• 융합정보논문지
• /
• 제8권6호
• /
• pp.117-122
• /
• 2018

본 논문에서는 매년 기관에서 보도된 보안이슈 내용을 살펴보고 IT 환경에서 종사하는 실무자들이 업무를 진행하면서 필요한 보안사항이라고 우려한 사항들과의 공통점과 차이점에 대해 분석하고자 한다. 정부기관, 금융업, 일반 기업, 항공사 등 다양한 IT 업무 환경에서 종사하는 실무자를 대상으로 미래 정보보안 관점에서의 우려 사항이 무엇인지 직접 인터뷰 및 설문조사를 하여 의견을 수집했다. 수집된 의견을 분석하여 핵심 키워드를 도출했다. 도출된 결과를 매년 상반기와 하반기 시점에 보안업체나, 정보보호와 관련된 기관들이 보도하는 당해 보안이슈 키워드나 통계자료와 비교하여 공통으로 고려되는 보안 동향을 발견하고 차이점을 분석하여 추가로 보완해야 할 위험사항은 없는지 살펴보았다. 보안업체나, 정보보호와 관련된 기관들에서 보도된 주요 보안이슈와 IT 실무자들이 예측하는 미래의 보안 우려 사항을 종합적으로 분석하여 발견된 보완점을 현존하는 4차 산업혁명 시대의 보안위협에 대비하고자 한다.

• Healthcare Informatics Research
• /
• 제24권4호
• /
• pp.300-308
• /
• 2018

Objectives: Prompt detection is a cornerstone in the control and prevention of infectious diseases. The Integrated Disease Surveillance Project of India identifies outbreaks, but it does not exactly predict outbreaks. This study was conducted to assess temporal correlation between Google Trends and Integrated Disease Surveillance Programme (IDSP) data and to determine the feasibility of using Google Trends for the prediction of outbreaks or epidemics. Methods: The Google search queries related to malaria, dengue fever, chikungunya, and enteric fever for Chandigarh union territory and Haryana state of India in 2016 were extracted and compared with presumptive form data of the IDSP. Spearman correlation and scatter plots were used to depict the statistical relationship between the two datasets. Time trend plots were constructed to assess the correlation between Google search trends and disease notification under the IDSP. Results: Temporal correlation was observed between the IDSP reporting and Google search trends. Time series analysis of the Google Trends showed strong correlation with the IDSP data with a lag of -2 to -3 weeks for chikungunya and dengue fever in Chandigarh (r > 0.80) and Haryana (r > 0.70). Malaria and enteric fever showed a lag period of -2 to -3 weeks with moderate correlation. Conclusions: Similar results were obtained when applying the results of previous studies to specific diseases, and it is considered that many other diseases should be studied at the national and sub-national levels.

• 한국해양공학회지
• /
• 제33권5호
• /
• pp.427-434
• /
• 2019

Artificial intelligence (AI)-aided research currently enjoys active use in a wide array of fields thanks to the rapid development of computing capability and the use of Big Data. Until now, forecasting methods were primarily based on physics models and statistical studies. Today, AI is utilized in disaster prevention forecasts by studying the relationships between physical factors and their characteristics. Current studies also involve combining AI and physics models to supplement the strengths and weaknesses of each aspect. However, prior to these studies, an optimization algorithm for the AI model should be developed and its applicability should be studied. This study aimed to improve the forecast performance by constructing a model for neural network optimization. An artificial neural network (ANN) followed the ever-changing path of a typhoon to produce similar typhoon predictions, while the optimization achieved by the neural network algorithm was examined by evaluating the activation function, hidden layer composition, and dropouts. A learning and test dataset was constructed from the available digital data of one typhoon that affected Korea throughout the record period (1951-2018). As a result of neural network optimization, assessments showed a higher degree of forecast accuracy.

• 응용통계연구
• /
• 제32권1호
• /
• pp.139-148
• /
• 2019

본 연구는 KTX 수송수요를 예측하기 위한 방법으로 다중개입 시계열 모형을 제안하였다. 구체적으로 2011년 이전의 자료로서 경부 2단계 개통 개입만 고려한 Kim과 Kim (Korean Society for Railway, 14, 470-476, 2011)의 연구를 수정 보완하기 위해 다양한 개입이 추가적으로 발생하고 있는 2011년 이후의 시계열 자료를 효과적으로 모델링하는 한편 KTX 수송수요를 정확히 예측하기 위한 방법으로 다중개입 계절형 ARIMA 모형을 도입하였다. 자료 분석을 통해 KTX 수송수요에 영향을 주었던 경부 및 호남 2단계 개통, 메르스 발병과 설추석 명절 등 다양한 개입의 효과를 효과적으로 해석하는 한편, 이를 통해 예측의 정확성을 높일 수 있음을 확인하였다.

• 한국재난정보학회 논문집
• /
• 제17권2호
• /
• pp.329-340
• /
• 2021

연구목적: 본 연구는 인공신경망 라이브러리 기술을 이용하여, 기상 데이터 변화 예측을 통한 한반도 가뭄 취약지역 분석을 목적으로 하였다. 연구방법: 연구지역 중 북한 지역의 다양한 기상데이터의 확보가 힘든 특수성을 고려하여 연구지역의 월별 누적강수량 데이터를 활용하였으며, 통계프로그램 R을 이용하여 인공신경망 알고리즘을 통한 기상데이터 추정을 수행하였다. 연구결과: 본 논문에서 진행한 연구 결과, 실제 데이터와 예측 데이터 간의 상관계수 값은 인공신경망 알고리즘을 활용한 결과가 회귀분석 결과보다 평균 0.043879 더 높은 것으로 확인되었다. 결론: 연구의 결과는 가뭄 대응을 위한 재난대응 기초 연구 자료로 활용 가능할 것으로 기대한다.

• 동의신경정신과학회지
• /
• 제31권4호
• /
• pp.289-299
• /
• 2020

Objectives: The aim of this study is to investigate current research trends of Four Pillars of Destiny and verify its values and potential in the counselling scene, as the Four Pillars of Destiny's territory has been expanding to counselling, medical and psychiatric realm nowadays. Methods: The studies were searched from psychotherapy to general consultation, directly or indirectly related to counseling and Four Pillars of Destiny. Twenty-one published research studies were selected for analysis. The studies were categorized into 7 groups, meta-analysis, comparison with other personality tests, user's trend analysis, utilization in job counseling, disease prediction study, utilization in treatment counseling, and use in Korean medicine. Results: The selected studies attempted to expand Four Pillars of Destiny's usage through combination with other fields such as artificial intelligence, Korean medicine, and personality test. Furthermore by analyzing Four Pillars of Destiny itself to extract its key elements in counseling, such as therapeutic counseling factors and occupational counseling factors. Conclusions: At present, there are no standard use of Four Pillars of Destiny in counseling scene, for no large-scale research has been conducted or completed on this subject. This current status quo leads this paper to end up just understanding the counseling factors and possibilities of Four Pillars of Destiny rather than its psychological theory and clinical effect. However, this research trend analysis will be helpful in preparing future studies investigating Four Pillars of Destiny's counseling effect, application in the counseling scene and its psychological theory. Also, further studies, including confirmation of the theory through the operational definition, prospective research, control study, statistical technique are required in order to evaluate Four Pillars of Destiny's psychological theory and its effects to verify its use in clinical scenes.

• 대한금속재료학회지
• /
• 제46권3호
• /
• pp.118-124
• /
• 2008

Abstract: A minimum commitment method(MCM) was applied to predict the long-term creep rupture life for type 316LN stainless steel(SS). Lots of the creep-rupture data for the type 316LN SS were collected through world-wide literature surveys and the experimental data of KAERI. Using these data, the long-term creep rupture life above ${10}^5$ hour was predicted by means of the MCM. In order to obtain the most appropriate value for the constant A being used in the MCM equation, trial and error method was used for the wide ranges from -0.12 to 0.12, and the best value was determined by using the coefficient of determination, $R^2$ which is a statistical parameter. A suitable value for the A in type 316LN stainless steel was found to be at -0.02 ~ -0.05 ranges. It is considered that the MCM will be superior in creep-life prediction to commonly-used timetemperature parametric method, because the P(T) and G($\sigma$) functions are determined from the regression method based on experimental data.

• 응용통계연구
• /
• 제34권2호
• /
• pp.153-166
• /
• 2021

약물유전체학 연구의 주요 목표는 고차원의 유전 변수를 기반으로 개인의 약물 반응성을 예측하는 것이다. 변수의 개수가 많기 때문에 변수의 개수를 줄이기 위해서는 변수 선택이 필요하며, 선택된 변수들은 머신러닝 알고리즘을 사용하여 예측 모델을 구축하는데 사용된다. 본 연구에서는 400명의 뇌전증 환자의 차세대 염기서열 분석 데이터에 로지스틱 회귀, ReliefF, TurF, 랜덤 포레스트, LASSO의 조합과 같은 여러 가지 혼합 변수 선택 방법을 적용하였다. 선택된 변수들에 랜덤포레스트, 그래디언트 부스팅, 서포트벡터머신을 포함한 머신러닝 방법들을 적용했고 스태킹을 통해 앙상블 모형을 구축하였다. 본 연구의 결과는 랜덤포레스트와 ReliefF의 혼합 변수 선택 방법을 이용한 스태킹 모형이 다른 모형보다 더 좋은 성능을 보인다는 것을 보여주었다. 5-폴드 교차 검증을 기반으로 하여 적합한 최적 모형의 평균 검증 정확도는 0.727이고 평균 검증 AUC 값은 0.761로 나타났다. 또한, 동일한 변수를 사용할 때 스태킹 모델이 단일 머신러닝 예측 모델보다 성능이 우수한 것으로 나타났다.

• 대한의용생체공학회:의공학회지
• /
• 제43권1호
• /
• pp.27-34
• /
• 2022

Drunk driving defines a driver as unable to drive a vehicle safely due to drinking. To crack down on drunk driving, alcohol concentration evaluates through breathing and crack down on drinking using S-shaped courses. A method for assessing drunk driving without using BAC or BrAC is measurement via biosignal. Depending on the individual specificity of drinking, alcohol evaluation studies through various biosignals need to be conducted. In this study, we measure biosignals that are related to alcohol concentration, predict BrAC through SVM, and verify the effectiveness of the S-shaped course. Participants were 8 men who have a driving license. Subjects conducted a d2 test and a scenario evaluation of driving an S-shaped course when they attained BrAC's certain criteria. We utilized SVR to predict BrAC via biosignals. Statistical analysis used a one-way Anova test. Depending on the amount of drinking, there was a tendency to increase pupil size, HR, normLF, skin conductivity, body temperature, SE, and speed, while normHF tended to decrease. There was no apparent change in the respiratory rate and TN-E. The result of the D2 test tended to increase from 0.03% and decrease from 0.08%. Measured biosignals have enabled BrAC predictions using SVR models to obtain high Figs in primary and secondary cross-validations. In this study, we were able to predict BrAC through changes in biosignals and SVMs depending on alcohol concentration and verified the effectiveness of the S-shaped course drinking control method.

• 대기
• /
• 제31권5호
• /
• pp.489-510
• /
• 2021

In this paper, we propose an algorithm for detecting convective initiation (CI) using GEO-KOMPSAT-2A/advanced meteorological imager data. The algorithm identifies clouds that are likely to grow into convective clouds with radar reflectivity greater than 35 dBZ within the next two hours. This algorithm is developed using statistical and qualitative analysis of cloud characteristics, such as atmospheric instability, cloud top height, and phase, for convective clouds that occurred on the Korean Peninsula from June to September 2019. The CI algorithm consists of four steps: 1) convective cloud mask, 2) cloud object clustering and tracking, 3) interest field tests, and 4) post-processing tests to remove non-convective objects. Validation, performed using 14 CI events that occurred in the summer of 2020 in Korean Peninsula, shows a total probability of detection of 0.89, false-alarm ratio of 0.46, and mean lead-time of 39 minutes. This algorithm can be useful warnings of rapidly developing convective clouds in future by providing information about CI that is otherwise difficult to predict from radar or a numerical prediction model. This CI information will be provided in short-term forecasts to help predict severe weather events such as localized torrential rainfall and hail.