http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
오늘 본 자료
Investment strategy using Adjusted ESG rating: Focusing on a Korean Market
Eunchong KIM,Hanwook JEONG 한국유통과학회 2022 The Journal of Industrial Distribution & Business( Vol.13 No.1
Purpose: This study used ESG grade, but defined AESG (Adjusted ESG), adjusted to the size of a company and examines whether it can be used as an investment strategy. Research design, data and methodology: The analysis sample in this study is a company that has given an ESG rating among companies listed on the Korea Stock Exchange. We examine the results through portfolio analysis and Fama-macbeth regression analysis. Results: As result of examining the long-only performance and the long-short performance by constructing quintile portfolios, it was observed that a significant positive return was shown. It was observed that there was an alpha that could not be explained in asset pricing models. Also, AESG had a return prediction effect in the result of a Fama-Macbeth regression that controlled corporate characteristic variables in individual stocks. Next, we confirmed AESG’s usage through various portfolio composition. In the portfolio optimization, the Risk Efficient method was the most superior in terms of sharpe ratio and the construct multi-factor model with Value, Momentum and Low Vol showed statistically significant performance improvement. Conclusions: The results of this study suggest that it can be helpful in ESG investment to reflect the ESG rating of relatively small companies more through the scale adjustment of the ESG rating (i.e.AESG).
Training Deep Neural Networks with Synthetic Data for Off-Road Vehicle Detection
Eunchong Kim,Kanghyun Park,Hunmin Yang,Se-Yoon Oh 제어로봇시스템학회 2020 제어로봇시스템학회 국제학술대회 논문집 Vol.2020 No.10
In tandem with growing deep learning technology, vehicle detection using convolutional neural network is now become a mainstream in the field of autonomous driving and ADAS. Taking advantage of this, lots of real image datasets have been produced in spite of the painstaking work of data collection and ground truth annotation. As an alternative, virtually generated images are introduced. This makes data collection and annotation much easier, but a different kind of problem called ‘domain gap’ is announced. For instance, in off-road vehicle detection, there is a difficulty in producing off-road image dataset not only by collecting real images, but also by synthesizing images sidestepping the domain gap. In this paper, focusing on the off-road army tank detection, we introduce a synthetic image generator using domain randomization on off-road scene context. We train a deep learning model on synthetic dataset using low level features form feature extractor pre-trained on real common object dataset. With proposed method, we improve the model accuracy to 0.86 AP@0.5IOU, outperforming naïve domain randomization approach.
신경회로망을 이용한 말벌 인식 및 분류와 양봉 환경 요소 이상 감지
김은총(Eunchong Kim),우예빈(Yebin Woo),이원욱(Wonuk Lee),한지수(Jisu Han),이인수(Insoo Lee) 한국정보기술학회 2022 Proceedings of KIIT Conference Vol.2022 No.6
본 논문에서는 꿀벌, 장수말벌, 등검은말벌의 비행소리를 FFT(Fast fourier transform) 방법으로 변환하여 주파수 영역에서 분석하였다. 그리고 벌의 종류에 따라 다르게 나타나는 주파수 대역의 특징을 인공신경망에 적용하여 종류를 분류하도록 하였다. 그리고 꿀벌의 생장에 영향을 미치는 환경 요인 모니터링도 수행하였다. 본 연구를 통해 꿀벌을 위협하는 요소들을 효과적으로 감지 및 관리함으로써 양봉 농가의 꿀벌 개체수 보존과 수입 증대에 도움이 될 것으로 예상한다. In this paper, the buzzing sound of Honey bees, Asian giant hornets, and Asian predatory wasp was analyzed in the frequency domain with FFT (Fast fourier transform) method. In addition, the characteristics of the frequency which appear different to each other according to the species of bee were applied to the Artificial Neural Network to classify the kind of bees. This makes it possible to detect the appearance of wasps and handle the changes rapidly. Moreover, the monitoring of environmental factors affecting the growth of honeybees were conducted. it is expected that it will help bee farmers preserve the bee population and promote their income increase by effectively detecting and managing factors that threaten honeybees through this study.