http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
다양한 데이터 전처리 기법과 데이터 오버샘플링을 적용한 GRU 모델 기반 이상 탐지 성능 비교
유승태,김강석,Yoo, Seung-Tae,Kim, Kangseok 한국정보보호학회 2022 정보보호학회논문지 Vol.32 No.2
According to the recent change in the cybersecurity paradigm, research on anomaly detection methods using machine learning and deep learning techniques, which are AI implementation technologies, is increasing. In this study, a comparative study on data preprocessing techniques that can improve the anomaly detection performance of a GRU (Gated Recurrent Unit) neural network-based intrusion detection model using NGIDS-DS (Next Generation IDS Dataset), an open dataset, was conducted. In addition, in order to solve the class imbalance problem according to the ratio of normal data and attack data, the detection performance according to the oversampling ratio was compared and analyzed using the oversampling technique applied with DCGAN (Deep Convolutional Generative Adversarial Networks). As a result of the experiment, the method preprocessed using the Doc2Vec algorithm for system call feature and process execution path feature showed good performance, and in the case of oversampling performance, when DCGAN was used, improved detection performance was shown.
Doedecyl-Benzene sulfon酸 Soda의 性能 및 用途에 關하여
柳承泰 忠州大學校 1967 한국교통대학교 논문집 Vol.1 No.-
As i made clear in this study, I beieve that the quality of the home-made Dodedyl Benzene Sodium Sulfate is none the inferior to that the foreing-made and also its superiority can be highly recognized. Therefore I wish this study will be of a little helf for the selection, the use and the quantity of surface active Agent which in widely used in every field of our domestic industry (Oct. 1. 1967) Dodedyl Benzene sulfon 酸sodadml 構造式 ? ~ ? Dodedyl Benzene Sulfonic acid의 分析表 有效性分 ; 97.01% 石油ether可溶分 ;2.59% 遊離黃酸 0.40% 鐵分 1.4 p.p.m
I-Naphthalene Acetic Acid의 合成法에 關하여
柳承泰 충주대학교 1970 한국교통대학교 논문집 Vol.3 No.-
I-Naphthalene Acetic Acid(called as N.A.A.from now) is to be composed by using naphthalene, byproducts obtained from the develpment of domestic petrolium Industry. Changing this matters into N-or K-salts and ester, it must contribute to getting a kind of agricultural medicine which was not produced in Korea and was imported with foreign currendies considerably spent. Alternately, using the Blanc reactions, this investigation was carried out to consider the several technical problems in composing N.A.A.
柳承泰 忠州大學校 1968 한국교통대학교 논문집 Vol.2 No.-
Aniline is being used in many fields as a raw materials of dyes, especially of azo dye, and other synthetic parmaceuticals. According to this experiment, it was realized that, of the various methsds of its preparation, aniline could be synthesized by the Bechamp's Reduction Method with a good result even if the less quantities then the theoretical values of the iron and acid were used, and what is more, the yield of aniline was over 90%. In order to increase the reaction rate nitrocompound was added after etching the iron and acid, and in order to agitate smoothly excess water was added. It is also confirmed that the reaction was being run with a small quantities of hydrochloric acid because the ferrous chloride formed by the reaction was conversed, on account of the existence of water and aniline, to ferrous hydroxide and hydrochloric acid. If we pay attention to the remarkable keypoints like above in manufacturing of aniline, the product that have high quality and low cost can be preparet.
유승태,박경선,이윤서,황성진,김강석 한국산업보안연구학회 2020 한국산업보안연구 Vol.10 No.2
최근 4차 산업혁명이 본격적으로 도래한 후, 인공지능, 사물인터넷(IoT), 빅데이터 등 관련 새로운 기술들이 빠르게 성장하고 있다. 기업들은 이러한 추세에 따른신기술의 도입 및 개발을 추진하고 있고, 이와 더불어 사이버보안, 기술유출 등과같은 다양한 보안에 필요성을 느끼게 되었다. 이에 따라 산업보안에 관한 관심이높아지고 있고, 관련 연구도 활발히 진행되고 있다. 그러나 연구의 진행이 실제 필요한 방향으로 진행되고 있는지에 대한 연구가 부족하다. 그러므로 현재 산업보안의 연구 동향을 체계적으로 파악하는 시도가 필요하다. 따라서 본 연구는 토픽 모델링(Topic Modeling) 기법 중 하나인 LDA(Latent Dirichlet Allocation)을 적용하여 산업보안과 관련된 2015년 1월 1일부터 2019년 12 월 31일까지 최근 5년간의 국내 학술 논문과 보안 관련 기사 데이터를 수집하여 동향을 분석하였다. 또한 논문과 기사 데이터 간의 비교 분석을 통해 최신 트렌드와보완점을 반영하여 연구가 활발히 이루어지고 있는지 조사하였다. 본 연구의 결과가 현재 산업보안 동향을 분석하고 미래 트렌드를 예측할 수 있도록 정보를 제공하는데 기여할 수 있을 것으로 기대하는 바이다. With the advent of the fourth industrial revolution in earnest recently, related new technologies such as artificial intelligence, Internet of Things (IoT), and big data have been growing rapidly. Companies have been pursuing the introduction and development of new technologies according to this trend, and are feeling the need for various securities such as cyber security and technology leakage. Accordingly, the interest in industrial security is increasing, and related studies are actively being conducted. However, there is a lack of research on whether the research is actually proceeding in the required direction. Therefore, an attempt to systematically grasp the current industrial security research trend is needed. Thus, this study applied the Latent Dirichlet Allocation (LDA) technique, one of the topical modeling techniques, to extract the data of domestic academic papers and articles related to industrial security over the last five years from January 1, 2015 to December 31, 2019, to analyze trends and predict future growth trends. In addition, a comparative analysis between the paper and the article data was conducted to examine whether the research was actively carried out, reflecting the latest trends and complements. The results of this study are expected to contribute to analyzing current trends and providing information to predict future trends.