• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권12호
• /
• pp.3100-3116
• /
• 2012

Reversible data hiding enables the embedding of messages in a host image without any loss of host content, which is proposed for image authentication that if the watermarked image is deemed authentic, we can revert it to the exact copy of the original image before the embedding occurred. In this paper, we present an improved histogram-based reversible data hiding scheme based on prediction and sorting. A rhombus prediction is employed to explore the prediction for histogram-based embedding. Sorting the prediction has a good influence on increasing the embedding capacity. Characteristics of the pixel difference are used to achieve large hiding capacity while keeping low distortion. The proposed scheme exploits a two-stage embedding strategy to solve the problem about communicating peak points. We also present a histogram shifting technique to prevent overflow and underflow. Performance comparisons with other existing reversible data hiding schemes are provided to demonstrate the superiority of the proposed scheme.

• 한국항공운항학회지
• /
• 제25권4호
• /
• pp.124-129
• /
• 2017

Clouds are an important factor in aircraft flight. In particular, a significant impact on small aircraft flying at low altitude. Therefore, we have verified and characterized the low level cloud prediction data of the Unified Model(UM) - based Local Data Assimilation and Prediction System(LDAPS) operated by KMA in order to develop cloud forecasting service and contents important for safety of low-altitude aircraft flight. As a result of the low level cloud test for seven airports in Korea, a high correlation coefficient of 0.4 ~ 0.7 was obtained for 0-36 leading time. Also, we found that the prediction performance does not decrease as the lead time increases. Based on the results of this study, it is expected that model-based forecasting data for low-altitude aviation meteorology services can be produced.

• Genomics & Informatics
• /
• 제16권4호
• /
• pp.32.1-32.7
• /
• 2018

Ovarian cancer is one of the leading causes of cancer-related deaths in gynecological malignancies. Over 70% of ovarian cancer cases are high-grade serous ovarian cancers and have high death rates due to their resistance to chemotherapy. Despite advances in surgical and pharmaceutical therapies, overall survival rates are not good, and making an accurate prediction of the prognosis is not easy because of the highly heterogeneous nature of ovarian cancer. To improve the patient's prognosis through proper treatment, we present a prognostic prediction model by integrating high-dimensional RNA sequencing data with their clinical data through the following steps: gene filtration, pre-screening, gene marker selection, integrated study of selected gene markers and prediction model building. These steps of the prognostic prediction model can be applied to other types of cancer besides ovarian cancer.

• Journal of Information Processing Systems
• /
• 제15권2호
• /
• pp.305-319
• /
• 2019

The prediction of the sum of container is very important in the field of container transport. Many influencing factors can affect the prediction results. These factors are usually composed of many variables, whose composition is often very complex. In this paper, we use gray relational analysis to set up a proper forecast index system for the prediction of the sum of containers in foreign trade. To address the issue of the low accuracy of the traditional prediction models and the problem of the difficulty of fully considering all the factors and other issues, this paper puts forward a prediction model which is combined with a back-propagation (BP) neural networks and the support vector machine (SVM). First, it gives the prediction with the data normalized by the BP neural network and generates a preliminary forecast data. Second, it employs SVM for the residual correction calculation for the results based on the preliminary data. The results of practical examples show that the overall relative error of the combined prediction model is no more than 1.5%, which is less than the relative error of the single prediction models. It is hoped that the research can provide a useful reference for the prediction of the sum of container and related studies.

• International journal of advanced smart convergence
• /
• 제7권1호
• /
• pp.24-32
• /
• 2018

An outlier detection method using mixed prediction model has been described in this paper. The mixed prediction model consists of time-series model and regression model. The parameter estimation of the prediction model was performed using supervised learning and a genetic algorithm is adopted for a learning method. The experiments were performed in artificial and real data set. The prediction performance is compared with the existing prediction methods using artificial data. Outlier detection is conducted using the real sensor measurements in a dam. The validity of the proposed method was shown in the experiments.

• 한국환경과학회지
• /
• 제27권11호
• /
• pp.1141-1154
• /
• 2018

Numerical experiments were carried out to investigate the effect of data assimilation of observational data on weather and PM (particulate matter) prediction. Observational data applied to numerical experiment are aircraft observation, satellite observation, upper level observation, and AWS (automatic weather system) data. In the case of grid nudging, the prediction performance of the meteorological field is largely improved compared with the case without data assimilations because the overall pressure distribution can be changed. So grid nudging effect can be significant when synoptic weather pattern strongly affects Korean Peninsula. Predictability of meteorological factors can be expected to improve through a number of observational data assimilation, but data assimilation by single data often occurred to be less predictive than without data assimilation. Variation of air pressure due to observation nudging with high prediction efficiency can improve prediction accuracy of whole model domain. However, in areas with complex terrain such as the eastern part of the Korean peninsula, the improvement due to grid nudging were only limited. In such cases, it would be more effective to aggregate assimilated data.

• 인터넷정보학회논문지
• /
• 제11권4호
• /
• pp.85-94
• /
• 2010

본 논문은 사용자가 이동하려는 위치를 사전에 예측하고 예측된 정보를 이용하여 사용자 서비스를 미리 제공할 수 있도록 하는 위치예측 구조를 제안한다. 제안한 구조는 7개의 단계를 거쳐 사용자의 위치예측 및 지능화된 서비스를 제공하도록 한다. 물리적 센서와 히스토리 데이터베이스로부터 수집된 상황정보는 이질적인 데이터 형태를 갖기 때문에 이로 인한 데이터의 중요도 및 추상화 과정에 어려움이 있다. 이에 본 논문은 데이터의 유형을 동질적인 형태로 바꾸어 특징 추출을 하는 위치 예측구조를 제안한다. 추출된 값은 SOFM을 통해 군집화하고 ARIMA를 통해 미리 사용자의 위치 정보를 얻으며, 추론 엔진을 거쳐 최종 서비스를 실현한다. 제안된 위치예측 구조의 검증을 위해 테스트베드를 구축하고 시나리오에 따라 실험한다.

• Journal of the Korean Data and Information Science Society
• /
• 제19권4호
• /
• pp.1007-1018
• /
• 2008

The purpose of this case study is to demonstrate database-marketing management. First, we explore original variables for insurance customer's data, modify them if necessary, and go through variable selection process before analysis. Then, we develop churn prediction models using logistic regression, neural network and SVM analysis. We also compare these three data mining models in terms of misclassification rate.

• Architectural research
• /
• 제24권1호
• /
• pp.1-11
• /
• 2022

As the occurrence of a crime is dependent on different factors, their correlations are beyond the ordinary cognitive range. Owing to this limitation, systems face difficulty in correlating various factors, thereby requiring the assistance of artificial intelligence (AI) to overcome such limitations. Therefore, AI has become indispensable for crime prediction. Crimes can cause severe and irrevocable damage to a society. Recently, big data has been introduced for developing highly accurate models for crime prediction. Prediction of night crimes should be given significant consideration, because crimes primarily occur during nights, when the spatiotemporal characteristics become vulnerable to crimes. Many environmental factors that influence crime rate are applied for crime prediction, and their influence on crime rate may differ based on temporal characteristics and the nature of crime. This study aims to identify the environmental factors that influence sex and theft crimes occurring at night and proposes an artificial neural network (ANN) model to predict sex and theft crimes at night in random areas. The crime data of A district in Seoul for 12 years (2004-2015) was used, and environmental factors that influence sex and theft crimes were derived through multiple regression analysis. Two types of crime prediction models were developed: Type A using all environmental factors as input data; Type B with only the significant factors (obtained from regression analysis) as input data. The Type B model exhibited a greater accuracy than Type A, by 3.26 and 9.47 % higher for theft and sex crimes, respectively.

• 인터넷정보학회논문지
• /
• 제19권6호
• /
• pp.101-112
• /
• 2018

A lot of manpower and budgets are being used to prevent fires, and only a small portion of the data generated during this process is used for disaster prevention activities. This study develops a prediction model of fire occurrence probability based on data mining in order to more actively use these data for disaster prevention activities. For this purpose, variables for predicting fire occurrence probability of various buildings were selected and data of construction administrative system, national fire information system, and Korea Fire Insurance Association were collected and integrated data set was constructed. After appropriate data cleansing and preprocessing, various data mining methodologies such as artificial neural network, decision trees, SVM, and Naive Bayesian were used to develop a prediction model of the fire occurrence probability of buildings. The most accurate model among the derived models is Linear SVM model which shows 68.42% as experimental data and 63.54% as verification data and it is the best model to predict fire occurrence probability of buildings. As this study develops the prediction model which uses only the set values of the specific ranges, future studies may explore more opportunites to use various setting values not shown in this study.