Search Results

Now showing 1 - 4 of 4

Some of the metrics are blocked by your
consent settings
LSCR: Latent Space Coordination Relation for Anomaly Prediction
(2023-01-01)
Chalongvorachai, Thasorn
;
Woraratpanya, Kuntpong
Anomaly time series prediction is a crucial yet challenging task in real-world systems. Existing techniques often require a substantial amount of data to achieve satisfactory performance, posing a significant challenge as anomaly data is scarce and difficult to obtain. Despite attempts to address this issue using traditional machine learning techniques, their effectiveness remains limited, resulting in performance degradation or costly trade-offs. Therefore, in this paper, we propose a novel approach called Latent Space Coordination Relation for Anomaly Prediction to overcome these challenges. Our framework leverages the power of the Variational Autoencoder (VAE) and learns the coordination relations of points in the latent space to detect anomalies. By exploiting the latent space, our method enables effective learning and prediction of anomalies. Additionally, the decoder of the VAE aids in restoring the data, further improving the accuracy of anomaly detection. Experimental results demonstrate that our approach outperforms baseline models when training data is limited. The predicted anomalous signals exhibit lower error rates, highlighting the efficacy of our method. This improvement is attributed to the utilization of the latent space for learning and assisting in anomaly prediction, along with the signal restoration capabilities of the decoder.
Some of the metrics are blocked by your
consent settings
Exploring the i3DVAE-LSTM Framework for Generating Exceptionally Rare Anomaly Signals
(2023-01-01)
Kaewkiriya, Thongchai
;
Woraratpanya, Kuntpong
In the era of data-driven approaches, ensuring data quality is crucial for developing effective machine learning and deep learning models. While data augmentation is commonly used to increase the sample size, it does not guarantee data quality. Data generation goes beyond augmentation by incorporating additional steps to ensure high-quality output samples. This technique is particularly valuable for anomaly classification tasks with limited training samples. A recent study introduced a 3DVAE-LSTM (3-Dimensional Variational Autoencoders-Long Short-Term Memory) approach for generating extremely rare case signals. Although this framework synthesized samples for training deep learning models, it faced challenges with long sequential data. To address this, the authors proposed an improved version called i3DVAE-LSTM (Improvement of 3-Dimensional Variational Autoencoders-Long Short-Term Memory) and presented the evaluation of the i3DVAE-LSTM framework. The proposed framework adopts a divide-and-conquer technique, splitting long sequence data into smaller fragments to enhance the quality of generated samples, which are then concatenated together. Experimental results demonstrated that classification models trained with data generated by i3DVAE-LSTM outperformed baselines in all aspects.
Some of the metrics are blocked by your
consent settings
3DVAE-LSTM for Extremely Rare Anomaly Signal Generation
(2022-01-01)
Kaewkiriya, Thongchai
;
Woraratpanya, Kuntpong
To overcome the uncontrolled quality output problem of data augmentation, many data generation frameworks have been proposed recently. The main concept of the data generation is for ensuring the quality of the output samples which maintain the original characteristics and highly provide the diversity of data. The benefit of this concept is improving the performance of deep learning tasks that suffer from the lack of available training samples, such as anomaly classification. Recently, 3D variational autoencoder for extremely rare case signal generation (3DVAE-ERSG) was introduced. This framework achieves the best synthesis samples for multi-class classification deep learning training. However, it is not so well applicable to sequential data. Therefore, this paper proposed a 3DVAE-LSTM framework. The new framework was replaced a VAE's feed-forward neural network with a long short-term memory (LSTM) neural network that works well with time-series signals. The experimental results show that the classification models trained with data generated by 3DVAE-LSTM have better performance than 3DVAE-ERSG in every aspect.
Some of the metrics are blocked by your
consent settings
3DVAE-ERSG: 3D Variational Autoencoder for Extremely Rare Signal Generation
(2021-01-01)
Chalongvorachai, Thasorn
;
Woraratpanya, Kuntpong
Data generation is not data augmentation. Our data generation is a new technique that can synthesize a dataset from a very small number of samples and ensure the quality of its outputs. Recently, this concept has been proposed and applied in a framework called Data Generation Framework for Extremely Rare Case Signals (DGERS) to solve a problem of a limited number of anomaly signals. With the power of DGERS consisting of principal components, including various data augmentation techniques on diverse domains, Signal Fragment Assembler (SFA), Variational Autoencoder (VAE), Data Picker (DP), and Quality Classifier (QC), the generated dataset had the good quality, when evaluated with a performance tester. Nevertheless, the DGERS has not used the full potential of VAE yet. The previous framework used the VAE latent space in only two dimensions. To use a higher potential of VAE, this paper proposed a 3D Variational Autoencoder for Extremely Rare Signal Generation (3DVAE-ERSG). This method increases the dimension of the latent space from 2D to 3D. We also proposed the 3D Data Picker for data exploration. To test this hypothesis, we experimented with the same datasets that the DGERS method was tested before. The results show that our 3DVAE-ERSG can outperform the baseline in most cases.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results