• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.6
• /
• pp.555-567
• /
• 2023

The cracks in the tunnel are currently determined through visual inspections conducted by inspectors based on images acquired using tunnel imaging acquisition systems. This labor-intensive approach, relying on inspectors, has inherent limitations as it is subject to their subjective judgments. Recently research efforts have actively explored the use of deep learning to automatically detect tunnel cracks. However, most studies utilize public datasets or lack sufficient objectivity in the analysis process, making it challenging to apply them effectively in practical operations. In this study, we selected test datasets consisting of images in the same format as those obtained from the actual inspection system to perform an objective evaluation of deep learning models. Additionally, we introduced ensemble techniques to complement the strengths and weaknesses of the deep learning models, thereby improving the accuracy of crack detection. As a result, we achieved high recall rates of 80%, 88%, and 89% for cracks with sizes of 0.2 mm, 0.3 mm, and 0.5 mm, respectively, in the test images. In addition, the crack detection result of deep learning included numerous cracks that the inspector could not find. if cracks are detected with sufficient accuracy in a more objective evaluation by selecting images from other tunnels that were not used in this study, it is judged that deep learning will be able to be introduced to facility safety inspection.

• Science of Emotion and Sensibility
• /
• v.13 no.1
• /
• pp.47-60
• /
• 2010

Most of the researches about classification usually have used kNN(k-Nearest Neighbor), SVM(Support Vector Machine), which are known as learn-based model, and Bayesian classifier, NNA(Neural Network Algorithm), which are known as statistics-based methods. However, there are some limitations of space and time when classifying so many web pages in recent internet. Moreover, most studies of classification are using uni-gram feature representation which is not good to represent real meaning of words. In case of Korean web page classification, there are some problems because of korean words property that the words have multiple meanings(polysemy). For these reasons, LSA(Latent Semantic Analysis) is proposed to classify well in these environment(large data set and words' polysemy). LSA uses SVD(Singular Value Decomposition) which decomposes the original term-document matrix to three different matrices and reduces their dimension. From this SVD's work, it is possible to create new low-level semantic space for representing vectors, which can make classification efficient and analyze latent meaning of words or document(or web pages). Although LSA is good at classification, it has some drawbacks in classification. As SVD reduces dimensions of matrix and creates new semantic space, it doesn't consider which dimensions discriminate vectors well but it does consider which dimensions represent vectors well. It is a reason why LSA doesn't improve performance of classification as expectation. In this paper, we propose new LSA which selects optimal dimensions to discriminate and represent vectors well as minimizing drawbacks and improving performance. This method that we propose shows better and more stable performance than other LSAs' in low-dimension space. In addition, we derive more improvement in classification as creating and selecting features by reducing stopwords and weighting specific values to them statistically.

• Journal of the Economic Geographical Society of Korea
• /
• v.11 no.1
• /
• pp.59-77
• /
• 2008

The purpose of this study is to investigate the impact of traffic-related air pollution on the urban population in the Metropolitan Seoul area. In particular, this study analyzes urban population exposure to traffic-related particulate materials(PM). For the purpose, this study examines the relationships between traffic flows and PM concentration levels during the last fifteen years. Traffic volumes have been decreased significantly in recent year in Seoul, however, PM levels have been declined less compare to traffic volumes. It may be related with the rapid growth in the population and vehicle numbers in Gyenggi, the outskirt of Seoul, where several New Towns have been developed in the middle of 1990's. The spatial pattern of commuting has changed, and thus and travel distances and traffic volumes have increased along the main roads connecting CBDs in Seoul and New Towns consisting of large residential apartment complexes. These changes in traffic flows and travel behaviors cause increasing exposure to traffic-related air pollution for urban population over the Metropolitan Seoul area. GIS techniques are applied to analyze the spatial patterns of traffic flows, population distributions, PM distributions, and passenger flows comprehensively. This study also analyzes real time base traffic flow data and passenger flow data obtained from T-card transaction database applying data mining techniques. This study also attempts to develop a space-time model for assessing journey-time exposure to traffic related air pollutants based on travel passenger frequency distribution function. The results of this study can be used for the implications for sustainable transport systems, public health and transportation policy by reducing urban air pollution and road traffics in the Metropolitan Seoul area.

• The KIPS Transactions:PartA
• /
• v.12A no.2 s.92
• /
• pp.127-136
• /
• 2005

This paper measured a proper ratio of the size of demand fetch cache $L_1$ to that of prefetch cache $L_P$ by imulation when the size of $L_1$ and $L_P$ are constant which organize space-limited level 1 cache of a single microprocessor chip. The analysis of our experiment showed that in the condition of the sum of the size of $L_1$ and $L_P$ are 16 KB, the level 1 cache organization by constituting $L_P$ with 4 KB and employing OBL and FIFO as a prefetch technique and a cache replacement policy respectively resulted in the best performance. Also, this analysis showed that in the condition of the sum of the size of $L_1$ and $L_P$ are over 32 KB, employing dynamic filtering as prefetch technique of $L_P$ are more advantageous and splitting level 1 cache by constituting $L_1$ with 28 KB and $L_P$ with 4 KB in the case of 32 KB of space are available, by constituting $L_1$ with 48 KB and $L_P$ with 16 KB in the case of 64 KB elicited the best performance.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.11 no.1
• /
• pp.11-22
• /
• 2009

Tunnel excavation with several sections and appropriate auxiliary measures such as face bolt and pre-grouting are widely used in case of weak and less rigid ground for the stability of a tunnel face during excavation. This papers first described the evaluation methods proposed in technical literature to maintain the tunnel face stable, and then studied by FEM analysis whether face reinforcement is need in what degree of ground deformation and strength features for the stability of a tunnel face when excavating by full excavation with sub-bench. Lastly, a three dimensional FEM analysis was performed to study how the tunnel face itself and the ground around the tunnel behave depending on different bolt layouts, length of bolts, number of bolts. There were relative differences in comparison of results on the stability of a tunnel face by a theoretical evaluation methods and FEM analysis, but the same in reinforced effect of face. It was found that the stability of a tunnel face can be obtained with face bolt installed longer than 1.0D (tunnel width), bolt density of about 1 bolt per every $1.5\;m^2$ (layout of grid type), and reinforcement area of $120^{\circ}$ arch area of upper section.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.21-29
• /
• 2011

At existing skin detection methods using skin color information defined based on the prior knowldege, threshold value to be used at the stage of dividing the backround and the skin region was decided on a subjective point of view through experiments. Also, threshold value was selected in a passive manner according to their background and illumination environments in these existing methods. These existing methods displayed a drawback in that their performance was fully influenced by the threshold value estimated through repetitive experiments. To overcome the drawback of existing methods, this paper propose a skin region detection method using a histogram approximation based on the mean shift algorithm. The proposed method is to divide the background region and the skin region by using the mean shift method at the histogram of the skin-map of the input image generated by the comparison of the similarity with the standard skin color at the CbCr color space and actively finding the maximum value converged by brightness level. Since the histogram has a form of discontinuous function accumulated according to the brightness value of the pixel, it gets approximated as a Gaussian Mixture Model (GMM) using the Bezier Curve method. Thus, the proposed method detects the skin region by using the mean shift method and actively finding the maximum value which eventually becomes the dividing point, not by using the manually selected threshold value unlike other existing methods. This method detects the skin region high performance effectively through experiments.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.39 no.11
• /
• pp.24-32
• /
• 2002

In this paper we implemented various image processing filtering using the format converter. This design method is based on realized the large processor-per-pixel array by integrated circuit technology. These two types of integrated structure are can be classify associative parallel processor and parallel process DRAM(or SRAM) cell. Layout pitch of one-bit-wide logic is identical memory cell pitch to array high density PEs in integrate structure. This format converter design has control path implementation efficiently, and can be utilize the high technology without complicated controller hardware. Sequence of array instruction are generated by host computer before process start, and instructions are saved on unit controller. Host computer is executed the pixel-parallel operation starting at saved instructions after processing start. As a result, we obtained three result that 1)simple smoothing suppresses higher spatial frequencies, reducing noise but also blurring edges, 2) a smoothing and segmentation process reduces noise while preserving sharp edges, and 3) median filtering, like smoothing and segmentation, may be applied to reduce image noise. Median filtering eliminates spikes while maintaining sharp edges and preserving monotonic variations in pixel values.

• Tunnel and Underground Space
• /
• v.33 no.6
• /
• pp.547-560
• /
• 2023

Recently, research on predicting ground classification using machine learning techniques, TBM excavation data, and ground data is increasing. In this study, a multi-classification prediction study for uniaxial compressive strength (UCS) was conducted by applying random forest model based on a decision tree among machine learning techniques widely used in various fields to machine data and ground data acquired at three slurry shield TBM sites. For the classification prediction, the training and test data were divided into 7:3, and a grid search including 5-fold cross-validation was used to select the optimal parameter. As a result of classification learning for UCS using a random forest, the accuracy of the multi-classification prediction model was found to be high at both 0.983 and 0.982 in the training set and the test set, respectively. However, due to the imbalance in data distribution between classes, the recall was evaluated low in class 4. It is judged that additional research is needed to increase the amount of measured data of UCS acquired in various sites.

• Journal of Wetlands Research
• /
• v.14 no.4
• /
• pp.657-665
• /
• 2012

The development projects distort the natural water circulation system and increase the non-point source pollution by changing the natural cover type. The low impact development (LID) techniques are considering as new development approach to decrease the ecological- and hydrological impacts from high imperviousness rate. The high imperviousness rate is because of the construction of building, parking lot and road for human activities. Knowing the basic characteristics of rood runoff can give the direction for setting up the water management strategy. The monitoring results show the pollutant EMCs of roof runoff are 3~13 times lower than EMCs of the road and parking lot. The pollutant sources from roof runoff are mainly from leafs, cigarette butts, atmospheric deposition and materials of the roof. The EMC is occurred around 15minutes later after starting runoff and more than 8 storm events are needed to have the average EMCs.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2007.05a
• /
• pp.162-167
• /
• 2007

수질오염총량관리제에서 단위유역 할당부하량은 지자체의 개발용량과 밀접한 관계를 가지고 있기 때문에 상 하류 지역간의 첨예한 관심거리가 되고 있다. 총량관리제는 기준유량과 목표수질에 대한 기준배출부하량의 달성을 목적으로 하고 있기 때문에 합리적이고 과학적인 기준유량 및 목표수질의 설정이 무엇보다 중요하다. 또한 합리적인 수질모델링을 필요로 하는데, 유량배분은 모델링 과정에서 중요한 영향을 미치며, 지역의 기준배출부하량을 결정하는 결정적인 요소 중의 하나이다. 기존의 유량배분은 대부분 관측지점을 기준으로 한 단순한 면적비 유량배분기법(SAWA; simple area-based water-balance analysis)에 의존해왔다. 그러나 SAWA는 특정유역의 토지피복, 토양, 지형경사 및 강우분포 등의 수문학적 특성을 고려하지 못하는 한계점을 가지고 있다. 즉, 동일한 면적의 유역이라도 이러한 수문 특성인자에 따라 유출되는 유량이 달라지는 현상을 고려하지 못하고 있다. 이는 곧 지역의 기준배출부하량의 신뢰성에 영향을 미치기 때문에 지역간 분쟁의 소지가 될 수 있다. 본 연구는 기존의 유량배분 방법인 SAWA가 가지는 한계점을 극복하고자 강우분포 및 토지피복의 수문학적 특성을 이용한 유량배분기법(HIWA; hydro-infomatical water-balance analysis)의 개발을 목적으로 수행되었다. 강우분포와 토지피복이 하천유량에 미치는 영향을 분석하고 공간정보화 한 후 지형정보체계(GIS)의 수문분석 기법을 이용하여 유량을 배분하였다 ARC/INFO의 KRIGING 보간법을 이용하여 구축한 등강우분포도와 토지피복에 따른 유출특성을 분석하여 강우유출 해석을 위한 가중지형정보를 생성하였다. 연구는 2003년 10월-2004년 3월의 미호천수계 및 수질오염총량관리단위유역 말단지점의 실측자료를 이용하였으며, 연구결과 기존의 SAWA보다 본 연구에서 제안한 HIWA가 유량배분의 정확도를 높일 수 있음이 입증되었다.