In hyperspectral unmixing (HU), spectral variability in hyperspectral images (HSIs) is a major challenge which has received a lot of attention over the last few years. Here, we propose a method utilizing a generative ...
详细信息
In hyperspectral unmixing (HU), spectral variability in hyperspectral images (HSIs) is a major challenge which has received a lot of attention over the last few years. Here, we propose a method utilizing a generative adversarial network (GAN) for creating synthetic HSIs having a controllable degree of realistic spectral variability from existing HSIs with established ground truth abundance maps. Such synthetic images can be a valuable tool when developing HU methods that can deal with spectral variability. We use a variational autoencoder (VAE) to investigate how the variability in the synthesized images differs from the original images and perform blind unmixing experiments on the generated images to illustrate the effect of increasing the variability.
As the trend in climate change continues, extreme weather events are expected to occur with increasing frequency and severity and pose a significant threat to the electric power infrastructure. Regardless of the effor...
详细信息
As the trend in climate change continues, extreme weather events are expected to occur with increasing frequency and severity and pose a significant threat to the electric power infrastructure. Regardless of the efforts a utility puts towards hardening the grid, storm-induced damage to the utility assets such as cables and distributed energy resources (DERs) that are particularly vulnerable to such events is unavoidable. Access to a highly granular, in space and time, outage forecasting tool with long lead times (i.e., days ahead) will enhance the efficiency of service restoration efforts. In this study, we propose to develop and implement a multi -model framework as an operational tool based on a granular and multi -day outage forecasting model using operational numerical weather prediction model forecasts and detailed component outage information. An innovative two-layered recurrent neural network, i.e., a long-short-term-memory (LSTM)-based variational autoencoder (VAE) framework and a sliding window are used to address the uneven distribution of different types of weather events and make better use of the time -series data. Case studies are performed to demonstrate the performance of the new framework.
This method of identifying plant leaf disease generally involves a large team of experts with extensive knowledge of plant diseases, and it can be expensive, time-consuming, and subjective. Hence, a novel plant leaf d...
详细信息
This method of identifying plant leaf disease generally involves a large team of experts with extensive knowledge of plant diseases, and it can be expensive, time-consuming, and subjective. Hence, a novel plant leaf disease classification framework is proposed to classify the plant diseases and then take preventive measures based on the classified outcomes. The plant leaf images are collected from traditional databases. The classification of leaf diseases is done with the support of the developed Multi-scale Feature Fusion-based Adaptive Deep Network (MFF-ADNet). In this developed MFF-ADNet, two processes are carried out such as feature extraction and classification. The collected images are given to the feature extraction phase, where the Visual Geometry Group (16) (VGG16), variational autoencoder (VAE), and Visual Transformer (ViT) network are used for extracting the features. The extracted features are fused and the resultant Multi-scale fused features are provided to the input of the classification process. Here, the Adaptive Convolutional Neural Network with Attention Mechanism (CNNAM) is utilized for classifying the plant leaf diseases and the parameters are optimized using the Enhanced Gannet Optimization Algorithm (EGOA) approach. From the results, the median value is obtained for a proposed method that is more than 7.18% of MAO-MFF-ADNet, 4.11% of TSO-MFF-ADNet, 8.03% of CO-MFF-ADNet and 4.07% of GOA-MFF-ADNet. Therefore, the experimental outcome of the developed plant leaf classification model is validated over various approaches to ensure the goodness of the developed scheme.
Deep learning is usually applied to static datasets. If used for classification based on data streams, it is not easy to take into account a non-stationarity. This thesis presents work in progress on a new method for ...
详细信息
Deep learning is usually applied to static datasets. If used for classification based on data streams, it is not easy to take into account a non-stationarity. This thesis presents work in progress on a new method for online deep classifi- cation learning in data streams with slow or moderate drift, highly relevant for the application domain of malware detection. The method uses a combination of multilayer perceptron and variational autoencoder to achieve constant mem- ory consumption by encoding past data to a generative model. This can make online learning of neural networks more accessible for independent adaptive sys- tems with limited memory. First results for real-world malware stream data are presented, and they look promising. 1
Energy theft causes a lot of economic losses every year. In the practical environment of energy theft detection, it is required to solve imbalanced data problem where normal user data are significantly larger than ene...
详细信息
Energy theft causes a lot of economic losses every year. In the practical environment of energy theft detection, it is required to solve imbalanced data problem where normal user data are significantly larger than energy theft data. In this paper, a variational autoencoder-generative adversarial network (VAE-GAN)-based energy theft-detection model is proposed to overcome the imbalanced data problem. In the proposed model, the VAE-GAN generates synthetic energy theft data with the features of real energy theft data for augmenting the energy theft dataset. The obtained balanced dataset is applied to train a detector which is designed as one-dimensional convolutional neural network. The proposed model is simulated on the practical dataset for comparing with various generative models to evaluate their performance. From simulation results, it is confirmed that the proposed model outperforms the other existing models. Additionally, it is shown that the proposed model is also very useful in the environments of extreme data imbalance for a wide variety of applications by analyzing the performance of detector according to the balance rate.
Lung sound auscultation is an essential method for diagnosing lung diseases;however, most existing lung sound recognition methods fail to identify classes that are unknown in training. Thus, we proposed an open-set lu...
详细信息
Lung sound auscultation is an essential method for diagnosing lung diseases;however, most existing lung sound recognition methods fail to identify classes that are unknown in training. Thus, we proposed an open-set lung sound recognition model based on the conditional Gaussian capsule network and variational time- frequency feature reconstruction. The proposed model incorporates an inference network, a cubic encoder, an attention module, a classifier, a cubic decoder, and a generative network. First, the inference network is employed to extract the time-frequency features of lung sounds at a single time step. Then, the variational distribution of lung sounds is computed using the capsule network and optimized to approximate the Gaussian model of the class to which the sample belongs according to the labels. Time-frequency synchronized feature extraction and reconstruction are performed on the entire lung sound sample using the cubic encoder and cubic decoder. Finally, we utilize the generative network to refactor the lung sound features for open-set recognition. The proposed model was evaluated experimentally on a combined dataset using two different category assignment schemes. The results demonstrate that the proposed model achieved accuracies of 82.31% and 88.47%, respectively, thereby outperforming existing methods.
The novel coronavirus (COVID-19) has significantly spread over the world and comes up with new challenges to the research community. Although governments imposing numerous containment and social distancing measures, t...
详细信息
The novel coronavirus (COVID-19) has significantly spread over the world and comes up with new challenges to the research community. Although governments imposing numerous containment and social distancing measures, the need for the healthcare systems has dramatically increased and the effective management of infected patients becomes a challenging problem for hospitals. Thus, accurate short-term forecasting of the number of new contaminated and recovered cases is crucial for optimizing the available resources and arresting or slowing down the progression of such diseases. Recently, deep learning models demonstrated important improvements when handling time-series data in different applications. This paper presents a comparative study of five deep learning methods to forecast the number of new cases and recovered cases. Specifically, simple Recurrent Neural Network (RNN), Long short-term memory (L STM), Bidirectional L STM (BiL STM), Gated recurrent units (GRUs) and variational autoencoder (VAE) algorithms have been applied for global forecasting of COVID-19 cases based on a small volume of data. This study is based on daily confirmed and recovered cases collected from six countries namely Italy, Spain, France, China, USA, and Australia. Results demonstrate the promising potential of the deep learning model in forecasting COVID-19 cases and highlight the superior performance of the VAE compared to the other algorithms. (c) 2020 Elsevier Ltd. All rights reserved.
Due to the strategic importance of satellites, the safety and reliability of satellites have become more important. Sensors that monitor satellites generate lots of multivariate time series, and the abnormal patterns ...
详细信息
Due to the strategic importance of satellites, the safety and reliability of satellites have become more important. Sensors that monitor satellites generate lots of multivariate time series, and the abnormal patterns in the multivariate time series may imply malfunctions. The existing anomaly detection methods for multivariate time series have poor effects when processing the data with few dimensions or sparse relationships between sequences. This paper proposes an unsupervised anomaly detection model based on the variational Transformer to solve the above problems. The model uses the Transformer's self-attention mechanism to capture the potential correlations between sequences and capture the multi-scale temporal information through the improved positional encoding and up-sampling algorithm. Then, the model comprehensively considers the extracted features through the residual variational autoencoder to perform effective anomaly detection. Experimental results on a real dataset and two public datasets show that the proposed method is superior to the mainstream and state-ofthe-art methods.
Anomaly detection methods exploiting autoencoders (AE) have shown good performances. Unfortunately, deep non-linear architectures are able to perform high dimensionality reduction while keeping reconstruction error lo...
详细信息
Anomaly detection methods exploiting autoencoders (AE) have shown good performances. Unfortunately, deep non-linear architectures are able to perform high dimensionality reduction while keeping reconstruction error low, thus worsening outlier detecting performances of AEs. To alleviate the above problem, recently some authors have proposed to exploit variational autoencoders (VAE) and bidirectional Generative Adversarial Networks (GAN), which arise as a variant of standard AEs designed for generative purposes, both enforcing the organization of the latent space guaranteeing continuity. However, these architectures share with standard AEs the problem that they generalize so well that they can also well reconstruct anomalies. In this work we argue that the approach of selecting the worst reconstructed examples as anomalies is too simplistic if a continuous latent space autoencoder-based architecture is employed. We show that outliers tend to lie in the sparsest regions of the combined latent/error space and propose the VAEOut and LatentOut unsupervised anomaly detection algorithms, identifying outliers by performing density estimation in this augmented feature space. The proposed approach shows sensible improvements in terms of detection performances over the standard approach based on the reconstruction error.
Recent developments in attributed network clustering combine graph neural networks and autoencoders for unsupervised learning. Although effective, these techniques suffer from either (a) clustering-unfriendly embeddin...
详细信息
Recent developments in attributed network clustering combine graph neural networks and autoencoders for unsupervised learning. Although effective, these techniques suffer from either (a) clustering-unfriendly embedding spaces or (b) limited utilization of attribute information. To address these issues, we propose a novel model called variational Co-embedding Learning Model for Attributed Network Clustering (VCLANC), which utilizes much deeper information from the network by reconstructing both the network structure and the node attributes to perform self-supervised learning. Technically, VCLANC consists of dual variational autoencoders that co-embed nodes and attributes into the same latent space, along with a trainable Gaussian mixture prior that simultaneously performs representation learning and node clustering. To optimize the variational autoencoders and infer the latent variables of embeddings and clustering assignments, we derive a new variational lower bound that maximizes the joint likelihood of the observed network structure and node attributes. Furthermore, we also adopt a mutual distance loss on the cluster centers and a clustering assignment hardening loss on the node embeddings to strengthen clustering quality. Our experimental results on four real-world datasets demonstrate the outstanding performance of VCLANC for attributed network clustering.
暂无评论