Image Denoising Methods based on DAECNN for Medication Prescriptions

Dashdondov Khongorzul,Lee Sang-Mu,Yong-Ki Kim,Mi-Hye Kim 한국융합학회 2019 한국융합학회논문지 Vol.10 No.5

본 연구는 환자의 알레르기 예방시스템을 구축하기 위해 스마트폰을 이용하여 저장된 처방전의 이미지잡음제거 를 위한 ROI 추출 방법에 중점을 두었다. 현재 ROI 추출은 제한된 실험 환경에서 좋은 성능을 보여 주었지만 실제 환경에서의 성능은 잡음으로 인해 좋지 않았다. 따라서 본 연구에서는 정확도 높은 ROI 추출을 위해 스마트폰 영상에 서 발생하는 잡음제거 방법을 제안한다. SMF, DIN, DAE, DAECNN(Denoising Autoencoder with Convolution Neural Network) and median filter with DAECNN(MF+DAECNN) 방법을 실험하였고 그 결과 DAECNN 및 MF + DAECNN 방법이 스마트폰에서 이미지의 잡음제거가 효과적임을 보여주었다. 성능 향상을 검증하기 위해 SSIM, PSNR 및 MSE 방법을 사용하였고 이 시스템은 OpenCV, C ++ 및 Python로 구현 및 실험되었고 실제 이미지에서 성능 테스트를 거쳐 자연잡음(natural noise)을 제거하는데 본 논문에서 제안한 DAECNN과 MF+DAECNN이 각 69%로 기존의 DAE 방법 55% 보다 상대적으로 높은 결과를 도출하였다. We aimed to build a patient-based allergy prevention system using the smartphone and focused on the region of interest (ROI) extraction method for Optical Character Recognition (OCR) in the general environment. However, the current ROI extraction method has shown good performance in the experimental environment, but the performance in the real environment was not good due to the noisy background. Therefore, in this paper, we propose the compared methods of reducing noisy background to solve the ROI extraction problem. There five methods used as a SMF, DIN, Denoising Autoencoder(DAE), DAE with Convolution Neural Network(DAECNN) and median filter(MF) with DAECNN (MF+DAECNN). We have shown that our proposed DAECNN and MF+DAECNN methods are 69%, respectively, which is relatively higher than the conventional DAE method 55%. The verification of performance improvement uses MSE, PSNR and SSIM. The system has implemented OpenCV, C++and Python, including its performance, is tested on real images.

고혈압 위험 예측에 적용된 특징 선택 방법의 비교

dashdondov khongorzul,김미혜 한국정보처리학회 2022 정보처리학회논문지. 소프트웨어 및 데이터 공학 Vol.11 No.3

In this paper, we have enhanced the risk prediction of hypertension using the feature selection method in the Korean National Healthand Nutrition Examination Survey (KNHANES) database of the Korea Centers for Disease Control and Prevention. The study identifiedvarious risk factors correlated with chronic hypertension. The paper is divided into three parts. Initially, the data preprocessing stepof removes missing values, and performed z-transformation. The following is the feature selection (FS) step that used a factor analysis(FA) based on the feature selection method in the dataset, and feature importance (FI) and multicollinearity analysis (MC) were comparedbased on FS. Finally, in the predictive analysis stage, it was applied to detect and predict the risk of hypertension. In this study, wecompare the accuracy, f-score, area under the ROC curve (AUC), and mean standard error (MSE) for each model of classification. Asa result of the test, the proposed MC-FA-RF model achieved the highest accuracy of 80.12%, MSE of 0.106, f-score of 83.49%, and AUCof 85.96%, respectively. These results demonstrate that the proposed MC-FA-RF method for hypertension risk predictions is outperformedother methods. 본 논문에서는 질병관리청 국민건강영양조사(KNHANES: Korea National Health and Nutrition Examination Survey) 데이터베이스에서 특징선택 방법으로 고혈압을 감지 예측하는 방법을 개선했다. 또한 만성 고혈압과 관련된 다양한 위험 요인을 확인하였다. 본 논문은 3가지로 나누어,첫째 결측값을 제거하고 Z-변환을 하는 데이터 전처리 단계이다. 다음은 데이터 셋에서 특징선택법을 기반으로 하는 요인분석(FA)을 사용하는특징선택 단계이며, 특징선택을 기반으로 다중공선형 분석(MC)와 특징중요도(FI)을 비교했다. 마지막으로 예측분석단계에서 고혈압 위험을 감지하고예측하는데 적용했다. 본 연구에서는 각 분류 모델에 대해 ROC 곡선(AUC) 아래의 평균 표준 오차(MSE), F1 점수 및 면적을 비교한다. 테스트결과 제안한 MC-FA-RF모델은 80.12% 가장 높은 정확도를 보이고, MSE, f-score, AUC 모델의 경우 각각 0.106, 83.49%의, 85.96% 으로 나타났다. 이러한 결과는 고혈압위험 예측에 대한 제안된 MC-FA-RF 방법이 다른 방법에 비해 우수함을 보이고 있다.

Multivariate Outlier Removing for the Risk Prediction of Gas Leakage based Methane Gas

Khongorzul Dashdondov,Mi-Hye Kim 한국융합학회 2020 한국융합학회논문지 Vol.11 No.12

본 연구에서는, 천연가스(NG) 데이터와 가스 관련 환경 요소 간의 관계를 기계학습 알고리즘을 사용하여 가스 누출 데이터를 직접 측정하지 않고 가스 누출 위험 수준을 예측하였다. 이번 연구는 서버가 제공하는 오픈 데이터인 IoT 기반 원격 제어 피카로(Picarro) 가스 센서 사양을 기반으로 사용했다. 천연 가스는 공기 중으로 누출이 되며, 대기 오염, 환경, 그리고 건강에 큰 문제가 된다. 본 연구에서 제안하는 방법은 천연 가스의 누출 위험 예측을 위한 랜덤 포레스트(Random Forest) 분류 기반 다변량 특이치 제거 방법이다. 비지도 k-평균 클러스터링 후에 실험 데이 터 집합은 불균형 데이터이다. 따라서 우리는 제안된 모델이 중간과 높은 위험 수준을 가장 잘 예측할 수 있다는 점에 초점을 맞춘다. 이 경우 각 분류 모델에 대한 수신자 조작 특성(ROC) 곡선, 정확도, 평균 표준 오차(MSE)를 비교했다. 실험 결과로 정확도, 수신자 조작 특성의 곡선 아래 영역(AUC, Area Under the ROC Curve), MSE가 각각 MOL_RF 의 경우 99.71%, 99.57%, 및 0.0016의 결과 값을 얻었다. In this study, the relationship between natural gas (NG) data and gas-related environmental elements was performed using machine learning algorithms to predict the level of gas leakage risk without directly measuring gas leakage data. The study was based on open data provided by the server using the IoT-based remote control Picarro gas sensor specification. The naturel gas leaks into the air, it is a big problem for air pollution, environment and the health. The proposed method is multivariate outlier removing method based Random Forest (RF) classification for predicting risk of NG leak. After, unsupervised k-means clustering, the experimental dataset has done imbalanced data. Therefore, we focusing our proposed models can predict medium and high risk so best. In this case, we compared the receiver operating characteristic (ROC) curve, accuracy, area under the ROC curve (AUC), and mean standard error (MSE) for each classification model. As a result of our experiments, the evaluation measurements include accuracy, area under the ROC curve (AUC), and MSE; 99.71%, 99.57%, and 0.0016 for MOL_RF respectively.

한국 남성의 고혈압에 대한 특징 선택 기반 위험 예측

홍고르출 ( Khongorzul Dashdondov ),김미혜 ( Mi-hye Kim ) 한국정보처리학회 2021 한국정보처리학회 학술대회논문집 Vol.28 No.1

In this article, we have improved the prediction of hypertension detection using the feature selection method for the Korean national health data named by the KNHANES database. The study identified a variety of risk factors associated with chronic hypertension. The paper is divided into two modules. The first of these is a data pre-processing step that uses a factor analysis (FA) based feature selection method from the dataset. The next module applies a predictive analysis step to detect and predict hypertension risk prediction. In this study, we compare the mean standard error (MSE), F1-score, and area under the ROC curve (AUC) for each classification model. The test results show that the proposed FIFA-OE-NB algorithm has an MSE, F1-score, and AUC outcomes 0.259, 0.460, and 64.70%, respectively. These results demonstrate that the proposed FIFA-OE method outperforms other models for hypertension risk predictions.

설명 가능한 인공지능 기술을 활용한 가스누출과 고혈압의 연관 분석

홍고르출 ( Khongorzul Dashdondov ),조겨리 ( Kyuri Jo ),김미혜 ( Mi-hye Kim ) 한국정보처리학회 2022 한국정보처리학회 학술대회논문집 Vol.29 No.2

Hypertension is a severe health problem and increases the risk of other health issues, such as heart disease, heart attack, and stroke. In this research, we propose a machine learning-based prediction method for the risk of chronic hypertension. The proposed method consists of four main modules. In the first module, the linear interpolation method fills missing values of the integration of gas and meteorological datasets. In the second module, the OrdinalEncoder-based normalization is followed by the Decision tree algorithm to select important features. The prediction analysis module builds three models based on k-Nearest Neighbors, Decision Tree, and Random Forest to predict hypertension levels. Finally, the features used in the prediction model are explained by the DeepSHAP approach. The proposed method is evaluated by integrating the Korean meteorological agency dataset, natural gas leakage dataset, and Korean National Health and Nutrition Examination Survey dataset. The experimental results showed important global features for the hypertension of the entire population and local components for particular patients. Based on the local explanation results for a randomly selected 65-year-old male, the effect of hypertension increased from 0.694 to 1.249 when age increased by 0.37 and gas loss increased by 0.17. Therefore, it is concluded that gas loss is the cause of high blood pressure.

고혈압 예측을 위한 이상치 탐지 알고리즘 및 데이터 통합 기법

홍고르출 ( Khongorzul Dashdondov ),김미혜 ( Mi-hye Kim ),송미화 ( Mi-hwa Song ) 한국정보처리학회 2023 한국정보처리학회 학술대회논문집 Vol.30 No.1

Histopathology Image Enhancement of Lung Cancer using Deep CNN-based Image Denoising Methods

Anudari Khishigdelger,Khongorzul Dashdondov,Mi-Hye Kim,Hyun-Soo Kang 한국콘텐츠학회 2022 한국콘텐츠학회 ICCC 논문집 Vol.2022 No.12

Performance Analysis of Channel Error Probability using Markov Model for SCTP Protocol

Shinn, Byung-Cheol,Feng, Bai,Khongorzul, Dashdondov The Korea Institute of Information and Commucation 2008 Journal of information and communication convergen Vol.6 No.2

In this paper, we propose an analysis model for the performance of channel error probability in Stream Control Transmission Protocol (SCTP) using Markov model. In this model it is assumed that the compressor and decompressor work in Unidirectional Mode. And the average throughput of SCTP protocol is obtained by finding the throughputs of when the initial channel state is good or bad.