http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Detection and Correction Method of Erroneous Data Using Quantile Pattern and LSTM
Hwang, Chulhyun,Kim, Hosung,Jung, Hoekyung The Korea Institute of Information and Commucation 2018 Journal of information and communication convergen Vol.16 No.4
The data of K-Water waterworks is collected from various sensors and used as basic data for the operation and analysis of various devices. In this way, the importance of the sensor data is very high, but it contains misleading data due to the characteristics of the sensor in the external environment. However, the cleansing method for the missing data is concentrated on the prediction of the missing data, so the research on the detection and prediction method of the missing data is poor. This is a study to detect wrong data by converting collected data into quintiles and patterning them. It is confirmed that the accuracy of detecting false data intentionally generated from real data is higher than that of the conventional method in all cases. Future research we will prove the proposed system's efficiency and accuracy in various environments.
황수진(Sujin Hwang),황철현(Chulhyun Hwang),박용준(Yongjun Park) 한국정보과학회 2004 한국정보과학회 학술발표논문집 Vol.31 No.1A
방송과 관련된 디지털 기술과 통신 기술의 급격한 발전은 방송 산업의 다양화와 컨텐츠의 수적 증가를 유도한 반면 시청자의 시청 환경을 고려하는 편의성과 최적 정보 전달 기술의 발전은 더디게 진행되어왔다. 본 논문에서는 국내에서 최근 상용 서비스가 실시된 양방향 TV 환경에서 양방향 방송 서비스를 제공하고, 시청자의 행위, 선호도, 성향 등을 분석하여 개인화된 프로그램 채널 추천, 표적화된 광고의 제공, T-Commerce 환경을 지원할 수 있는 양방향 TV 개인화 시스템을 설계하고 구현한다.
황수진(Sujin Hwang),황철현(Chulhyun Hwang) 한국정보과학회 2005 한국정보과학회 학술발표논문집 Vol.32 No.1
배경음악 서비스는 최근 저작권법의 강화, Music Contents 시장의 발전과 함께 많은 화두가 되고 있는 분야이다. 하지만 국내의 배경음악 관련 현황은 일괄 CD를 구입하고 대형업체만이 소수의 전문가로만 운영하여 관련 법규 대응과 음악 제공 수준이 극히 저조한 상태이다. 이러한 문제를 해결하기 위해 본 논문에서는 배경음악과 관련된 업계의 상황과 선진 사례를 기준으로 개인화된 배경음악 시스템의 표준 구조 운영 모델 및 시스템 구조 모델을 제시하고자 한다. 표준 운영 구조 모델은 취약한 국내 서비스 환경하에서의 최소한의 운영 요구 사항과 운영목표 달성을 위한 Guideline을 제시하고 함께 시스템 구조 모델을 통해 그 실현 가능성을 살펴 보았다.
CNN-LSTM Coupled Model for Prediction of Waterworks Operation Data
Cao, Kerang,Kim, Hangyung,Hwang, Chulhyun,Jung, Hoekyung Korea Information Processing Society 2018 Journal of information processing systems Vol.14 No.6
In this paper, we propose an improved model to provide users with a better long-term prediction of waterworks operation data. The existing prediction models have been studied in various types of models such as multiple linear regression model while considering time, days and seasonal characteristics. But the existing model shows the rate of prediction for demand fluctuation and long-term prediction is insufficient. Particularly in the deep running model, the long-short-term memory (LSTM) model has been applied to predict data of water purification plant because its time series prediction is highly reliable. However, it is necessary to reflect the correlation among various related factors, and a supplementary model is needed to improve the long-term predictability. In this paper, convolutional neural network (CNN) model is introduced to select various input variables that have a necessary correlation and to improve long term prediction rate, thus increasing the prediction rate through the LSTM predictive value and the combined structure. In addition, a multiple linear regression model is applied to compile the predicted data of CNN and LSTM, which then confirms the data as the final predicted outcome.
우리나라 관광안내표지의 개선을 위한 사례 연구: 강원도 평창군을 중심으로
김보미 ( Bomi Kim ),황병중 ( Byungjung Hwang ),서철현 ( Chulhyun Suh ) 관광경영학회 2018 관광경영연구 Vol.82 No.-
This study aims to investigate the present state of tour guide signs and induce some useful suggestions centered on Pyeongchang-gun. For this we have observed and investigated tour guide signs established around the streets of Pyeongchang-gun. We drew some evaluation categories from the preceding studies and related guides. Those categories are composed of component, mark factor, and manufacturing and installation. As a result of our observation and investigation of the tour guide signs of Pyeongchang-gun, some problems are revealed in the aspect of component such as excess of draft, confusion of distance informations, missing of arrows, omission of guide informations. In the aspect of mark factor, some problems are found such as error or incongruence of symbols, and insufficiency of readability. Finally, in the aspect of manufacturing and installation, insufficient maintenance, too much installation, lack of harmony with surroundings, and of consideration for human body are revealed. It’s been concluded that these problems should be improved immediately. For this, total investigation of tour guide signs needs to be made. And after constructing DB about them, some efforts should be made to improve problems systematically. Also, we need to make guideline of tour guide signs appropriate to local characteristics, and develop new designs of tour guide signs, and install them.
YOLOv4 기반의 공장 근로자 안전관리를 위한 학습 데이터 구축과 모델 학습
이태준(Taejun Lee),조민우(Minwoo Cho),송지호(Jiho Song),황철현(Chulhyun Hwang),정회경(Heokyung Jung) 한국정보통신학회 2021 한국정보통신학회 종합학술대회 논문집 Vol.25 No.1
산업안전보건연구원에 따르면 2019년 산업재해자 수가 109,242명으로 2018년에 비해 6.8% 증가하였다. 이러한 산업 안전보건 분야는 질병보다 사고가 더 자주 발생하고 있다. 이러한 상황에서 정부와 기업은 건설 시공 분야에서 ICT 기반 현장 안전사고 예방 핵심 기술 개발이 논의되고 있는 실정이다. 이러한 분야에서 최근 컴퓨터 비전과 인공지능을 활용한 기술들이 많이 사용되고 있다. 본 논문에서는 공장 근로자들의 안전관리를 위한 학습 데이터를 구축하고 YOLOv4를 기반으로 모델을 학습시켰다. 이를 통해 공장에서 근로자들의 위험 상황을 예측하는 초기 연구로써 활용할 수 있을 것으로 사료된다. According to the Institute for Occupational Safety and Health, the number of industrial injuries in 2019 was 109,242, an increase of 6.8% from 2018. In this situation, the government and companies are discussing the development of core technologies for preventing safety accidents on site based on ICT in the field of construction and construction. In these fields, technologies using computer vision and artificial intelligence have recently been widely used. In this paper, we built training data for safety management of factory workers and trained a model based on YOLOv4. It is believed that this can be used as an initial study to predict the risk situation of workers in factories.
Suchit Kumar,Jong-Min Kim,Jang Gyu Cha,Ji Young Hwang,Seung Eun Jung,Chulhyun Lee,Chang-Hyun Oh 대한자기공명의과학회 2023 Investigative Magnetic Resonance Imaging Vol.27 No.1
Purpose: To propose a novel standard magnetic resonance imaging (MRI) phantom, hereafter called the Korea Magnetic Resonance Phantom-4th edition (KMRP-4). Its related quality control (QC) assessment protocols and its comparison with the American College of Radiology (ACR) phantom and its QC assessment protocols. Materials and Methods: Internally, the KMRP-4 phantom is composed of cubic and triangular vessels, brain tissue structures, and a uniform region designed to facilitate a variety of QC protocols. Using magnetic resonance (MR) images of these structures, we quantitatively evaluated a total of 10 parameters, seven from those of existing ACR protocols (i.e., geometric accuracy, high-contrast spatial resolution, slice thickness accuracy, slice position accuracy, image intensity uniformity, percent signal ghosting, and low-contrast object detectability) and three additional parameters for evaluating vessel conspicuity, brain tissue contrast, and signal-to-noise ratio (SNR) introduced in the KMRP-4 protocols. Twentytwo MRI systems of 0.32–3.0 T static magnetic field strength were tested using both ACR and KMRP-4 phantoms. Mann–Whitney U-tests were performed on the seven evaluation items of the ACR method to compare KMRP-4 and ACR methods. Results: The results of Mann–Whitney U-test demonstrated that p-values were more than 0.05 for all seven items that could be assessed with both ACR and KMRP-4, indicating similar results between the two methods. Additionally, assessments of vessel conspicuity, brain tissue contrast, and SNR using the KMRP-4 method demonstrated utility of the KMRP-4 phantom. Conclusion: A novel standard phantom and related QC methods were developed to perform objective, observer-independent, and semi-automatic QC tests. Quantitative comparisons of MR images with KMPR-4 and ACR phantoms were performed. Results demonstrated the utility of the newly proposed KMRP-4 phantom and its related QC methods.