http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Study on the Determination of Cable Defective Products for Smart Factory
Seungmin Oh,Yeonggwang Kim,Dongsu Lee 한국디지털콘텐츠학회 2020 The Journal of Contents Computing Vol.2 No.2
Recently, studies have been underway to improve the quality of products by applying artificial intelligence for smart factories to identify defective products and increase corporate profits. In this paper, we aim to improve the performance of our model by applying conveyor belt environment construction, cable data collection, and pre-processing of collected data to study cable defect discrimination methods for smart factories. To develop a deep learning vision solution for cable data, we study the vision solution model with the highest performance compared to the performance of CNN-based models and the number of learning parameters, and the derived model showed a high performance of 99.8%.
Optimizing Energy Consumption Prediction Models using Genetic Algorithms
Seungmin Oh,Yeonggwang Kim,Muhammad Firoz Mridha 한국디지털콘텐츠학회 2021 The Journal of Contents Computing Vol.3 No.1
Prediction and managing energy consumption is essential for smart grid, smart energy management. Recently, Various AI models are being researched to predict energy consumption. Machine learning or deep learning models are essential to improve performance through hyper-parameter optimization. However, Optimization has the disadvantage of having sufficient relevant knowledge or requiring mathematical calculations. In this paper, the performance improvement of XGBoost Regression, RNN, and LSTM models using genetic algorithms could be achieved by improving performance up to 72% on the MSE.
Implications of the Hippocratic oath ceremony for holistic medical humanities education
Oh, SeungMin,Kim, Pyung Man 가톨릭대학교(성심교정) 인간학연구소 2020 인간연구 Vol.0 No.42
의료인문학 교육은 의학 교육에서 갈수록 중요한 주제가 되고 있다. 이를 위한 여러 교육 과정 중에 많은 의과대학에서 시행되고 있는 히포크라테스 선서식이 있다. 히포크라테스 선서는 과거와 마찬가지로 윤리적 의료 행위와 의학교육의 근간을 이루며 많은 의학교육 기관의 전인적 인문학 교육에 의미를 주고 있다. 의학 교육에서 선서를 다루는 것은 미래의 의사들이 의학의 본질에 대해 고민하고 전인적 의료인으로 성장하며 전문직 정체성을 함양하는 것에 도움을 준다. 본 연구를 통하여서 기존의 히포크라테스 선서에 담긴 의미를 찾아보는 것에서 더 나아가 인문의학교육에서 이루어지고 있는 선서식의 전반적 현황을 살펴보고 전인적 의료인 양성을 위한 의료인문학 교육에 주는 가치를 살펴 볼 것이다. Teaching Medical Humanities is an increasingly important subject in medical education. Among various educational courses available, an oath-taking ceremony using the Hippocratic Oath currently performed in a number of medical schools throughout the world was the focus of this study. Taking an oath ceremony during a holistic education course helps future doctors consider the essence of medicine and consolidate their professional identity as medical professionals. Taking an oath ceremony still has great significance in medical humanities education.
A Study on Super Resolution of SRCNN according to Early Up-sampling Method
Seungmin Oh,Sangwon Oh,Hyeju Shin,Jinsul Kim 한국디지털콘텐츠학회 2021 The Journal of Contents Computing Vol.3 No.2
Super resolution is a technology that converts low-resolution images into high-resolution images, and super resolution technologies using deep learning have recently been studied. The SRCNN model was first studied as a deep learning-based super-resolution technology, and the SRCNN model performs early up-sampling and learning using interpolation to perform super-resolution. In this paper, the best performance early up-sampling interpolation was investigated through the performance comparison of the early up-sampling method. Through this, it was found that the bicubic interpolation method derived good performance from up to 35% to at least 17% compared to other interpolation methods.
Methods of Generating Time Series Image for detecting Anomalies in Time Series data
Sangwon Oh,Seungmin Oh,Yeonggwang Kim,Junchurl Yoon,Tai-Won Um 한국디지털콘텐츠학회 2021 The Journal of Contents Computing Vol.3 No.2
To detect anomalies in time series data, statistical techniques such as PCA and autoencoder are used, or anomalies are detected based on deep learning models such as RNN. It is difficult to expect good performance only with simple statistical techniques or RNN-based deep learning models because the environment and causes in which anomalies are recorded are not simple and various variables affect them. In this paper, we proposed a method of detecting anomalies using CNN-based deep learning model, a binary classification model of representative images, by imaging time series data. RP, GASF, GADF, and MAF algorithms were used as methods for imaging. All of time series image-based models showed equal or higher accuracy than conventional LSTM-based models, and among imaging-based CNN models, the method of imaging with MTF algorithm derived the highest accuracy.