• Imaging Science in Dentistry
• /
• v.49 no.2
• /
• pp.131-137
• /
• 2019

Purpose: This study was designed to investigate the effects of voxel size, the oversampling technique, and the direction and area of measurement on modulation transfer function (MTF) values to identify the optimal method of MTF measurement. Materials and Methods: Images of the wire inserts of the SedentexCT IQ phantom were acquired, and MTF values were calculated under different conditions(voxel size of 0.1, 0.2, and 0.3 mm; 5 oversampling techniques; simulated pixel location errors; and different directions and areas of measurement). The differences in the MTF values across various conditions were evaluated. Results: The MTF 10 values showed smaller standard deviations than the MTF 50 values. Stable and accurate MTF values were obtained in the 0.1-mm voxel images. In the 0.3-mm voxel images, oversampling techniques of 11 lines or more did not show significant differences in MTF values depending on the presence of simulated location errors. MTF 10 values showed significant differences according to the direction and area of the measurement. Conclusion: To measure more accurate and stable MTF values, it is better to measure MTF 10 values in small-voxel images. In large-voxel images, the proper oversampling technique is required. MTF values from the radial and tangential directions may be different, and MTF values vary depending on the measured area.

• Journal of IKEEE
• /
• v.10 no.1 s.18
• /
• pp.10-15
• /
• 2006

In this paper, a clock and data recovery (CDR) circuit for a serial link with a half rate 4x oversampling phase and frequency detector structure without a reference clock is described. The phase detector (PD) and frequency detector (FD)are designed by 4X oversampling method. The PD, which uses bang-bang method, finds the phase error by generating four up/down signal and the FD, which uses the rotational method, finds the frequency error by generating up/down signal made by the PD output. And the six signals of the PD and the FD control an amount of current that flows through the charge pump. The VCO composed of four differential buffer stages generates eight differential clocks. Proposed circuit is designed using the 0.18um CMOS technology and operating voltage is 1.8V. With a 4X oversampling PD and FD technique, tracking range of 24% at 3.125Gbps is achieved.

• The Korean Journal of Applied Statistics
• /
• v.35 no.2
• /
• pp.177-188
• /
• 2022

The support vector machine (SVM) has been successfully applied to various classification areas with a high level of classification accuracy. However, it is infeasible to use the SVM in analyzing massive data because of its significant computational problems. When analyzing imbalanced data with different class sizes, furthermore, the classification accuracy of SVM in minority class may drop significantly because its classifier could be biased toward the majority class. To overcome such a problem, we propose the DOC-SVM method, which uses divide-oversampling and conquers techniques. The proposed DOC-SVM divides the majority class into a few subsets and applies an oversampling technique to the minority class in order to produce the balanced subsets. And then the DOC-SVM obtains the final classifier by aggregating all SVM classifiers obtained from the balanced subsets. Simulation studies are presented to demonstrate the satisfactory performance of the proposed method.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.2
• /
• pp.201-211
• /
• 2022

According to the recent change in the cybersecurity paradigm, research on anomaly detection methods using machine learning and deep learning techniques, which are AI implementation technologies, is increasing. In this study, a comparative study on data preprocessing techniques that can improve the anomaly detection performance of a GRU (Gated Recurrent Unit) neural network-based intrusion detection model using NGIDS-DS (Next Generation IDS Dataset), an open dataset, was conducted. In addition, in order to solve the class imbalance problem according to the ratio of normal data and attack data, the detection performance according to the oversampling ratio was compared and analyzed using the oversampling technique applied with DCGAN (Deep Convolutional Generative Adversarial Networks). As a result of the experiment, the method preprocessed using the Doc2Vec algorithm for system call feature and process execution path feature showed good performance, and in the case of oversampling performance, when DCGAN was used, improved detection performance was shown.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.233-239
• /
• 2022

The injection molding process is a process in which thermoplastic resin is heated and made into a fluid state, injected under pressure into the cavity of a mold, and then cooled in the mold to produce a product identical to the shape of the cavity of the mold. It is a process that enables mass production and complex shapes, and various factors such as resin temperature, mold temperature, injection speed, and pressure affect product quality. In the data collected at the manufacturing site, there is a lot of data related to good products, but there is little data related to defective products, resulting in serious data imbalance. In order to efficiently solve this data imbalance, undersampling, oversampling, and composite sampling are usally applied. In this study, oversampling techniques such as random oversampling (ROS), minority class oversampling (SMOTE), ADASYN(Adaptive Synthetic Sampling), etc., which amplify data of the minority class by the majority class, and complex sampling using both undersampling and oversampling, are applied. For composite sampling, SMOTE+ENN and SMOTE+Tomek were used. Artificial neural network techniques is used to predict product quality. Especially, MLP and RNN are applied as artificial neural network techniques, and optimization of various parameters for MLP and RNN is required. In this study, we proposed an SA technique that optimizes the choice of the sampling method, the ratio of minority classes for sampling method, the batch size and the number of hidden layer units for parameters of MLP and RNN. The existing sampling methods and the proposed SA method were compared using accuracy, precision, recall, and F1 Score to prove the superiority of the proposed method.

• Proceedings of the KIEE Conference
• /
• 1991.07a
• /
• pp.861-865
• /
• 1991

Sigma delta modulation has been the preferred technique for oversampling conversion. In this paper we present the basic principles of oversampled sigma-delta Converters. Basic operation and theory behind sigma-delta modulation is reviewed. The different structures of the sigma-delta converters are described and the concepts of designing modulators and digital filters are discussed. The latest designs are also reviewed.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.24 no.5
• /
• pp.566-573
• /
• 2013

Inverse synthetic aperture radar(ISAR) images have been widely used in non-cooperative target recognition(NCTR). One of the most important issues in ISAR imaging is the improvement of the image smeared by target motion. In this paper, we propose the discrete Gabor representation(DGR) in an oversampling scheme for efficient acquisition of high-quality ISAR images. The DGR compartmentally assigns the Gabor coefficients to unit cells of the time-frequency grid related to the given Gabor logons. Thus, it can show an excellent time-frequency concentration and effectively discriminates the Doppler components from point-scatterers. The simulation results demonstrated that the DGR not only obtained high-quality ISAR images but also retained computational efficiency.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.1C
• /
• pp.14-23
• /
• 2003

This thesis proposes a sigma-delta modulator architecture with 2 Ms/s data rate and 12 bit resolution. A sigma-delta modulate has the features of oversampling and noise shaping. With these features, it can be connected with low resolution A/D converter to achieve higher resolution A/D converter. Most previous researches have been concentrated on high resolution but low data rate applications, e.g. audio applications. But, in order to be applied to various applications such as wireless data communication, researches on sigma-delta modulator architecture for higher data rate are required. The proposed sigma-delta modulator architecture has the sampling rate of 16 times Nyquist rate to achieve high data rate, and consists of a cascade of two 2nd order sigma-delta modulator to get relatively high resolution. The experimental result shows that the proposed architecture achieves 12-bit resolution at 2 Ms/s data rate.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.10C
• /
• pp.1378-1386
• /
• 2004

In this paper, we propose an OFDM scheme to increase the BER performance. The proposed OFDM scheme makes the baseband OFDM signal by using the oversampled OFDM signal values which are obtained by inserting N(=2$\^$k/) zeros and carrying out 2N point IFFT. In the demodulation part, the sampling operation for A/D conversion is carried out with the 2 times high sampling speed. 2 N point FFT is carried out for the data demodulation. In this paper, we show, with the mathematical method and the computer simulation, that the SNR of the proposed OFDM scheme is 3 dB higher than that of the conventional OFDM in the same AWGN channel conditions given.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.37-42
• /
• 2019

In this paper, we explore the details of three classic data augmentation methods and two generative model based oversampling methods. The three classic data augmentation methods are random sampling (RANDOM), Synthetic Minority Over-sampling Technique (SMOTE), and Adaptive Synthetic Sampling (ADASYN). The two generative model based oversampling methods are Conditional Generative Adversarial Network (CGAN) and Wasserstein Generative Adversarial Network (WGAN). In imbalanced data, the whole instances are divided into majority class and minority class, where majority class occupies most of the instances in the training set and minority class only includes a few instances. Generative models have their own advantages when they are used to generate more plausible samples referring to the distribution of the minority class. We also adopt CGAN to compare the data augmentation performance with other methods. The experimental results show that WGAN-based oversampling technique is more stable than other approaches (RANDOM, SMOTE, ADASYN and CGAN) even with the very limited training datasets. However, when the imbalanced ratio is too small, generative model based approaches cannot achieve satisfying performance than the conventional data augmentation techniques. These results suggest us one of future research directions.