• 한국철도학회:학술대회논문집
• /
• 한국철도학회 1999년도 추계학술대회 논문집
• /
• pp.503-510
• /
• 1999

NIC@E is the software for prediction of various outdoor Noise. The Program is based on the ray tracing technique which has been widely used in an environmental noise prediction and analysis. In this paper, we analyze the Railway noise on the various types of geometrical source conditions in 3D and develope the expression method of 3D Graphics for noise level.

• 한국측량학회지
• /
• 제35권5호
• /
• pp.423-430
• /
• 2017

Recently, data analysis research has been carried out using the deep learning technique in various fields such as image interpretation and/or classification. Various types of algorithms are being developed for many applications. In this paper, we propose a precipitation prediction algorithm based on deep learning with high accuracy in order to take care of the possible severe damage caused by climate change. Since the geographical and seasonal characteristics of Korea are clearly distinct, the meteorological factors have repetitive patterns in a time series. Since the LSTM (Long Short-Term Memory) is a powerful algorithm for consecutive data, it was used to predict precipitation in this study. For the numerical test, we calculated the PWV (Precipitable Water Vapor) based on the tropospheric delay of the GNSS (Global Navigation Satellite System) signals, and then applied the deep learning technique to the precipitation prediction. The GNSS data was processed by scientific software with the troposphere model of Saastamoinen and the Niell mapping function. The RMSE (Root Mean Squared Error) of the precipitation prediction based on LSTM performs better than that of ANN (Artificial Neural Network). By adding GNSS-based PWV as a feature, the over-fitting that is a latent problem of deep learning was prevented considerably as discussed in this study.

• 품질경영학회지
• /
• 제47권4호
• /
• pp.687-700
• /
• 2019

Purpose: The purpose of this study is to investigate the interaction effects between price determinants of artworks. We expand the methodology in art market by applying machine learning techniques to estimate the price of artworks and compare linear regression and machine learning in terms of prediction accuracy. Methods: Moderated regression analysis was performed to verify the interaction effects of artistic characteristics on price. The moderating effects were studied by confirming the significance level of the interaction terms of the derived regression equation. In order to derive price estimation model, we use multiple linear regression analysis, which is a parametric statistical technique, and k-nearest neighbor (kNN) regression, which is a nonparametric statistical technique in machine learning methods. Results: Mostly, the influences of the price determinants of art are different according to the auction types and the artist 's reputation. However, the auction type did not control the influence of the genre of the work on the price. As a result of the analysis, the kNN regression was superior to the linear regression analysis based on the prediction accuracy. Conclusion: It provides a theoretical basis for the complexity that exists between pricing determinant factors of artworks. In addition, the nonparametric models and machine learning techniques as well as existing parameter models are implemented to estimate the artworks' price.

• 대한임베디드공학회논문지
• /
• 제4권2호
• /
• pp.55-62
• /
• 2009

The power consumption of a high-end microprocessor increases very rapidly. High power consumption will lead to a rapid increase in the chip temperature as well. If the temperature reaches beyond a certain level, chip operation becomes either slow or unreliable. Therefore various approaches for Dynamic Thermal Management (DTM) have been proposed. In this paper, we propose a learning based temperature prediction scheme for a multi-core system. In this approach, from repeatedly executing an application, we learn the thermal patterns of the chip, and we control the temperature in advance through DTM. When the predicted temperature may go beyond a threshold value, we reduce the temperature by decreasing the operation frequencies of the corresponding core. We implement our temperature prediction on an Intel's Quad-Core system which has integrated digital thermal sensors. A Dynamic Frequency System (DFS) technique is implemented to have four frequency steps on a Linux kernel. We carried out experiments using Phoronix Test Suite benchmarks for Linux. The peak temperature has been reduced by on average $5^{\circ}C{\sim}7^{\circ}C$. The overall average temperature reduced from $72^{\circ}C$ to $65^{\circ}C$.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 제36회 하계학술대회 논문집 전기설비
• /
• pp.31-33
• /
• 2005

The accelerating of industrial development causes electricity demand to increase. By that power equipments need high power, multi function and intelligence. Also consumers demand for guarantee power supplying of good quality and reasonable operating equipment. Also they require for reliance and stabilization of power facility. Therefore preventive maintenance of electric installation must be developed and improvement of domestic technical level is needed in the maintenance management of equipment. The diagnosis of trouble existence is technique that compares steady state with unusual condition, whereas the prediction technique makes a diagnosis of remaining equipments life. It is difficult for us to diagnose trouble existence of electric installation and to develop prediction method in building because of a wide scope for electric installation in building. And in this paper we will investigate diagnosis and prediction method for only switch part of electric installation in building.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.165-165
• /
• 2023

Streamflow prediction is a critical task in water resources management and essential for planning and decision-making purposes. However, the streamflow prediction is challenging due to the complexity and non-linear nature of hydrological processes. The transfer learning is a powerful technique that enables a model to transfer knowledge from a source domain to a target domain, improving model performance with limited data in the target domain. In this study, we apply the transfer learning using the Informer model, which is a state-of-the-art deep learning model for streamflow prediction. The model was trained on a large-scale hydrological dataset in the source basin and then fine-tuned using a smaller dataset available in the target basin to predict the streamflow in the target basin. The results demonstrate that transfer learning using the Informer model significantly outperforms the traditional machine learning models and even other deep learning models for streamflow prediction, especially when the target domain has limited data. Moreover, the results indicate the effectiveness of streamflow prediction when knowledge transfer is used to improve the generalizability of hydrologic models in data-sparse regions.

• 한국공간정보시스템학회 논문지
• /
• 제9권1호
• /
• pp.1-13
• /
• 2007

현재 무선 통신 기술과 위치 정보 기술의 발달은 다양한 위치 기반 서비스(LBS: Location Based Services)의 발전을 가져왔으며, 위치 기반 서비스에서 이동 객체의 미래 위치를 빠르게 예측하기 위한 미래 인덱스의 필요성이 높아지고 있다. 미래 인덱스와 관련한 대표적인 연구로써 도로 네트워크 환경에서 이동 객체의 과거 궤적 정보를 이용하여 신뢰성을 높인 확률 궤적 예측 기법이 연구되었다. 그러나, 이 기법은 장기간 미래 질의 시 방대한 미래 궤적 탐색 부하로 인해 예측 성능이 떨어지게 되며, 이 때문에 발생하는 빈번한 미래 궤적 갱신으로 인해 인덱스 유지비용이 매우 높아지게 된다. 따라서, 본 논문에서는 효율적인 장기간 미래 위치 예측을 위한 셀 기반의 미래 인덱싱 기법인 PCT-Tree(Probability Cell Trajectory-Tree)를 제시한다. PCT-Tree는 방대한 과거 궤적의 확률을 셀 단위로 재구성함으로써 인덱스 크기를 줄이고, 장기간 미래 질의의 예측 성능을 개선시킨다. 또한, 과거 궤적 정보를 이용하여 신뢰성있는 미래 궤적을 예측함으로써 미래 궤적 예측 오류에 따르는 통신비용과 미래 궤적 갱신으로 인한 인덱스 재구성 비용을 최소화 할 수 있다. 실험을 통해 도로 네트워크 환경에서 PCT-Tree가 기존 인덱싱 기법보다 장기간 미래 질의 성능이 우수함을 입증하였다.

• 대한전자공학회논문지SP
• /
• 제46권5호
• /
• pp.66-79
• /
• 2009

본 논문에서는 최신 압축 기술인 H.264/AVC의 화면내 부호화 효율을 향상시키기 위해 1차원 및 2차원 정수 변환을 이용한 적응적 화면내 부호화 기법을 제안한다. 제안 기법에서는 부호화될 블록에 대해 예측모드에 따라서 1차원 정수 변환과 2차원 정수 변환을 수행한 후 가장 효과적인 예측모드와 정수 변환 방법이 선택된다. 1차원 정수 변환을 이용한 부호화를 수행할 경우에는 먼저 예측모드에 따라 $4{\times}4$ 블록을 $1{\times}4$ 또는 $4{\times}1$의 서브블록으로 분할하고, 각각의 서브블록에 대해 예측을 수행한다. 이때 서브블록들에 대한 예측 신호는 이전의 재생된 서브블록을 이용하여, 예측 방향으로 가장 가까운 신호를 예측에 사용함으로써, 상관성의 활용을 극대화한다. 각각의 서브블록들은 생성된 예측 신호와의 뺄셈 과정을 통해 잔여신호를 생성하고, 1차원 정수 변환 및 양자화 과정을 통해 양자화된 신호를 생성한다. 양자화된 서브블록들은 다시 분할되기 이전의 $4{\times}4$ 블록 단위로 합쳐지고, 예측모드에 따라 DC에 우선 순위를 둔 스캐닝 패턴을 이용하여 1차원으로 정렬된다. 1차원 정수 변환을 사용하여 생성된 해당 블록의 비트스트림이 기존 2차원 정수 변환을 사용하여 생성한 비트스트림과 부호화 효율 측면에서 비교되어, 최종적으로 부호화될 예측모드와 변환 계수가 선택되어 전송된다. 제안 기술은 실험 결과를 통해 다양한 영상과 비트율에서 H.264/AVC보다 평균적으로 BD-PSNR을 0.34dB 향상 또는 BD-bitrate를 4.03% 감소시킴으로써, 기존의 H.264/AVC 부호화 효율을 크게 개선할 수 있음을 보여준다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2005년도 학술발표회(1)
• /
• pp.722-723
• /
• 2005

• 한국진공학회:학술대회논문집
• /
• 한국진공학회 2013년도 제44회 동계 정기학술대회 초록집
• /
• pp.113-114
• /
• 2013

Time-of-flight secondary ion mass spectrometry (TOF-SIMS) imaging is a powerful technique for producing chemical images of small biomolecules (ex. metabolites, lipids, peptides) "as received" because of its high molecular specificity, high surface sensitivity, and submicron spatial resolution. In addition, matrix-assisted laser desorption and ionization time-of-flight (MALDI-TOF) imaging is an essential technique for producing chemical images of large biomolecules (ex. genes and proteins). For this talk, we will show that label-free mass imaging technique can be a platform technology for biomedical studies such as early detection/diagnostics, accurate histologic diagnosis, prediction of clinical outcome, stem cell therapy, biosensors, nanomedicine and drug screening [1-7].