to improve the accuracy of modeling for fault ***,uncertainty ...
详细信息
ISBN:
(数字)9789887581581
ISBN:
(纸本)9798350366907
To ensure the safety and reliability of complex industrial processes are very ***,extracting multiple features of data effectively is a great significance to improve the accuracy of modeling for fault ***,uncertainty and nonlinearity are main characteristics of industrial process ***,it is challenging for modeling to extract multiple features of process data at the same *** this paper,an integrated nonlinear dynamic system model is proposed for fault diagnosis based on variational autoencoder-linear dynamic system(VAE-LDS).First,the deep learning algorithm variational autoencoder(VAE) is used to extract the nonlinear data feature and learn the potential representation of ***,the VAE model is embedded into the linear dynamic system(LDS) so that the dynamics and uncertainty underlying data can be extracted *** this way,A comprehensive model integrating multiple features can be ***,the proposed method is applied to the TE process for fault diagnosis comparing with other *** results show the proposed method has superior performance.
The high-resolution scanning devices developed in recent decades provide biomedical volume datasets that support the study of molecular structure and drug design. Isosurface analysis is an important tool in these stud...
详细信息
The high-resolution scanning devices developed in recent decades provide biomedical volume datasets that support the study of molecular structure and drug design. Isosurface analysis is an important tool in these studies, and the key is to construct suitable description vectors to support subsequent tasks, such as classification and retrieval. Traditional methods based on handcrafted features are insufficient for dealing with complex structures, while deep learning-based approaches have high memory and computation costs when dealing directly with volume data. To address these problems, we propose IsoExplorer, an isosurface-driven framework for 3D shape analysis of biomedical volume data. We first extract isosurfaces from volume data and split them into individual 3D shapes according to their connectivity. Then, we utilize octree-based convolution to design a variational autoencoder model that learns the latent representations of the shape. Finally, these latent representations are used for low-dimensional isosurface representation and shape retrieval. We demonstrate the effectiveness and usefulness of IsoExplorer via isosurface similarity analysis, shape retrieval of real-world data, and comparison with existing methods.
Underground infrastructures are rapidly growing in size and complexity. However, their operations are affected by several hazards, including hidden structural deterioration and effects of random external constructions...
详细信息
Underground infrastructures are rapidly growing in size and complexity. However, their operations are affected by several hazards, including hidden structural deterioration and effects of random external constructions. Dynamic monitoring of these hazards is essential to provide early warning. We propose a vibration-based self-supervised incremental learning model for dynamic monitoring of emerging operational threats by recognizing abnormal responses. The model comprises teacher and student models based on a variational autoencoder (VAE) with a metric function. When the teacher model detects a new category of abnormal vibration, the student model is trained to recognize this abnormality through sample rehearsals and knowledge distillations. Subsequently, it becomes the teacher model for the next round of incremental learning. We demonstrate through a case study that catastrophic forgetting can be avoided and memory consumption can be reduced during dynamic network updates. Moreover, the use of a metric function in the VAE increases the vibration identification accuracy.
暂无评论