Synthetic data generation research has been progressing at a rapid pace and novel methods are being designed every now and then. Earlier, statistical methods were used to learn the distributions of real data and then ...
详细信息
Synthetic data generation research has been progressing at a rapid pace and novel methods are being designed every now and then. Earlier, statistical methods were used to learn the distributions of real data and then sample synthetic data from those distributions. Recent advances in generative models have led to more efficient modeling of complex high-dimensional datasets. Also, privacy concerns have led to the development of robust models with lesser risk of privacy breaches. Firstly, the paper presents a comprehensive survey of existing techniques for tabular data generation and evaluation matrices. Secondly, it elaborates on a comparative analysis of state-of- the-art synthetic data generation techniques, specifically CTGAN and TVAE for small, medium, and large-scale datasets with varying data distributions. It further evaluates the synthetic data using quantitative and qualitative metrics/techniques. Finally, this paper presents the outcomes and also highlights the issues and shortcomings which are still need to be addressed.
The labyrinth of the inner ear is an important auditory and balanced sensory organ and is closely related to tinnitus, hearing loss, vertigo, and Meniere diseases. Quantitative description and measurement of the labyr...
详细信息
The labyrinth of the inner ear is an important auditory and balanced sensory organ and is closely related to tinnitus, hearing loss, vertigo, and Meniere diseases. Quantitative description and measurement of the labyrinth is a challenging task in both clinical practice and medical research. A data-driven-based labyrinth morphological modeling method is proposed for extracting simple and low-dimensional representations or feature vectors to quantify the normal and abnormal labyrinths in morphology. Firstly, a two-stage pose alignment strategy is introduced to align the segmented inner ear labyrinths. Then, an energy-adaptive spatial and inter-slice dimensionality reduction strategy is adopted to extract compact morphological features via a variational autoencoder (VAE). Finally, a statistical model of the compact feature in the latent space is established to represent the morphology distribution of the labyrinths. As one of an application of our model, a reference-free quality evaluation for the segmentation of the labyrinth is explored. The experimental results show that the consistency between the proposed method and the Dice similarity coefficient (DSC) reaches 0.78. Further analysis showed that the model also has a high potential to apply to morphological analysis, such as anomaly detection, of the labyrinths.
Automatic MRI brain tumor segmentation is of vital importance for the disease diagnosis, monitoring, and treatment planning. In this paper, we propose a two-stage encoder-decoder based model for brain tumor subregiona...
详细信息
ISBN:
(纸本)9783030720834;9783030720841
Automatic MRI brain tumor segmentation is of vital importance for the disease diagnosis, monitoring, and treatment planning. In this paper, we propose a two-stage encoder-decoder based model for brain tumor subregional segmentation. variational autoencoder regularization is utilized in both stages to prevent the overfitting issue. The second-stage network adopts attention gates and is trained additionally using an expanded dataset formed by the first-stage outputs. On the BraTS 2020 validation dataset, the proposed method achieves the mean Dice score of 0.9041, 0.8350, and 0.7958, and Hausdorff distance (95%) of 4.953, 6.299, 23.608 for the whole tumor, tumor core, and enhancing tumor, respectively. The corresponding results on the BraTS 2020 testing dataset are 0.8729, 0.8357, and 0.8205 for Dice score, and 11.4288, 19.9690, and 15.6711 for Hausdorff distance. The code is publicly available at https://***/shu-hai/two-stage-VAE-Attention-gate-BraTS2020.
In end-to-end optimized learned image compression, it is standard practice to use a convolutional variational autoencoder with generalized divisive normalization (GDN) to transform images into a latent space. Recently...
详细信息
ISBN:
(纸本)9781665441155
In end-to-end optimized learned image compression, it is standard practice to use a convolutional variational autoencoder with generalized divisive normalization (GDN) to transform images into a latent space. Recently, Operational Neural Networks (ONNs) that learn the best non-linearity from a set of alternatives, and their "self-organized" variants, Self-ONNs, that approximate any non-linearity via Taylor series have been proposed to address the limitations of convolutional layers and a fixed nonlinear activation. In this paper, we propose to replace the convolutional and GDN layers in the variational autoencoder with self-organized operational layers, and propose a novel self-organized variational autoencoder (Self-VAE) architecture that benefits from stronger non-linearity. The experimental results demonstrate that the proposed Self-VAE yields improvements in both rate-distortion performance and perceptual image quality.
In this study,the hourly directions of eight banking stocks in Borsa Istanbul were predicted using linear-based,deep-learning(LSTM)and ensemble learning(Light-GBM)*** models were trained with four different feature se...
详细信息
In this study,the hourly directions of eight banking stocks in Borsa Istanbul were predicted using linear-based,deep-learning(LSTM)and ensemble learning(Light-GBM)*** models were trained with four different feature sets and their performances were evaluated in terms of accuracy and F-measure *** the first experiments directly used the own stock features as the model inputs,the second experiments utilized reduced stock features through variational autoencoders(VAE).In the last experiments,in order to grasp the effects of the other banking stocks on individual stock performance,the features belonging to other stocks were also given as inputs to our *** combining other stock features was done for both own(named as allstock_own)and VAE-reduced(named as allstock_VAE)stock features,the expanded dimensions of the feature sets were reduced by Recursive Feature *** the highest success rate increased up to 0.685 with allstock_own and LSTM with attention model,the combination of allstock_VAE and LSTM with the attention model obtained an accuracy rate of *** the classification results achieved with both feature types was close,allstock_VAE achieved these results using nearly 16.67%less features compared to allstock_*** all experimental results were examined,it was found out that the models trained with allstock_own and allstock_VAE achieved higher accuracy rates than those using individual stock *** was also concluded that the results obtained with the VAE-reduced stock features were similar to those obtained by own stock features.
OBJECTIVE Electrocardiography (ECGs) has been a vital tool for cardiovascular disease (CVD) diagnosis, which visually depicts the heart's electrical activity. To enhance automatic classification between normal and...
详细信息
OBJECTIVE Electrocardiography (ECGs) has been a vital tool for cardiovascular disease (CVD) diagnosis, which visually depicts the heart's electrical activity. To enhance automatic classification between normal and diseased ECG, it is essential to extract consistent and qualitative features. METHODS Precision of ECG classification through a hybrid Deep Learning (DL) approach leverages both Convolutional Neural Network (CNN) architecture and variational autoencoder (VAE) techniques. By combining these methods, we aim to achieve more accurate and robust ECG interpretation. The method is trained and tested over the PTB-XL dataset, which contains 21,799 with 12-lead ECGs from 18,869 patients, each spanning 10 s. The classification evaluation of five super-classes and 23 sub-classes of CVD, with the proposed CNN-VAE model is compared. RESULTS The classification of various CVDs resulted in the highest accuracy of 98.51%, specificity of 98.12%, sensitivity of 97.9%, and F1-score of 97.95%. We have also achieved the minimum false positive and false negative rates of 2.07% and 1.87%, respectively, during validation. The results are validated upon the annotations given by individual cardiologists, who assigned potentially multiple ECG statements to each record. CONCLUSION When compared to other deep learning methods, our suggested CNN-VAE model performs significantly better in the testing phase. This study proposes a new architecture of combining CNN-VAE for CVD classification from ECG data, this can help clinicians to identify the disease earlier and carry out further treatment. The CNN-VAE model can better characterize input signals due to its hybrid architecture. (Hellenic Journal of Cardiology 2025;81:75-84) (c) 2024 Hellenic Society of Cardiology. Publishing services by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).
Traffic matrices (TMs) contain crucial information for managing networks, optimizing traffic flow, and detecting anomalies. However, directly measuring traffic to construct a TM is resource-intensive and computational...
详细信息
Traffic matrices (TMs) contain crucial information for managing networks, optimizing traffic flow, and detecting anomalies. However, directly measuring traffic to construct a TM is resource-intensive and computationally expensive. A more practical approach involves estimating the TM from readily available link load measurements, which falls under the category of inferential network monitoring based on indirect measurements known as network tomography. This paper focuses on solving the problem of estimating the traffic matrix from link loads by utilizing deep generative models. The proposed models are trained using historical data-specifically, previously observed TMs-and are then leveraged to transform traffic matrix estimation (TME) into a simpler minimization problem in a lower-dimensional latent space. This transformed problem can be efficiently solved using a gradient-based optimizer. Our work aims to examine and test different model architectures and optimization approaches. The performance of the proposed methods is comparatively evaluated over a comprehensive set of suitable metrics on two publicly available datasets comprising actual traffic matrices obtained from real backbone networks. In addition, we compare our approach with a state-of-the-art method previously published in the literature.
Network intrusion datasets often face class imbalance issues in intrusion detection tasks, where the number of majority class samples is much higher than minority class samples. Current solutions face notable limitati...
详细信息
Network intrusion datasets often face class imbalance issues in intrusion detection tasks, where the number of majority class samples is much higher than minority class samples. Current solutions face notable limitations: traditional normalization weakens the multimodal distribution of continuous features, while mainstream generative models focus excessively on minority class mining while neglecting majority class information. To address these issues, we propose M2M-VAEGAN, which innovatively incorporates a variational Gaussian Mixture (VGM) model to preserve multimodal characteristics of continuous features. We design a transfer learning framework, pre-training on majority classes to capture general attack patterns, followed by fine-tuning with balanced batches of majority and minority samples to prevent catastrophic forgetting. Additionally, we enhance the VAEGAN architecture with an auxiliary classifier to strengthen conditional information learning. On the NSL-KDD and CIC-IDS2017 datasets, M2M-VAEGAN outperforms methods such as SMOTE, CTGAN, and CTABGAN, achieving a 1.25% to 6.42% improvement in minority class recall. These results demonstrate the effectiveness of the proposed approach.
Quality variables, which are usually measured offline, play important roles in describing process behaviors. However, online data obtained from soft sensors are significant as they provide accurate and immediate infor...
详细信息
Quality variables, which are usually measured offline, play important roles in describing process behaviors. However, online data obtained from soft sensors are significant as they provide accurate and immediate information. The reliability of online soft sensors is questionable due to changes in sensors, equipment, raw material availability, and operation conditions. In addition, chemical plants have dynamic properties and complex correlations amidst a large number of process variables. This causes most of the predictions obtained from steady-state soft sensors to be inaccurate in representing the particular chemical process. In this paper, the latent dynamic variational autoencoder is proposed to provide an estimation model and supervise soft-sensors. The input data are encoded in the latent space to remove underlying noises and disturbances in the data. Afterward, the dynamical properties are learned in the latent space through the bi-directional recurrent neural network, whose output (latent variable) is used to reconstruct back the input data. A simulation case study is conducted to show the effectiveness of the proposed method. Copyright (C) 2021 The Authors.
Analysis of ultrasonic testing (UT) data is a time-consuming assignment. In order to make it less demanding we propose an approach based on a variational autoencoder (VAE) to filter out the scans without anomalies/def...
详细信息
ISBN:
(纸本)9781665426398
Analysis of ultrasonic testing (UT) data is a time-consuming assignment. In order to make it less demanding we propose an approach based on a variational autoencoder (VAE) to filter out the scans without anomalies/defects and in doing so, partially automate the procedure. The implemented approach uses an additional encoder network allowing to encode the reconstructed images. The differences in encodings of input and reconstructed images have shown to be good indicators of anomalous data. Anomaly detection results surpass the results of other VAE based anomaly criteria.
暂无评论