• 한국인공지능학회지
• /
• 제11권3호
• /
• pp.23-27
• /
• 2023

The purpose of this study is to identify and analyze suicide factors of adolescents using the Random Forest algorithm. According to statistics on the cause of death by the National Statistical Office in 2019, suicide was the highest cause of death in the 10-19 age group, which is a major social problem. Using machine learning algorithms, research can predict whether individual adolescents think of suicide without investigating suicidal ideation and can contribute to protecting adolescents and analyzing factors that affect suicide, establishing effective intervention measures. As a result of predicting with the random forest algorithm, it can be said that the possibility of identifying and predicting suicide factors of adolescents was confirmed. To increase the accuracy of the results, continuous research on the factors that induce youth suicide is necessary.

• 한국인공지능학회지
• /
• 제10권1호
• /
• pp.1-7
• /
• 2022

In this paper, a study was conducted to predict natural disasters in Afghanistan based on machine learning. Natural disasters need to be prepared not only in Korea but also in other vulnerable countries. Every year in Afghanistan, natural disasters(snow, earthquake, drought, flood) cause property and casualties. We decided to conduct research on this phenomenon because we thought that the damage would be small if we were to prepare for it. The Azure Machine Learning Studio used in the study has the advantage of being more visible and easier to use than other Machine Learning tools. Decision Forest is a model for classifying into decision tree types. Decision forest enables intuitive analysis as a model that is easy to analyze results and presents key variables and separation criteria. Also, since it is a nonparametric model, it is free to assume (normality, independence, equal dispersion) required by the statistical model. Finally, linear/non-linear relationships can be searched considering interactions between variables. Therefore, the study used decision forest. The study found that overall accuracy was 89 percent and average accuracy was 97 percent. Although the results of the experiment showed a little high accuracy, items with low natural disaster frequency were less accurate due to lack of learning. By learning and complementing more data, overall accuracy can be improved, and damage can be reduced by predicting natural disasters.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.805-807
• /
• 2021

In-hospital cardiac arrest is a significant problem for medical systems. Although the traditional early warning systems have been widely applied, they still contain many drawbacks, such as the high false warning rate and low sensitivity. This paper proposed a strategy that involves a deep learning approach based on a novel interpretable deep tabular data learning architecture, named TabNet, for the Rapid Response System. This study has been processed and validated on a dataset collected from two hospitals of Chonnam National University, Korea, in over 10 years. The learning metrics used for the experiment are the area under the receiver operating characteristic curve score (AUROC) and the area under the precision-recall curve score (AUPRC). The experiment on a large real-time dataset shows that our method improves compared to other machine learning-based approaches.

• 한국콘텐츠학회논문지
• /
• 제19권1호
• /
• pp.108-116
• /
• 2019

본 논문에서는 인공지능기술을 통합보안관제 기술에 효율적으로 적용하는 방안을 제안하였다. 즉, 통합보안관제시스템에 수집된 빅 데이터를 기반으로 머신러닝 학습을 인공지능에 적용하여 사이버공격을 탐지하도록 하고 적절한 대응을 한다. 기술의 발달에 따라서 늘어나는 보안장비와 보안 프로그램들로부터 쌓이는 수많은 대용량의 로그들을 사람이 일일이 분석하기에는 한계에 부딪히고 있다. 분석방법 또한 한 가지 로그가 아닌 여러 가지 이기종간의 보안장비의 로그까지 서로 상관분석을 해야 하기 때문에 더욱 더 통합보안관제에 적용되어서 신속한 분석이 이루어져야 하겠다. 이런 행위를 분석하고 대응하는 과정들이 효과적인 학습방법을 통해서 점진적으로 진화를 거쳐 성숙해가는 인공지능기반 통합보안관제 서비스모델을 새롭게 제안하였다. 제안된 모델에서 예상되는 핵심적인 문제점들에 대한 해결방안을 모색하였다. 그리고 정상 행위 기반의 학습모델을 개발하여 식별되지 않는 비 정상행위 위협에 대응력을 강화하는 학습방법을 도출하였다. 또한, 제안된 보안 서비스모델을 통하여 보안담당자들의 분석과 대응을 효율적으로 지원할 수 있는 보안관제에 대한 향후 연구방향을 제시하였다.

• 상하수도학회지
• /
• 제36권4호
• /
• pp.239-248
• /
• 2022

The prediction of algal bloom is an important field of study in algal bloom management, and chlorophyll-a concentration(Chl-a) is commonly used to represent the status of algal bloom. In, recent years advanced machine learning algorithms are increasingly used for the prediction of algal bloom. In this study, XGBoost(XGB), an ensemble machine learning algorithm, was used to develop a model to predict Chl-a in a reservoir. The daily observation of water quality data and climate data was used for the training and testing of the model. In the first step of the study, the input variables were clustered into two groups(low and high value groups) based on the observed value of water temperature(TEMP), total organic carbon concentration(TOC), total nitrogen concentration(TN) and total phosphorus concentration(TP). For each of the four water quality items, two XGB models were developed using only the data in each clustered group(Model 1). The results were compared to the prediction of an XGB model developed by using the entire data before clustering(Model 2). The model performance was evaluated using three indices including root mean squared error-observation standard deviation ratio(RSR). The model performance was improved using Model 1 for TEMP, TN, TP as the RSR of each model was 0.503, 0.477 and 0.493, respectively, while the RSR of Model 2 was 0.521. On the other hand, Model 2 shows better performance than Model 1 for TOC, where the RSR was 0.532. Explainable artificial intelligence(XAI) is an ongoing field of research in machine learning study. Shapley value analysis, a novel XAI algorithm, was also used for the quantitative interpretation of the XGB model performance developed in this study.

• 실천공학교육논문지
• /
• 제15권2호
• /
• pp.529-538
• /
• 2023

보편적 인공지능교육의 필요성이 확대되고 직무 변화가 이루어지고 있는 현 시점에서, 가장 먼저 인공지능을 직무의 일부분으로 경험하게 되는 대학의 비전공자를 위한 인공지능 교양교육에 대한 연구 및 논의는 미흡한 실정이다. 비전공자 대상 인공지능 교육과정이 운영되고 있지만 주로 인공지능의 개념 및 원리에 대한 이론 중심의 교육으로 운영되고 있다. 비전공자 대상 인공지능에 대한 일반적인 개념을 이해하기 위해 체험학습을 병행하여 진행 할 필요가 있다. 따라서 본 연구는 비전공자의 특성을 고려하여 학습에 흥미를 갖고, 인공지능 수업에 대한 부담감을 낮출 수 있는 난이도의 인공지능 체험교육 학습콘텐츠를 설계한 후 앱인벤터와 오렌지 인공지능 플랫폼을 활용한 체험 교육의 학습효과를 살펴보고자 한다. 팀 별 인공지능 관련 프로젝트 작성을 통해 수집된 학습관련 데이터와 설문조사 자료를 바탕으로 분석한 결과 인공지능 교육의 필요성에 대한 인식의 긍정적인 변화와 인공지능 리터러시 능력이 향상된 것으로 나타났다. 교수자에게는 인공지능 체험교육 학습을 위한 학습모형을 설계하는 데 기틀을 마련해 주는 계기가 될 것으로 기대한다.

• Korean Journal of Radiology
• /
• 제25권6호
• /
• pp.550-558
• /
• 2024

Hepatocellular carcinoma (HCC) is a biologically heterogeneous tumor characterized by varying degrees of aggressiveness. The current treatment strategy for HCC is predominantly determined by the overall tumor burden, and does not address the diverse prognoses of patients with HCC owing to its heterogeneity. Therefore, the prognostication of HCC using imaging data is crucial for optimizing patient management. Although some radiologic features have been demonstrated to be indicative of the biologic behavior of HCC, traditional radiologic methods for HCC prognostication are based on visually-assessed prognostic findings, and are limited by subjectivity and inter-observer variability. Consequently, artificial intelligence has emerged as a promising method for image-based prognostication of HCC. Unlike traditional radiologic image analysis, artificial intelligence based on radiomics or deep learning utilizes numerous image-derived quantitative features, potentially offering an objective, detailed, and comprehensive analysis of the tumor phenotypes. Artificial intelligence, particularly radiomics has displayed potential in a variety of applications, including the prediction of microvascular invasion, recurrence risk after locoregional treatment, and response to systemic therapy. This review highlights the potential value of artificial intelligence in the prognostication of HCC as well as its limitations and future prospects.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.119-130
• /
• 2022

Crime is a common social problem that affects the quality of life. As the number of crimes increases, it is necessary to build a model to predict the number of crimes that may occur in a given period, identify the characteristics of a person who may commit a particular crime, and identify places where a particular crime may occur. Data privacy is the main challenge that organizations face when building this type of predictive models. Federated learning (FL) is a promising approach that overcomes data security and privacy challenges, as it enables organizations to build a machine learning model based on distributed datasets without sharing raw data or violating data privacy. In this paper, a federated long short- term memory (LSTM) model is proposed and compared with a traditional LSTM model. Proposed model is developed using TensorFlow Federated (TFF) and the Keras API to predict the number of crimes. The proposed model is applied on the Boston crime dataset. The proposed model's parameters are fine tuned to obtain minimum loss and maximum accuracy. The proposed federated LSTM model is compared with the traditional LSTM model and found that the federated LSTM model achieved lower loss, better accuracy, and higher training time than the traditional LSTM model.

• 한국항공운항학회지
• /
• 제30권2호
• /
• pp.34-43
• /
• 2022

In Efforts to prevent CFIT accidents so far, have been emphasizing various education measures to minimize the occurrence of human errors, as well as enforcement measures. However, current engineering measures remain in a system (TAWS) that gives warnings before colliding with ground or obstacles, and even actual automatic avoidance maneuvers are not implemented, which has limitations that cannot prevent accidents caused by human error. Currently, various attempts are being made to apply machine learning-based artificial intelligence agent technologies to the aviation safety field. In this paper, we propose a deep reinforcement learning-based artificial intelligence agent that can recognize CFIT situations and control aircraft to avoid them in the simulation environment. It also describes the composition of the learning environment, process, and results, and finally the experimental results using the learned agent. In the future, if the results of this study are expanded to learn the horizontal and vertical terrain radar detection information and camera image information of radar in addition to the terrain database, it is expected that it will become an agent capable of performing more robust CFIT autonomous avoidance.

• 문화기술의 융합
• /
• 제4권2호
• /
• pp.197-204
• /
• 2018

현재 우리가 사는 21세기에서 가장 핫한 이슈중 하나는 AI이다. 농경사회에서 산업혁명을 통해 육체노동의 자동화를 이루었듯이 정보사회에서 SW혁명을 통해 지능정보사회가 도래햇다. Google '알파고'의 등장으로 인해 컴퓨터가 스스로 학습하고 예측하는 machine learning (머신러닝) 사례를 보면서 이제 바둑의 세계 까지 인간이 컴퓨터를 이길 수 없는, 다시 말하면 컴퓨터가 인간을 뛰어넘는 시대가 왔다. 기계학습ML(machine learning)은 인공 지능 분야로, 인공지능 컴퓨터가 인간을 뛰어넘는 시대가 도래했다. 기계학습ML(machine learning)은 인공지능의 분야로, 인공지능 컴퓨터가 혼자 학습 하도록 알고리즘 기술 개발을 하는 뜻을 의미하는데, 많은 기업들이 머신러닝을 바둑의 세계까지 인간이 컴퓨터를 이길 수 없는, 다시 말하면 컴퓨터가 인간을 뛰어넘는 시대가 왔다. 많은 기업들이 머신러닝을 용하는데 그 예로는 Facebook에서 이미지를 계속 학습하여 나중에 그 이미지가 누구인지 알려주는 것도 머신러닝의 한 사례이다. 또한 구글의 데이터 센터 최적화를 위해서 효율적인 에너지 사용 모델 구축을 위해 neural network(신경망)을 활용하였다. 또 다른 사례로 마이크로소프트의 실시간 통역 모델은 번역 학습을 통해 언어관련 인풋 데이터가 증가할수록 더 정교한 번역을 해주는 모델이다. 이처럼 많은 분야에 머신러닝이 점차 쓰이면서 이제 우리 21세기 사회에서 앞으로 나아가려면 AI산업으로 뛰어들어야 한다.