• Journal of information and communication convergence engineering
• /
• 제21권1호
• /
• pp.98-102
• /
• 2023

This paper presents a study on how augmenting semi-synthetic image data improves the performance of human detection algorithms. In the field of object detection, securing a high-quality data set plays the most important role in training deep learning algorithms. Recently, the acquisition of real image data has become time consuming and expensive; therefore, research using synthesized data has been conducted. Synthetic data haves the advantage of being able to generate a vast amount of data and accurately label it. However, the utility of synthetic data in human detection has not yet been demonstrated. Therefore, we use You Only Look Once (YOLO), the object detection algorithm most commonly used, to experimentally analyze the effect of synthetic data augmentation on human detection performance. As a result of training YOLO using the Penn-Fudan dataset, it was shown that the YOLO network model trained on a dataset augmented with synthetic data provided high-performance results in terms of the Precision-Recall Curve and F1-Confidence Curve.

• 상하수도학회지
• /
• 제24권2호
• /
• pp.231-236
• /
• 2010

A compressible media filtration process with synthetic fiber media was studied for combined sewer overflows (CSOs) treatment. Since the operation performance of fiber media filtration was dependent on the pattern of CSOs, the flow rate of CSOs was investigated and it was characterized by a big fluctuation. Thus, in this study, the fiber media filtration process was tested with wide range of filtration velocity. The removal efficiency was proportion to the increase in compressibility. As the filtration velocity was increased, the treatment efficiency was decreased and consequently leveled off when the velocity exceeded 750 $m^3/m^2$/d. An exponential equation was introduced to express the relationship between the removal efficiency and up-flow velocity. At columm test, six repetition of filtration and backwash cycle did not after the filtering velocity under the constant pressure condition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권7호
• /
• pp.1858-1872
• /
• 2023

With the advance of radar technologies, the availability of synthetic aperture radar (SAR) images increases. To improve application of SAR images, a management system for SAR images is proposed in this paper. The system provides trainable land cover classification module and display of SAR images on the map. Users of the system can create their own classifier with their data, and obtain the classified results of newly captured SAR images by applying the classifier to the images. The classifier is based on convolutional neural network structure. Since there are differences among SAR images depending on capturing method and devices, a fixed classifier cannot cover all types of SAR land cover classification problems. Thus, it is adopted to create each user's classifier. In our experiments, it is shown that the module works well with two different SAR datasets. With this system, SAR data and land cover classification results are managed and easily displayed.

• 상하수도학회지
• /
• 제19권1호
• /
• pp.3-7
• /
• 2005

In the present study a feasibility of a novel filtration process using synthetic for secondary effluent reclamation was investigated. Polyurethane was chosen as a filter medium among tested three media. Compressibility and up-flow velocity were changed to determine the optimum operation for the system. An equation was introduced to express the relationship between the removal efficiency and up-flow velocity. In pilot study, the synthetic medium filtration with compression showed very stable effluent quality without clogging trouble, though the system operated with 3 times higher filtration rate and much longer backwashing interval than conventional systems.

• 한국환경과학회지
• /
• 제22권7호
• /
• pp.801-810
• /
• 2013

To improve the physical and chemical properties of the soil and increasing water-retaining property of the soil, Superabsorbent synthetic polymeric materials have been used. The experiment carried out from April to July 2012 after the influence evaluation of Superabsorbent synthetic polymeric materials to vines plant. The result shows that the study of Hedera japonica Tobler, the growth and the survival rates rank as media > hydroponic > superabsorbent synthetic polymers, and the growth and the survival rates are considerably pessimistic in the experiment of hydroponic and superabsorbent synthetic polymers. In the study of Trachelospermum asiaticum var. intermedium, the growth and the survival rates rank as hydroponic > media > superabsorbent synthetic polymers, the difference between the experiment of hydroponic and is very small and the survival rates are not very good in the experiment of superabsorbent synthetic polymers. In the study of Euonymus fortunei var. radicans Rehder,it is insignificantly difference among the different of planting based. Judging from these results, the differences are depending on the species of plants. The thesis holds that the characteristics of plant should be considered in plant cultivation and soil improvement in the future, and it is desirable to use the appropriate mixing ratio of soil in soil improvement as well.

• 한국수산과학회지
• /
• 제28권6호
• /
• pp.812-813
• /
• 1995

Lactococcal cells are nutritionally fastidious and thus, generally cultured either in milk or M17 medium (Terzaghi and Sandine, 1975). In this study, Lactococcus cremoris wild-type (KH) and its less­proteolytic mutant (KHA1) cells were grown on the M17 medium or with modified M17 medium by replicated parallel experiments. The modified M17 medium had the same composition as M17 medium, except that lactose was replaced by glucose. Analyses of culture-broth samples, in which the M17 and the modified M17 media were used, were conducted by high-performance liquid chromatography (HPLC). But, working with these media created noisy problems in analyses of samples. Therefore, a new semi-synthetic medium was developed on the basis of nutritional requirements (Morishita et al., 1981). The composition of the semi-synthetic medium determined on the basis of the nutritional requirements and the composition of milk, is presented in Table 1. The composition of M17 medium is also presented and compared in the table. L. cremoris KH and KHA1 cells were grown again on the new synthetic medium containing glucose or lactose. The broth samples were then drawn and analyzed by HPLC. Clearer separations of fermented products were achieved from the new medium than those with the M17 and the modified M17 media. In comparison with the M17 or the modified M17 media, growth on the new medium was good (Kim et al, 1993). Additional fermentations were also carried out at a controlled pH of 7.0, where enhanced growth of lactococcal cells was obtained. In the fermentations, samples were also analyzed for the concentrations of sugar and lactic acid. The results showed that the new synthetic medium was as good as or better than the M 17 and the modified M 17 media. This is because casein hydrolysate in the synthetic medium provided a ready supply of amino acids and peptides for L. cremoris KH and KHA1 cells. Lactic acid bacteria (LAB) including Lactococcal cells have been known to be an effective means of preserving foods, at the same time as giving particular tastes in fields of dairy products. LAB also have always occupied an important place in the technology of sea products, and marine LAB have known to be present in traditional fermented products (Ohhira et al, 1988). To apply the new synthetic medium to marine LAB, two different LAB were isolated from pickled anchovy and pollacks caviar and were grown on the new media in which various concentrations of NaCl $(3, 5, 7 and 10\%)$ added. They were also grown on the medium solution in natural seawater $(35\%o\;salinity)$ and on the solution of natural seawater itself, too. As seen in Fig. 1, Marine LAB were grown best on the synthetic medium solution in natural seawater and the higher concentrations of NaCl were added to the medium, the longer lag-phase of growth profile appeared. Marine LAB in natural seawater were not grown well. From these results, the synthetic medium seems good to cultivate cells which are essential to get salted fish aged. In this study, it showed that the new synthetic medium provided adequate nutrition for L. cremoris KH and KHA1 cells, which have been used as cheese starters (Stadhouders et al, 1988). Using this new medium, the acid production capability of starter cultures could be also measured quantitatively. Thus, this new medium was inferior to the M17 or the modified M17 medium in culturing the cheese starters and in measuring fermentation characteristics of the starter cells. Moreover, this new medium found to be good for selected and well-identified marine LAB which are used in rapid fermentations of low-salted fish.

• Journal of electromagnetic engineering and science
• /
• 제14권4호
• /
• pp.405-410
• /
• 2014

In this paper, we compare the quality of images reconstructed by a conventional delayed-sum (DS) algorithm and radiation pattern-based DS algorithm. In order to evaluate the quality of images, we apply the target-to-clutter ratio (TCR), which is commonly used in synthetic aperture radar (SAR) image assessment. The radiation pattern-based DS algorithm enhances the TCR of the image by focusing the target signals and preventing contamination of the radar scene. We first consider synthetic data obtained through GprMax2D/3D, a finite-difference time-domain (FDTD) forward solver. Experimental data of a 2-GHz bandwidth stepped-frequency signal are collected using a vector network analyzer (VNA) in an anechoic chamber setup. The radiation pattern-based DS algorithm shows a 6.7-dB higher TCR compared to the conventional DS algorithm.

• 대한화학회지
• /
• 제52권5호
• /
• pp.523-529
• /
• 2008

• 한국지구물리탐사학회:학술대회논문집
• /
• 한국지구물리탐사학회 2007년도 공동학술대회 논문집
• /
• pp.197-202
• /
• 2007

Most of seismic reflection prospecting assumes subsurface formation to be homogeneous media. These models are not capable of estimating small scale heterogeneity which is verified by well log data or drilling core. And those synthetic seismograms by homogeneous media are limited to explain various changes at field data. So we developed a inhomogeneous velocity model which can estimate inhomogeneity of background medium to implement numerical modeling from homogeneous medium and inhomogeneous medium on the model. Background medium using three autocorrelation functions in order to generate inhomogeneous velocity media was according to dominant wavelength of background medium and correlation length of random medium. And then we compared shot gathers. The results show that numerical modeling implemented at inhomogeneous medium depicts complex wave propagation of field data.

• 스마트미디어저널
• /
• 제8권4호
• /
• pp.33-37
• /
• 2019

심전도 신호는 시간 및 환경 변화에 따라 측정되는 시계열 데이터로 매번 등록 데이터와 동일한 크기의 비교 데이터를 취득해야 하는 문제점이 발생한다. 본 논문에서는 신호 크기 부적합 문제를 해결하기 위해 가상 생체신호 생성을 위한 보조 분류기 기반 적대적 생성 신경망(Auxiliary Classifier Generative Adversarial Networks)의 네트워크 모델을 제안한다. 생성된 가상 생체신호의 유사성을 확인하기 위해 코사인 각도와 교차 상관관계를 이용하였다. 실험 결과, 코사인 유사도 측정 결과로 평균 유사도는 0.991의 결과를 나타냈으며, 교차 상관관계를 이용한 유클리디언 거리 기반 유사성 측정 결과는 평균 0.25 유사도 결과를 나타냈다. 이는 등록 데이터와 실험 데이터간의 크기가 일치하지 않더라도 가상 생체신호 생성을 통해 신호 크기 부적합 문제를 해결함을 확인하였다.