Recently, many studies are being conducted to extract emotion from text and verify its information power in the field of finance, along with the recent development of big data analysis technology. A number of prior studies use pre-defined sentiment dictionaries or machine learning methods to extract sentiment from the financial documents. However, both methods have the disadvantage of being labor-intensive and subjective because it requires a manual sentiment learning process. In this study, we developed a financial sentiment dictionary that automatically extracts sentiment from the body text of analyst reports by using modified Bayes rule and verified the performance of the model through a binary classification model which predicts actual stock price movements. As a result of the prediction, it was found that the proposed financial dictionary from this research has about 4% better predictive power for actual stock price movements than the representative Loughran and McDonald’s (2011) financial dictionary. The sentiment extraction method proposed in this study enables efficient and objective judgment because it automatically learns the sentiment of words using both the change in target price and the cumulative abnormal returns. In addition, the dictionary can be easily updated by re-calculating conditional probabilities. The results of this study are expected to be readily expandable and applicable not only to analyst reports, but also to financial field texts such as performance reports, IR reports, press articles, and social media.
본 연구는 미중 경쟁이 심화되고 있는 오늘날, 동남아시아를 포괄한 동아시아 지역에 있어 일본의 원조 이념 변화가 미친 정책적 영향이 무엇이고 어떠한 함의를 가지고 있는가에 대한 질문에서 출발했다. 이 에 대한 연구의 주요 결론은 다음과 같다. 2000년대 이후 일본은 '원 조 이념의 변화'를 추진했고 이를 통해 기존의 '비군사화 규범' 중심의 원조 이념에서 벗어나 안전보장 규범을 적극적으로 수용했으며, 특히 해상법집행에 중점을 두고 동남아시아 국가의 해양능력구축을 지원하 고 있다. 이제까지 방산수출을 통한 접근은 전무하다고 보아도 좋을 정 도로 제한적이었으나, 원조 이념의 변화와 함께 방위장비 해외이전이 자유로워지고 '원조화'하면서 장기적으로는 변화의 가능성이 보이고 있 다. 한국은 일본의 사례를 참고하면서, 동남아시아 역내 국가들의 수요 와 우려가 무엇인지를 상대국 입장에서 파악하는 해양능력구축 지원을 추진할 필요가 있다.
Recently, local studies looking at the 'local(region) as a whole' are gradually increasing. The study of local architectural history is important in that it provides specific information that encompasses the local and the entire and clues to three-dimensionalize the time and space in the local. To infer the 'presentness' of each era, reliable data in various fields are needed. Recently, as many databases (DB) and archives, from the 'National Archives of Korea' to other local archives, have been established and publicized, research resources in the local are growing rapidly in quantity and quality. Nevertheless, it is difficult to comprehensively check the data necessary to study the local architectural history(local architectural history research resources). Against this background, this study confirmed the trend of changes in the archive construction environment and the status and problems of local architectural history research resources in places that currently disclose local history research resources among generalized web-archives. Next, the relationship between the actual research on local architectural history was confirmed through the analysis of existing studies and the data used for Jeju. As a result, local studies, local archives, and local architectural history research agree with recent changes in local research trends, and the degree of archival construction has reached the same level as the available research resources except core data in local architectural history research. However, there is a problem that the density of information that can be used is low because the local architectural history research resources that can be obtained are fragmented because there are no archives and construction entities specialized in local architecture. As each archive has entered the stabilization and upgrading stage, the construction of new archives needs to be reconsidered, but it is time to find a detailed way to link related information quickly and accurately, such as private records, to reduce the gap in information needed in terms of research on local architecture and architecture history.
The management of algal bloom is essential for the proper management of water supply systems and to maintain the safety of drinking water. Chlorophyll-a(Chl-a) is a commonly used indicator to represent the algal concentration. In recent years, advanced machine learning models have been increasingly used to predict Chl-a in freshwater systems. Machine learning models show good performance in various fields, while the process of model development requires considerable labor and time by experts. Automated machine learning(auto ML) is an emerging field of machine learning study. Auto ML is used to develop machine learning models while minimizing the time and labor required in the model development process. This study developed an auto ML to predict Chl-a using auto sklearn, one of most widely used open source auto ML algorithms. The model performance was compared with other two popular ensemble machine learning models, random forest(RF) and XGBoost(XGB). The model performance was evaluated using three indices, root mean squared error, root mean squared error-observation standard deviation ratio(RSR) and Nash-Sutcliffe coefficient of efficiency. The RSR of auto ML, RF, and XGB were 0.659, 0.684 and 0.638, respectively. The results shows that auto ML outperforms RF, and XGB shows better prediction performance than auto ML, while the differences between model performances were not significant. Shapley value analysis, an explainable machine learning algorithm, was used to provide quantitative interpretation about the model prediction of auto ML developed in this study. The results of this study present the possible applicability of auto ML for the prediction of water quality.
본 글의 문제의식은 위성정당 출현의 재발을 막기 위해 선거법에 대한 여야합의처리의 중요성을 강조하는 것이다. 본 글의 목적은 선거법 개정 방향의 대안을 모색하기 위해 여야합의가 깨진 상황에서 민주당의 다수 결주의에 따른 졸속적인 준연동형 비례제 선거법의 강행처리가 어떻게 위성정당을 제도화하고 21대 총선에서 양당제 효과를 구축하였는지를 인 과론적으로 살펴보는 데 있다. 당연한 결과이지만 이런 위성정당의 출현 과 제도화는 소수정당의 정치적 진출을 활성화하여 다당체제 구축 효과 를 기대했던 준연동형 비례제 선거법의 취지를 무력화하였다는 점에서, 졸속적인 선거법 논의과정과 다수결주의에 따른 강행처리의 문제점을 근 본적으로 시정해야 한다는 것을 강조하였다. 본 글에서는 “독일식 연동형 비례대표제” 대신 “한국식 병립형 비례대표제”로의 전환을 제언하고 있다.
PURPOSES : In this study, an existing speed-controlled Marshall stability tester was systemized as an Internet of Things(IoT) system. The Marshall stability test data were transmitted to the cloud in real-time, and an IoT optional-controlled board capable of additional load and displacement control was proposed.
METHODS : The IoT systemization was built based on an improvement of an IoT height measuring system, the re-verification of standard samples for comparative analysis, and the development of a wireless IG-IoT board. The developed wireless Induk-GeoTS(IG)-IoT board was compared with existing commercial data logger using displacement- and load- calibration equipment. After the conformity of the developed wireless IoT board was established, a urethane standard sample was reproduced and verified using the recipe presented in a previous study to conduct a round-robin test. In addition, the adequacy of the speed, load, and displacement control tests for the optional-controlled characteristics was verified. the round-robin test for the Marshall stability and deformation strength and the comparative test of indirect tensile strength with the existing Marshall tester were performed using the re-verified standard sample.
RESULTS : The improved two-point IoT height measurement system reduced the average relative error by 2.11% relative to the one-point measurement. From the re-verification results of the regenerated urethane standard sample, it was suitable with relative error of 3.65% in the loading elastic modulus and 4.07% in the unloading elastic modulus, compared to the existing standard sample. From the comparative analysis of the developed wireless IG-IoT board and existing commercial data logger, it was confirmed that the wireless IoT board could be reliably used, based on the average relative error of the wireless IoT board, 0.64% and that of the data logger, 3.79% in terms of the displacement(flow value) and an average relative error of 0.78% for the wireless IoT board and 0.79% for the data logger in terms of the load(stability). By analyzing the optional-controlled characteristics, it was found that the Marshall stability speed control conditions were satisfied based on the error results, with an average relative value of 2.96% under deformation strength test condition of 30mm/min, 3.23% under the indirect tensile strength test condition of 50mm/min, and 2.6% under the Marshall stability test condition of 50.8mm/min. It was also found that proper control characteristics were obtained, with an average relative error of 0.72% within the experimental load range in the load control conditions, and an average relative error of 2.4% in the experimental displacement range in the displacement control conditions. The results from the round-robin Marshall stability and deformation strength testing to verify the applicability of the IoT optional-controlled board show that the data were reliable based on the 3σ quality control method. In addition, by comparing the results of the indirect tensile strength tests, the usability of the wireless IG-IoT board was verified, with an average relative error of 0.96%. CONCLUSIONS : The IoT height measuring system was improved, and a wireless IG-IoT board that can transmit test data to a cloud platform was developed. The usability of the developed wireless IoT board was verified by round-robin testing using a re-verified urethane specimen. The IG-IoT optional-controlled board extends the verified wireless IG-IoT board, it was developed and validated for not only the existing speed control, but also for load, and displacement control.
‘한자고고학’은 “한자에 남겨진 흔적을 통해 그 배후의 말 없는 문화사를 발굴, 해 석하는 학문”이라 정의할 수 있다. 이는 한자를 대상으로, 특히 한자의 어원을 통해 이에 반영된 문화성을 밝히는 학문으로, 이의 증명에 언어문자학, 문헌학, 고고학, 인 류학 등의 자료들이 동원될 수 있다. 여기서는 ‘한자고고학’의 개념 정립을 비롯해 그 실천적 사례로 ‘일(壹)’자의 어원과 상징 분석을 통해 ‘한자고고학’의 방법론적 구 축 가능성을 검토했다. 이를 위해 (1)문자학적 측면에서 일(壹)의 어원과 상징, (2)고 고학적 측면에서의 호(壺)와 인면호(人面壺)의 상징, (3)인류학적 측면에서의 호리병 박 숭배 전통, (4)출토문헌에서의 관련 자료들, (5)확장적 연구로서의 여러 유사 자료 들도 함께 논의했다. 이를 통해 기존의 한자학을 문화연구로 그 영역을 확장시키고, 인접학문과의 접속 속에서 그간의 한자 내부에 한정되었던 시선을 밖으로 확장함으 로써, 새로운 해석과 관련 영역을 개척할 수 있는 이론적 틀을 마련하고자 하였다.
한-아프리카 농식품기술협력 협의체 KAFACI(Korea-Africa Food and Agriculture Cooperation Initiative)는 2010년 7월 아프리카 16개국과 한국을 포함하여 17개 회 원국으로 출범하였다. KAFACI는 농촌진흥청(농진청) 주도의 농업연구개발 다자간 협력 사업으로 아프리카의 공통 농업현안 해결을 목표로 한다. 그러나 출범 당시 농진청은 아프리카 농업연구개발에 대한 경험이 부족하였고, 아프리카 국가들도 한국 농업연구에 대해서 아는 바가 거의 없었다. 따라서 농진청-아프리카 농업연 구소 간 상호이해와 협력관계 구축이 시급하였으며, 이를 위하여 출범 후 5년 동 안은 각 회원국이 희망하는 분야의 농업기술을 개발하는 국별과제에 집중하였다. 이를 통하여 구축된 협력관계를 바탕으로 2015년 3차 총회에서 국별과제를 다자 협력에 적합한 분야별 사업으로 개편하고, 기초·식량·원예·축산·농촌지도 5개 분야 협력과제를 착수하였다. 이러한 분야별 공통현안 발굴 및 추진 체계는 현재 까지 지속되고 있다. KAFACI는 분야별 협력체계 구축과 병행하여 성과의 조기 도 출을 위한 중점 분야 발굴을 시도하였다. 세네갈, DR콩고, 카메룬이 추진한 벼 관 련 국별과제와 아프리카녹색혁명동맹(AGRA)과의 협력으로 추진한 약배양기술 적 용 벼 품종 개발을 통하여 아프리카 벼 육종 사업의 필요성과 가능성을 확인하고 본격적인 벼 개발 협력사업을 기획하여 예산을 확보하였다. 2016년 아프리카벼연 구소(AfricaRice)와 공동으로 9년간의 ‘아프리카 벼 개발 파트너십‘ 과제를 착수 하였다. 2017년에 세네갈 생루이 소재 AfricaRice 사헬센터에 약배양연구실을 설 치하고 벼 육종전문가를 파견하였다. KAFACI는 한국의 통일형 벼와 각 회원국의 유전자원을 활용하고, 약배양기술을 적용하여 우수계통을 선발하고 있으며, 현재 까지 회원국에 총 1,547 계통을 제공하였다. 이와 병행하여 회당 4~5명의 연구원 을 사헬센터로 초청하여 벼 재배 전기간에 걸친 벼 육종훈련을 연 2회, 총 5회 추 진하여 회원국 벼 육종역량 강화에 기여하였다. 회원국에서는 제공받은 우수계통 에 대한 지역적응시험 및 농민참여선발을 추진하여, 현재까지 5국에서 11품종을 등록하였다. 이러한 성과와 추진방식은 유튜브 동영상 ’한국 통일벼와 사랑에 빠 진 아프리카‘을 통하여 국내에서 주목을 받았으며(2022.8.10 기준 132만회 조회), 2021년 OECD 공공부분 혁신 우수사례(OPSI, Observatory of Public Sector Innovation)로 채택되었다. KAFACI 벼 사업이 조기에 품종등록 성과를 도출할 수 있었던 주 요인 중 하나는 단순 양자 또는 다자협력을 틀을 넘어 농진청-국제연 구기관-회원국의 삼각협력으로 추진되었다는 점이다. 한국이 보유하고 있는 기술 을 현장이해도가 낮은 상황에서 개발도상국에 직접 전달하기보다는 국제기관의 경험 및 인프라와 결합하여 전수하는 삼각협력 방식은 다른 분야 국제개발협력 사업에도 적용가능한 모델이다.
The prediction of algal bloom is an important field of study in algal bloom management, and chlorophyll-a concentration(Chl-a) is commonly used to represent the status of algal bloom. In, recent years advanced machine learning algorithms are increasingly used for the prediction of algal bloom. In this study, XGBoost(XGB), an ensemble machine learning algorithm, was used to develop a model to predict Chl-a in a reservoir. The daily observation of water quality data and climate data was used for the training and testing of the model. In the first step of the study, the input variables were clustered into two groups(low and high value groups) based on the observed value of water temperature(TEMP), total organic carbon concentration(TOC), total nitrogen concentration(TN) and total phosphorus concentration(TP). For each of the four water quality items, two XGB models were developed using only the data in each clustered group(Model 1). The results were compared to the prediction of an XGB model developed by using the entire data before clustering(Model 2). The model performance was evaluated using three indices including root mean squared error-observation standard deviation ratio(RSR). The model performance was improved using Model 1 for TEMP, TN, TP as the RSR of each model was 0.503, 0.477 and 0.493, respectively, while the RSR of Model 2 was 0.521. On the other hand, Model 2 shows better performance than Model 1 for TOC, where the RSR was 0.532. Explainable artificial intelligence(XAI) is an ongoing field of research in machine learning study. Shapley value analysis, a novel XAI algorithm, was also used for the quantitative interpretation of the XGB model performance developed in this study.
본 논문에서는 BIM을 활용한 흙막이 시스템을 개발하고 소개한다. 선행 연구 분석을 통해서 흙막이 BIM 시스템을 이루는 기술들 에 대한 조사를 바탕으로 요소 기술들을 개발하였다. 첫 번째 요소 기술로, 선행 연구 및 표준 등을 활용해 BIM라이브러리를 구축하여 범용성과 재사용성을 확보하였다. 두 번째로, 토공 2D 기반의 토공 물량 산출법들을 분석하고 흙막이 BIM 시스템으로 활용하되 추가 로 IDW 보간법을 활용하여 지형 생성 및 토공량 산출 시스템을 구축하였다. 세 번째로, 물량 산출을 위한 4가지 수식을 제안하여 객체 마다 각각 다르게 물량 산출법을 적용하여 개발하였다. 이후, 시스템에서 산출되는 물량산출서와 2D 기반 물량산출서와의 비교와 검 증을 통해서 시스템이 앞으로 나아가야할 방향과 한계에 대해 알아보았다.
For this study, we established a system for the CPU cooling performance evaluation and conducted performance tests on air-cooling and water-cooling to understand the effect of the CPU cooling method on performance. For the performance evaluation, the test chamber and water-cooling system were set up, the workload S/W was selected, and a case file was created. In the case of the air-cooling, the CPU temperature is sensitively affected by the outside air temperature, the direction of the board installation, and the influence of the airflow formed around it, and may cause a lot of fluctuations in the CPU temperature. When the water-cooling system was applied, the CPU temperature decreased from 75℃℃ to 37℃ compared to the air-cooled type under the test conditions of 28.5℃ and 3LPM cooling water supply temperature and flow rate. As the CPU clock speed increased due to the decrease in temperature, it was found that the job execution time was reduced by 15~23%. In the future, it is expected that using this performance evaluation environment established through this study will enable us to easily conduct test evaluations for various processors, cooling methods, and changes in operating conditions.
Recently, in Korea, if a very large forest fire occurs due to the people’s carelessness, it is of great interest because it spreads into a large forest fire. If a wildfire spreads and becomes large, it will inflict great damage (appointment and property), and the damage is irreversible. The best way to extinguish a wildfire is to prevent it before it occurs. If a forest fire occurs due to a failure in prevention, the early firefighting activities to prevent the progress of the forest fire by promptly dispatching it by reporting it and approaching the site as soon as possible should now be managed with a systematic integrated management system. To do so, it is necessary to prepare a preventive system, such as issuing warnings for each weather condition by the Korea Forest Service, consisting of cooperation (support) activities for forest fire prevention by related organizations, etc. In order to minimize the loss of precious lives and forests, measures have been taken to establish a system, to establish a prompt and accurate situation reporting system, and to establish an integrated command system (ICS) for on-site commanders.