Convolutional Autoencoder Based Feature Extraction in Radar Data Analysis

Lee, Hansoo; Kim, Jonggeun; Kim, Baekcheon; Kim, Sungshin

doi:10.1109/scis-isis.2018.00023

Cited by 15 publications

(10 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In another related work, Lee et al [33] use a CAE to perform feature extraction and dimensionality reduction for radar data analysis. The aim of their study is to obtain a Fig.…”

Section: Related Workmentioning

confidence: 99%

The effect of feature extraction and data sampling on credit card fraud detection

2023

View full text Add to dashboard Cite

Training a machine learning algorithm on a class-imbalanced dataset can be a difficult task, a process that could prove even more challenging under conditions of high dimensionality. Feature extraction and data sampling are among the most popular preprocessing techniques. Feature extraction is used to derive a richer set of reduced dataset features, while data sampling is used to mitigate class imbalance. In this paper, we investigate these two preprocessing techniques, using a credit card fraud dataset and four ensemble classifiers (Random Forest, CatBoost, LightGBM, and XGBoost). Within the context of feature extraction, the Principal Component Analysis (PCA) and Convolutional Autoencoder (CAE) methods are evaluated. With regard to data sampling, the Random Undersampling (RUS), Synthetic Minority Oversampling Technique (SMOTE), and SMOTE Tomek methods are evaluated. The F1 score and Area Under the Receiver Operating Characteristic Curve (AUC) metrics serve as measures of classification performance. Our results show that the implementation of the RUS method followed by the CAE method leads to the best performance for credit card fraud detection.

show abstract

“…In another related work, Lee et al [33] use a CAE to perform feature extraction and dimensionality reduction for radar data analysis. The aim of their study is to obtain a Fig.…”

Section: Related Workmentioning

confidence: 99%

The effect of feature extraction and data sampling on credit card fraud detection

2023

View full text Add to dashboard Cite

show abstract

“…In [16] Benamara et al for example applied convolutional NNs to extract human emotions based on facial images. Autoencoders like in [17][18][19] are able to learn important features of the input data by first encoding the input data to a lower dimensional space and then decoding it to reconstruct the input. While the unsupervised extraction of patterns from image or video data is a common task for Convolutional Autoencoders (CAE), the pattern discovery in time series is an underrepresented problem.…”

Section: Related Workmentioning

confidence: 99%

Pattern discovery in time series using autoencoder in comparison to nonlearning approaches

Noering

Schroeder

Jonas

et al. 2021

ICA

View full text Add to dashboard Cite

In technical systems the analysis of similar situations is a promising technique to gain information about the system’s state, its health or wearing. Very often, situations cannot be defined but need to be discovered as recurrent patterns within time series data of the system under consideration. This paper addresses the assessment of different approaches to discover frequent variable-length patterns in time series. Because of the success of artificial neural networks (NN) in various research fields, a special issue of this work is the applicability of NNs to the problem of pattern discovery in time series. Therefore we applied and adapted a Convolutional Autoencoder and compared it to classical nonlearning approaches based on Dynamic Time Warping, based on time series discretization as well as based on the Matrix Profile. These nonlearning approaches have also been adapted, to fulfill our requirements like the discovery of potentially time scaled patterns from noisy time series. We showed the performance (quality, computing time, effort of parametrization) of those approaches in an extensive test with synthetic data sets. Additionally the transferability to other data sets is tested by using real life vehicle data. We demonstrated the ability of Convolutional Autoencoders to discover patterns in an unsupervised way. Furthermore the tests showed, that the Autoencoder is able to discover patterns with a similar quality like classical nonlearning approaches.

show abstract

“…There are three methods for data balancing, 18 which are called data-level methods, [19][20][21][22] algorithm-level methods, [23][24][25][26][27][28] and hybrid approaches. [29][30][31][32][33] Ji and Lee 34 proposed generative adversarial networks (GAN) to improve the CNN-based classifier performance.…”

Section: Related Workmentioning

confidence: 99%

“…Many models have been proposed to deal with data imbalance problems. 16,17,[31][32][33][34] The CAE model is used for data generation purposes to solve the data imbalance issue in this study. The CAE model is an unsupervised DL model.…”

Section: Data Balancing With Caementioning

confidence: 99%

See 1 more Smart Citation

A Deep convolutional neural network with residual blocks for wafer map defect pattern recognition

Wang

Chou

Amogne

2021

Quality & Reliability Eng

View full text Add to dashboard Cite

Different deep convolution neural network (DCNN) models have been proposed for wafer map pattern identification and classification tasks in previous studies. However, factors such as input image resolution effect on the classification performance of the proposed models and class imbalance in the training set after splitting the data into training and test sets have not been considered in the previous studies. We propose a DCNN model with residual blocks, called the Opt-ResDCNN model, for wafer map defect pattern classification by considering 26 × 26, 64 × 64, 96 × 96, and 256 × 256 input images and class imbalance issues. The model with a balance function can improve the performance.We compare the proposed model with the published defect pattern classification models in terms of accuracy, precision, recall, and F1 value. Using a publicly available wafer map data set (WM-811K), the proposed method on the four different resolutions can obtain an excellent average accuracy, precision, recall, and F1 score. Regarding accuracy, the proposed model results are 99.90%, 99.86%, 90.28%, 98.88%, respectively. These results are better than the published papers.

show abstract

Convolutional Autoencoder Based Feature Extraction in Radar Data Analysis

Cited by 15 publications

References 6 publications

The effect of feature extraction and data sampling on credit card fraud detection

The effect of feature extraction and data sampling on credit card fraud detection

Pattern discovery in time series using autoencoder in comparison to nonlearning approaches

A Deep convolutional neural network with residual blocks for wafer map defect pattern recognition

Contact Info

Product

Resources

About