http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
이원진 대한치과의사협회 2022 대한치과의사협회지 Vol.60 No.5
Deep learning is a subset of machine learning, and machine learning is also a subset of artificial intelligence (AI). The biggest difference between machine learning and deep learning is that in the learning of artificial intelligence models, machine learning basically requires a human feature extraction process before learning, but deep learning does not require this process and the original data is directly used as input. The development of deep learning coincides with the development of artificial neural networks (ANNs), and many people have contributed to the development of artificial neural networks for decades. The following five models are the representative architectures most widely used in deep learning. That is, Deep Feedforward Neural Network (DFFNN), Convolutional Neural Network (CNN), Deep Belief Network (DBN), Autoencoders (AE), and Long Short-Term Memory (LSTM) Network. A convolutional neural network (CNN) is a feedforward NN composed of a convolutional layer, a ReLU activation function, and a pooling layer. CNNs provide properties of weight sharing and local connectivity to process high-dimensional data. In dental and medical fields, an AI model that can be interpretable or explainable (XAI) is needed to increase patient persuasiveness. In the future, explainable AI (XAI) will become an indispensable and practical component in order to obtain an improved, transparent, secure, fair and unbiased AI learning model.
Prediction of Hypertension Complications Risk Using Classification Techniques
이원진,이정혜,이혜선,전치혁,박일수,강성홍 대한산업공학회 2014 Industrial Engineeering & Management Systems Vol.13 No.4
Chronic diseases including hypertension and its complications are major sources causing the national medical expenditures to increase. We aim to predict the risk of hypertension complications for hypertension patients, using the sample national healthcare database established by Korean National Health Insurance Corporation. We apply classification techniques, such as logistic regression, linear discriminant analysis, and classification and regression tree to predict the hypertension complication onset event for each patient. The performance of these three methods is compared in terms of accuracy, sensitivity and specificity. The result shows that these methods seem to perform similarly although the logistic regression performs marginally better than the others.
이원진,Lee, Won-Jin 한국환경보건학회 2011 한국환경보건학회지 Vol.37 No.2
Although pesticides have increased crop production and controlled disease, they have produced a number of adverse health effects. Pesticides have potential human toxicity and a variety of groups, such as farmers or industrial workers, as well as the general population, are exposed to pesticides. The purpose of this article, therefore, is to provide an overview of pesticide exposure and health through a literature review, focusing on exposure assessment, acute poisoning, chronic health effects, and future research needs. The exposure types and levels of pesticides vary by study subjects and need to be assessed by integrating several methods focused on the epidemiological purpose. Acute pesticide poisoning is a major public health problem in the world. Paraquat is the main causative pesticide for acute poisoning in Korea and should be banned in order to save several thousands of lives every year. Occupational pesticide exposure also causes numerous chronic diseases among farmers and industrial workers, including cancers, respiratory diseases, depression, retinal degeneration, diabetes, and abnormal menstrual cycle. However, controversy exists regarding the long-term effects of low-dose environmental pesticide exposure. The area of pesticide study is relatively new with broad study populations and it has received little academic and policy attention, particularly in Korea. More detailed studies investigating the risk of pesticide-related health effects and intervention efforts to reduce the problems are needed in Korea.
이원진,이지용,최들녘,신치만,조광래,김명훈,이정한,임세훈,이근무 대한마취통증의학회 2015 Anesthesia and pain medicine Vol.10 No.2
Background: The size and depth of the double-lumen tube (DLT) are important for one-lung ventilation (OLV). In patients of a short stature, it is difficult to perform OLV successfully. We designed this study to evaluate the dimensions and margin of safety of the left main bronchi in patients of a short stature for appropriate OLV. Methods: Chest computed tomography (CT) scans of 241 patients (22 male, 219 female) of a short stature (height below 155 cm) were analyzed retrospectively. The diameters of the trachea (DT), the right and left main bronchi (DR and DL), and the lengths of the right and left main bronchi (LR and LL) were measured at the coronal section of the chest CT scans using a picture archiving communication system program. Results: There were no significant correlations between the heights and lengths of the right and left main bronchi. In addition, the ages and weights of the patients showed no significant correlations with the airway dimensions. The lengths of the bronchial lumen of the left-sided Mallinckrodt DLT show variations of 3 to 5.5 mm with tubes of identical sizes. The margin of safety is 13.8 ± 4.1 mm assuming that appropriately sized DLTs are inserted. Conclusions: For successful and safe OLV in patients of a short stature, anesthesiologists should consider the length of the main bronchus and the actual length of the bronchial lumen of the DLT.
대청댐 유입량 예측을 위한 Adaptive Moments와 Improved Harmony Search의 결합을 이용한 다층퍼셉트론 성능향상
이원진,이의훈 한국수자원학회 2023 한국수자원학회논문집 Vol.56 No.1
High-reliability prediction of dam inflow is necessary for efficient dam operation. Recently, studies were conducted to predict the inflow of dams using Multi Layer Perceptron (MLP). Existing studies used the Gradient Descent (GD)-based optimizer as the optimizer among MLP operators to find the optimal correlation between data. However, the GD-based optimizers have disadvantages in that the prediction performance is deteriorated due to the possibility of convergence to the local optimal value and the absence of storage space. This study improved the shortcomings of the GD-based optimizer by developing Adaptive moments combined with Improved Harmony Search (AdamIHS), which combines Adaptive moments among GD-based optimizers and Improved Harmony Search (IHS). In order to evaluate the learning and prediction performance of MLP using AdamIHS, Daecheong Dam inflow was learned and predicted and compared with the learning and prediction performance of MLP using GD-based optimizer. Comparing the learning results, the Mean Squared Error (MSE) of MLP, which is 5 hidden layers using AdamIHS, was the lowest at 11,577. Comparing the prediction results, the average MSE of MLP, which is one hidden layer using AdamIHS, was the lowest at 413,262. Using AdamIHS developed in this study, it will be possible to show improved prediction performance in various fields.