• Journal of Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.147-168
• /
• 2017

There have been many studies on accurate stock market forecasting in academia for a long time, and now there are also various forecasting models using various techniques. Recently, many attempts have been made to predict the stock index using various machine learning methods including Deep Learning. Although the fundamental analysis and the technical analysis method are used for the analysis of the traditional stock investment transaction, the technical analysis method is more useful for the application of the short-term transaction prediction or statistical and mathematical techniques. Most of the studies that have been conducted using these technical indicators have studied the model of predicting stock prices by binary classification - rising or falling - of stock market fluctuations in the future market (usually next trading day). However, it is also true that this binary classification has many unfavorable aspects in predicting trends, identifying trading signals, or signaling portfolio rebalancing. In this study, we try to predict the stock index by expanding the stock index trend (upward trend, boxed, downward trend) to the multiple classification system in the existing binary index method. In order to solve this multi-classification problem, a technique such as Multinomial Logistic Regression Analysis (MLOGIT), Multiple Discriminant Analysis (MDA) or Artificial Neural Networks (ANN) we propose an optimization model using Genetic Algorithm as a wrapper for improving the performance of this model using Multi-classification Support Vector Machines (MSVM), which has proved to be superior in prediction performance. In particular, the proposed model named GA-MSVM is designed to maximize model performance by optimizing not only the kernel function parameters of MSVM, but also the optimal selection of input variables (feature selection) as well as instance selection. In order to verify the performance of the proposed model, we applied the proposed method to the real data. The results show that the proposed method is more effective than the conventional multivariate SVM, which has been known to show the best prediction performance up to now, as well as existing artificial intelligence / data mining techniques such as MDA, MLOGIT, CBR, and it is confirmed that the prediction performance is better than this. Especially, it has been confirmed that the 'instance selection' plays a very important role in predicting the stock index trend, and it is confirmed that the improvement effect of the model is more important than other factors. To verify the usefulness of GA-MSVM, we applied it to Korea's real KOSPI200 stock index trend forecast. Our research is primarily aimed at predicting trend segments to capture signal acquisition or short-term trend transition points. The experimental data set includes technical indicators such as the price and volatility index (2004 ~ 2017) and macroeconomic data (interest rate, exchange rate, S&P 500, etc.) of KOSPI200 stock index in Korea. Using a variety of statistical methods including one-way ANOVA and stepwise MDA, 15 indicators were selected as candidate independent variables. The dependent variable, trend classification, was classified into three states: 1 (upward trend), 0 (boxed), and -1 (downward trend). 70% of the total data for each class was used for training and the remaining 30% was used for verifying. To verify the performance of the proposed model, several comparative model experiments such as MDA, MLOGIT, CBR, ANN and MSVM were conducted. MSVM has adopted the One-Against-One (OAO) approach, which is known as the most accurate approach among the various MSVM approaches. Although there are some limitations, the final experimental results demonstrate that the proposed model, GA-MSVM, performs at a significantly higher level than all comparative models.

• The Korean Journal of Archival Studies
• /
• no.33
• /
• pp.155-206
• /
• 2012

Interests in archives management are getting expanded from the public sector into the cultural and artistic field for the ten years after legislation of "Act on the Management of Public Archives" in 1999. However, due to lack of recognition on the importance of archives in the cultural and artistic field, it is rather frequent that information is kept scattered or archives are lost. As an example, absence of precise contract documents or notes of bestowal keeps people from locating great amount of cultural properties, and because of it these creative properties are in the risk of thefts, the closed-door auctioning, or trades in unofficial channels. As how a nation manages cultural and artistic creation inside the nation reflects its cultural level, it can be said that one of the indexes to notice the extent of a nation's cultural level is to take a look at how they are circulated. This study started from this point. Growing economy and rising interests in culture and art made the society more cognizant of the importance and value that visual artworks have, but the archives and information which are showing the context of these artworks and are produced in the course of social interaction are relatively disregarded because too much emphasis lies on the work itself. It is harder to find archives or documentations in Korea than in other advanced countries about the artists themselves or philosophical discourse on the background of the artworks. There is not so much interest to preserve the archives and information produced after the exhibition also, and they are used for no more than promotion or reference. Hereupon, the researcher recognized the importance of visual arts archives and believed that systemic management on them are high in need. And metadata is an essential way for the systemic management, as recently management on artworks or their archives are conducted using the system of the agencies even though they are not produced electronically. The objective of this study is to manage visual arts archives systematically by designing a data model reflecting traits of visual arts archives. Metadata are needed in the every course of archives from acquisition to management, preservation and application. Visual arts archives find its rich value only when a systemic relationship is established among information on artist, artwork and events including exhibition. By establishing a Multiple Entity Data Model, in which artworks, artists and events (exhibitions) make relationship all together, metadata for management on visual arts archive gets more efficiency and at the same time explanatory trait of the archive gets higher. For this reason we, in the study, tried to design a data model by setting each as an independent entities and designating relations between them, in order to find a way to manage visual arts archives more systematically.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.23-45
• /
• 2020

Big data is creating in a wide variety of fields such as medical care, manufacturing, logistics, sales site, SNS, and the dataset characteristics are also diverse. In order to secure the competitiveness of companies, it is necessary to improve decision-making capacity using a classification algorithm. However, most of them do not have sufficient knowledge on what kind of classification algorithm is appropriate for a specific problem area. In other words, determining which classification algorithm is appropriate depending on the characteristics of the dataset was has been a task that required expertise and effort. This is because the relationship between the characteristics of datasets (called meta-features) and the performance of classification algorithms has not been fully understood. Moreover, there has been little research on meta-features reflecting the characteristics of multi-class. Therefore, the purpose of this study is to empirically analyze whether meta-features of multi-class datasets have a significant effect on the performance of classification algorithms. In this study, meta-features of multi-class datasets were identified into two factors, (the data structure and the data complexity,) and seven representative meta-features were selected. Among those, we included the Herfindahl-Hirschman Index (HHI), originally a market concentration measurement index, in the meta-features to replace IR(Imbalanced Ratio). Also, we developed a new index called Reverse ReLU Silhouette Score into the meta-feature set. Among the UCI Machine Learning Repository data, six representative datasets (Balance Scale, PageBlocks, Car Evaluation, User Knowledge-Modeling, Wine Quality(red), Contraceptive Method Choice) were selected. The class of each dataset was classified by using the classification algorithms (KNN, Logistic Regression, Nave Bayes, Random Forest, and SVM) selected in the study. For each dataset, we applied 10-fold cross validation method. 10% to 100% oversampling method is applied for each fold and meta-features of the dataset is measured. The meta-features selected are HHI, Number of Classes, Number of Features, Entropy, Reverse ReLU Silhouette Score, Nonlinearity of Linear Classifier, Hub Score. F1-score was selected as the dependent variable. As a result, the results of this study showed that the six meta-features including Reverse ReLU Silhouette Score and HHI proposed in this study have a significant effect on the classification performance. (1) The meta-features HHI proposed in this study was significant in the classification performance. (2) The number of variables has a significant effect on the classification performance, unlike the number of classes, but it has a positive effect. (3) The number of classes has a negative effect on the performance of classification. (4) Entropy has a significant effect on the performance of classification. (5) The Reverse ReLU Silhouette Score also significantly affects the classification performance at a significant level of 0.01. (6) The nonlinearity of linear classifiers has a significant negative effect on classification performance. In addition, the results of the analysis by the classification algorithms were also consistent. In the regression analysis by classification algorithm, Naïve Bayes algorithm does not have a significant effect on the number of variables unlike other classification algorithms. This study has two theoretical contributions: (1) two new meta-features (HHI, Reverse ReLU Silhouette score) was proved to be significant. (2) The effects of data characteristics on the performance of classification were investigated using meta-features. The practical contribution points (1) can be utilized in the development of classification algorithm recommendation system according to the characteristics of datasets. (2) Many data scientists are often testing by adjusting the parameters of the algorithm to find the optimal algorithm for the situation because the characteristics of the data are different. In this process, excessive waste of resources occurs due to hardware, cost, time, and manpower. This study is expected to be useful for machine learning, data mining researchers, practitioners, and machine learning-based system developers. The composition of this study consists of introduction, related research, research model, experiment, conclusion and discussion.

• Journal of the Korean GEO-environmental Society
• /
• v.19 no.11
• /
• pp.31-37
• /
• 2018

Most of tall building systems are composed of above-ground structure and underground structure used for parking and stores. The underground structure may have a pronounced influence on tall building response, but its influence is still not well understood. In a widely referred report on seismic design of tall buildings, it is recommended to model the underground structure ignoring the surrounding ground and to impose input ground motion calculated considering the underground structure-soil kinematic interaction between at its base. In this study, dynamic analyses are performed on 1B and 5B basements. The motions at the base are calculated to free field responses. The motions are further compared to two procedures outlined in the report to account for the kinematic interaction. It is shown that one of the procedure fits well for the 1B model, whereas both procedures provide poor fit with 5B model analysis result.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.1
• /
• pp.401-405
• /
• 2006

A uniform velocity field of crust can be obtained by cumulative multi-year GPS data. Then the shortening and sliding of drape zones between Chinese Continent Blocks can be researched through the velocity field and dynamics meaning is also analyzed. A model of movement and strain is created to extract displacing and rotating information of blocks in this paper. On the basis of it, the shortening vectors and sliding states of drape zones between blocks can be obtained by the model of level center of gravity moving velocity vectors between neighboring blocks. Some result show as follows. India plate jostles greatly toward north, so a complicated movement situation is formed for 14 sub-blocks. And self-deformations of inner tectosomes can be greatly reflected according to the characteristics of drape zones between tectosomes. The extrusion deformation exists between Himalaya and Qiangtang blocks. Its contraction ratio is about 20.1 $mm.a^{-1}$. However, it only is $mm.a^{-1}$ between Tarim and Zhungar. The deformation characteristics and contraction ratio of other drape zones are obviously different with the former. The movement characteristics of contraction, shear, dislocation, etc. are showed in these zones. The average contraction ratio is about 5.0 $mm.a^{-1}$. The whole trend in the west continent has a big movement toward north, and in the east continent has a small movement toward south or southeast. The strain of west continent is far bigger than that of east, and the strain of southwest is bigger than that of the southeast. It is whole showed that India plate jostles toward north-east and the south-north zone has cutting and absorbing phenomena. The total characteristics and present-day trends of deformation of inland drape zones are basically described by the sinistrorse dislocation in south-north zone and Arjin fracture, the sinistrorse shear between south china and north china, etc.

• 한국해양학회지
• /
• v.29 no.2
• /
• pp.119-131
• /
• 1994

Vertical structures of wind-driven and tidal currents in a rectangular shaped uniform-depth basin of homogeneous water have been investigated using a mode-splitted, multi-level grid-box, hydrodynamic numerical model. The model was verified using analytical solutions for various vertical eddy viscosity profiles such as: a constant eddy viscosity, a linearly decreasing or increasing variation with depth, a quadratic variation with depth and an exponential variation with depth. Particular attention has been paid on the effects of "near-surface wall layer" on vertical shear of velocity. In numerical calculations, the whole water depth was divided into 13 levels with an unequal grid spacing. the model satisfactorily reproduces the velocity profile, but in case the eddy viscosity decreases rapidly with depth as in quadratical or exponential variation with depth, the vertical gradient of velocity near the bottom became very steep, and analytical solutions and numerical results showed some discrepancy. The vertical structures of horizontal velocity vary with both the depth-averaged value of eddy viscosity and its profiles. the velocity near the sea surface and near the bottom responded sensitively to the eddy viscosity of wall layer. For wind-driven current, the strong velocity shear was generated near the sea surface as eddy viscosity near the surface became small. For tidal current, the velocity above the sea bottom layer was almost constant regardless of the profiles of vertical eddy viscosity, but velocity in the sea bottom layer showed strong shear as eddy viscosity became small.

• The Journal of the Korea Contents Association
• /
• v.18 no.12
• /
• pp.25-34
• /
• 2018

With the higher competition of university environment, universities has been adapted Customer Satisfaction Index (CSI). However, the problem of CSI focuses on score and ranking announcement. In public sectors, PCSI model is used because of increasing its strategic utilization by providing diagnosis of the phenomenon and direction for future improvement through causal model analysis. The purpose of this research is to develop a measurements of university satisfaction using PCSI. This research demonstrates validity and reliability of PCSI using test-retest method using multi-group confirmatory factor analysis. The results of this research indicate that the reliability and validity of the PCSI model is verified. Service product quality, service delivery quality, environment quality and social quality have positive effects on customer satisfaction. In turn, customer satisfaction have positve effects on university performance and social performance. In conclusion, service quality, PCSI, and service performance are clarified to be appropriate components of the satisfaction survey. These results can be used to measure the satisfaction level of education at actual universities. It is expected that practical basic data can be obtained to improve the quality of university education.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.30 no.6
• /
• pp.242-252
• /
• 2018

It is well known that an Oscillating Water Column Wave Energy Converter (OWC-WEC) is one of the most efficient wave absorber equipment. This device transforms the vertical motion of water column in the air chamber into the air flow velocity and produces electricity from the driving force of turbine as represented by the Wells turbine. Therefore, in order to obtain high electric energy, it is necessary to amplify the water surface vibration by inducing resonance of the piston mode in the water surface fluctuation in the air chamber. In this study, a new type of OWC-WEC with a seawater channel is used, and the wave deformation by the structure, water surface fluctuation in the air chamber, air outflow velocity from the nozzle and seawater flow velocity in the seawater channel are evaluated by numerical analysis in detail. The numerical analysis model uses open CFD code OLAFLOW model based on multi-phase analysis technique of Navier-Stokes solver. To validate model, numerical results and existing experimental results are compared and discussed. It is revealed within the scope of this study that the air flow velocity at nozzle increases as the Ursell number becomes larger, and the air velocity that flows out from the inside of the air chamber is larger than the velocity of incoming air into the air chamber.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1709-1722
• /
• 2022

The rise in temperature induced by global warming caused in El Nino and La Nina, and abnormally changed the temperature of seawater. Rainfall concentrates in some locations due to abnormal variations in seawater temperature, causing frequent abnormal floods. It is important to rapidly detect flooded regions to recover and prevent human and property damage caused by floods. This is possible with synthetic aperture radar. This study aims to generate a model that directly derives flood-damaged areas by using modified U-NET and TerraSAR-X images based on Multi Kernel to reduce the effect of speckle noise through various characteristic map extraction and using two images before and after flooding as input data. To that purpose, two synthetic aperture radar (SAR) images were preprocessed to generate the model's input data, which was then applied to the modified U-NET structure to train the flood detection deep learning model. Through this method, the flood area could be detected at a high level with an average F1 score value of 0.966. This result is expected to contribute to the rapid recovery of flood-stricken areas and the derivation of flood-prevention measures.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.1
• /
• pp.93-114
• /
• 2023

Information extraction can facilitate the intensive analysis of documents by providing semantic triples which consist of named entities and their relations recognized in the texts. However, most of the research so far has been carried out separately for named entity recognition and relation extraction as individual studies, and as a result, the effective performance evaluation of the entire information extraction systems was not performed properly. This paper introduces two models of end-to-end information extraction that can extract various entity names in clinical records and their relationships in the form of semantic triples, namely pipeline and joint models and compares their performances in depth. The pipeline model consists of an entity recognition sub-system based on bidirectional GRU-CRFs and a relation extraction module using multiple encoding scheme, whereas the joint model was implemented with a single bidirectional GRU-CRFs equipped with multi-head labeling method. In the experiments using i2b2/VA 2010, the performance of the pipeline model was 5.5% (F-measure) higher. In addition, through a comparative experiment with existing state-of-the-art systems using large-scale neural language models and manually constructed features, the objective performance level of the end-to-end models implemented in this paper could be identified properly.