Semi-Supervised Recurrent Variational Autoencoder Approach for Visual Diagnosis of Atrial Fibrillation

Costa, Nahuel; Sánchez, Luciano; Couso, Inés

doi:10.1109/access.2021.3064854

Cited by 9 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the lack of existing comparable work in this field, and since most comparable works introduce some form of classification into the training process (Costa et al, 2021;Pastor-Serrano et al, 2021), it is difficult to compare this work to prior literature without extending the scope of this paper. Due to the high uncertainty in the scoring for respiratory events in sleep medicine we consider the contributions made in this paper, an advantage over the use of semi-supervised approaches for this type of application.…”

Section: Discussionmentioning

confidence: 99%

“…Outside medical approaches, VAE has been used for tasks such as anomaly detection (An & Cho, 2015), text classification (Xu, Sun, Deng, & Tan, 2017), and recommender systems (Li & She, 2017). In the medical field, VAE and other AE methods have been applied in various ways, mainly for the electrocardiogram (ECG) (Costa, Sánchez, & Couso, 2021;Kuznetsov, Moskalenko, Gribanov, & Zolotykh, 2021;Oluwasanmi et al, 2021), but also with some applications for the electromyogram (EMG) and EEG (Singh & Ogunfunmi, 2021). The application of VAE and other generative machine learning models for biomedical signal analysis is a largely unexplored field.…”

Section: Related Workmentioning

confidence: 99%

“…The application of VAE and other generative machine learning models for biomedical signal analysis is a largely unexplored field. (Costa et al, 2021) applied a novel class dependent implementation of the VAE for detecting atrial fibrillation, improving the latent space clustering by simultaneously training a classifier on the latent space with the VAE. (Pastor-Serrano, Lathouwers, & Perkó, 2021) proposed an adversarial VAE trained to generate and classify respiratory signals, using the latent space to classify baseline shift breathing irregularities, during training.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Exploration of Sleep Events in the Latent Space of Variational Autoencoders on a Breath-by-Breath Basis

Thordarson,

Islind,

Arnardottir

et al. 2023

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

In this exploratory paper, we attempt to address a growing demand for unsupervised machine learning techniques on sleep data by applying a variational autoencoder on respiratory sleep data on a breath-by-breath basis. We transform respiratory signals into a latent representation and cluster them together using KMeans clustering. We calculate the cluster preference of scored events and attempt to explain their position in the latent space. We show that a variational autoencoder can accurately reconstruct three respiratory signals from individual breaths despite being sampled through a latent dimension 384 times smaller than the input data. Our results also indicate that respiratory events in particular show a tendency to cluster together in the latent space despite a purely unsupervised learning approach. Finally, we lay the groundwork for future work made possible in this paper.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Exploration of Sleep Events in the Latent Space of Variational Autoencoders on a Breath-by-Breath Basis

Thordarson,

Islind,

Arnardottir

et al. 2023

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

show abstract

“…Reconstruction methods involve reconstructing data and detecting anomalies using the difference between original and reconstructed data. Autoencoder (AE) [40], [48], [49], VAE [8], [9], [10], [11], [12], [50], and transformer based models [5], [6], [7], [51], [52] use such reconstruction errors. In [50], a semi-supervised framework is introduced, employing a VAE and a one-class support vector machine for the detection of structural anomalies.…”

Section: B Anomaly Detection Using Deep Learningmentioning

confidence: 99%

Anomaly VAE-Transformer: A Deep Learning Approach for Anomaly Detection in Decentralized Finance

Song,

Seo,

Kim

2023

IEEE Access

View full text Add to dashboard Cite

DeFi, a decentralized financial service based on blockchain, not only provides innovative financial services, but also poses various risks, such as the Terra Luna crash. Therefore, anomaly detection in DeFi is necessary to ensure the safety and reliability of the DeFi ecosystem. However, this is very difficult because of the complex protocol, interaction among smart contracts, and high market volatility. In this study, we propose a novel method to effectively detect anomalies in DeFi. To the best of our knowledge, this is the first study that utilizes deep learning to detect anomalies in DeFi. We propose a deep learning model, anomaly VAE-Transformer, which combines the variational autoencoder to extract local information in the short term, and the transformer, to identify dependencies between data in the long term. Based on a deep understanding of DeFi protocols, the proposed model collects and analyzes various on-chain data of Olympus DAO, a representative DeFi protocol, for extracting features suitable for anomaly detection. Then, we demonstrate the superiority of the proposed model by analyzing four anomaly cases detected successfully by the proposed model in Olympus DAO. A malicious attack attempt and structural changes in DeFi protocols can be identified quickly using the proposed method; this is expected to help protect the assets of DeFi users and improve the safety, reliability, and transparency of the DeFi market. The dataset and codes are available at https://github.com/fialle/Anomaly-VAE-Transformer INDEX TERMS Anomaly detection, blockchain, deep learning, DeFi, Olympus DAO.

show abstract

“…Tang et al [ 25 ] combined the VAE model and deep variational information bottleneck (VIB) to monitor and identify quality-related and quality-unrelated faults. Costa et al [ 26 ] proposed a semi-supervised recurrent variational autoencoder (RVAE) method to effectively address the diagnosis of atrial fibrillation (AF). Kim et al [ 27 ] presented a fault diagnosis model to robustly process drift by modeling process drift with a variational autoencoder (VAE).…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Reliable Fault Diagnosis of Bearings Using an Optimized Stacked Variational Denoising Auto-Encoder

Yan

She

et al. 2021

Entropy

View full text Add to dashboard Cite

Variational auto-encoders (VAE) have recently been successfully applied in the intelligent fault diagnosis of rolling bearings due to its self-learning ability and robustness. However, the hyper-parameters of VAEs depend, to a significant extent, on artificial settings, which is regarded as a common and key problem in existing deep learning models. Additionally, its anti-noise capability may face a decline when VAE is used to analyze bearing vibration data under loud environmental noise. Therefore, in order to improve the anti-noise performance of the VAE model and adaptively select its parameters, this paper proposes an optimized stacked variational denoising autoencoder (OSVDAE) for the reliable fault diagnosis of bearings. Within the proposed method, a robust network, named variational denoising auto-encoder (VDAE), is, first, designed by integrating VAE and a denoising auto-encoder (DAE). Subsequently, a stacked variational denoising auto-encoder (SVDAE) architecture is constructed to extract the robust and discriminative latent fault features via stacking VDAE networks layer on layer, wherein the important parameters of the SVDAE model are automatically determined by employing a novel meta-heuristic intelligent optimizer known as the seagull optimization algorithm (SOA). Finally, the extracted latent features are imported into a softmax classifier to obtain the results of fault recognition in rolling bearings. Experiments are conducted to validate the effectiveness of the proposed method. The results of analysis indicate that the proposed method not only can achieve a high identification accuracy for different bearing health conditions, but also outperforms some representative deep learning methods.

show abstract

Semi-Supervised Recurrent Variational Autoencoder Approach for Visual Diagnosis of Atrial Fibrillation

Cited by 9 publications

References 26 publications

Exploration of Sleep Events in the Latent Space of Variational Autoencoders on a Breath-by-Breath Basis

Exploration of Sleep Events in the Latent Space of Variational Autoencoders on a Breath-by-Breath Basis

Anomaly VAE-Transformer: A Deep Learning Approach for Anomaly Detection in Decentralized Finance

Reliable Fault Diagnosis of Bearings Using an Optimized Stacked Variational Denoising Auto-Encoder

Contact Info

Product

Resources

About