• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 추계학술발표대회
• /
• pp.55-56
• /
• 2022

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.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2022년도 학술발표회
• /
• pp.134-134
• /
• 2022

Streamflow forecasting plays a crucial role in water resource control, especially in highly urbanized areas that are very vulnerable to flooding during heavy rainfall event. In addition to providing the accurate prediction, the evaluation of effects and importance of the input predictors can contribute to water manager. Recently, machine learning techniques have applied their advantages for modeling complex and nonlinear hydrological processes. However, the techniques have not considered properly the importance and uncertainty of the predictor variables. To address these concerns, we applied the GA-BART, that integrates a genetic algorithm (GA) with the Bayesian additive regression tree (BART) model for hourly streamflow forecasting and analyzing input predictors. The Jungrang urban basin was selected as a case study and a database was established based on 39 heavy rainfall events during 2003 and 2020 from the rain gauges and monitoring stations. For the goal of this study, we used a combination of inputs that included the areal rainfall of the subbasins at current time step and previous time steps and water level and streamflow of the stations at time step for multistep-ahead streamflow predictions. An analysis of multiple datasets including different input predictors was performed to define the optimal set for streamflow forecasting. In addition, the GA-BART model could reasonably determine the relative importance of the input variables. The assessment might help water resource managers improve the accuracy of forecasts and early flood warnings in the basin.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2023년도 제67차 동계학술대회논문집 31권1호
• /
• pp.103-106
• /
• 2023

코로나 팬데믹 사태로 인해 업무환경이 재택근무를 하는 환경으로 바뀌고 악성코드의 변종 또한 빠르게 발전하고 있다. 악성코드를 분석하고 백신 프로그램을 만들면 새로운 변종 악성코드가 생기고 변종에 대한 백신프로그램이 만들어 질 때까지 변종된 악성코드는 사용자에게 위협이 된다. 본 연구에서는 머신러닝 알고리즘을 사용하여 악성파일 여부를 예측하는 방법을 제시하였다. 일반적인 악성코드의 구조를 갖는 Portable Executable 구조 파일을 파이썬의 LIEF 라이브러리를 사용하여 Certificate, Imports, Opcode 등 3가지 feature에 대해 정적분석을 하였다. 학습 데이터로는 정상파일 320개와 악성파일 530개를 사용하였다. Certificate는 hasSignature(디지털 서명정보), isValidcertificate(디지털 서명의 유효성), isNotExpired(인증서의 유효성)의 feature set을 사용하고, Imports는 Import Address Table의 function 빈도수를 비교하여 feature set을 구축하였다. Opcode는 tri-gram으로 추출하여 빈도수를 비교하여 feature set을 구축하였다. 테스트 데이터로는 정상파일 360개 악성파일 610개를 사용하였으며 Feature set을 사용하여 random forest, decision tree, bagging, adaboost 등 4가지 머신러닝 알고리즘을 대상으로 성능을 비교하였고, bagging 알고리즘에서 약 0.98의 정확도를 보였다.

• 무역학회지
• /
• 제45권3호
• /
• pp.55-69
• /
• 2020

This study examines the research trends and knowledge structure of international trade studies using topic modeling method, which is one of the main methodologies of text mining. We collected and analyzed English abstracts of 1,868 papers of three Korean major journals in the area of international trade from 2003 to 2019. We used the Latent Dirichlet Allocation(LDA), an unsupervised machine learning algorithm to extract the latent topics from the large quantity of research abstracts. 20 topics are identified without any prior human judgement. The topics reveal topographical maps of research in international trade and are representative and meaningful in the sense that most of them correspond to previously established sub-topics in trade studies. Then we conducted a regression analysis on the document-topic distributions generated by LDA to identify hot and cold topics. We discovered 2 hot topics(internationalization capacity and performance of export companies, economic effect of trade) and 2 cold topics(exchange rate and current account, trade finance). Trade studies are characterized as a interdisciplinary study of three agendas(i.e. international economy, International Business, trade practice), and 20 topics identified can be grouped into these 3 agendas. From the estimated results of the study, we find that the Korean government's active pursuit of FTA and consequent necessity of capacity building in Korean export firms lie behind the popularity of topic selection by the Korean researchers in the area of int'l trade.

• Geomechanics and Engineering
• /
• 제36권5호
• /
• pp.441-453
• /
• 2024

Sinkhole subsidence and collapse is a common geohazard often formed in karst areas such as the state of Florida, United States of America. To predict the sinkhole occurrence, we need to understand the formation mechanism of sinkhole and its karst hydrogeology. For this purpose, investigating the factors affecting sinkholes is an essential and important step. The main objectives of the presenting study are (1) the development of a machine learning (ML)-based model, namely C5.0 decision tree (C5.0 DT), for the prediction of sinkhole susceptibility, which accounts for sinkhole/subsidence inventory and sinkhole contributing factors (e.g., geological/hydrogeological) and (2) the construction of a regional-scale sinkhole susceptibility map. The study area is east central Florida (ECF) where a cover-collapse type is commonly reported. The C5.0 DT algorithm was used to account for twelve (12) identified hydrogeological factors. In this study, a total of 1,113 sinkholes in ECF were identified and the dataset was then randomly divided into 70% and 30% subsets for training and testing, respectively. The performance of the sinkhole susceptibility model was evaluated using a receiver operating characteristic (ROC) curve, particularly the area under the curve (AUC). The C5.0 model showed a high prediction accuracy of 83.52%. It is concluded that a decision tree is a promising tool and classifier for spatial prediction of karst sinkholes and subsidence in the ECF area.

• 한국인공지능학회지
• /
• 제12권1호
• /
• pp.25-29
• /
• 2024

In this study, research was conducted to predict the probability of cervical cancer occurrence associated with the use of hormonal contraceptives. Cervical cancer is influenced by various environmental factors; however, the human papillomavirus (HPV) is detected in 99% of cases, making it the primary attributed cause. Additionally, although cervical cancer ranks 10th in overall female cancer incidence, it is nearly 100% preventable among known cancers. Early-stage cervical cancer typically presents no symptoms but can be detected early through regular screening. Therefore, routine tests, including cytology, should be conducted annually, as early detection significantly improves the chances of successful treatment. Thus, we employed artificial intelligence technology to forecast the likelihood of developing cervical cancer. We utilized the logistic regression algorithm, a predictive model, through Microsoft Azure. The classification model yielded an accuracy of 80.8%, a precision of 80.2%, a recall rate of 99.0%, and an F1 score of 88.6%. These results indicate that the use of hormonal contraceptives is associated with an increased risk of cervical cancer. Further development of the artificial intelligence program, as studied here, holds promise for reducing mortality rates attributable to cervical cancer.

• 인터넷정보학회논문지
• /
• 제6권1호
• /
• pp.105-114
• /
• 2005

본 논문에서는 다중 시계열 패턴을 분석하여 계측 값을 예측하는 방법에 관하여 기술한다. 본 논문의 목적은 표본패턴들 중에서 입력패턴과 가장 유사한 패턴을 찾은 다음 그 표본패턴이 가지는 실측값과의 오차율을 산출하는 것이다. 따라서 인식이 아니라 계측이며 하드웨어가 아닌 소프트웨어 기술을 제안하다. 본 논문에서 제안하는 방법은 초기화, 인식 및 계측 등의 단계로 구성된다. 초기화 단계에서는 중요도를 사용하여 인자들 각각의 가중치를 산출한다. 학습 단계에서는 수집된 표본패턴을 먼저 DTW와 LBG 알고리즘을 사용하여 각 인자별 독립적으로 군집화를 수행한 다음, 모든 표본패턴에 대하여 군집의 번호들로 구성된 코드열을 생성한다. 계측 단계에서는 입력패턴에 대한 코드열을 생성한 다음 해슁으로 표본패턴들 중에서 같은 코드열을 가지는 표본들을 찾고, 이 표본들 중에서 입력패턴에 가장 잘 정합되는 하나의 표본을 선택하다. 최종적으로 이 패턴이 가지고 있는 실측값과 오차율을 출력한다. 성능평가는 반도체생산장치 중에서 하나인 식각장치로부터 얻어진 자료에 적용하여 수행한다.

• 전기학회논문지
• /
• 제66권5호
• /
• pp.833-842
• /
• 2017

In this study, the design methodology of radial basis function neural networks based on incremental K-means clustering is introduced for learning and processing the big data. If there is a lot of dataset to be trained, general clustering may not learn dataset due to the lack of memory capacity. However, the on-line processing of big data could be effectively realized through the parameters operation of recursive least square estimation as well as the sequential operation of incremental clustering algorithm. Radial basis function neural networks consist of condition part, conclusion part and aggregation part. In the condition part, incremental K-means clustering algorithms is used tweights of the conclusion part are given as linear function and parameters are calculated using recursive least squareo get the center points of data and find the fitness using gaussian function as the activation function. Connection s estimation. In the aggregation part, a final output is obtained by center of gravity method. Using machine learning data, performance index are shown and compared with other models. Also, the performance of the incremental K-means clustering based-RBFNNs is carried out by using PSO. This study demonstrates that the proposed model shows the superiority of algorithmic design from the viewpoint of on-line processing for big data.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제23권2호
• /
• pp.104-109
• /
• 2017

본고에서는 다중 웨어러블 센서 데이터로부터 사용자의 일상 생활 행동 패턴을 분석할 수 있는 새로운 기계학습 모델을 제안한다. 제안하는 모델은 다중 웨어러블 센서 데이터를 효과적으로 학습하기 위하여 사람이 다중 센서 정보를 처리하는 방법을 적용한 새로운 신경망 모델이다. 제안하는 Gated multi-modal neural netoworks는 계층적 신경망 구조를 가지고 있으며 Gate 모듈을 통해 각 센서 데이터를 선택적으로 결합하여 처리하는 특징을 가진다. 실험을 위해 다중 웨어러블 장치를 착용하고 일상 생활 중 한 가지인 레스토랑에서의 행동 센서 데이터를 수집하였다. 실험 결과로서, 제시하는 모델을 이용하여 실제 웨어러블 센서 데이터를 분석하였을 때 분류 정확도가 비교적 정확하고 빠르게 처리할 수 있음을 확인하였다. 또한 모델의 중간 계층에서의 노드의 활성화 패턴 분석을 통해 자동으로 일상생활 패턴을 추출할 수 있고 이를 이용하여 지식 스키마를 생성할 수 있음을 확인하였다.

• 한국인터넷방송통신학회논문지
• /
• 제20권3호
• /
• pp.171-179
• /
• 2020

최근 연구 결과에 따르면, 컨볼루션 신경 회로망은 이미지 분류, 객체 검출, 이미지 생성 등의 문제에서 최고의 성능을 보여주고 있다. 비전 카메라를 사용한 결함 검사는 다른 결함 검사보다 경제적이기 때문에 공장 자동화에 있어서 아주 중요하고, 딥러닝의 지도학습은 전통 기계학습 방식의 결함 검사 성능을 월등히 뛰어넘었다. 하지만, 딥러닝의 지도학습은 엄청난 양의 데이터 주석 작업을 요구하기 때문에, 이를 실제 산업 현장에 적용하는 것은 효율적이지 않다. 따라서 본 연구는 최근 이미지 생성 과업에서 큰 성공을 보여주고 있는 변분 오토인코더와 적대적 생성 신경망을 활용하여 비지도 방식의 비정상 검출을 위한 신경망 회로 구조를 제안하였고, 이를 MNIST, 용접 결함 데이터에 적용하여 비정상 검출 성능을 검증하였다.