• Tunnel and Underground Space
• /
• v.30 no.3
• /
• pp.214-225
• /
• 2020

Uniaxial compressive strength (UCS) of rock is one of the important factors to determine the advance speed during shield TBM tunnel excavation. UCS can be obtained through the Geotechnical Data Report (GDR), and it is difficult to measure UCS for all tunneling alignment. Therefore, the purpose of this study is to predict UCS by utilizing TBM machine driving data and machine learning technique. Several machine learning techniques were compared to predict UCS, and it was confirmed the stacking model has the most successful prediction performance. TBM machine data and UCS used in the analysis were obtained from the excavation of rock strata with slurry shield TBMs. The data were divided into 8:2 for training and test and pre-processed including feature selection, scaling, and outlier removal. After completing the hyper-parameter tuning, the stacking model was evaluated with the root-mean-square error (RMSE) and the determination coefficient (R²), and it was found to be 5.556 and 0.943, respectively. Based on the results, the sacking models are considered useful in predicting rock strength with TBM excavation data.

• Tunnel and Underground Space
• /
• v.32 no.2
• /
• pp.131-143
• /
• 2022

The lunar exploration autonomous vehicle operates based on the lunar topography information obtained from real-time image characterization. For highly accurate topography characterization, a large number of training images with various background conditions are required. Since the real lunar topography images are difficult to obtain, it should be helpful to be able to generate mimic lunar image data artificially on the basis of the planetary analogs site images and real lunar images available. In this study, we aim to artificially create lunar topography images by using the location information-based style transfer algorithm known as Wavelet Correct Transform (WCT2). We conducted comparative experiments using lunar analog site images and real lunar topography images taken during China's and America's lunar-exploring projects (i.e., Chang'e and Apollo) to assess the efficacy of our suggested approach. The results show that the proposed techniques can create realistic images, which preserve the topography information of the analog site image while still showing the same condition as an image taken on lunar surface. The proposed algorithm also outperforms a conventional algorithm, Deep Photo Style Transfer (DPST) in terms of temporal and visual aspects. For future work, we intend to use the generated styled image data in combination with real image data for training lunar topography objects to be applied for topographic detection and segmentation. It is expected that this approach can significantly improve the performance of detection and segmentation models on real lunar topography images.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.3
• /
• pp.47-53
• /
• 2002

In this paper, we proposed a content-based video search method using the eigen value of key frame and intensity component. We divided the video stream into shot units to extract key frame representing each shot, and get the intensity distribution of the shot from the database generated by using ECA(Eigen Component Analysis). The generated codebook, their index value for each key frame, and the intensity values were used for database. The query image is utilized to find video stream that has the most similar frame by using the euclidean distance measure among the codewords in the codebook. The experimental results showed that the proposed algorithm is superior to any other methols in the search outcome since it makes use of eigen value and intensity elements, and reduces the processing time etc.

• Korean Journal of Remote Sensing
• /
• v.29 no.1
• /
• pp.137-149
• /
• 2013

Solar insolation is essential to understand the interaction between the earth and solar system, and it is a significant parameter that is utilized in various research fields including earth science, agriculture, and energy engineering. Although solar insolation is broadly measured in the ground-based observation station, it is difficult to identify the spatial distribution of solar insolation accurately. The remote sensing approach is known to have several benefits because it can provide continuous data sets for large area. In this study, we conducted the validation of solar insolation from COMS in the South Korea by comparing with flux tower observation. The results showed that the correlations between COMS and observation were high in both 30 minutes interval data and daily average data. Thus, we can identify that COMS can provide a reasonable estimate of solar insolation.

• Journal of the Korean Society of Groundwater Environment
• /
• v.1 no.2
• /
• pp.113-120
• /
• 1994

One of the delicate problems in aquifer management is the identification of the spatial distribution of tile hydrological parameters. The observed data are insufficient to identify the distribution of transmissivities in LAN aquifer. To determine the distribution of the transmissivity in LAN aquifer, it would be required to transform the observed heads at the pilot points into transmissivities. Therefore, three procedures wire tackled for the identification of the spatial distribution of the hydrological parameters; geostatistical estimate of the parameter field on the basis of known well point, heads reconstructed by a numerical model, and modification of the values at pilot points by a minimization algorithm. The variogram of Kriging has been applied to a total of 258 transmissivity value in attempt to quantify their distribution of LAN aquifer. Variogram of the observed and optimized transmissivities at pilot points are adapted to the exponential form. So, it is fitted by theoretical one with coefficients of w=0.623, a=2.743. Values of head obtained through numerical analysis are adjusted to the observed values so that heads have been transformed completely into the transmissivities at the observation wells. The procedure represented contour map of the estimated transmissivities and the calculated head.

• Journal of Korea Multimedia Society
• /
• v.7 no.4
• /
• pp.550-558
• /
• 2004

Previous researches on scalability problem of distributed virtual environment (DVE) have been mainly focused on spatial partitioning of area of interest (AOI). Congestion phenomena by avatar groups in AOI have been neglected relatively However, AOI congestion is highly related to scalability of DVE because it exhausts system resources such as network bandwidth and rendering time, and could be a bar to perform collaboration among participants. In this paper, this will be defined as the problem that must be solved for the realization of the scalable DVE, and a model will be proposed to measure and control congestion situation in AOI. The purposes of the proposed model are to prevent high density of participants in AOI, and to protect stable collaboration in DVE. For evaluation of the performance it is compared with a previous method by defining the resource cost model which is dynamically activated to AOI congestion.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.744-749
• /
• 2007

물체 추적시스템은 비디오 감시 시스템, 화상회의 시스템과 같은 다양한 비전 응용 분야에서 점점 비중이 높아지고 있다. 이 시스템에서 가장 널리 사용되고 있는 방법 중 하나로 Particle-Filter를 들 수 있다. 하지만, 이 Particle-Filter의 단점은 유사한 여러 물체를 추적할 때에 그 물체들이 겹치거나 사라질 경우 정확한 추적을 하기 어렵다는 것이다. 이 단점을 극복하기 위해 많은 연구가 진행되고 있으며, 본 논문에서는 이 문제를 극복하기 위한 새로운 방법을 제안하고자 한다. 다중 물체 추적에서 빈번히 일어나는 문제는 두 가지로 요약할 수 있는데, 동일한 다중 물체가 부분적으로 엇갈리거나 다른 객체에 완전히 겹친 후 떨어질 때 한 물체를 중복하여 추적하는 문제(merge and split problem)와 이 때 분리되어 추적은 됐지만, 물체를 혼동하여 추적하는 문제(Labeling problem)이다. 본 논문에서는 이 러한 문제들을 풀기 위해 이미지 필드에서 보다 정확한 확률분포를 만들고, 이 확률분포의 신뢰성을 높이기 위해서 물체의 특징정보를 표현하는 몇 가지 방법을 제안한다. 전자의 문제는 두 가지 문제로 나누어 생각해 보았다. 첫째, 복잡환 환경에서의 분포를 찾아내는 것과 둘째, 추적 중인 물체를 잃어버릴 경우 새로운 샘플을 생성함으로써 나누어 보았다. 이 문제 중 첫번째는 K-means 클러스터링을 이용하여 유사한 물체가 주변에 퍼져 있을 때, 하나의 후보 위치가 아닌, K개의 후보 위치들을 만들어 내어 보다 정확한 추적이 가능하게 하였으며, 두 번째 문제는 추적 중인 물체가 다른 커다란 물체에 가려질 경우이다. 이 상황에서 샘플을 생성하는 방법은 지금까지 해왔던 간단한 환경에서의 생성 범위와는 다르게 넓게 해야 생성시켜야 한다. 이 때 샘플링의 수를 늘리지 않으면서, 최대한 정확하게 추적하기 위해서 동영상에서 물체의 모션을 이용한 모션 히스토그램을 얻어내고, 그 정보를 이용하여 샘플을 생성하는 위치를 조절함으로써 이 문제를 풀어 보았다. 그리고, 후자의 문제인 이미지 필드상에서 확률분포의 신뢰성을 높이기 위한 특징 정보는 기존에 많이 사용하던 칼라 히스토그램에 공간정보의 의미를 부여하는 칼라 히스토그램을 분할하는 방법과 SIFT에서 사용하는 방향정보와 크기정보를 사용했다. 이것들을 사용하여 보다 정확한 물체추적시스템을 다음과 같이 제안한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.8B
• /
• pp.1577-1585
• /
• 1999

In this paper, we propose detection methods for gradual scene changes such as dissolve, pan, and zoom. The proposal method to detect a dissolve region uses scene features based on spatial statistics of the image. The spatial statistics to define shot boundaries are derived from squared means within each local area. We also propose a method of the camera motion detection using four representative motion vectors in the background. Representative motion vectors are derived from macroblock motion vectors which are directly extracted from MPEG streams. To reduce the implementation time, we use DC sequences rather than fully decoded MPEG video. In addition, to detect the gradual scene change region precisely, we use all types of the MPEG frames(I, P, B frame). Simulation results show that the proposed detection methods perform better than existing methods.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.1
• /
• pp.1-16
• /
• 2020

With the advent of the fourth industrial revolution era, there has been a growing interest in deep learning using big data, and studies using deep learning have been actively conducted in various fields. In the transportation sector, there are many advantages to using deep learning in research as much as using deep traffic big data. In this study, a short -term travel speed prediction model using LSTM, a deep learning technique, was constructed to predict the travel speed. The LSTM model suitable for time series prediction was selected considering that the travel speed data, which is used for prediction, is time series data. In order to predict the travel speed more precisely, we constructed a model that reflects both temporal and spatial effects. The model is a short-term prediction model that predicts after one hour. For the analysis data, the 5minute travel speed collected from the Seoul Transportation Information Center was used, and the analysis section was selected as a part of Gangnam where traffic was congested.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.1
• /
• pp.6-11
• /
• 2003

Recently, the modular network was proposed in a way to keep the size of the neural network small. The modular network solves the problem by splitting it into sub-problems. In this aspect, fuzzy systems act in a similar way. However, in a fuzzy system, there must be an expert rule which separates the input space. To overcome this, fuzzy-neural network has been used. However, the number of fuzzy rules grows exponentially as the number of input variables grow. In this paper, we would like to solve the size problem of neural networks using modular network with the hierarchic structure. In the hierarchic structure, the output of precedent module affects only the THEN part of the rule. Finally, the rules become shorter being compared to the rule of fuzzy-neural system. Also, the relations between input and output could be understood more easily in the Proposed modular network and that makes design easier.