• The Journal of the Acoustical Society of Korea
• /
• v.43 no.1
• /
• pp.9-18
• /
• 2024

The importance of active sonar systems is emerging due to the quietness of underwater targets and the increase in ambient noise due to the increase in maritime traffic. However, the low signal-to-noise ratio of the echo signal due to multipath propagation of the signal, various clutter, ambient noise and reverberation makes it difficult to identify underwater targets using active sonar. Attempts have been made to apply data-based methods such as machine learning or deep learning to improve the performance of underwater target recognition systems, but it is difficult to collect enough data for training due to the nature of sonar datasets. Methods based on mathematical modeling have been mainly used to compensate for insufficient active sonar data. However, methodologies based on mathematical modeling have limitations in accurately simulating complex underwater phenomena. Therefore, in this paper, we propose a sonar signal synthesis method based on a deep neural network. In order to apply the neural network model to the field of sonar signal synthesis, the proposed method appropriately corrects the attention-based encoder and decoder to the sonar signal, which is the main module of the Tacotron model mainly used in the field of speech synthesis. It is possible to synthesize a signal more similar to the actual signal by training the proposed model using the dataset collected by arranging a simulated target in an actual marine environment. In order to verify the performance of the proposed method, Perceptual evaluation of audio quality test was conducted and within score difference -2.3 was shown compared to actual signal in a total of four different environments. These results prove that the active sonar signal generated by the proposed method approximates the actual signal.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.13 no.3
• /
• pp.102-109
• /
• 2009

Purpose: Flash 3D (pixon(R) method; 3D OSEM) was developed as a software program to shorten exam time and improve image quality through reconstruction, it is an image processing method that usefully be applied to nuclear medicine tomography. If perfoming brain diamox perfusion scan by reconstructing subtracted images by Flash 3D with shortened image acquisition time, there was a problem that SNR of subtracted image is lower than basal image. To increase SNR of subtracted image, we use LEAP collimators, and we emphasized on sensitivity of vessel dilatation than resolution of brain vessel. In this study, our purpose is to confirm possibility of application of LEAP collimators at brain diamox perfusion tomography, identify proper reconstruction factors by using Flash 3D. Materials and methods: (1) The evaluation of phantom: We used Hoffman 3D Brain Phantom with $^{99m}Tc$. We obtained images by LEAP and LEHR collimators (diamox image) and after 6 hours (the half life of $^{99m}Tc$: 6 hours), we use obtained second image (basal image) by same method. Also, we acquired SNR and ratio of white matters/gray matters of each basal image and subtracted image. (2) The evaluation of patient's image: We quantitatively analyzed patients who were examined by LEAP collimators then was classified as a normal group and who were examined by LEHR collimators then was classified as a normal group from 2008. 05 to 2009. 01. We evaluate the results from phantom by substituting factors. We used one-day protocol and injected $^{99m}Tc$-ECD 925 MBq at both basal image acquisition and diamox image acquisition. Results: (1) The evaluation of phantom: After measuring counts from each detector, at basal image 41~46 kcount, stress image 79~90 kcount, subtraction image 40~47 kcount were detected. LEAP was about 102~113 kcount at basal image, 188~210 kcount at stress image and 94~103 at subtraction image kcount were detected. The SNR of LEHR subtraction image was decreased than LEHR basal image about 37%, the SNR of LEAP subtraction image was decreased than LEAP basal image about 17%. The ratio of gray matter versus white matter is 2.2:1 at LEHR basal image and 1.9:1 at subtraction, and at LEAP basal image was 2.4:1 and subtraction image was 2:1. (2) The evaluation of patient's image: the counts acquired by LEHR collimators are about 40~60 kcounts at basal image, and 80~100 kcount at stress image. It was proper to set FWHM as 7 mm at basal and stress image and 11mm at subtraction image. LEAP was about 80~100 kcount at basal image and 180~200 kcount at stress image. LEAP images could reduce blurring by setting FWHM as 5 mm at basal and stress images and 7 mm at subtraction image. At basal and stress image, LEHR image was superior than LEAP image. But in case of subtraction image like a phantom experiment, it showed rough image because SNR of LEHR image was decreased. On the other hand, in case of subtraction LEAP image was better than LEHR image in SNR and sensitivity. In all LEHR and LEAP collimator images, proper subset and iteration frequency was 8 times. Conclusions: We could archive more clear and high SNR subtraction image by using proper filter with LEAP collimator. In case of applying one day protocol and reconstructing by Flash 3D, we could consider application of LEAP collimator to acquire better subtraction image.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.107-122
• /
• 2017

Volatility in the stock market returns is a measure of investment risk. It plays a central role in portfolio optimization, asset pricing and risk management as well as most theoretical financial models. Engle(1982) presented a pioneering paper on the stock market volatility that explains the time-variant characteristics embedded in the stock market return volatility. His model, Autoregressive Conditional Heteroscedasticity (ARCH), was generalized by Bollerslev(1986) as GARCH models. Empirical studies have shown that GARCH models describes well the fat-tailed return distributions and volatility clustering phenomenon appearing in stock prices. The parameters of the GARCH models are generally estimated by the maximum likelihood estimation (MLE) based on the standard normal density. But, since 1987 Black Monday, the stock market prices have become very complex and shown a lot of noisy terms. Recent studies start to apply artificial intelligent approach in estimating the GARCH parameters as a substitute for the MLE. The paper presents SVR-based GARCH process and compares with MLE-based GARCH process to estimate the parameters of GARCH models which are known to well forecast stock market volatility. Kernel functions used in SVR estimation process are linear, polynomial and radial. We analyzed the suggested models with KOSPI 200 Index. This index is constituted by 200 blue chip stocks listed in the Korea Exchange. We sampled KOSPI 200 daily closing values from 2010 to 2015. Sample observations are 1487 days. We used 1187 days to train the suggested GARCH models and the remaining 300 days were used as testing data. First, symmetric and asymmetric GARCH models are estimated by MLE. We forecasted KOSPI 200 Index return volatility and the statistical metric MSE shows better results for the asymmetric GARCH models such as E-GARCH or GJR-GARCH. This is consistent with the documented non-normal return distribution characteristics with fat-tail and leptokurtosis. Compared with MLE estimation process, SVR-based GARCH models outperform the MLE methodology in KOSPI 200 Index return volatility forecasting. Polynomial kernel function shows exceptionally lower forecasting accuracy. We suggested Intelligent Volatility Trading System (IVTS) that utilizes the forecasted volatility results. IVTS entry rules are as follows. If forecasted tomorrow volatility will increase then buy volatility today. If forecasted tomorrow volatility will decrease then sell volatility today. If forecasted volatility direction does not change we hold the existing buy or sell positions. IVTS is assumed to buy and sell historical volatility values. This is somewhat unreal because we cannot trade historical volatility values themselves. But our simulation results are meaningful since the Korea Exchange introduced volatility futures contract that traders can trade since November 2014. The trading systems with SVR-based GARCH models show higher returns than MLE-based GARCH in the testing period. And trading profitable percentages of MLE-based GARCH IVTS models range from 47.5% to 50.0%, trading profitable percentages of SVR-based GARCH IVTS models range from 51.8% to 59.7%. MLE-based symmetric S-GARCH shows +150.2% return and SVR-based symmetric S-GARCH shows +526.4% return. MLE-based asymmetric E-GARCH shows -72% return and SVR-based asymmetric E-GARCH shows +245.6% return. MLE-based asymmetric GJR-GARCH shows -98.7% return and SVR-based asymmetric GJR-GARCH shows +126.3% return. Linear kernel function shows higher trading returns than radial kernel function. Best performance of SVR-based IVTS is +526.4% and that of MLE-based IVTS is +150.2%. SVR-based GARCH IVTS shows higher trading frequency. This study has some limitations. Our models are solely based on SVR. Other artificial intelligence models are needed to search for better performance. We do not consider costs incurred in the trading process including brokerage commissions and slippage costs. IVTS trading performance is unreal since we use historical volatility values as trading objects. The exact forecasting of stock market volatility is essential in the real trading as well as asset pricing models. Further studies on other machine learning-based GARCH models can give better information for the stock market investors.