Liquefied hydrogen is attracting attention as an energy source of the future due to its hydrogen storage rate and low risk. However, the disadvantage is that the unit price is high due to technical difficulties in production, transportation, and storage. This study was conducted to improve the design accuracy and development period of needle valves, which are important parts with a wide technical application range among liquefied hydrogen equipment. Since the needle valve must discharge an appropriate flow rate of the liquefied fluid, it is important to determine the needle valve design parameters suitable for the target flow rate. Computational Fluid Dynamics and Artificial Neural Network technology used to determine the design variables of fluid flow were applied to improve the setting and analysis time of the parameter. In addition, procedures and methods for applying the design parameter of needle valves to Convolutional Neural Networks were presented. The procedure and appropriate conditions for selecting parameters and functional conditions of the Convolutional Neural Network were presented, and the accuracy of predicting the flow coefficient according to the design parameter was secured 95%. It is judged that this method can be applied to other structures and machines.

In this study we present a new approach to estimating termite populations size. So far, termite researchers have been using the mark-capture-recapture method. This method has a disadvantage that measurement time is long and error range is large. To this end, we built an agent-based model to simulate termite tunneling behavior. Using this model, we made simulated tunnel patterns that are determined by three variables: the number of simulated termites (N), the passing probability of two encountering termites (P), and the distance that termites move soil parcels (D). To explore whether the N value can be estimated with a partial termite tunnel pattern, we generated four groups of tunnel patterns that are partially obscured in complete tunnel pattern image: (1) A pattern group in which the outer area of the tunnel pattern is obscured (I-pattern), (2) a pattern group in which half of the tunnel pattern is obscured (H-pattern), (3) a pattern group in which the inner region of the tunnel pattern is obscured (O-pattern), and (4) a pattern group combining I- and O-pattern (IO-pattern). For each group, 80% of the tunnel patterns were learned through a convolution neural network (CNN) and the remaining 20% of the patterns were used for estimating N value. The estimation results showed that the N estimates for the IO-pattern are the most accurate and are in the order I-, H-, and O-patterns. This means that the termite population size can be estimated based on tunnel information near the center of the colony.

Three CNN (Convolutional Neural Network) models of GoogLeNet, VGGNet, and Alexnet were evaluated to select the best deep learning based image analysis mothod that can detect pavement distresses of pothole, spalling, and punchout on expressway. Education data was obtained using pavement surface images of 11,056km length taken by Gopro camera equipped with an expressway patrol car. Also, deep learning framework of Caffe developed by Berkeley Vision and Learning Center was evaluated to use the three CNN models with other frameworks of Tensorflow developed by Google, and CNTK developed by Microsoft. After determing the optimal CNN model applicable for the distress detection, the analyzed images and corresponding GPS locations, distress sizes (greater than distress length of 150mm), required repair material quantities are trasmitted to local maintenance office using LTE wireless communication system through ICT center in Korea Expressway Corporation. It was found out that the GoogLeNet, AlexNet, and VGG-16 models coupled with the Caffe framework can detect pavement distresses by accuracy of 93%, 86%, and 72%, respectively. In addition to four distress image groups of cracking, spalling, pothole, and punchout, 22 different image groups of lane marking, grooving, patching area, joint, and so on were finally classified to improve the distress detection rate.

본 논문에서는 게임 영상에 대한 색연필 드로잉 렌더링 기법을 제안한다. 제안하는 방법의 키 아이디어는 양방향 회선 필터(bilateral convolution filter)를 이용하여 다양한 스타일의 연필 스트로크를 만드는 것이다. 이 필터는 기존의 컨볼루션 기반 기법들과 달리 경계 흐림 현상을 획기적으로 보완하였다. 더불어 연필 스트로크의 속성들을 직관적으로 제어할 수 있도록 한다. 또한 그릴 물체의 모양으로부터 스트로크 방향을 결정하는 기법을 제안한다. 특징선(feature line)에 가까운 픽셀들에 대해서는 완만한 탄젠트 흐름(smooth tangent flow)을 사용하고, 영역의 내부에는 부분적으로 유사한 흐름을 사용한다. 배경에는 고정된 방향의 흐름을 사용한다. 이처럼 다른 스타일의 스트로크 방향을 사용함으로써, 결과 연필화의 현실성을 증가시킬 수 있다. 제안하는 방법은 사진에 대해 시각적으로 만족스러운 연필 드로잉 효과를 만들어 낸다.

Ground penetrating radar (GPR) is a typical sensor system for underground objects detection area. The multichannel GPR devices can give more detail and informative three-dimensional (3D) data for classification underground objects. Spatial information of underground objects can be well characterized in the three-dimensional GPR block data which consists of several B-scan and C-scan data. In this article underground object classification method is proposed by using 3D GRP data. Deep learning technique is recently being adopted into this field due to its powerful image classification capacity. The 3D GRP block data is then used to train deep three-dimensional convolution neural network (3D CNN). The proposed method successfully classifies cavity, pipe, manhole and subsoils having small false positive errors. The suggested method is experimentally validated by area data collected on urban roads in Seoul, South Korea.

Groundwater level hydrographs from observation wells in Jeju island clearly illustrate distinctive features of recharge showing the time-delaying and dispersive process, mainly affected by the thickness and hydrogeologic properties of the unsaturated zone. Most groundwater flow models have limitations on delineating temporal variation of recharge, although it is a major component of the groundwater flow system. Recently, a convolution model was suggested as a mathematical technique to generate time series of recharge that incorporated the time-delaying and dispersive process. A groundwater flow model was developed to simulate transient groundwater level fluctuations in Pyoseon area of Jeju island. The model used the convolution technique to simulate temporal variations of groundwater levels. By making a series of trial-and-error adjustments, transient model calibration was conducted for various input parameters of both the groundwater flow model and the convolution model. The calibrated model could simulate water level fluctuations closely coinciding with measurements from 8 observation wells in the model area. Consequently, it is expected that, in transient groundwater flow models, the convolution technique can be effectively used to generate a time series of recharge.

Temporal variation of groundwater levels in Jeju Island reveals time-delaying and dispersive process of recharge, mainly caused by the hydrogeological feature that thickness of the unsaturated zone is highly variable. Most groundwater flow models have limitations on delineating temporal variation of recharge, although it is a major component of the groundwater flow system. A new mathematical model was developed to generate time series of recharge from precipitation data. The model uses a convolution technique to simulate the time-delaying and dispersive process of recharge. The vertical velocity and the dispersivity are two parameters determining the time series of recharge for a given thickness of the unsaturated zone. The model determines two parameters by correlating the generated recharge time series with measured groundwater levels. The model was applied to observation wells of Jeju Island, and revealed distinctive variations of recharge depending on location of wells. The suggested model demonstrated capability of the convolution method in dealing with recharge undergoing the time-delaying and dispersive process. Therefore, it can be used in many groundwater flow models for generating a time series of recharge.

In order to fast predict the wind-driven current in a small bay, a convolution method in which the wind-driven current can be generated only with the local wind is developed and applied in the idealized bay and the idealized Sachon Bay. The accuracy of the convolution method is assessed through a series of the numerical experiments carried out in the idealized bay and the idealized Sachon Bay. The optimum response function for the convolution method is obtained by minimizing the root mean square (rms) difference between the current given by the numerical model and the current given by the convolution method. The north-south component of the response function shows simultaneous fluctuations in the wind and wind-driven current at marginal region while it shows "sea-saw" fluctuations (in which the wind and wind-driven current have opposite direction) at the central region in the idealized Sachon Bay. The present wind is strong enough to influence on the wind-driven current especially in the idealized Sachon Bay. The spatial average of the rms ratio defined as the ratio of the rms error to the rms speed is 0.05 in the idealized bay and 0.26 in the idealized Sachon Bay. The recover rate of kinetic energy(rrke) is 99% in the idealized bay and 94% in the idealized Sachon Bay. Thus, the predicted wind-driven current by the convolution model is in a good agreement with the computed one by the numerical model in the idealized bay and the idealized Sachon Bay.