• Journal of Korean Society of Disaster and Security
• /
• v.15 no.4
• /
• pp.87-98
• /
• 2022

In recent years, frequent localized heavy rainfalls, which have a lot of rainfall in a short period of time, have been increasingly causing flooding damages. To prevent damage caused by localized heavy rainfalls, Hydrological Quantitative Precipitation Forecast (HQPF) was developed using the Local ENsemble prediction System (LENS) provided by the Korea Meteorological Administration (KMA) and Machine Learning and Probability Matching (PM) techniques using Digital forecast data. HQPF is produced as information on the impact of heavy rainfall to prepare for flooding damage caused by localized heavy rainfalls, but there is a tendency to overestimate the low rainfall intensity. In this study, we improved HQPF by expanding the period of machine learning data, analyzing ensemble techniques, and changing the process of Probability Matching (PM) techniques to improve predictive accuracy and over-predictive propensity of HQPF. In order to evaluate the predictive performance of the improved HQPF, we performed the predictive performance verification on heavy rainfall cases caused by the Changma front from August 27, 2021 to September 3, 2021. We found that the improved HQPF showed a significantly improved prediction accuracy for rainfall below 10 mm, as well as the over-prediction tendency, such as predicting the likelihood of occurrence and rainfall area similar to observation.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04a
• /
• pp.928-930
• /
• 2004

명령어간의 데이터 종속 관계는 동적으로 스케줄 되는 파이프라인 프로세서의 병렬 처리에 중요한 장애로 남아 있다. 마이크로프로세서의 데이터 종속에 기인한 파이프라인 대기 시간을 줄일 대표적인 두 가지 방법으로 생성 값의 지역성에 기초를 둔 데이터 값 예측과 공간 지역성에 기반으로 예측하는 주소 예측이 있다. 본 논문에서는 성능 개선을 위해 이 두 가지 기술을 독립적으로 수행하는 것 보다 혼합한 형태의 예측이 더 좋은 예측 정확성이 나타나는 것을 보인다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.4
• /
• pp.698-707
• /
• 2017

This paper deals with predictive control methods of mobile robots for reference trajectory tracking control. Predictive control methods using predictive model are known as effective schemes that minimize the future errors between the reference trajectories and system states; however, the amount of real-time computation for the predictive control are huge so that their applications were limited to slow dynamic systems such as chemical processing plants. Lately with high computing power due to advanced computer technologies, the predictive control methods have been applied to fast systems such as mobile robots. These predictive controllers have some control parameters related to control performance. But these parameters have not been optimized. In this paper we employed the genetic algorithm to optimize the control parameters of the predictive controller for mobile robots. The improved performances of the proposed control method are demonstrated by the computer simulation studies.

• The Journal of Society for e-Business Studies
• /
• v.25 no.2
• /
• pp.49-63
• /
• 2020

The accurate prediction of box office in the early stage is crucial for film industry to make better managerial decision. With aims to improve the prediction performance, the purpose of this paper is to evaluate the use of machine learning methods. We tested both classification and regression based methods including k-NN, SVM and Random Forest. We first evaluate input variables, which show that reputation-related information generated during the first two-week period after release is significant. Prediction test results show that regression based methods provides lower prediction error, and Random Forest particularly outperforms other machine learning methods. Regression based method has better prediction power when films have small box office earnings. On the other hand, classification based method works better for predicting large box office earnings.

• Journal of Internet Computing and Services
• /
• v.11 no.3
• /
• pp.25-32
• /
• 2010

It takes quite amount of time to study a game because there are many game characters and different stages are exist for games. This paper used reinforcement learning algorithm for characters to learn, and so they can move intelligently. On learning early, the learning speed becomes slow. Improved sequential prediction method was used to improve the speed of learning. To compare a normal learning to an improved one, a game was created. As a result, improved character‘s ability was improved 30% on learning speed.

• Proceedings of the KIPE Conference
• /
• 2012.07a
• /
• pp.71-72
• /
• 2012

비례-적분(PI) 제어기 출력이 포화되었을 때, windup현상이 나타나며 이것은 큰 오버슈트 및 느린 정착 시간과 같은 성능저하를 야기시킨다. 이 논문에서는 이러한 문제점을 개선하기 위해 적분 상태 예측기를 갖는 Anti-windup PI제어기를 이용한 전류제어 방법을 제안한다. PSIM을 이용한 시뮬레이션을 통해 성능을 증명하였다. 이 방법은 PI제어기 출력이 포화되었을 경우와 그렇지 않을 경우에 따라 적분 상태가 각각 제어된다. 실험결과는 PI제어 방법과 비교하여 오버슈트 및 정착 시간과 같은 제어 성능이 개선되었음을 보여준다.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2005.11a
• /
• pp.299-303
• /
• 2005

In the present study, in order to improve precision of the component characteristic maps generated by the scaling method, a map generation method which can produce a compressor map from some experimental performance data using GAs(Genetic Algorithms) was proposed. However, in case of the proposed map generation method only using GAs, because it has a drawback for estimating correctly the surge points and the choke points of the compressor map, a modified GAs method was additionally proposed through complementally use of the scaling method to determine obviously those points of the compressor map.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.1
• /
• pp.33-40
• /
• 2007

Processor pipelines have been growing deeper and issue widths wider over the years. If this trend continues, the branch misprediction penalty will become very high. Branch misprediction is the single most significant performance limiter for improving processor performance using deeper pipelining. Therefore, more accurate branch predictor becomes an essential part of modern processors. Several branch predictors combine a part of the branch address with a fixed amount of global branch history to make a prediction. These predictors cannot perform uniformly well across all programs because the best amount of branch history to be used depends on the program and branches in the program. Therefore, predictors that use a fixed history length are unable to perform up to their potential performance. In this paper, we propose a branch prediction mechanism, using variable length history, which predicts using a bank having higher prediction accuracy among predictions from five banks. Bank 0 is a bimodal predictor which is indexed with the 12 least significant bits of the branch address. Banks 1, 2, 3 and 4 are predictors which are indexed with different global history bits and the branch PC. In simulation results, the proposed mechanism outperforms gshare predictors using fixed history length of 12 and 13 , up to 6.34% in prediction accuracy. Furthermore, the proposed mechanism outperforms gshare predictors using best history lengths for benchmarks, up to 2.3% in prediction accuracy.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.18-22
• /
• 2019

FAQ 분류는 자주 묻는 질문을 범주화하고 사용자 질의에 대해 가장 유사한 클래스를 추론하는 방식으로 진행된다. FAQ 데이터셋은 클래스가 다수 존재하기 때문에 클래스 간 포함 및 연관 관계가 존재하고 특정 데이터가 서로 다른 클래스에 동시에 속할 수 있다는 특징이 있다. 그러나 최근 FAQ 분류는 다중 클래스 분류 방법론을 적용하는 데 그쳤고 FAQ 데이터셋의 특징을 모델에 반영하는 연구는 미미했다. 현 분류 방법론은 이러한 FAQ 데이터셋의 특징을 고려하지 못하기 때문에 정답으로 해석될 수 있는 예측도 오답으로 여기는 경우가 발생한다. 본 논문에서는 신뢰성이 부족한 FAQ 데이터셋에서도 분류를 잘 하기 위해 손실 함수를 조정하는 정규화 기법을 소개한다. 이 정규화 기법은 클래스 간 포함 및 연관 관계를 반영할 수 있도록 오답을 예측한 경우에도 예측 강도에 비례하여 손실을 줄인다. 이는 오답을 높은 확률로 예측할수록 데이터의 신뢰성이 낮을 가능성이 크다고 판단하여 학습을 강하게 하지 않게 하기 위함이다. 실험을 위해서는 다중 클래스 분류에서 가장 좋은 성능을 보이고 있는 모형인 BERT를 이용했으며, 비교 실험을 위한 정규화 방법으로는 통상적으로 사용되는 라벨 스무딩을 채택했다. 실험 결과, 본 연구에서 제안한 방법은 기존 방법보다 성능이 개선되고 보다 안정적으로 학습이 된다는 것을 확인했으며, 데이터의 신뢰성이 부족한 상황에서 효과적으로 분류를 수행함을 알 수 있었다.

• Journal of Broadcast Engineering
• /
• v.27 no.4
• /
• pp.477-486
• /
• 2022

In this paper, we propose a novel intra-prediction method using convolutional neural network (CNN) to improve a quality of a predicted block in VVC. The proposed algorithm goes through a two-step procedure. First, an input prediction block is generated using one of the VVC intra-prediction modes. Second, the prediction block is further refined through a CNN model, by inputting the prediction block itself and reconstructed reference samples in the boundary. The proposed algorithm outputs a refined block to reduce residual signals and enhance coding efficiency, which is enabled by a CU-level flag. Experimental results demonstrate that the proposed method achieves improved rate-distortion performance as compared a VVC reference software, I.e., VTM version 10.0.