• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.1
• /
• pp.100-105
• /
• 2011

Needs of intelligent system has risen continuously to solve given problem optimally using learning and reasoning. This system has performed important roles in diverse fields for improving the human-life quality in past, present, and future. So, it is important to analyze the trend of technology forecasting for the intelligent system. In this paper, we propose a patent analysis method for technology forecasting of the intelligent system using objective patent data. To verify our study, we use the patent data applied and registered until now.

• Journal of the Korean earth science society
• /
• v.40 no.3
• /
• pp.259-271
• /
• 2019

A statistical downscaling method was adopted in order to establish the high-resolution wave prediction system in the East Sea coastal area. This system used forecast data from the Global Wave Watch (GWW) model, and the East Sea and Busan Coastal Wave Watch (CWW) model operated by the Korea Meteorological Administration (KMA). We used the CWW forecast data until three days and the GWW forecast data from three to seven days to implement the statistical downscaling method (inverse distance weight interpolation and conditional merge). The two-dimensional and station wave heights as well as sea surface wind speed from the high-resolution coastal prediction system were verified with statistical analysis, using an initial analysis field and oceanic observation with buoys carried out by the KMA and the Korea Hydrographic and Oceanographic Agency (KHOA). Similar to the predictive performance of the GWW and the CWW data, the system has a high predictive performance at the initial stages that decreased gradually with forecast time. As a result, during the entire prediction period, the correlation coefficient and root mean square error of the predicted wave heights improved from 0.46 and 0.34 m to 0.6 and 0.28 m before and after applying the statistical downscaling method.

• The KIPS Transactions:PartB
• /
• v.14B no.2
• /
• pp.127-134
• /
• 2007

There are many researches about the intelligent stock trading systems with the help of the advance of the artificial intelligence such as machine learning techniques, Though the establishment of the reasonable trading policy plays an important role in the performance of the trading systems most researches focused on the improvement of the predictability. Also some previous works, which treated the trading policy, treated the simplified versions dependent on the predictors in less systematic ways. In this paper, we propose the integrated multiple simulation' as a method of optimizing trading performance of stock trading systems. The propose method is adopted in the NXShell a development environment for neural network based stock trading systems. Under the proposed integrated multiple simulation', we simulate the multiple tradings for all combinations of the neural network's outputs and the trading policy parameters, evaluate the learning performance according to the various metrics and establish the optimal policy for a given prediction module based on the resulting performance. In the experiment, we present the trading policy comparison results using the stock value data from the KOSPI and KOSDAQ.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.2
• /
• pp.242-247
• /
• 2009

Recently an intelligent system is developed for the service what users want not a passive system which just answered user's request. This intelligent system is used for personalized recommendation system and representative techniques are content-based and collaborative filtering. In this study, we propose a prediction system which is based on the techniques of recommendation system using a collaborative filtering and a fuzzy system to solve the collaborative filtering problems. In order to verify the prediction system, we used the data that is user's rating about movies. We predicted the user's rating using this data. The accuracy of this prediction system is determined by computing the RMSE(root mean square error) of the system's prediction against the actual rating about the each movie and is compared with the existing system. Thus, this prediction system can be applied to base technology of recommendation system and also recommendation of multimedia such as music and books.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.62-62
• /
• 2019

본 연구에서는 기상청에서 제공하는 인공위성 관측자료와 레이더 자료를 합성하여 예측된 선행시간 2시간의 강수량 예측자료를 이용하여 도시유역의 침수 발생 여부를 확인할 수 있는 시스템을 개발하였다. 대상유역은 부산광역시에 위치하고 있는 유역면적 $54km^2$의 온천천유역으로, $10m{\times}10m$의 해상도로 지표면의 침수예측을 수행한다. 침수예측에 이용되는 모델은 지표면과 하수관망 사이의 상호작용을 효과적으로 고려할 수 있도록 지표면 2차원, 하수관망 1차원 모델을 연계하였으며, 침수예측에 소요되는 시간을 최소화하기 위하여 OpenMP기반의 병렬해석 기법을 적용하였다. 또한 초기조건에 의한 오차를 줄이기 위하여 하천수위 관측소에 관측된 수위자료를 예측모델의 초기조건으로 입력할 수 있도록 시스템을 구성하였으며 유역 하류단에서 경계조건으로 활용되는 예측수위자료는 시계열자료의 예측에 뛰어난 성능을 보여주는 것으로 알려진 LongShort-term Memory(LSTM) 기법을 적용하여 이용하였다. 본 연구에서 개발된 실시간 도시침수 예측 시스템은 집중호우 발생시 침수 발생 위치를 사전에 빠르게 예측하여 도시유역의 인적 물적 자원의 피해를 저감하는데 적극적으로 활용될 수 있을 것으로 기대된다.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.12
• /
• pp.439-446
• /
• 2016

In this paper, an efficient prediction accuracy enhancement strategy is proposed for improving the performance of the prediction-based parallel event-driven gate-level timing simulation. The proposed new strategy adopts the static double prediction and the dynamic prediction for input and output values of local simulations. The double prediction utilizes another static prediction data for the secondary prediction once the first prediction fails, and the dynamic prediction tries to use the on-going simulation result accumulated dynamically during the actual parallel simulation execution as prediction data. Therefore, the communication overhead and synchronization overhead, which are the main bottleneck of parallel simulation, are maximally reduced. Throughout the proposed two prediction enhancement techniques, we have observed about 5x simulation performance improvement over the commercial parallel multi-core simulation for six test designs.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.5A
• /
• pp.451-458
• /
• 2006

In this paper, we propose a novel scheduling algorithm for downlink transmission which utilizes scarce wireless resource efficiently in an Orthogonal Frequency Division Multiple Access/Time Division Duplex system. Scheduling schemes which exploit channel information between a Base Station and terminals have been proposed recently for improved performance. Time series analysis is used to estimate the channel state of mobile terminals. The predicted information is then used for prioritized scheduling of downlink transmissions for improved throughput, delay and jitter performance. Through simulation, we show that the total throughput and mean delay of the proposed scheduling algorithm are improved compared with those of the Proportional Fairness and Maximum Carrier to Interference Ratio schemes.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.956-959
• /
• 2020

본 연구에서는 아파트를 대표할 수 있는 내·외적 데이터를 수집하고 인공지능 기술들을 활용하여 아파트 가격을 예측하는 시스템을 구축하고자 한다. 구체적으로 웹크롤링 기법을 통해 수집한 아파트 내·외적 데이터의 변수들에 대한 특성 선택(Feature Selection)을 수행하였고, 다양한 인공지능 기법을 활용하여 부동산 가격 예측 모형을 개발하였다. 아파트 가격 예측 모형 생성을 위해 Linear Regression, Ridge, Xgboost, Lightgbm, Catboost 등의 기계학습 알고리즘을 사용하였고, RMSE를 사용하여 각 예측 모형 간의 성능 비교를 수행하였다. 가장 성능이 좋은 예측 모형은 Xgboost기반 예측 모형이였으며, RMSE값이 약 0.0366으로 가장 낮았으며 테스트 데이터에 대한 정확도는 약 95.1%였다.

• Journal of Korea Spatial Information System Society
• /
• v.8 no.1 s.16
• /
• pp.17-25
• /
• 2006

TPR*-tree is the most widely-used index structure for effectively predicting the future positions of moving objects. The TPR*-tree, however, has the problem that both of the dead space in a bounding region and the overlap among hounding legions become larger as the prediction time in the future gets farther. This makes more nodes within the TPR*-tree accessed in query processing time, which incurs the performance degradation. In this paper, we examine the performance problem quantitatively with a series of experiments. First, we show how the performance deteriorates as a prediction time gets farther, and also show how the updates of positions of moving objects alleviates this problem. Our contribution would help provide Important clues to devise strategies improving the performance of TPR*-trees further.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.112-112
• /
• 2023

발전용댐의 댐 유입량 예측 및 운영을 위해서 (주)한국수력원자력에서는 수자원통합 운영시스템(Water resources Integrated System, WIOS)을 운영 중에 있다. 해당 시스템에서는 댐 유입량을 예측하기 위해서 기상청 수치예보모델 중 하나인 국지예보모델(Local Data Assimilation and Prediction System, LDAPS)의 예측강우를 수문모형의 입력자료로 활용하고 있으며, 레이더 기반의 초단시간 강우예측 기법을 자체 개발 중에 있다. 기상청 국지예보모델은 강우의 on/off에 대한 정확도는 90%를 상회할 만큼 높으나 정량적인 강우량의 정확도는 매우 낮고, 레이더 기반의 초단시간 예측 강우는 선행 1~2시간 예측에서는 정량적 정확도는 높으나, 그 이후 예측성능이 급격히 떨어지는 경향을 보인다. 따라서 댐 유입량의 정량적 예측 정확도를 확보하기 위해 초단시간 모델과 국지예보모델의 강우예측 결과를 병합(blending)하는 기법을 적용하여 초기 6시간 동안의 예측 성능을 향상시켜야 한다. 본 연구에서는 선행시간 0~6시간에 대해서 병합하는 기법들을 적용하고 평가하고자 한다. 기본적으로 병합은 초단시간 예측강우와 수치예보자료 간 가중치를 통해 수행된다. 일반적으로 초기 1시간 선행시간에서 레이더 기반 예측강우는 완벽한 예측자료(외삽 관측자료의 가중치는 1.0)로 가정하며, tanh 함수를 이용하여 선행시간의 증가에 따라 가중치를 감소시키면서, 6시간 선행시간에서는 수치예보 예측강우가 완벽한 예측자료라고 가정한다. 본 연구에서는 일반적인 병합 방법 외에 병합된 예측강우에 과거 관측강우와 예측강우의 평균편이를 적용하여 보정하는 방법, 사례별 변동성이 큰 병합된 예측강우 특성을 고려하여 병합 가중치를 신뢰도에 따라 가변시키는 방법을 적용하여 평가한다. 이를 통해 댐 유입량 예측에 최적이 되는 병합기법을 선정하고자 한다.