• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1222-1230
• /
• 2022

As the number of signal sources with low detectability by using various modulation techniques increases, research to classify signal modulation methods is steadily progressing. Recently, a Convolutional Neural Network (CNN) deep learning technique using FFT as a preprocessing process has been proposed to improve the performance of received signal classification in signal interference or noise environments. However, due to the characteristics of the FFT in which the window is fixed, it is not possible to accurately classify the change over time of the detection signal. Therefore, in this paper, we propose a CNN model that has high resolution in the time domain and frequency domain and uses wavelet transform as a preprocessing process that can express various types of signals simultaneously in time and frequency domains. It has been demonstrated that the proposed wavelet transform method through simulation shows superior performance regardless of the SNR change in terms of accuracy and learning speed compared to the FFT transform method, and shows a greater difference, especially when the SNR is low.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.11
• /
• pp.1608-1614
• /
• 2022

As competition between universities intensifies due to the recent decrease in the number of students, it is recognized as an essential task of universities to predict students who are underperforming at an early stage and to make various efforts to prevent dropouts. For this, a high-performance model that accurately predicts student performance is essential. This paper proposes a method to improve prediction performance by removing or amplifying abnormal data in a classification prediction model for identifying underperforming students. Existing anomaly data processing methods have mainly focused on deleting or ignoring data, but this paper presents a criterion to distinguish noise from change indicators, and contributes to improving the performance of predictive models by deleting or amplifying data. In an experiment using open learning performance data for verification of the proposed method, we found a number of cases in which the proposed method can improve classification performance compared to the existing method.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.85-85
• /
• 2023

유량 측정을 위해 도섭법, 횡측선법 등의 인력에 의한 방법이 적용되고 있으나, 이는 야간 및 휴일 측정, 인력 부족 등 여러 제약으로 인해 고수위 홍수를 측정하는 데에 한계가 있다. 이를 해결하기 위해 시공간적 제약이 없는 도플러 방식 초음파유속계(Acousitc Doppler Velocity Meter, ADVM)와 자동유속관측시스템(Portable Automatic Velocity Observation System; PAVOs)이 제안되었다. 이 방법들은 교량에 설치된 장치를 통해 실시간으로 유속이 계측되어 시공간적 제약이 없으며 홍수 관리에 유용하게 사용될 수 있다. 실시간으로 계측된 유속 데이터는 오·결측 값이 발생하며 ADVM의 경우 수위-유량관계식을 활용하는 등 전처리 방법이 활용되고 있지만 전자파표면유속계를 활용한 PAVOs 데이터의 전처리 방법에 대한 연구는 부족하다. 따라서 본 연구에서는 PAVOs에서 실시간으로 계측된 유속 데이터의 전 처리 과정(Pre-processing)을 개발하였다. PAVOs를 통해 측정된 데이터는 5분 단위로 10개의 유속이 한번에 측정되며 비정상성(Non-stationary)인 특징을 가진다. 이 데이터의 전처리 과정으로 오·결측값에 대한 처리 및 보간법 적용 이후 10개 값 중 실제 유속을 판단하고 잡음제거(Denoising)를 수행하였다. 이를 강원도 홍천강에 위치한 홍천교에서 계측된 유속 데이터에 적용하였다. 그 결과 데이터의 상승부와 하강부에서 일정한 경향성을 파악할 수 있다. 이 데이터를 통해 산정한 유량과 실측 기반의 평균유속과 관계를 통해 계산한 유량을 비교해 보았을 때 낮은 편차율을 가지는 것을 확인하였다. 전 처리 된 실시간 유속 데이터를 활용한다면 최고수위가 발생하였을 경우 홍수량을 산정할 수 있을 것이다. 또한, 강우 또는 하천 공사에 의해 변동하는 수위-유량관계곡선식을 실시간으로 개발할 수 있을 것이며 이는 효과적인 홍수관리에 큰 역할을 할 수 있을 것이다.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.5
• /
• pp.422-428
• /
• 2023

Ultrafast ultrasound imaging has been applied to various imaging approaches, including shear wave elastography, ultrafast Doppler, and super-resolution imaging. However, these methods are still challenging in real-time implementation for three Dimension (3D) or portable applications because of their massive data rate required. In this paper, we proposed an adaptive quantization method that effectively reduces the data rate of large Radio Frequency (RF) data. In soft tissue, ultrasound backscatter signals require a high dynamic range, and thus typical quantization used in the current systems uses the quantization level of 10 bits to 14 bits. To alleviate the quantization level to expand the application of ultrafast ultrasound imaging, this study proposed a depth-sectional quantization approach that reduces the quantization errors. For quantitative evaluation, Field II simulations, phantom experiments, and in vivo imaging were conducted and CNR, spatial resolution, and SSIM values were compared with the proposed method and fixed quantization method. We demonstrated that our proposed method is capable of effectively reducing the quantization level down to 3-bit while minimizing the image quality degradation.

• Nuclear Engineering and Technology
• /
• v.20 no.3
• /
• pp.170-178
• /
• 1988

An automated ultrasonic flaw detection system was developed for thin-walled and short tubes such as Zircaloy-4 tubes used for cladding heavy-water reactor fuel. The system was based on the two channels immersion pulse-echo technique using 14 MHz shear wave and the specially developed helical scanning technique, in which the tube to be tested is only rotated and the small water tank with spherical focus ultrasonic transducers is translated along the tube length. The optimum angle of incidence of ultrasonic beam was 26 degrees, at which the inside and outside surface defects with the same size and direction could be detected with the same sensitivity. The maximum permissible defects in the Zircaloy-4 tubes, i.e., the longitudinal and circumferential v notches with the length of 0.76mm and 0.38mm, respectively and the depth of 0.04 mm on the inside and outside surface, could be easily detected by the system with the inspection speed of about 1 m/min and the very excellent reproducibility. The ratio of signal to noise was greater than 20 dB for the longitudinal defects and 12 dB for the circumferential defects.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.2
• /
• pp.143-149
• /
• 2022

In this paper, we evaluate the underwater frequency diversity communication performance of Selective Combination (SC) using Maximum Likelihood Estimation (MLE). In an underwater multipath frequency selective channel, destructive interference fading due to delay spread of a received signal affects the increase in error and Signal to Noise Ratio (SNR) variability of an underwater acoustic communication. Selective Combination frequency diversity using a single sensor is applied as a transmission performance improvement technique according to the frequency selectivity of a channel. In the sea experiment applying MLE for SC decision value extraction, we evaluate the performance of SC frequency diversity and MLE-SC frequency diversity. In experiment result, we confirm through experiment that the Bit Error Rate (BER) is relatively lower when the decision value extracted through MLE-SC is applied than when the SC decision value is fixed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.474-476
• /
• 2021

Glioblastoma is the most common brain malignancies arising from glial cells. Early diagnosis and treatment plan establishment are important, and cancer is diagnosed mainly through T1CE imaging through injection of a contrast agent. However, the risk of injection of gadolinium-based contrast agents is increasing recently. Region segmentation that marks cancer regions in medical images plays a key role in CAD systems, and deep neural network models for synthesizing new images are also being studied. In this study, we propose a model that simultaneously learns the generation of T1CE images and segmentation of cancer regions. The performance of the proposed model is evaluated using similarity measurements including mean square error and peak signal-to-noise ratio, and shows average result values of 21 and 39 dB.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.5
• /
• pp.109-114
• /
• 2023

In this paper, a 2-channel Image-Reject receiver using a 65-nm CMOS process is presented for Ka-band compact radars. The designed receiver consists of Low-Noise Amplifier (LNA), IQ mixer, and Analog Baseband (ABB). ABB includes a complex filter in order to suppress unwanted images, and the variable gain amplifiers (VGAs) in RF block and ABB have gain tuning range from 4.5-56 dB for wide dynamic range. The gain of the receiver is controlled by on-chip SPI controllers. The receiver has noise figure of <15 dB, OP1dB of >4 dBm, image rejection ratio of >30 dB, and channel isolation of >45 dB at the voltage gain of 36 dB, in the Ka-band target frequency. The receiver consumes 420 mA at 1.2 V supply with die area of 4000×1600 ㎛.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.3
• /
• pp.123-128
• /
• 2007

This Paper Presents new transient signal classification algorithms for underwater transient signals. In general. the ambient noise has small spectral deviation and energy variation. while a transient signal has large fluctuation. Hence to detect the transient signal, we use the spectral deviation and power variation. To classify the detected transient signal. the feature Parameters are obtained by using the Wigner-Ville distribution based eigenvalue decomposition. The correlation is then calculated between the feature vector of the detected signal and all the feature vectors of the reference templates frame-by-frame basis, and the detected transient signal is classified by the frame mapping rate among the class database.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.1
• /
• pp.32-43
• /
• 2009

In this paper, we improve the performance of cardiac disorder classification by continuous heart sound signals using automatic segmentation and extreme learning machine (ELM). The accuracy of the conventional cardiac disorder classification systems degrades because murmurs and click sounds contained in the abnormal heart sound signals cause incorrect or missing starting points of the first (S1) and the second heart pulses (S2) in the automatic segmentation stage, In order to reduce the performance degradation due to segmentation errors, we find the positions of the S1 and S2 pulses, modify them using the time difference of S1 or S2, and extract a single period of heart sound signals. We then obtain a feature vector consisting of the mel-scaled filter bank energy coefficients and the envelope of uniform-sized sub-segments from the single-period heart sound signals. To classify the heart disorders, we use ELM with a single hidden layer. In cardiac disorder classification experiments with 9 cardiac disorder categories, the proposed method shows the classification accuracy of 81.6% and achieves the highest classification accuracy among ELM, multi-layer perceptron (MLP), support vector machine (SVM), and hidden Markov model (HMM).