• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume I
• /
• pp.156-156
• /
• 2006

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume I
• /
• pp.158-158
• /
• 2006

• 한국광물학회지
• /
• 제21권1호
• /
• pp.99-115
• /
• 2008

• 대한자원환경지질학회:학술대회논문집
• /
• 대한자원환경지질학회 2005년도 춘계 학술발표회 논문집
• /
• pp.314-316
• /
• 2005

• 한국암석학회:학술대회논문집
• /
• 한국암석회.한국광물학회 2009년도 공동학술발표회 논문집
• /
• pp.61-61
• /
• 2009

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2004년도 Korea-Russia Joint Conference on Geometics
• /
• pp.35-37
• /
• 2004

• 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.

• 한국측량학회지
• /
• 제36권5호
• /
• pp.355-369
• /
• 2018

LiDAR (Light Detection And Ranging) strip adjustment is process to improve geo-referencing of the ALS (Airborne Laser Scanner) strips that leads to seamless LiDAR data. Multiple strips are required to collect data over the large areas, thus the strips are overlapped in order to ensure data continuity. The LSA (LiDAR Strip Adjustment) consists of identifying corresponding features and minimizing discrepancies in the overlapping strips. The corresponding features are utilized as control features to estimate transformation parameters. This paper applied SURF (Speeded Up Robust Feature) to identify corresponding features. To improve determination of the corresponding feature, false matching points were removed by applying three schemes: (1) minimizing distance of the SURF feature vectors, (2) selecting reliable matching feature with high cross-correlation, and (3) reflecting geometric characteristics of the matching pattern. In the strip adjustment procedure, corresponding points having large residuals were removed iteratively that could achieve improvement of accuracy of the LSA eventually. Only a few iterations were required to reach reasonably high accuracy. The experiments with simulated and real data show that the proposed method is practical and effective to airborne LSA. At least 80 % accuracy improvement was achieved in terms of RMSE (Root Mean Square Error) after applying the proposed schemes.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2004년도 춘계학술발표회
• /
• pp.319-326
• /
• 2004

Uncertainty is inevitably involved in rock slope engineering since the rock masses are formed by natural process and subsequently the geotechnical characteristics of rock masses cannot be exactly obtained. Therefore the reliability analysis method has been suggested to deal properly with uncertainty. The reliability analysis method can be divided into level I, II and III on the basis of the approach for consideration of random variable and probability density function of reliability function. The level II approach, which is focused in this study, assumes the probability density function of random variables as normal distribution and evaluates the probability of failure with statistical moments such as mean and standard deviation. This method has the advantage that can be used the problem which the Monte Carlo simulation approach cannot be applied since the complete information on the random variables are not available. In this study, the analysis results of level II reliability approach compared with the analysis results of level III approach to verify the appropriateness of the level II approach. In addition, the results are compared with the results of the deterministic analysis.

• 한국측량학회지
• /
• 제30권6_2호
• /
• pp.673-680
• /
• 2012

Long-term GPS data analysis was performed in order to analyze the seasonal variation of tropospheric delay and the success rate of the ambiguity resolution. For this analysis, a total of 57 stations including 10 IGS stations in East Asia were processed together with double-differenced observables using Bernese GPS Software V5.0. The time span for this study ranges from 2002.0 to 2012.5 (10.5 years). The average baseline length is 339.0 km and the maximum reaches up to 2,000 km. The analysis is focused on two things: the annual variation of the tropospheric delay and the ambiguity resolution rate. The tropospheric delay is closely related to the weather condition, especially relative humidity, therefore it was estimated that the maximum would be in summer, while reaching its minimum in winter with the apparent seasonal variations. On the contrary, however, the success rate of the ambiguity resolution shows the opposite pattern: its maximum was in winter and minimum in summer. The fact seems to be induced by the surrounding conditions; that is, the trees thick with leaves near the GPS antenna interfere with GPS signals in summer. This seems to confirm partly that there is a distinct trend in the decreasing success rate since 2006 because the trees are growing every year. It is necessary to eliminate the factors that degrade the GPS quality and the tropospheric modeling for Korea needs to be studied further.