• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.1
• /
• pp.61.2-61.2
• /
• 2021

SkyMapper is the largest-aperture optical wide-field telescope in Australia and can be used for transient detection in the Southern sky. Reference images from its Southern Survey cover the sky at δ <+10 deg to a depth of I ~ 20 mag. It has been used for surveys of extragalactic transients such as supernovae, optical counterparts to gravitational-wave (GW) and fast radio bursts. We adopt an ensemble-based machine learning technique and further filtering scheme that provides high completeness ~98% and purity ~91% across a wide magnitude range. Here we present an important use-case of our robotic transient search, which is the follow-up of GW event triggers from LIGO/Virgo. We discuss the facility's performance in the case of the second binary neutron star merger GW190425. In time for the LIGO/Virgo O4 run, we will have deeper reference images for galaxies within out to ~200 Mpc distance, allowing rapid transient detection to i ~ 21 mag.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.426-427
• /
• 2023

최근 현대인의 식습관 및 고령화로 인해 당뇨병 환자의 수가 연간 증가하고 있다. 따라서 현재는 아직 당뇨병이 발생하지 않았더라도 미래에 발생할 가능성 예측의 중요성이 커지고 있다. 기존의 당뇨병 발생 여부 진단 연구는 회귀 분석과 같은 단일 모델을 사용하여 수행된다. 그러나 당뇨병에 영향을 미치는 변수들은 복잡하게 얽혀있어 단일 모델만으로는 패턴을 충분히 학습하기 어렵다. 본 논문에서는 데이터에 적합하게 자동으로 다층 스태킹 앙상블 모델을 구성하는 알고리즘을 이용한 다층 스태킹 앙상블 모델을 제안한다. 제안하는 방법은 성능이 높은 모델들을 기준으로 층을 쌓으며 모델을 구성하며 실험 결과 다른 자동 기계학습 라이브러리와 비교해 F1 score 기준으로 최대 12.89%p의 성능 향상을 보였다.

• International Journal of Computer Science & Network Security
• /
• v.24 no.4
• /
• pp.211-221
• /
• 2024

Pakistan is a top producer and exporter of high-quality rice, but traditional methods are still being used for detecting rice diseases. This research project developed an automated rice blast disease diagnosis technique based on deep learning, image processing, and transfer learning with pre-trained models such as Inception V3, VGG16, VGG19, and ResNet50. The modified connection skipping ResNet 50 had the highest accuracy of 99.16%, while the other models achieved 98.16%, 98.47%, and 98.56%, respectively. In addition, CNN and an ensemble model K-nearest neighbor were explored for disease prediction, and the study demonstrated superior performance and disease prediction using recommended web-app approaches.

• Journal of Korea Water Resources Association
• /
• v.44 no.3
• /
• pp.199-208
• /
• 2011

The objective of this study is to develop real-time river flow forecast model by linking continuous rainfall-runoff model with ensemble Kalman filter technique. Andong dam basin is selected as study area and the model performance is evaluated for two periods, 2006. 7.1~8.18 and 2007. 8.1~9.30. The model state variables for data assimilation are defined as soil water content, basin storage and channel storage. This model is designed so as to be updated the state variables using measured inflow data at Andong dam. The analysing result from the behavior of the state variables, predicted state variable as simulated discharge is updated 74% toward measured one. Under the condition of assuming that the forecasted rainfall is equal to the measured one, the model accuracy with and without data assimilation is analyzed. The model performance of the former is better than that of the latter as much as 49.6% and 33.1% for 1 h-lead time during the evaluation period, 2006 and 2007. The real-time river flow forecast model using rainfall-runoff model linking with data assimilation process can show better forecasting result than the existing methods using rainfall-runoff model only in view of the results so far achieved.

• Atmosphere
• /
• v.34 no.1
• /
• pp.23-34
• /
• 2024

The Korea Meteorological Administration has improved medium-range weather forecasts by implementing post-processing methods to minimize numerical model errors. In this study, we employ a statistical correction technique known as the minimum continuous ranked probability score (CRPS) to refine medium-range forecast guidance. This technique quantifies the similarity between the predicted values and the observed cumulative distribution function of the Unified Model Ensemble Prediction System for Global (UM EPSG). We evaluated the performance of the medium-range forecast guidance for surface air temperature and relative humidity, noting significant enhancements in seasonal bias and root mean squared error compared to observations. Notably, compared to the existing the medium-range forecast guidance, temperature forecasts exhibit 17.5% improvement in summer and 21.5% improvement in winter. Humidity forecasts also show 12% improvement in summer and 23% improvement in winter. The results indicate that utilizing the minimum CRPS for medium-range forecast guidance provide more reliable and improved performance than UM EPSG.

• Journal of Digital Convergence
• /
• v.16 no.1
• /
• pp.231-242
• /
• 2018

The efficient management of the Length of Stay(LOS) is important in hospital. It is import to reduce medical cost for patients and increase profitability for hospitals. In order to efficiently manage LOS, it is necessary to develop an artificial intelligence-based prediction model that supports hospitals in benchmarking and reduction ways of LOS. In order to develop a predictive model of LOS for acute stroke patients, acute stroke patients were extracted from 2013 and 2014 discharge injury patient data. The data for analysis was classified as 60% for training and 40% for evaluation. In the model development, we used traditional regression technique such as multiple regression analysis method, artificial intelligence technique such as interactive decision tree, neural network technique, and ensemble technique which integrate all. Model evaluation used Root ASE (Absolute error) index. They were 23.7 by multiple regression, 23.7 by interactive decision tree, 22.7 by neural network and 22.7 by esemble technique. As a result of model evaluation, neural network technique which is artificial intelligence technique was found to be superior. Through this, the utility of artificial intelligence has been proved in the development of the prediction LOS model. In the future, it is necessary to continue research on how to utilize artificial intelligence techniques more effectively in the development of LOS prediction model.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.7
• /
• pp.4105-4110
• /
• 2014

The role of bass in band or ensemble music literally sets up the foundation of harmony, which must be regarded first. On the other hand, this is also considered so basic or stable that it can be slightly boring to the listeners. Consideration is needed to make the varied trials more exciting. In this sense, Rutger Gunnarsson showed these fine examples not in performing music but in pop music through the Great ABBA. He could make a fabulous sound with only a basic performance, not with a florid technique or rhetorical skills. All bassists must bear in mind that the overall performance depends on the bass. In short, to make better music, remember to practice continually and find better methods.

• Proceedings of the KSME Conference
• /
• 2001.06e
• /
• pp.542-547
• /
• 2001

A non-intrusive Planar Laser-Induced Fluorescence(PLIF) technique was applied to study the turbulent mixing process in a Rushton turbine reactor. Instantaneous and ensemble averaged concentration fields are obtained by measuring the fluorescence intensity of Rhodamine B tracer excited by a thin Nd:Yag laser sheet illuminating the whole center plane of the stirred tank. The gray level images captured by a 14-bit cooled CCD camera can be transformed to the local concentration values using a calibration matrix. The dye injection point was selected at the tank wall with three quarter height (3/4H) from the tank bottom to observe the mixing characteristics in upper bulk flow region. There exist distinct two time scales: the rapid decay of mean concentration in each region after the dye infusion reflects the large scale mixing while the followed slow decay reveals the small scale mixing. The temporal change of concentration probability functions conjectures the two sequential processes in the batch type mixing. An inactive column of water existed above the impeller disk, in which the fluid rotates with the shaft but is isolated from the mean bulk flow.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.26 no.8
• /
• pp.1145-1152
• /
• 2002

A non-intrusive Planar Laser-Induced Fluorescence(PLIF) technique was applied to study the turbulent mixing process in a Rushton turbine reactor. Instantaneous and ensemble averaged concentration fields was obtained by measuring the fluorescence intensity of Rhodamine B tracer excited by a thin Nd:Yag laser sheet illuminating the whole center plane of the stirred tank. The gray level images captured by a 14-bit cooled CCD camera could be transformed to the local concentration values using a calibration matrix. The dye injection point was selected at the tank wall with three quarter. height (3/4H) from the tank bottom to observe the mixing characteristics in upper bulk flow region. There exist distinct two time scales: the rapid decay of mean concentration after the dye infusion reflects the large scale turbulent mixing while the fellowed slow decay reveals the small scale molecular mixing. The temporal change of concentration variance field conjectures the two sequential processes for the batch type mixing. An inactive column of water is existed above the impeller disk, in which the fluid rotates with the shaft but is isolated from the mean bulk flow.

• Journal of Intelligence and Information Systems
• /
• v.5 no.1
• /
• pp.95-101
• /
• 1999

In this paper, a comparison between different methods to combine predictions from neural networks will be given. These methods are bagging, bumping, and balancing. Those are based on the analysis of the ensemble generalization error into an ambiguity term and a term incorporating generalization performances of individual networks. Neural Networks and AI machine learning models are prone to overfitting. A strategy to prevent a neural network from overfitting, is to stop training in early stage of the learning process. The complete data set is spilt up into a training set and a validation set. Training is stopped when the error on the validation set starts increasing. The stability of the networks is highly dependent on the division in training and validation set, and also on the random initial weights and the chosen minimization procedure. This causes early stopped networks to be rather unstable: a small change in the data or different initial conditions can produce large changes in the prediction. Therefore, it is advisable to apply the same procedure several times starting from different initial weights. This technique is often referred to as training ensembles of neural networks. In this paper, we presented a comparison of three statistical methods to prevent overfitting of neural network.