• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.6B
• /
• pp.1106-1113
• /
• 2000

In this, paper, a DFT based polyphase filter bank for the fractional ratio oversampling is proposed. Proper fractional oversampling ratio gives lower aliasing than the critical sampling and, at the same time, lower computational load than the integer ratio oversampling. In addition, filter bank design becomes easier by the reduced aliasing effect of fractional ratio oversampling. Proposed fractional ratio oaversampling polyphase structure is applied to a subband adaptive filter for acoustic echo cancellation where long adaptive filter are ofter required. Echo cancellation results show that fractional ratio oversampling gives comparable performance to the integer ratio oversampling with less computational load.

• Journal of Digital Contents Society
• /
• v.10 no.2
• /
• pp.189-198
• /
• 2009

In this paper, we propose a method to improve the performance of orthogonal frequency division multiplexing (OFDM) receivers by using oversampling the received signals. Demodulation of the received OFDM signals is to detect the amplitude and phase components of the subcarriers. From the oversampled OFDM signals, we can get redundant informations in frequency domain for the data, which are different in phase but the same in amplitude. By using these properties, we can obtain signal to noise ratio (SNR) gain by the oversampling ratio compared to the receivers which sampled with symbol rate. In this paper, we propose oversampled receivers whose oversampling ratio is expanded from integer to general rational number. Through computer simulations, we show the validity of the proposed methods by comparing the performance of the receivers with nonideal band-limiting filters.

• Journal of the Korea Convergence Society
• /
• v.12 no.1
• /
• pp.49-55
• /
• 2021

Recently, with the development of database, it is possible to store a lot of data generated in finance, security, and networks. These data are being analyzed through classifiers based on machine learning. The main problem at this time is data imbalance. When we train imbalanced data, it may happen that classification accuracy is degraded due to over-fitting with majority class data. To overcome the problem of data imbalance, oversampling strategy that increases the quantity of data of minority class data is widely used. It requires to tuning process about suitable method and parameters for data distribution. To improve the process, In this study, we propose a strategy to explore and optimize oversampling combinations and ratio based on various methods such as synthetic minority oversampling technique and generative adversarial networks through genetic algorithms. After sampling credit card fraud detection which is a representative case of data imbalance, with the proposed strategy and single oversampling strategies, we compare the performance of trained classifiers with each data. As a result, a strategy that is optimized by exploring for ratio of each method with genetic algorithms was superior to previous strategies.

• 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.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.5
• /
• pp.808-815
• /
• 1990

This paper treats with the design method for the single loop oversampled Sigma-Delta A/D converter with one delay and the digital integrator. Such an integrator was kgenerated by means of the bilinear transform of the analog integrator. The frequency spectrums of the quantizer and the decimator output signal are evaluated by FFT respectively. With the performance evaluation system, the values of SNR are obtained versus the input sinusoidal signal amplitude, frequency, the oversampling ratio, the DC-input level, the loop gain and the limitting value of the integrator. As compared with existing results, values of SNR versus the input signal amplitude and the oversampling ratio for the suggested system are about 6dB higher then previously reported results respectively. Furthermore, this approach achieves an about 60dB input dynamic range.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.30A no.12
• /
• pp.98-107
• /
• 1993

This paper describes a design of a multi-bit oversampling noise-shaping D/A converter which achieves a resolution of 12 bits using oversampling technique. In the architecture the essential block which determines the whole accuracy is the analog internal D/A converter, and the designed charge-integration internal D/A converter adopts a differential structure in order to minimize the reduction of the resolution due to process variation. As the proposed circuit is driven by signal clocks which contains the information of the data variation from the noise-shaping coder, it minimizes the disadvantage of a charge-integration circuit in the time axis. In order to verify the circuit, it was integrated with the active area of 950$\times$650${\mu}m^{2}$ in a double metal 1.5-$\mu$m CMOS process, and testified that it can achieve a S/N ratio of 75 dB and a S/(N+D) ratio of 60 dB for the signal bandwidth of 9.6 kHz by the measurement with a spectrum analyzer.

• 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.

• Proceedings of the IEEK Conference
• /
• 2000.11b
• /
• pp.152-155
• /
• 2000

Oversampling modulators based on high-order sigma-delta modulation provide an effective means of achieving high-resolution A/D conversion in a VLSI technology. Because high-order noise shaping great]y reduces the quantization noise in the signal band. This paper introduces a third-order cascaded sigma-delta modulator that is stable for large input level. Modulator was simulated 3.3V single power supply voltage in 0.65$\mu\textrm{m}$ CMOS technology. It achieves 80㏈ SNR for a 20㎑ input signal bandwidth. A lock frequency is 3㎒ that is 80 oversampling ratio.

• Journal of Sensor Science and Technology
• /
• v.26 no.5
• /
• pp.348-352
• /
• 2017

In this paper, we propose a high resolution A/D converter for a sensor interface that processes low frequency AC signals. A 6b SAR ADC with low power consumption and a 11b incremental ADC with high resolution are combined together to perform 15b resolution. Conventional hybrid ADC has a disadvantage that it can convert t only DC signal, but in this paper, it is possible to convert data to AC signal by increasing input range of incremental ADC. The decimation filter is implemented on-chip. The designed Hybrid ADC operates at supply voltage of 1.8V and consumes the current of 6.98uA. The OSR (oversampling ratio) is 90. And SFDR, SNDR, ENOB and FoMs are 96.59dB, 88.47dB, 14.4-bit and 139.5dB, respectively.