•Variational graph auto-encoders are excellent for predicting miRNA-disease associations.•Graph convolutional networks obtain good representations for miRNAs and diseases.•Variational auto-encoders ...can deal with missing data in the miRNA-disease network.•Integrating different databases helps predict novel miRNA-disease associations.
Cumulative experimental studies have demonstrated the critical roles of microRNAs (miRNAs) in the diverse fundamental and important biological processes, and in the development of numerous complex human diseases. Thus, exploring the relationships between miRNAs and diseases is helpful with understanding the mechanisms, the detection, diagnosis, and treatment of complex diseases. As the identification of miRNA-disease associations via traditional biological experiments is time-consuming and expensive, an effective computational prediction method is appealing. In this study, we present a deep learning framework with variational graph auto-encoder for miRNA-disease association prediction (VGAE-MDA). VGAE-MDA first gets the representations of miRNAs and diseases from the heterogeneous networks constructed by miRNA-miRNA similarity, disease-disease similarity, and known miRNA-disease associations. Then, VGAE-MDA constructs two sub-networks: miRNA-based network and disease-based network. Combining the representations based on the heterogeneous network, two variational graph auto-encoders (VGAE) are deployed for calculating the miRNA-disease association scores from two sub-networks, respectively. Lastly, VGAE-MDA obtains the final predicted association score for a miRNA-disease pair by integrating the scores from these two trained networks. Unlike the previous model, the VGAE-MDA can mitigate the effect of noises from random selection of negative samples. Besides, the use of graph convolutional neural (GCN) network can naturally incorporate the node features from the graph structure while the variational autoencoder (VAE) makes use of latent variables to predict associations from the perspective of data distribution. The experimental results show that VGAE-MDA outperforms the state-of-the-art approaches in miRNA-disease association prediction. Besides, the effectiveness of our model has been further demonstrated by case studies.
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.
•Monitoring CO2 plumes during geologic CO2 sequestration projects is essential.•High-fidelity simulations can be prohibitively expensive for history matching.•A deep learning framework is developed ...for efficient CO2 plume visualization.•Onset time is used for visualization of a propagating CO2 saturation front.•Variational autoencoder is used to compress high dimentional image data.
Monitoring CO2 plumes throughout the operation of geologic CO2 sequestration projects is essential to environmental safety. The evolution of underground CO2 saturation can be predicted using high-fidelity numerical simulations. However, high-fidelity simulations can be prohibitively expensive to compute. As a result of recent developments in data-driven models, rapid predictions of the CO2 plume can now be made using readily available pressure and temperature measurements. This study presents a novel deep learning-based workflow for efficiently visualizing CO2 plumes in near real-time while considering their uncertainties.
In our deep learning workflow, we visualize the CO2 plume images in the reservoir as a propagating saturation front, represented by ‘onset time’, using field measurements, including downhole pressure and temperature. At a given location, the ‘onset time’ is the calendar time when the CO2 saturation exceeds a certain threshold. Therefore, a single image of the CO2 front propagation is captured using the ‘onset time’ rather than storing multiple CO2 saturation images at different time steps. The use of ‘onset time’ significantly reduces memory and computational cost of deep learning-based framework, enabling large-scale field applications.
We use a variational autoencoder-decoder (VAE) network to compress high dimensional ‘onset time’ images into low dimensional latent variables while considering uncertainties of the predicted images. The use of VAE and onset time, simplifies the overall neural network architecture and significantly enhances the training efficiency. To estimate the latent variables of the VAE network, we train a feed forward neural network model that incorporates available monitoring data such as downhole pressure and temperature measurements. The estimated latent variables are then fed into a trained decoder network to generate 3D onset time images, visualizing the propagation of CO2 plume in near real time.
The proposed workflow is applied to both synthetic and field cases, where the field application is a large-scale geological carbon storage project in a carbonate reef reservoir in the Northern Niagaran Pinnacle Reef Trend in Michigan, USA. The field measurements include distributed temperature sensing (DTS) and distributed pressure responses from down-hole gauges along the monitoring well. The predicted CO2 plume images provided by the proposed workflow are shown to be consistent with the simulation results of traditional history matched model using genetic algorithm. Our deep learning-based framework can predict the CO2 front propagation in terms of onset time in seconds, making it well-suited for real time decision-making and operational optimization.
Data-driven modeling will be complicated for a process if the output quality indices are defined in a high-dimensional space, e.g., a quality distribution. In this work, a novel probabilistic ...modeling method is proposed for industrial processes with low-dimensional inputs and high-dimensional outputs. First, based on a limited sample set, the variational autoencoder (VAE) is applied to extract features of the high-dimensional outputs. Next, a Gaussian Process (GP) model is established on the sub-manifold space defined by the low-dimensional features, and the high-dimensional predictions can be obtained through the VAE reverse procedure. Finally, a deep composing kernel strategy is developed to capture the nonlinearity and correlation hidden in the features. It can significantly improve the generalization performance of the GP model. The effectiveness of the proposed modeling algorithm is demonstrated by applications in a continuous crystallizer system and an ethylene homo-polymerization system.
The world is slowly recovering from the Coronavirus disease 2019 (COVID-19) pandemic; however, humanity has experienced one of its According to work by Mishra et al. (2020), the study’s first phase ...included a cohort of 5,262 subjects, with 3,325 Fitbit users constituting the majority. However, among this large cohort of 5,262 subjects, most significant trials in modern times only to learn about its lack of preparedness in the face of a highly contagious pathogen. To better prepare the world for any new mutation of the same pathogen or the newer ones, technological development in the healthcare system is a must. Hence, in this work, PCovNet+, a deep learning framework, was proposed for smartwatches and fitness trackers to monitor the user’s Resting Heart Rate (RHR) for the infection-induced anomaly. A convolutional neural network (CNN)-based variational autoencoder (VAE) architecture was used as the primary model along with a long short-term memory (LSTM) network to create latent space embeddings for the VAE. Moreover, the framework employed pre-training using normal data from healthy subjects to circumvent the data shortage problem in the personalized models. This framework was validated on a dataset of 68 COVID-19-infected subjects, resulting in anomalous RHR detection with precision, recall, F-beta, and F-1 score of 0.993, 0.534, 0.9849, and 0.6932, respectively, which is a significant improvement compared to the literature. Furthermore, the PCovNet+ framework successfully detected COVID-19 infection for 74% of the subjects (47% presymptomatic and 27% post-symptomatic detection). The results prove the usability of such a system as a secondary diagnostic tool enabling continuous health monitoring and contact tracing.
•A CNN-VAE-based anomaly detection model and an LSTM network to generate temporal-aware embeddings of the latent vector of the primary model is used.•Healthy patient data is used to pretrain the base model and fine-tuned using each subject’s baseline data to achieve a personalized version.•The proposed model is validated on 68 COVID-19-infected individuals’ data.
We propose to learn a low-dimensional probabilistic deformation model from data which can be used for the registration and the analysis of deformations. The latent variable model maps similar ...deformations close to each other in an encoding space. It enables to compare deformations, to generate normal or pathological deformations for any new image, or to transport deformations from one image pair to any other image. Our unsupervised method is based on the variational inference. In particular, we use a conditional variational autoencoder network and constrain transformations to be symmetric and diffeomorphic by applying a differentiable exponentiation layer with a symmetric loss function. We also present a formulation that includes spatial regularization such as the diffusion-based filters. In addition, our framework provides multi-scale velocity field estimations. We evaluated our method on 3-D intra-subject registration using 334 cardiac cine-MRIs. On this dataset, our method showed the state-of-the-art performance with a mean DICE score of 81.2% and a mean Hausdorff distance of 7.3 mm using 32 latent dimensions compared to three state-of-the-art methods while also demonstrating more regular deformation fields. The average time per registration was 0.32 s. Besides, we visualized the learned latent space and showed that the encoded deformations can be used to transport deformations and to cluster diseases with a classification accuracy of 83% after applying a linear projection.
Accurate myocardial segmentation is crucial in the diagnosis and treatment of myocardial infarction (MI), especially in Late Gadolinium Enhancement (LGE) cardiac magnetic resonance (CMR) images, ...where the infarcted myocardium exhibits a greater brightness. However, segmentation annotations for LGE images are usually not available. Although knowledge gained from CMR images of other modalities with ample annotations, such as balanced-Steady State Free Precession (bSSFP), can be transferred to the LGE images, the difference in image distribution between the two modalities (i.e., domain shift) usually results in a significant degradation in model performance. To alleviate this, an end-to-end Variational autoencoder based feature Alignment Module Combining Explicit and Implicit features (VAMCEI) is proposed. We first re-derive the Kullback-Leibler (KL) divergence between the posterior distributions of the two domains as a measure of the global distribution distance. Second, we calculate the prototype contrastive loss between the two domains, bringing closer the prototypes of the same category across domains and pushing away the prototypes of different categories within or across domains. Finally, a domain discriminator is added to the output space, which indirectly aligns the feature distribution and forces the extracted features to be more favorable for segmentation. In addition, by combining CycleGAN and VAMCEI, we propose a more refined multi-stage unsupervised domain adaptation (UDA) framework for myocardial structure segmentation. We conduct extensive experiments on the MSCMRSeg 2019, MyoPS 2020 and MM-WHS 2017 datasets. The experimental results demonstrate that our framework achieves superior performances than state-of-the-art methods.
In many industries, statistical process monitoring techniques play a key role in improving processes through variation reduction and defect prevention. Modern large-scale industrial processes require ...appropriate monitoring techniques that can efficiently address high-dimensional nonlinear processes. Such processes have been successfully monitored with several latent variable-based methods. However, because these monitoring methods use Hotelling’s T2 statistics in the reduced space, a normality assumption underlies the construction of these tools. This assumption has limited the use of latent variable-based monitoring charts in both nonlinear and nonnormal situations. In this study, we propose a variational autoencoder (VAE) as a monitoring method that can address both nonlinear and nonnormal situations in high-dimensional processes. VAE is appropriate for T2 charts because it causes the reduced space to follow a multivariate normal distribution. The effectiveness and applicability of the proposed VAE-based chart were demonstrated through experiments on simulated data and real data from a thin-film-transistor liquid-crystal display process.
•We propose a variational autoencoder (VAE)-based process monitoring technique.•VAE is a nonlinear feature extraction method that appropriate for T2 charts.•VAE chart can reduce both unwanted false alarms and misdetections in process control.•VAE charts outperform the existing latent variable-based control charts.