• 대한불안의학회지
• /
• 제9권1호
• /
• pp.10-18
• /
• 2013

The increasing suicide rate is a serious problem in Korea. Because of increased awareness of suicidality as a problem and because completed suicide is the fourth leading cause of death, it is very important to assess the risk of suicide. The purpose of this review is to provide a systematic examination of predictive validity of measures of suicidal ideation and behavior. A number of instruments are described as useful for identifying individuals "at high risk" for suicidal behavior. However, the predictive validity for most suicide measures has not been established. The present review only includes suicide assessment instruments with published predictive validity. In addition to evaluating the suicide assessment with respect to predictive validity, the present review describes and summarizes the psychometric properties of each measure. In conclusion, because of the complexity of studying the risk of suicide and the paucity of well-designed studies, it is extremely difficult to compare and generalize these findings. In addition, only a few instruments, such as the Scale for Suicide Ideation, Suicide Intent Scale and the Beck Hopelessness Scale, have been found to be significant risk factors for completed suicide. Another problem in the field involves that there have been few suicide measures designed for elderly populations. Clearly, future research is needed to investigate the predictive validity of standardized measures for completed suicide, especially targeting elderly populations.

• 정보처리학회논문지D
• /
• 제13D권7호
• /
• pp.1027-1038
• /
• 2006

대용량 데이터베이스에서의 추천시스템은 많은 문제점들을 지니고 있으므로, 대규모 인터넷 쇼핑몰에 적합한 추천 시스템 구조와 데이터 마이닝 기법의 필요성이 요구되고 있다. 따라서 본 논문에서는 k-mean 클러스터링과 순차 패턴 기법을 이용한 VLDB(very large database) 기반의 상품 추천 시스템을 설계 및 구현한다. 본 논문에서는 사용자의 정보를 일괄처리하고 다양한 카테고리를 계층적으로 정의하며, 탐색엔진에 순차 패턴 마이닝 기법을 이용한다. 예측 모델을 만들기 위하여 사용자의 로그 데이터 중에서 카테고리에 대한 사용자의 선호도를 추출하여 이용한다. 본 논문에서는 실험과 성능 평가를 위하여 국내 인터넷 쇼핑몰에서 30일 동안 수집한 실제 데이터를 이용한다. 또한 성능평가를 위하여 추천 예측 정확율(PRP: Predictive Recommend Precision), 추천 예측 재현율(PRR: Predictive Recommend Recall), 정확도 인수(PF1 : Predictive Factor One-measure)를 제안하여 사용한다. 성능평가 결과 가장 빠른 추천시간 및 학습시간은 O(N)이었고, 다양한 실험에서의 측도들의 값이 상당히 우수하였다.

• 한국정보통신학회논문지
• /
• 제25권6호
• /
• pp.749-756
• /
• 2021

제조 생산공정에는 다양한 센서를 통해 실시간으로 양질의 데이터가 데이터베이스에 축적되고 있다. 이와 함께 통계적으로 접근하기 까다로운 데이터에 대해서 높은 수준의 정확도로 예측모델을 구축할 수 있는 머신러닝이 보급되면서 '4차 산업화 시대'를 맞이하고 있다. 본 논문에서는 이러한 제조업계의 흐름에 따라 업계의 주요 관심사인 제품의 품질특성을 예측하는 머신러닝 모델의 성능을 향상하는 방법을 제시한다. 머신러닝 모델의 성능을 향상하는데 일반적으로 사용되는 샘플 크기의 증가, Hyper-Parameter의 최적화 및 적절한 알고리즘 선택의 효과를 검증한다. 그리고, 새로운 성능향상 방법을 제시하고, 그 효과를 검증해본다. 논문에서 제시한 방법을 통해서 제조업에서는 더욱 향상된 성능의 예측모델을 구축, 품질예측과 관리에 크게 이바지할 수 있을 것이다.

• 수산경영론집
• /
• 제54권1호
• /
• pp.37-49
• /
• 2023

Climate change is a major global problem. Oysters, one of the most representative farmed fish in Korea, are attracting attention as candidates for blue carbon, an alternative to carbon neutrality. This study is analyzed by the SSP scenarios to determine the impact of oyster aquaculture production according to climate change. Based on the analysis, future productions of oysters are predicted by the SSP scenario. Significant differences by the SSP scenario are confirmed through predictive power tests among scenarios. Regression analysis was conducted from January 2001 to December 2014. As a result of the analysis, water temperature, water temperature quadratic term, salinity, salinity quadratic term, and month × water temperature cross term were estimated as significant variables. Oyster production which is predicted by the SSP scenario based on the significant variables from 2015 to 2022 was compared with actual production. The model with the highest predictive power was selected by RMSE and MAPE criteria. The predictive power was compared with the MDM test to determine which model was superior. As a result, based on RMSE and MAPE, the SSP1-2.6 scenario was selected as the best model and the SSP1-2.6, SSP2-4.5, and SSP3-7.0 scenarios all showed the same predictive power based on the MDM test. In conculusion, this study predicted oyster aquaculture production by 2030, not the distant future, due to the short duration of the analytical model. This study was found that oyster aquaculture production increased in all scenarios and there was no significant difference in predictive power by the SSP scenario.

• 대한안전경영과학회지
• /
• 제25권4호
• /
• pp.141-151
• /
• 2023

Recently, due to the expansion of the logistics industry, demand for logistics automation equipment is increasing. The modern logistics industry is a high-tech industry that combines various technologies. In general, as various technologies are grafted, the complexity of the system increases, and the occurrence rate of defects and failures also increases. As such, it is time for a predictive maintenance model specialized for logistics automation equipment. In this paper, in order to secure the operational safety and reliability of the parcel loading system, a predictive maintenance platform was implemented based on the Naive Bayes-LSTM(Long Short Term Memory) model. The predictive maintenance platform presented in this paper works by collecting data and receiving data based on a RabbitMQ, loading data in an InMemory method using a Redis, and managing snapshot DB in real time. Also, in this paper, as a verification of the Naive Bayes-LSTM predictive maintenance platform, the function of measuring the time for data collection/storage/processing and determining outliers/normal values was confirmed. The predictive maintenance platform can contribute to securing reliability and safety by identifying potential failures and defects that may occur in the operation of the parcel loading system in the future.

• 한국콘텐츠학회지
• /
• 제15권3호
• /
• pp.21-26
• /
• 2017

• 정보관리학회지
• /
• 제33권4호
• /
• pp.125-157
• /
• 2016

해외에 진출한 국내기업의 소송 사례가 증가하면서 기업들의 전자증거개시제도의 대응에 대한 요구가 증가하고 있다. 영미법에서 유래된 제도인 전자증거개시제도는 절차 진행과정에서 여러 곳에 산재해 있는 전자적 정보들을 중 제한된 시간 내에 소송과 관련된 전자적 정보들을 찾아 증거자료로 검토하여 제출하는 제도이다. 이는 하루에도 수많은 전자기록이 생산되는 국내기업들의 기록관리가 잘 이루어지지 않고 있는 현실에서 제한된 시간 이내에 증거자료를 추리고 검토하여 제출하는 것은 쉽지 않은 일이다. 검토대상을 줄이고 검토과정을 효율적으로 진행하는 것은 소송에서 승소를 위한 가장 중요한 과제 중 하나이다. Predictive Coding은 전자증거개시 검토 과정에서 사용되는 도구로써 기계학습을 이용하여 기업들이 보유하고 있는 전자적 정보들의 검토를 도와주는 도구이다. Predictive Coding이 기존의 검색도구보다 효율성이 높고 잠재적으로 소송과 관련된 전자적 정보를 추려내는데 강점이 있다고 판단된다. 기업의 효율적인 검색도구의 선택과 지속적인 기록관리를 통해 검토비용의 시간적, 비용적 절감을 꾀할 수 있을 것으로 예상된다. 따라서 기업은 전자증거개시 제도에 대응하기 위해서 시간과 비용적 측면을 고려한 전문적인 Predictive Coding 솔루션의 도입과 기업 기록관리를 통해 가장 효과적인 방법을 모색해야 할 것이다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1915-1919
• /
• 2004

In this paper, we propose a new discrete-time predictive current controller for a PMSM(Permanent Magnet Synchronous Motor). The main objectives of the current controllers are to ensure that the measured stator currents tract the command values accurately and to shorten the transient interval as much as possible, in order to obtain high-performance of ac drive system. The conventional predictive current controller is hard to implement in full digital current controller since a finite calculation time causes a delay between the current sensing time and the time that it takes to apply the voltage to motor. A new control strategy in this paper is seen the scheme that gets the fast adaptation of transient current change, the fast transient response tracking and is proposed simplified calculation. Moreover, the validity of the proposed method is demonstrated by numerical simulations and the simulation results will be verified the improvements of predictive controller and accuracy of the current controller.

• 대한간호학회지
• /
• 제43권3호
• /
• pp.442-451
• /
• 2013

Purpose: This descriptive study was done to develop a predictive model of depression in rural elders that will guide prevention and reduction of depression in elders. Methods: A cross-sectional descriptive survey was done using face-to-face private interviews. Participants included in the final analysis were 461 elders (aged${\geq}$ 65 years). The questions were on depression, personal and environmental factors, body functions and structures, activity and participation. Decision tree analysis using the SPSS Modeler 14.1 program was applied to build an optimum and significant predictive model to predict depression in rural elders. Results: From the data analysis, the predictive model for factors related to depression in rural elders presented with 4 pathways. Predictive factors included exercise capacity, self-esteem, farming, social activity, cognitive function, and gender. The accuracy of the model was 83.7%, error rate 16.3%, sensitivity 63.3%, and specificity 93.6%. Conclusion: The results of this study can be used as a theoretical basis for developing a systematic knowledge system for nursing and for developing a protocol that prevents depression in elders living in rural areas, thereby contributing to advanced depression prevention for elders.

• 성인간호학회지
• /
• 제27권1호
• /
• pp.29-38
• /
• 2015

Purpose: The purpose of the study was to validate fall risk assessment scales among hospitalized adult patients in South Korea using the electronic medical records by comparing sensitivity, specificity, positive predictive values, and negative predictive values of Morse Fall Scale (MFS), Bobath Memorial Hospital Fall Risk Assessment Scale (BMFRAS), and Johns Hopkins Hospital Fall Risk Assessment tool (JHFRAT). Methods: A total of 120 patients who experienced fall episodes during their hospitalization from June 2010 to December 2013 was categorized into the fall group. Another 120 patients, who didn't experience fall episodes with age, sex, clinical departments, and the type of wards matched with the fall group, were categorized to the comparison group. Data were analyzed for the comparisons of sensitivity, specificity, positive and negative predictive values, and the area under the curve of the three tools. Results: MFS at a cut-off score of 48 had .806 for ROC curves, 76.7% for sensitivity, 77.5% for specificity, 77.3% for positive predictive value, and 76.9% for negative predictive value, which were the highest values among the three fall assessment scales. Conclusion: The MFS with the highest score and the highest discrimination was evaluated to be suitable and reasonable for predicting falls of inpatients in med-surg units of university hospitals.