• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.29-45
• /
• 2012

Bond rating is regarded as an important event for measuring financial risk of companies and for determining the investment returns of investors. As a result, it has been a popular research topic for researchers to predict companies' credit ratings by applying statistical and machine learning techniques. The statistical techniques, including multiple regression, multiple discriminant analysis (MDA), logistic models (LOGIT), and probit analysis, have been traditionally used in bond rating. However, one major drawback is that it should be based on strict assumptions. Such strict assumptions include linearity, normality, independence among predictor variables and pre-existing functional forms relating the criterion variablesand the predictor variables. Those strict assumptions of traditional statistics have limited their application to the real world. Machine learning techniques also used in bond rating prediction models include decision trees (DT), neural networks (NN), and Support Vector Machine (SVM). Especially, SVM is recognized as a new and promising classification and regression analysis method. SVM learns a separating hyperplane that can maximize the margin between two categories. SVM is simple enough to be analyzed mathematical, and leads to high performance in practical applications. SVM implements the structuralrisk minimization principle and searches to minimize an upper bound of the generalization error. In addition, the solution of SVM may be a global optimum and thus, overfitting is unlikely to occur with SVM. In addition, SVM does not require too many data sample for training since it builds prediction models by only using some representative sample near the boundaries called support vectors. A number of experimental researches have indicated that SVM has been successfully applied in a variety of pattern recognition fields. However, there are three major drawbacks that can be potential causes for degrading SVM's performance. First, SVM is originally proposed for solving binary-class classification problems. Methods for combining SVMs for multi-class classification such as One-Against-One, One-Against-All have been proposed, but they do not improve the performance in multi-class classification problem as much as SVM for binary-class classification. Second, approximation algorithms (e.g. decomposition methods, sequential minimal optimization algorithm) could be used for effective multi-class computation to reduce computation time, but it could deteriorate classification performance. Third, the difficulty in multi-class prediction problems is in data imbalance problem that can occur when the number of instances in one class greatly outnumbers the number of instances in the other class. Such data sets often cause a default classifier to be built due to skewed boundary and thus the reduction in the classification accuracy of such a classifier. SVM ensemble learning is one of machine learning methods to cope with the above drawbacks. Ensemble learning is a method for improving the performance of classification and prediction algorithms. AdaBoost is one of the widely used ensemble learning techniques. It constructs a composite classifier by sequentially training classifiers while increasing weight on the misclassified observations through iterations. The observations that are incorrectly predicted by previous classifiers are chosen more often than examples that are correctly predicted. Thus Boosting attempts to produce new classifiers that are better able to predict examples for which the current ensemble's performance is poor. In this way, it can reinforce the training of the misclassified observations of the minority class. This paper proposes a multiclass Geometric Mean-based Boosting (MGM-Boost) to resolve multiclass prediction problem. Since MGM-Boost introduces the notion of geometric mean into AdaBoost, it can perform learning process considering the geometric mean-based accuracy and errors of multiclass. This study applies MGM-Boost to the real-world bond rating case for Korean companies to examine the feasibility of MGM-Boost. 10-fold cross validations for threetimes with different random seeds are performed in order to ensure that the comparison among three different classifiers does not happen by chance. For each of 10-fold cross validation, the entire data set is first partitioned into tenequal-sized sets, and then each set is in turn used as the test set while the classifier trains on the other nine sets. That is, cross-validated folds have been tested independently of each algorithm. Through these steps, we have obtained the results for classifiers on each of the 30 experiments. In the comparison of arithmetic mean-based prediction accuracy between individual classifiers, MGM-Boost (52.95%) shows higher prediction accuracy than both AdaBoost (51.69%) and SVM (49.47%). MGM-Boost (28.12%) also shows the higher prediction accuracy than AdaBoost (24.65%) and SVM (15.42%)in terms of geometric mean-based prediction accuracy. T-test is used to examine whether the performance of each classifiers for 30 folds is significantly different. The results indicate that performance of MGM-Boost is significantly different from AdaBoost and SVM classifiers at 1% level. These results mean that MGM-Boost can provide robust and stable solutions to multi-classproblems such as bond rating.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.21 no.4
• /
• pp.64-80
• /
• 2018

In Korea, citizens can only know general information about crime. Thus it is difficult to know how much they are exposed to crime. If the police can predict the crime risky area, it will be possible to cope with the crime efficiently even though insufficient police and enforcement resources. However, there is no prediction system in Korea and the related researches are very much poor. From these backgrounds, the final goal of this study is to develop an automated crime prediction system. However, for the first step, we build a big data set which consists of local real crime information and urban physical or non-physical data. Then, we developed a crime prediction model through machine learning method. Finally, we assumed several possible scenarios and calculated the probability of crime and visualized the results in a map so as to increase the people's understanding. Among the factors affecting the crime occurrence revealed in previous and case studies, data was processed in the form of a big data for machine learning: real crime information, weather information (temperature, rainfall, wind speed, humidity, sunshine, insolation, snowfall, cloud cover) and local information (average building coverage, average floor area ratio, average building height, number of buildings, average appraised land value, average area of residential building, average number of ground floor). Among the supervised machine learning algorithms, the decision tree model, the random forest model, and the SVM model, which are known to be powerful and accurate in various fields were utilized to construct crime prevention model. As a result, decision tree model with the lowest RMSE was selected as an optimal prediction model. Based on this model, several scenarios were set for theft and violence cases which are the most frequent in the case city J, and the probability of crime was estimated by $250{\times}250m$ grid. As a result, we could find that the high crime risky area is occurring in three patterns in case city J. The probability of crime was divided into three classes and visualized in map by $250{\times}250m$ grid. Finally, we could develop a crime prediction model using machine learning algorithm and visualized the crime risky areas in a map which can recalculate the model and visualize the result simultaneously as time and urban conditions change.

• Journal of Internet Computing and Services
• /
• v.17 no.1
• /
• pp.101-107
• /
• 2016

Due to the recent advancement in digital imaging technology, development of intervention equipment has become generalize. Video arbitration procedure is a process to insert a tiny catheter and a guide wire in the body, so in order to enhance the effectiveness and safety of this treatment, the high-quality of x-ray of image should be used. However, the increasing of radiation has become the problem. Therefore, the studies to improve the performance of x-ray detectors are being actively processed. Moreover, this intervention is based on the reference of the angiographic imaging and 3D medical image processing. In this paper, we propose a guidance system to support this intervention. Through this intervention, it can solve the problem of the existing 2D medical images based vessel that has a formation of cerebrovascular disease, and guide the real-time tracking and optimal route to the target lesion by intervention catheter and guide wire tool. As a result, the system was completely composed for medical image acquisition unit and image processing unit as well as a display device. The experimental environment, guide services which are provided by the proposed system Brain Phantom (complete intracranial model with aneurysms, ref H+N-S-A-010) was taken with x-ray and testing. To generate a reference image based on the Laplacian algorithm for the image processing which derived from the cerebral blood vessel model was applied to DICOM by Volume ray casting technique. $A^*$ algorithm was used to provide the catheter with a guide wire tracking path. Finally, the result does show the location of the catheter and guide wire providing in the proposed system especially, it is expected to provide a useful guide for future intervention service.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.107-120
• /
• 2014

This study proposes a novel recommender system using the structural hole analysis to reflect qualitative and emotional information in recommendation process. Although collaborative filtering (CF) is known as the most popular recommendation algorithm, it has some limitations including scalability and sparsity problems. The scalability problem arises when the volume of users and items become quite large. It means that CF cannot scale up due to large computation time for finding neighbors from the user-item matrix as the number of users and items increases in real-world e-commerce sites. Sparsity is a common problem of most recommender systems due to the fact that users generally evaluate only a small portion of the whole items. In addition, the cold-start problem is the special case of the sparsity problem when users or items newly added to the system with no ratings at all. When the user's preference evaluation data is sparse, two users or items are unlikely to have common ratings, and finally, CF will predict ratings using a very limited number of similar users. Moreover, it may produces biased recommendations because similarity weights may be estimated using only a small portion of rating data. In this study, we suggest a novel limitation of the conventional CF. The limitation is that CF does not consider qualitative and emotional information about users in the recommendation process because it only utilizes user's preference scores of the user-item matrix. To address this novel limitation, this study proposes cluster-indexing CF model with the structural hole analysis for recommendations. In general, the structural hole means a location which connects two separate actors without any redundant connections in the network. The actor who occupies the structural hole can easily access to non-redundant, various and fresh information. Therefore, the actor who occupies the structural hole may be a important person in the focal network and he or she may be the representative person in the focal subgroup in the network. Thus, his or her characteristics may represent the general characteristics of the users in the focal subgroup. In this sense, we can distinguish friends and strangers of the focal user utilizing the structural hole analysis. This study uses the structural hole analysis to select structural holes in subgroups as an initial seeds for a cluster analysis. First, we gather data about users' preference ratings for items and their social network information. For gathering research data, we develop a data collection system. Then, we perform structural hole analysis and find structural holes of social network. Next, we use these structural holes as cluster centroids for the clustering algorithm. Finally, this study makes recommendations using CF within user's cluster, and compare the recommendation performances of comparative models. For implementing experiments of the proposed model, we composite the experimental results from two experiments. The first experiment is the structural hole analysis. For the first one, this study employs a software package for the analysis of social network data - UCINET version 6. The second one is for performing modified clustering, and CF using the result of the cluster analysis. We develop an experimental system using VBA (Visual Basic for Application) of Microsoft Excel 2007 for the second one. This study designs to analyzing clustering based on a novel similarity measure - Pearson correlation between user preference rating vectors for the modified clustering experiment. In addition, this study uses 'all-but-one' approach for the CF experiment. In order to validate the effectiveness of our proposed model, we apply three comparative types of CF models to the same dataset. The experimental results show that the proposed model outperforms the other comparative models. In especial, the proposed model significantly performs better than two comparative modes with the cluster analysis from the statistical significance test. However, the difference between the proposed model and the naive model does not have statistical significance.

• Journal of Korea Water Resources Association
• /
• v.47 no.4
• /
• pp.371-384
• /
• 2014

This study developed a new algorithm of extreme rainfall extraction based on the Communication, Ocean and Meteorological Satellite (COMS) and the Tropical Rainfall Measurement Mission (TRMM) Satellite image data and evaluated its applicability for the heavy rainfall event in July-2011 in Seoul, South Korea. The power-series-regression-based Z-R relationship was employed for taking into account for empirical relationships between TRMM/PR, TRMM/VIRS, COMS, and Automatic Weather System(AWS) at each elevation. The estimated Z-R relationship ($Z=303R^{0.72}$) agreed well with observation from AWS (correlation coefficient=0.57). The estimated 10-minute rainfall intensities from the COMS satellite using the Z-R relationship generated underestimated rainfall intensities. For a small rainfall event the Z-R relationship tended to overestimated rainfall intensities. However, the overall patterns of estimated rainfall were very comparable with the observed data. The correlation coefficients and the Root Mean Square Error (RMSE) of 10-minute rainfall series from COMS and AWS gave 0.517, and 3.146, respectively. In addition, the averaged error value of the spatial correlation matrix ranged from -0.530 to -0.228, indicating negative correlation. To reduce the error by extreme rainfall estimation using satellite datasets it is required to take into more extreme factors and improve the algorithm through further study. This study showed the potential utility of multi-geostationary satellite data for building up sub-daily rainfall and establishing the real-time flood alert system in ungauged watersheds.

• Science of Emotion and Sensibility
• /
• v.13 no.1
• /
• pp.47-60
• /
• 2010

Most of the researches about classification usually have used kNN(k-Nearest Neighbor), SVM(Support Vector Machine), which are known as learn-based model, and Bayesian classifier, NNA(Neural Network Algorithm), which are known as statistics-based methods. However, there are some limitations of space and time when classifying so many web pages in recent internet. Moreover, most studies of classification are using uni-gram feature representation which is not good to represent real meaning of words. In case of Korean web page classification, there are some problems because of korean words property that the words have multiple meanings(polysemy). For these reasons, LSA(Latent Semantic Analysis) is proposed to classify well in these environment(large data set and words' polysemy). LSA uses SVD(Singular Value Decomposition) which decomposes the original term-document matrix to three different matrices and reduces their dimension. From this SVD's work, it is possible to create new low-level semantic space for representing vectors, which can make classification efficient and analyze latent meaning of words or document(or web pages). Although LSA is good at classification, it has some drawbacks in classification. As SVD reduces dimensions of matrix and creates new semantic space, it doesn't consider which dimensions discriminate vectors well but it does consider which dimensions represent vectors well. It is a reason why LSA doesn't improve performance of classification as expectation. In this paper, we propose new LSA which selects optimal dimensions to discriminate and represent vectors well as minimizing drawbacks and improving performance. This method that we propose shows better and more stable performance than other LSAs' in low-dimension space. In addition, we derive more improvement in classification as creating and selecting features by reducing stopwords and weighting specific values to them statistically.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.361-381
• /
• 2023

Research on corporate bankruptcy prediction has been focused on financial information. Since the company's financial information is updated quarterly, there is a problem that timeliness is insufficient in predicting the possibility of a company's business closure in real time. Evaluated companies that want to improve this need a method of judging the soundness of a company that uses information other than financial information to judge the soundness of a target company. To this end, as information technology has made it easier to collect non-financial information about companies, research has been conducted to apply additional variables and various methodologies other than financial information to predict corporate bankruptcy. It has become an important research task to determine whether it has an effect. In this study, we examined the impact of electronic payment-related information, which constitutes non-financial information, when predicting the closure of business operators using electronic payment service and examined the difference in closure prediction accuracy according to the combination of financial and non-financial information. Specifically, three research models consisting of a financial information model, a non-financial information model, and a combined model were designed, and the closure prediction accuracy was confirmed with six algorithms including the Multi Layer Perceptron (MLP) algorithm. The model combining financial and non-financial information showed the highest prediction accuracy, followed by the non-financial information model and the financial information model in order. As for the prediction accuracy of business closure by algorithm, XGBoost showed the highest prediction accuracy among the six algorithms. As a result of examining the relative importance of a total of 87 variables used to predict business closure, it was confirmed that more than 70% of the top 20 variables that had a significant impact on the prediction of business closure were non-financial information. Through this, it was confirmed that electronic payment-related information of non-financial information is an important variable in predicting business closure, and the possibility of using non-financial information as an alternative to financial information was also examined. Based on this study, the importance of collecting and utilizing non-financial information as information that can predict business closure is recognized, and a plan to utilize it for corporate decision-making is also proposed.

• Progress in Medical Physics
• /
• v.23 no.2
• /
• pp.91-98
• /
• 2012

Verification of internal organ motion during treatment and its feedback is essential to accurate dose delivery to the moving target. We developed an offline based internal organ motion verification system (IMVS) using cine EPID images and evaluated its accuracy and availability through phantom study. For verification of organ motion using live cine EPID images, a pattern matching algorithm using an internal surrogate, which is very distinguishable and represents organ motion in the treatment field, like diaphragm, was employed in the self-developed analysis software. For the system performance test, we developed a linear motion phantom, which consists of a human body shaped phantom with a fake tumor in the lung, linear motion cart, and control software. The phantom was operated with a motion of 2 cm at 4 sec per cycle and cine EPID images were obtained at a rate of 3.3 and 6.6 frames per sec (2 MU/frame) with $1,024{\times}768$ pixel counts in a linear accelerator (10 MVX). Organ motion of the target was tracked using self-developed analysis software. Results were compared with planned data of the motion phantom and data from the video image based tracking system (RPM, Varian, USA) using an external surrogate in order to evaluate its accuracy. For quantitative analysis, we analyzed correlation between two data sets in terms of average cycle (peak to peak), amplitude, and pattern (RMS, root mean square) of motion. Averages for the cycle of motion from IMVS and RPM system were $3.98{\pm}0.11$ (IMVS 3.3 fps), $4.005{\pm}0.001$ (IMVS 6.6 fps), and $3.95{\pm}0.02$ (RPM), respectively, and showed good agreement on real value (4 sec/cycle). Average of the amplitude of motion tracked by our system showed $1.85{\pm}0.02$ cm (3.3 fps) and $1.94{\pm}0.02$ cm (6.6 fps) as showed a slightly different value, 0.15 (7.5% error) and 0.06 (3% error) cm, respectively, compared with the actual value (2 cm), due to time resolution for image acquisition. In analysis of pattern of motion, the value of the RMS from the cine EPID image in 3.3 fps (0.1044) grew slightly compared with data from 6.6 fps (0.0480). The organ motion verification system using sequential cine EPID images with an internal surrogate showed good representation of its motion within 3% error in a preliminary phantom study. The system can be implemented for clinical purposes, which include organ motion verification during treatment, compared with 4D treatment planning data, and its feedback for accurate dose delivery to the moving target.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.141-154
• /
• 2019

Rapid growth of internet technology and social media is progressing. Data mining technology has evolved to enable unstructured document representations in a variety of applications. Sentiment analysis is an important technology that can distinguish poor or high-quality content through text data of products, and it has proliferated during text mining. Sentiment analysis mainly analyzes people's opinions in text data by assigning predefined data categories as positive and negative. This has been studied in various directions in terms of accuracy from simple rule-based to dictionary-based approaches using predefined labels. In fact, sentiment analysis is one of the most active researches in natural language processing and is widely studied in text mining. When real online reviews aren't available for others, it's not only easy to openly collect information, but it also affects your business. In marketing, real-world information from customers is gathered on websites, not surveys. Depending on whether the website's posts are positive or negative, the customer response is reflected in the sales and tries to identify the information. However, many reviews on a website are not always good, and difficult to identify. The earlier studies in this research area used the reviews data of the Amazon.com shopping mal, but the research data used in the recent studies uses the data for stock market trends, blogs, news articles, weather forecasts, IMDB, and facebook etc. However, the lack of accuracy is recognized because sentiment calculations are changed according to the subject, paragraph, sentiment lexicon direction, and sentence strength. This study aims to classify the polarity analysis of sentiment analysis into positive and negative categories and increase the prediction accuracy of the polarity analysis using the pretrained IMDB review data set. First, the text classification algorithm related to sentiment analysis adopts the popular machine learning algorithms such as NB (naive bayes), SVM (support vector machines), XGboost, RF (random forests), and Gradient Boost as comparative models. Second, deep learning has demonstrated discriminative features that can extract complex features of data. Representative algorithms are CNN (convolution neural networks), RNN (recurrent neural networks), LSTM (long-short term memory). CNN can be used similarly to BoW when processing a sentence in vector format, but does not consider sequential data attributes. RNN can handle well in order because it takes into account the time information of the data, but there is a long-term dependency on memory. To solve the problem of long-term dependence, LSTM is used. For the comparison, CNN and LSTM were chosen as simple deep learning models. In addition to classical machine learning algorithms, CNN, LSTM, and the integrated models were analyzed. Although there are many parameters for the algorithms, we examined the relationship between numerical value and precision to find the optimal combination. And, we tried to figure out how the models work well for sentiment analysis and how these models work. This study proposes integrated CNN and LSTM algorithms to extract the positive and negative features of text analysis. The reasons for mixing these two algorithms are as follows. CNN can extract features for the classification automatically by applying convolution layer and massively parallel processing. LSTM is not capable of highly parallel processing. Like faucets, the LSTM has input, output, and forget gates that can be moved and controlled at a desired time. These gates have the advantage of placing memory blocks on hidden nodes. The memory block of the LSTM may not store all the data, but it can solve the CNN's long-term dependency problem. Furthermore, when LSTM is used in CNN's pooling layer, it has an end-to-end structure, so that spatial and temporal features can be designed simultaneously. In combination with CNN-LSTM, 90.33% accuracy was measured. This is slower than CNN, but faster than LSTM. The presented model was more accurate than other models. In addition, each word embedding layer can be improved when training the kernel step by step. CNN-LSTM can improve the weakness of each model, and there is an advantage of improving the learning by layer using the end-to-end structure of LSTM. Based on these reasons, this study tries to enhance the classification accuracy of movie reviews using the integrated CNN-LSTM model.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.63-83
• /
• 2019

Investors prefer to look for trading points based on the graph shown in the chart rather than complex analysis, such as corporate intrinsic value analysis and technical auxiliary index analysis. However, the pattern analysis technique is difficult and computerized less than the needs of users. In recent years, there have been many cases of studying stock price patterns using various machine learning techniques including neural networks in the field of artificial intelligence(AI). In particular, the development of IT technology has made it easier to analyze a huge number of chart data to find patterns that can predict stock prices. Although short-term forecasting power of prices has increased in terms of performance so far, long-term forecasting power is limited and is used in short-term trading rather than long-term investment. Other studies have focused on mechanically and accurately identifying patterns that were not recognized by past technology, but it can be vulnerable in practical areas because it is a separate matter whether the patterns found are suitable for trading. When they find a meaningful pattern, they find a point that matches the pattern. They then measure their performance after n days, assuming that they have bought at that point in time. Since this approach is to calculate virtual revenues, there can be many disparities with reality. The existing research method tries to find a pattern with stock price prediction power, but this study proposes to define the patterns first and to trade when the pattern with high success probability appears. The M & W wave pattern published by Merrill(1980) is simple because we can distinguish it by five turning points. Despite the report that some patterns have price predictability, there were no performance reports used in the actual market. The simplicity of a pattern consisting of five turning points has the advantage of reducing the cost of increasing pattern recognition accuracy. In this study, 16 patterns of up conversion and 16 patterns of down conversion are reclassified into ten groups so that they can be easily implemented by the system. Only one pattern with high success rate per group is selected for trading. Patterns that had a high probability of success in the past are likely to succeed in the future. So we trade when such a pattern occurs. It is a real situation because it is measured assuming that both the buy and sell have been executed. We tested three ways to calculate the turning point. The first method, the minimum change rate zig-zag method, removes price movements below a certain percentage and calculates the vertex. In the second method, high-low line zig-zag, the high price that meets the n-day high price line is calculated at the peak price, and the low price that meets the n-day low price line is calculated at the valley price. In the third method, the swing wave method, the high price in the center higher than n high prices on the left and right is calculated as the peak price. If the central low price is lower than the n low price on the left and right, it is calculated as valley price. The swing wave method was superior to the other methods in the test results. It is interpreted that the transaction after checking the completion of the pattern is more effective than the transaction in the unfinished state of the pattern. Genetic algorithms(GA) were the most suitable solution, although it was virtually impossible to find patterns with high success rates because the number of cases was too large in this simulation. We also performed the simulation using the Walk-forward Analysis(WFA) method, which tests the test section and the application section separately. So we were able to respond appropriately to market changes. In this study, we optimize the stock portfolio because there is a risk of over-optimized if we implement the variable optimality for each individual stock. Therefore, we selected the number of constituent stocks as 20 to increase the effect of diversified investment while avoiding optimization. We tested the KOSPI market by dividing it into six categories. In the results, the portfolio of small cap stock was the most successful and the high vol stock portfolio was the second best. This shows that patterns need to have some price volatility in order for patterns to be shaped, but volatility is not the best.