• 한국컴퓨터정보학회논문지
• /
• 제23권9호
• /
• pp.81-86
• /
• 2018

Software defect severity is very important in projects with limited historical data or new projects. But general software defect prediction is very difficult to collect the label information of the training set and cross-project defect prediction must have a lot of data. In this paper, an unclassified data set with defect severity is clustered according to the distribution ratio. And defect severity-based prediction model is proposed by way of labeling. Proposed model is applied CLAMI in JM1, PC4 with the least ambiguity of defect severity-based NASA dataset. And it is evaluated the value of ACC compared to original data. In this study experiment result, proposed model is improved JM1 0.15 (15%), PC4 0.12(12%) than existing defect severity-based prediction models.

• 디지털산업정보학회논문지
• /
• 제20권2호
• /
• pp.1-10
• /
• 2024

For the purpose of predicting credit card customer churn accurately through data analysis, a model can be constructed with various machine learning algorithms, including decision tree. And feature importance has been utilized in selecting better input features that can improve performance of data analysis models for several application areas. In this paper, a method of utilizing feature importance calculated from the MDI method and its effects are investigated in the credit card customer churn prediction problem with classification trees. Compared with several random feature selections from case data, a set of input features selected from higher value of feature importance shows higher predictive power. It can be an efficient method for classifying and choosing input features necessary for improving prediction performance. The method organized in this paper can be an alternative to the selection of input features using feature importance in composing and using classification trees, including credit card customer churn prediction.

• 한국해양공학회지
• /
• 제31권6호
• /
• pp.425-430
• /
• 2017

In order to reduce the cost of corrections and time needed for the block assembly process, the reverse setting method is applied for a back-heated block to neutralize deck deformation. The proper reverse setting shape for a back-heated block to correct deformation improved the deck flatness, but an excessive amount of reverse setting could inversely affect the flatness of the block. A prediction method was developed for the proper reverse setting shape using a back-heated block, considering the complex geometry of blocks, thickness of the deck plate, and thermal loading conditions such as welding and back-heating. The prediction method was developed by combining the re-meshing technique and inherent strain-based deformation analysis using the finite element method. Because the flatness deviation was decreased until the lower critical point and thereafter it tended to increase again, the optimum value for which the flatness was the best case was selected by repeatedly calculating the predefined reverse setting values. Based on this analysis and the study of the back-heating deformation of large assembly blocks, including the reverse setting shape, the mechanism for selecting the optimum reverse setting value was identified. The developed method was applied to the actual blocks of a ship, and it was confirmed that the flatness of the block was improved. It is concluded that the developed prediction method can be used to predict the optimum reverse setting shape value of a ship's block, which will reduce the cost of corrections in the construction stage.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제4권3호
• /
• pp.81-84
• /
• 2015

클라우드 서비스는 다양한 장점들 덕분에 현대 IT 사업에서 주목을 받고 있다. 클라우드 환경에서 사용자의 요구는 동적이기 때문에 서비스 제공자는 사용자 요구량을 예측하고 이를 기반으로 자원을 제공하는 VM(Virtual Machine) 프로비저닝 기법이 필요하다. VM 프로비저닝은 사용자의 QoS를 만족시키고 자원 관리 비용을 최소화하여 서비스 제공자의 이득을 최대화하는 것을 목적으로 한다. 본 논문에서는 효율적인 VM 프로비저닝을 위해 사용자의 자원 요구량을 예측하고, 이를 기반으로 서비스 제공자의 총 경비에 대한 기대 값을 최소화시키기 위한 새로운 VM 프로비저닝 기법을 제안한다. 또한 제안 기법의 성능 분석을 위하여 실제 데이터를 이용하여 자원 요구 예측량과 자원 제공량을 계산하고, 이를 다른 기법들과 비교함으로써 제안 기법이 서비스 제공자의 총 경비를 최소화함을 보여준다.

• 디지털융복합연구
• /
• 제16권12호
• /
• pp.293-299
• /
• 2018

기상은 농작물 재배에 많은 영향을 미친다. 농작물 재배지의 기상정보는 효율적인 농작물 재배 및 관리에 필수적이다. 농업기상 정보의 높은 수요에도 불구하고 이에 대한 연구는 부족하다. 본 연구는 중장기 계절예측정보인 GloSea5와 심층 신경망을 통해 양파의 주산지인 전라남도의 농업기상 정보 생산 방법을 다룬다. 연구방법으로는 매일 생산되는 GloSea5 기상정보를 훈련시키기 위해 슬라이딩 창 방법을 활용한 심층신경망 모형이 사용되었다. 모형의 정확도평가는 농업기상관측소의 일 평균기온과 GloSea5 예측값 그리고 딥러닝 예측값 차이의 RMSE와 MAE로 계산하였다. 심층신경망 모형은 학습기간이 늘어날수록 정확도가 향상되므로 학습기간과 예측기간에 따른 예측성능을 비교하였다. 분석결과 학습기간과 예측기간은 비례하지만 계절변화에 따른 추세성이 반영되는 한계점이 있었다. 이를 보안하기 위해 예측값과 관측값의 차이를 다음날 예측값에 적용시킨 후보정 심층신경망 모형을 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.

• 융합정보논문지
• /
• 제12권3호
• /
• pp.1-10
• /
• 2022

배추와 같은 채소류는 자연재해의 영향을 많이 받기 때문에 폭우나 병해와 같은 재해로 인해 가격 변동이 심해져 농가 경제에 영향을 미치게 된다. 이러한 문제를 해결하기 위해서 농산물 가격 예측을 위한 다양한 노력이 행해졌지만 극심한 가격 예측 변동을 예측하기는 어렵다. 본 연구에서는 단일 분류기를 결합하여 다양한 여러 개의 분류기를 통해 최종 예측 결과를 결정하는 방식인 앙상블 Voting 기법으로 배추 가격을 분석하였다. 또한 시계 열 분석 방법인 LSTM과 부스팅 기법인 XGBoost와 RandomForest로 결과 비교를 하였다. 가격 데이터는 일별 데이터를 사용하였고 배추 가격에 영향을 주는 기상정보와 물가지수 등을 사용하였다. 연구 결과로는 실제값과 예측값의 차이를 보여주는 RMSE 값이 약 236 수준이다. 이 연구를 활용하여 농산물 가격 예측과 같은 다른 시계 열 분석 연구 모델 선정에 활용할 수 있을 것으로 기대된다.

• 산업경영시스템학회지
• /
• 제46권1호
• /
• pp.105-111
• /
• 2023

Recently, research on prediction algorithms using deep learning has been actively conducted. In addition, algorithmic trading (auto-trading) based on predictive power of artificial intelligence is also becoming one of the main investment methods in stock trading field, building its own history. Since the possibility of human error is blocked at source and traded mechanically according to the conditions, it is likely to be more profitable than humans in the long run. In particular, for the virtual currency market at least for now, unlike stocks, it is not possible to evaluate the intrinsic value of each cryptocurrencies. So it is far effective to approach them with technical analysis and cryptocurrency market might be the field that the performance of algorithmic trading can be maximized. Currently, the most commonly used artificial intelligence method for financial time series data analysis and forecasting is Long short-term memory(LSTM). However, even t4he LSTM also has deficiencies which constrain its widespread use. Therefore, many improvements are needed in the design of forecasting and investment algorithms in order to increase its utilization in actual investment situations. Meanwhile, Prophet, an artificial intelligence algorithm developed by Facebook (META) in 2017, is used to predict stock and cryptocurrency prices with high prediction accuracy. In particular, it is evaluated that Prophet predicts the price of virtual currencies better than that of stocks. In this study, we aim to show Prophet's virtual currency price prediction accuracy is higher than existing deep learning-based time series prediction method. In addition, we execute mock investment with Prophet predicted value. Evaluating the final value at the end of the investment, most of tested coins exceeded the initial investment recording a positive profit. In future research, we continue to test other coins to determine whether there is a significant difference in the predictive power by coin and therefore can establish investment strategies.

• 한국주거학회논문집
• /
• 제7권2호
• /
• pp.1-7
• /
• 1996

This study was designed to examine the effects of housing values on housing satisfaction model. The empirical model of this study was based on the Goulart(1982). Data were collected through questionnaire survey, and the sample consisted of 285 households in Kimhae. Housing values were grouped into four clusters : the health and convenience value, the personal and social value, the location value, and the economic value. The major findings were that 1) the concordance between values and the actual housing conditions contributes significantly to the prediction of housing astisfaction, and 2) the control variables including sociodemographic and economic characteristics and housing values themselves did not directly influence on housing satisfaction.

• 한국컴퓨터정보학회논문지
• /
• 제20권3호
• /
• pp.19-27
• /
• 2015

대체 에너지 기술 개발을 위해 지난 20년 동안 풍력 발전에 관련한 기술들이 축적되어왔다. 풍력 발전은 자연적으로 부는 바람을 에너지원으로 사용하므로 환경 친화적이며 경제적이다. 이러한 풍력 발전의 효율적인 운영을 위해서는 시시각각 변하는 자연 바람의 세기를 정확도 높게 예측할 수 있어야 한다. 풍속을 평균적으로 얼마나 정확하게 잘 예측하는지도 중요하지만 실제 값과 예측 값의 절대 오차의 최댓값을 최소화시키는 것 또한 중요하다. 발전 운영 계획 측면에서 예측 풍속을 통한 예측 발전량과 실제 발전량의 차이는 경제적 손실을 가져오는 원인이 되므로 유연한 운영 계획을 세우기 위해 최대 오차가 중요한 역할을 한다. 본 논문에서는 풍속 예측 방법으로 과거 풍속 변화 추세뿐만 아니라 기상청 예보와 시기적인 풍속의 특성을 고려하기 위한 경향 값을 반영하여 수치 예측 알고리즘으로 학습한 풍속 예보 모델을 제안한다. 기상청 예보는 풍력 발전 단지를 포함하는 비교적 넓은 지역의 풍속을 예보하지만 풍속을 예측하고자 하는 국소지점에 대한 풍속 예측의 정확도를 높이는데 상당히 기여한다. 또한 풍속 변화 추세는 긴 시간동안 관측한 풍속을 세세하게 반영할수록 풍속 예측의 정확도를 높인다.