• Journal of the Korean Society of Propulsion Engineers
• /
• v.26 no.4
• /
• pp.54-63
• /
• 2022

A 3-tonf class liquid rocket engine that powers the upper stage of a small launcher and lifts 500 kg payload to 500 km SSO is designed. The small launcher is to utilize the flight-proven technology of the 75-tonf class engine for the first stage. A combination of liquid oxygen and liquid methane has been selected as their cryogenic states can provide an extra boost in specific impulse as well as enable a weight saving via the common dome arrangement. An expander cycle is chosen among others as the low-pressure operation makes it robust and reliable while a specific impulse of over 360 seconds is achievable with the nozzle extension ratio of 120. Key components such as combustion chamber and turbopump are designed for additive manufacturing to a target cost. The engine system provides an evaporated methane for the autogenous pressurization system and the reaction control of the stage. This upper stage propulsion system can be extended to various missions including deep space exploration.

• Journal of the Korean Institute of Gas
• /
• v.27 no.1
• /
• pp.70-77
• /
• 2023

Air environment regulations have been strengthened due to increasing air pollutant emissions, the target of reducing emissions has increased and interest in gas measurement methods is also increasing. The sampling method is mainly used, but due to the spatial and temporal measurement limitations, the laser absorption spectroscopy which is a real-time and in-situ method is in the spotlight. In this study, we studied the wavelength modulation spectroscopy and described the calibration-free algorithm. The developed algorithm was modified to reflect 46 multi-absorption lines and was applied to light absorption signal analysis in visible and mid-infrared regions. In addition, the difference between the modulation parameters of laser was analyzed. As a result of reviewing the performance through O₂ and NO gas measurement experiments of various concentration conditions, the linearity was R²_O2=0.99999 and R²_NO=0.99967.

• Smart Media Journal
• /
• v.11 no.2
• /
• pp.77-83
• /
• 2022

The neuromorphic architecture uses a spiking neural network (SNN) model to derive more accurate results as more spike values are accumulated through inference experiments. When the inference result converges to a specific value, even if the inference experiment is further performed, the change in the result is smaller and power consumption may increase. In particular, in an AI-based IoT environment, power consumption can be a big problem. Therefore, in this paper, we propose a technique to reduce the power consumption of AI-based IoT by reducing the inference time by adjusting the inference image exposure time in the neuromorphic architecture environment. The proposed technique calculates the next inferred image exposure time by reflecting the change in inference accuracy. In addition, the rate of reflection of the change in inference accuracy can be adjusted with a coefficient value, and an optimal coefficient value is found through a comparison experiment of various coefficient values. In the proposed technique, the inference image exposure time corresponding to the target accuracy is greater than that of the linear technique, but the overall power consumption is less than that of the linear technique. As a result of measuring and evaluating the performance of the proposed method, it is confirmed that the inference experiment applying the proposed method can reduce the final exposure time by about 90% compared to the inference experiment applying the linear method.

• Journal of agriculture & life science
• /
• v.50 no.3
• /
• pp.31-41
• /
• 2016

This study was conducted to develop a handy earth auger for use in sloppy and rugged forest terrains in order to reduce labor cost which comprises a major part of the production costs in forest afforestation projects. The first prototype is developed consist of two parts, the soil-digging screw and the battery power source. The specifications of the first prototype screw are: length of 170mm, a top diameter of 60mm, bottom diameter of 47mm, 23° angle for each helix, and a 50mm awl-head tip. The use of a single line of screw was selected for reduced weight. In addition, a power source of rotary DC Motor(WD-6G2425, WONILL, Korea) with a maximum torque of 30kgf-cm, rotation of 20-30rpm, K6G30C decelerator with a reduction ratio of 30:1 which could be used with no load for 48 was operated. In consideration of its weight, a lithium battery was utilized in line with the goal of developing a lightweight auger. In order to evaluate the performance of the first prototype, test sites were selected as 6 areas. The rotational force was found to be highest in area A(Solid area), followed by areas F(Mounted slope 40° area) and E(Mounted slope 30° area). It was also observed that in general, the rotational force increased along with the increase in soil depth with the maximum rotational force recorded at 10cm.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.2A
• /
• pp.171-179
• /
• 2009

The porosity in porous media like concrete can be considered as a durability index since it may be a routine for the intrusion of harmful ions and room for the keeping moisture. Recently, modeling and analysis techniques for deterioration are provided based on the pore structure with the significance of durability and the relationship between porosity and durability characteristics is an important issue. In this paper, a series of mortar samples with five water to cement ratios are prepared and tests for durability performance are carried out including porosity measurement. The durability test covers those for compressive strength, air permeability, chloride diffusion coefficient, absorption, and moisture diffusion coefficient. They are compared with water to cement ratios and porosity. From the normalized data, when porosity increases to 1.45 times, air permeability, chloride diffusion coefficient, absorption, and moisture diffusion coefficient decrease to 2.3 times, 2.1 times, 5.5 times and 3.7 times, respectively, while compressive strength decreases to 0.6 times. It was evaluated that these are linearly changed with porosity showing high corelation factors. Additionally, intended durability performances are established from the test results and literature studies and a porosity for durable concrete is proposed based on them.

• The Bulletin of The Korean Astronomical Society
• /
• v.45 no.1
• /
• pp.56.1-56.1
• /
• 2020

한국의 고문헌 중에는 다양한 고천문 기록들이 한문 형태로 존재하며, 이를 학술적으로 활용하기 위해서는 전문 번역가 투입에 따른 많은 비용과 시간이 요구된다. 이에 인공신경망 기계학습에 의한 인공지능 번역기를 개발하여 비록 초벌 번역 수준일지라도 문장 형태의 한문을 한글로 자동번역해 주는 학술 도구를 소개하고자 한다. 이 자동번역기는 한국천문연구원이 한국정보화진흥원이 주관하는 2019년도 Information and Communication Technology 기반 공공서비스 촉진사업에 한국고전번역원과 공동 참여하여 개발 완료한 것이다. 이 연구는 고천문 도메인에 특화된 인공지능 기계학습용 데이터인 천문 고전 코퍼스를 구축하여 이를 기반으로 천문 고전 특화 자동번역 모델을 개발하고 번역 서비스하는 것을 목적으로 한다. 이를 위해 구축되는 시스템은 크게 세 가지이다. 첫째, 로그인이 필요 없이 누구나 웹 접속을 통해 사용이 가능한 클라우드 기반의 고문헌 자동번역 대국민서비스 시스템이다. 둘째, 참여 기관별로 구축된 코퍼스와 도메인 특화된 번역 모델의 생성 및 관리할 수 있는 클라우드 기반의 대기관 서비스 플랫폼 구축이다. 셋째, 개발된 자동번역 Applied Programmable Interface를 활용한 한국천문연구원 내 자체 서비스가 가능한 AITHA 시스템이다. 연구 결과로서 먼저 구축된 천문 고전 코퍼스 60,760건에 대한 샘플링 검수 결과는 품질 순도 99.9% 이상이다. 아울러 도출된 천문 고전 특화 번역 모델 총 20개 중 대표 모델에 대한 성능 평가 결과는 기계 번역 텍스트 품질 평가 알고리즘인 Bilingual Evaluation Understudy 평가에서 40.02점이며, 전문가에 의한 휴먼 평가에서 5.0 만점 중 4.05점이다. 이는 당초 연구 목표로 삼았던 초벌 번역 수준에 충분하며, 현재 개발된 시스템들은 자체 시험 운영 중이다. 이 연구는 특수 고문헌에 해당되는 고천문 기록들의 번역 장벽을 낮춰 관련 연구자들의 학술적 접근 및 다양한 연구에 도움을 줄 수 있다는 점에서 의의가 있다. 또한 고천문 분야가 인공지능 자동번역 확산 플랫폼 시범의 첫 케이스로써 추후 타 학문 분야 참여 시 시너지 효과도 기대해 볼 수 있다. 고문헌 자동번역기는 점차 더 많은 학습 데이터와 학습량이 쌓일수록 더 좋은 학술 도구로 진화할 것이다.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.5
• /
• pp.217-228
• /
• 2023

Video instance segmentation is an intelligent visual task with high complexity because it not only requires object instance segmentation for each image frame constituting a video, but also requires accurate tracking of instances throughout the frame sequence of the video. In special, human instance segmentation in drama videos has an unique characteristic that requires accurate tracking of several main characters interacting in various places and times. Also, it is also characterized by a kind of the class imbalance problem because there is a significant difference between the frequency of main characters and that of supporting or auxiliary characters in drama videos. In this paper, we introduce a new human instance datatset called MHIS, which is built upon drama videos, Miseang, and then propose a novel video data augmentation method, CDVA, in order to overcome the data imbalance problem between character classes. Different from the previous video data augmentation methods, the proposed CDVA generates more realistic augmented videos by deciding the optimal location within the background clip for a target human instance to be inserted with taking rich spatio-temporal context embedded in videos into account. Therefore, the proposed augmentation method, CDVA, can improve the performance of a deep neural network model for video instance segmentation. Conducting both quantitative and qualitative experiments using the MHIS dataset, we prove the usefulness and effectiveness of the proposed video data augmentation method.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.42-42
• /
• 2022

지금까지도 유역에서의 녹조 모니터링은 현장채수를 통한 점 단위 모니터링에 크게 의존하고 있어 기후, 유속, 수온조건 등에 따라 수체에 광범위하게 발생하는 녹조를 효율적으로 모니터링하고 대응하기에는 어려운 점들이 있어왔다. 또한, 그동안 제한된 관측 데이터로 인해 현장 측정된 실측 데이터 보다는 녹조와 관련이 높은 NDVI, FGAI, SEI 등의 파생적인 지수를 산정하여 원격탐사자료와 매핑하는 방식의 분석연구 등이 선행되었다. 본 연구는 녹조의 모니터링시 정확도와 효율성을 향상을 목표로 하여, 우선은 녹조 측정장비를 활용, 7000개 이상의 녹조 관측 데이터를 확보하였으며, 이를 바탕으로 동기간의 고해상도 위성 자료와 실측자료를 매핑하기 위해 다양한Machine Learning기법을 적용함으로써 그 효과성을 검토하고자 하였다. 연구대상지는 낙동강 내성천 상류에 위치한 영주댐 유역으로서 데이터 수집단계에서는 면단위 현장(in-situ) 관측을 위해 2020년 2~9월까지 4회에 걸쳐 7291개의 녹조를 측정하고, 동일 시간 및 공간의 Sentinel-2자료 중 Band 1~12까지 총 13개(Band 8은 8과 8A로 2개)의 분광특성자료를 추출하였다. 다음으로 Machine Learning 분석기법의 적용을 위해 algae_monitoring Python library를 구축하였다. 개발된 library는 1) Training Set과 Test Set의 구분을 위한 Data 준비단계, 2) Random Forest, Gradient Boosting Regression, XGBoosting 알고리즘 중 선택하여 적용할 수 있는 모델적용단계, 3) 모델적용결과를 확인하는 Performance test단계(R², MSE, MAE, RMSE, NSE, KGE 등), 4) 모델결과의 Visualization단계, 5) 선정된 모델을 활용 위성자료를 녹조값으로 변환하는 적용단계로 구분하여 영주댐뿐만 아니라 다양한 유역에 범용적으로 적용할 수 있도록 구성하였다. 본 연구의 사례에서는 Sentinel-2위성의 12개 밴드, 기상자료(대기온도, 구름비율) 총 14개자료를 활용하여 Machine Learning기법 중 Random Forest를 적용하였을 경우에, 전반적으로 가장 높은 적합도를 나타내었으며, 적용결과 Test Set을 기준으로 NSE(Nash Sutcliffe Efficiency)가 0.96(Training Set의 경우에는 0.99) 수준의 성능을 나타내어, 광역적인 위성자료와 충분히 확보된 현장실측 자료간의 데이터 학습을 통해서 조류 모니터링 분석의 효율성이 획기적으로 증대될 수 있음을 확인하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.212-215
• /
• 2022

In the era of so-called digital transformation today, the need for the construction and utilization of big data in various fields has increased. Today, a lot of data is produced and stored in a digital device and media-friendly manner, but the production and storage of data for a long time in the past has been dominated by print books. Therefore, the need for Optical Character Recognition (OCR) technology to utilize the vast amount of print books accumulated for a long time as big data was also required in line with the need for big data. In this study, a system for digitizing the structure and content of a document object inside a scanned book image is proposed. The proposal system largely consists of the following three steps. 1) Recognition of area information by document objects (table, equation, picture, text body) in scanned book image. 2) OCR processing for each area of the text body-table-formula module according to recognized document object areas. 3) The processed document informations gather up and returned to the JSON format. The model proposed in this study uses an open-source project that additional learning and improvement. Intelligent OCR proposed as a system in this study showed commercial OCR software-level performance in processing four types of document objects(table, equation, image, text body).

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.10
• /
• pp.299-308
• /
• 2023

As the spectrum shortage problem has accelerated by the emergence of various services, New Radio-Unlicensed (NR-U) has appeared, allowing users who communicated in licensed bands to communicate in unlicensed bands. However, NR-U network users reduce the performance of Wi-Fi network users who communicate in the same unlicensed band. In this paper, we aim to simultaneously maximize the fairness and throughput of the unlicensed band, where the NR-U network users and the WiFi network users coexist. First, we propose an optimal power allocation scheme based on Monte Carlo Policy Gradient of reinforcement learning to maximize the sum of rates of NR-U networks utilizing rate-splitting multiple access in unlicensed bands. Then, we propose a channel occupancy time division algorithm based on sequential Raiffa bargaining solution of game theory that can simultaneously maximize system throughput and fairness for the coexistence of NR-U and WiFi networks in the same unlicensed band. Simulation results show that the rate splitting multiple access shows better performance than the conventional multiple access technology by comparing the sum-rate when the result value is finally converged under the same transmission power. In addition, we compare the data transfer amount and fairness of NR-U network users, WiFi network users, and total system, and prove that the channel occupancy time division algorithm based on sequential Raiffa bargaining solution of this paper satisfies throughput and fairness at the same time than other algorithms.