• Journal of Korea Foundry Society
• /
• v.42 no.6
• /
• pp.369-376
• /
• 2022

The die-casting process is an important process for various industries, but there are limitations in the profitability and productivity of related companies due to the high defect rate. In order to overcome this, this study has developed die-casting fault detection modules based on industrial AI technologies. The developed module is constructed from three-stage models depending on the characteristics of the dataset. The first-stage model conducts fault detection based on supervised learning from the dataset without labels. The second-stage model realizes one-class classification based on semi-supervised learning, where the dataset only has production success labels. The third-stage model corresponds to fault detection based on supervised learning, where the dataset includes a small amount of production failure cases. The developed fault detection module exhibited outstanding performance with roughly 96% accuracy for actual process data.

• Journal of Internet Computing and Services
• /
• v.24 no.1
• /
• pp.49-59
• /
• 2023

Recently, attention to the pandemic situation represented by COVID-19 emerged problems caused by unexpected shortage of medical personnel. In this paper, we present a method for diagnosing the presence or absence of lesional sign on PA chest X-ray images as computer vision solution to support diagnosis tasks. Method for visual anomaly detection based on feature modeling can be also applied to X-ray images. With extracting feature vectors from PA chest X-ray images and divide to patch unit, region-specific abnormality can be detected. As preliminary experiment, we created simulation data set containing multiple objects and present results of the comparative experiments in this paper. We present method to improve both efficiency and performance of the process through hard masking of patch features to aligned images. By summing up regional specificity and global anomaly detection results, it shows improved performance by 0.069 AUROC compared to previous studies. By aggregating region-specific and global anomaly detection results, it shows improved performance by 0.069 AUROC compared to our last study.

• Korean Journal of Optics and Photonics
• /
• v.34 no.1
• /
• pp.13-21
• /
• 2023

We have investigated the acceptance angle and imaging performance of a curved artificial compound eye (ACE), depending on the sag height of the microlens array to maximize its sensitivity to light. When the h/r values increased from 0.22 to 0.37, the acceptance angle of the curved ACE was expanded from 28.70° to 49.02°, which is an enhancement by 70.8%. With the designed optical system, it was demonstrated that a microlens located at the 23rd position from the center of the main lens could still focus an incident beam tilted at 56.35°, so that the letter F was clearly observed.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.280-280
• /
• 2023

강수의 정확한 시·공간적 추정은 홍수 대응, 가뭄 관리, 수자원 계획 등 수문학적 모델링의 핵심 기술이다. 우주 기술의 발전으로 전지구 강수량 측정 프로젝트(Global Precipitation Measurement, GPM)가 시작됨에 따라 위성의 여러 센서를 이용하여 다양한 고해상도 강수량 자료가 생산되고 있으며, 기후변화로 인한 수재해의 빈도가 증가함에 따라 준실시간(Near-Real-Time) 위성 강수 자료의 활용성 및 중요성이 높아지고 있다. 하지만 준실시간 위성 강수 자료의 경우 빠른 지연시간(latency) 확보를 위해 관측 이후 최소한의 보정을 거쳐 제공되므로 상대적으로 강수 추정치의 불확실성이 높다. 이에 따라 본 연구에서는 앙상블 머신러닝 기반 수집된 위성 강수 자료들을 관측 자료와 병합하여 보정된 준실시간 강수량 자료를 생성하고자 한다. 모형의 입력에는 시단위 3가지 준실시간 위성 강수 자료(GSMaP_NRT, IMERG_Early, PERSIANN_CCS)와 방재기상관측 (AWS)의 온도, 습도, 강수량 지점 자료를 활용하였다. 지점 강수 자료의 경우 결측치를 고려하여 475개 관측소를 선정하였으며, 공간성을 고려한 랜덤 샘플링으로 375개소(약 80%)는 훈련 자료, 나머지 100개소(약 20%)는 검증 자료로 분리하였다. 모형의 정량적 평가 지표로는 KGE, MAE, RMSE이 사용되었으며, 정성적 평가 지표로 강수 분할표에 따라 POD, SR, BS 그리고 CSI를 사용하였다. 머신러닝 모형은 개별 원시 위성 강수 자료 및 IDW 기법보다 높은 정확도로 강수량을 추정하였으며 공간적으로 안정적인 결과를 나타내었다. 다만, 최대 강수량에서는 다소 과소추정되므로 이는 강수와 관련된 입력 변수의 개수 업데이트로 해결할 수 있을 것으로 판단된다. 따라서 불확실성이 높은 개별 준실시간 위성 자료들을 관측 자료와 병합하여 보정된 최적 강수 자료를 생성하는 머신러닝 기법은 돌발성 수재해에 실시간으로 대응 가능하며 홍수 예보에 신뢰도 높은 정량적인 강수량 추정치를 제공할 수 있다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.4
• /
• pp.687-697
• /
• 2023

Botnets, whose attack patterns are becoming more sophisticated and diverse, are recognized as one of the most serious cybersecurity threats today. This paper revisits the experimental results of botnet detection using autoencoder, a semi-supervised deep learning model, for UGR and CTU-13 data sets. To prepare the input vectors of autoencoder, we create data points by grouping the NetFlow records into sliding windows based on source IP address and aggregating them to form features. In particular, we discover a simple power-law; that is the number of data points that have some flow-degree is proportional to the number of NetFlow records aggregated in them. Moreover, we show that our power-law fits the real data very well resulting in correlation coefficients of 97% or higher. We also show that this power-law has an impact on the learning of autoencoder and, as a result, influences the performance of botnet detection. Furthermore, we evaluate the performance of autoencoder using the area under the Receiver Operating Characteristic (ROC) curve.

• Clean Technology
• /
• v.15 no.4
• /
• pp.245-252
• /
• 2009

Profiles development of melt spinning process of poly(lactic acid) (PLA) was simulated via a numerical method and the radial temperature distribution was calculated using finite difference method. The spinning speed ranged from 1 km/min to 5 km/min was analyzed and the effect of spinning conditions on the radial temperature distribution was investigated. At low spinning speed, the difference between PLA and poly(ethylene terephthalate) (PET) was relatively small. As the spinning speed increased, the difference in velocity profile became prominent. PLA showed a slower spinning speed than PET and solidified more slowly. The temperature difference between the core and surface of the PLA filament reached 4.6 K, which was less than that of PET filament with a difference of 10.4 K. The radial temperature difference increased with increasing the cooling-air velocity and the spinning temperature.

• The Journal of Korean Obstetrics and Gynecology
• /
• v.22 no.1
• /
• pp.125-139
• /
• 2009

Purpose: This experiment was designed to find out increasing effects of S. barbata. co-treatment with anti-cancer drugs at cancer cell's growth inhibition effect. Methods: Divergent observational study of the S. barbata. co-treatment with Cisplatin treatment on HeLa cell. Cell viability using MTT assay, Cell Culture and Cytotoxicity Studies, Cell Cycle Analysis, Annexin V-FITC/PI assay, Cell morphological assessment, PARP cleavage using Western blotting analysis when HeLa cell were co-treated with Cisplatin and Scutellaria Barbata extracts. Results: When HeLa cell were co-treated with Cisplatin and Scutellaria Barbata extracts, we found out viability of HeLa cell, changing in the distribution of cell cycle, Annexin V-FITC staining, DAPI staining, PARP clavage protein assay by Western-blot. So Scutellaria Barbata extracts have increased apoptosis Conclusion: When co-treated Scutellaria Barbata extracts with anti-cancer drugs, the anti-cancer effects were increased. We still not sure which constituent apoptosis at cancer cells and activates anti-cancer effects suppressing, but we believe that it'll be revealed here after with following experiments.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.2
• /
• pp.245-254
• /
• 2022

In this paper, a design optimization method for anti-jamming GPS antenna is presented. For this purpose, jamming performance analysis criteria and methods are presented. And based on the proposed analysis method, the antenna design elements that can realize the best performance were optimized. The anti-jamming GPS antenna for applying the presented method has a structure in which 7 radiating elements are arranged. Here, six radiating elements were circular arranged, and one element was arranged in the center of the circular arrangement. The optimized antenna design parameter(radius of the circular array) is 0.48 λ. As a result of the simulation, it was confirmed that when the steering angle(theta, phi) of the main lobe was (0°, 0°), the pattern null steering range(based on theta) was 57° to 90°.

• Journal of the Korea Institute of Building Construction
• /
• v.23 no.1
• /
• pp.11-22
• /
• 2023

In this work, a depth-by-depth evaluation on the deterioration of concrete is suggested by utilizing disk shaped concrete specimens. Dynamic elastic modulus of cylindrical concrete was measured using a free-free resonance column method and compared with dynamic elastic modulus of disk-shaped concrete measured by impulse excitation technique(IET) and impact resonance(IR). According to the results of the experiment, both IET and IR methods showed a smaller difference in dynamic elastic modulus with smaller deviation in data when thickness of the disk specimen was increased. This trend was more evident from dynamic elastic modulus measured by IR method compared to that measured by IET. Variation in data was also smaller with the IR result. To increase the accuracy of the data, it is recommended to use the IR method for disk specimen with a diameter of 100mm and a thickness of 25mm.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.62-62
• /
• 2022

홍수 예보를 위한 강우-유출 분석에서 정확한 예측 강우량 정보는 매우 중요한 인자이다. 이에 따라 강우 예측을 위하여 다양한 연구들이 수행되고 있지만 시·공간적으로 비균일한 특성 또는 변동성을 가진 강우를 정확하게 예측하는 것은 여전히 난제이다. 본 연구에서는 딥러닝 기반 ConvLSTM (Convolutinal Long Short-Term Memory) 모형을 사용하여 위성 강수 자료의 단기 예측을 수행하고 그 정확성을 분석하고자 한다. 대상유역은 메콩강 유역이며, 유역 면적이 넓고 강우 관측소의 밀도가 낮아 시·공간적 강우량 추정에 한계가 있으므로 정확한 강우-유출 분석을 위하여 위성 강수 자료의 활용이 요구된다. 현재 TRMM, GSMaP, PERSIANN 등 많은 위성 강수 자료들이 제공되고 있으며, 우선적으로 ConvLSTM 모형의 강수 예측 활용가능성 평가를 위한 입력자료로 가장 보편적으로 활용되는 TRMM_3B42 자료를 선정하였다. 해당 자료의 특성으로 공간해상도는 0.25°, 시간해상도는 일자료이며, 2001년부터 2015년의 자료를 수집하였다. 모형의 평가를 위하여 2001년부터 2013년 자료는 학습, 2014년 자료는 검증, 2015년 자료는 예측에 사용하였다. 또한 민감도 분석을 통하여 ConvLSTM 모형의 최적 매개변수를 추정하고 이를 기반으로 선행시간(lead time) 1일, 2일, 3일의 위성 강수 예측을 수행하였다. 그 결과 선행시간이 길어질수록 그 오차는 증가하지만, 전반적으로 3가지 선행시간 모두 자료의 강수량뿐만 아니라 공간적 분포까지 우수하게 예측되었다. 따라서 2차원 시계열 자료의 특성을 기억하고 이를 예측에 반영할 수 있는 ConvLSTM 모형은 메콩강과 같은 미계측 대유역에서의 안정적인 예측 강수량 정보를 제공할 수 있으며 홍수 예보를 위한 강우-유출 분석에 활용이 가능할 것으로 판단된다.