• Journal of Cadastre & Land InformatiX
• /
• v.50 no.1
• /
• pp.181-200
• /
• 2020

This study used the OLS model to estimate the determinants affecting the tenure of a home and then compared the predictive power of each model with SVM, Decision Tree, Random Forest, Gradient Boosting, XGBooest and LightGBM. There is a difference from the preceding study in that the Stacking model, one of the ensemble models, can be used as a base model to establish a more predictable model to identify the volume of housing transactions in the housing market. OLS analysis showed that sales profits, housing prices, the number of household members, and the type of residential housing (detached housing, apartments) affected the period of housing ownership, and compared the predictability of the machine learning model with RMSE, the results showed that the machine learning model had higher predictability. Afterwards, the predictive power was compared by applying each machine learning after rebuilding the data with the influencing variables, and the analysis showed the best predictive power of Random Forest. In addition, the most predictable Random Forest, Decision Tree, Gradient Boosting, and XGBooost models were applied as individual models, and the Stacking model was constructed using Linear, Ridge, and Lasso models as meta models. As a result of the analysis, the RMSE value in the Ridge model was the lowest at 0.5181, thus building the highest predictive model.

• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.139-153
• /
• 2017

Corporate bankruptcy can cause great losses not only to stakeholders but also to many related sectors in society. Through the economic crises, bankruptcy have increased and bankruptcy prediction models have become more and more important. Therefore, corporate bankruptcy has been regarded as one of the major topics of research in business management. Also, many studies in the industry are in progress and important. Previous studies attempted to utilize various methodologies to improve the bankruptcy prediction accuracy and to resolve the overfitting problem, such as Multivariate Discriminant Analysis (MDA), Generalized Linear Model (GLM). These methods are based on statistics. Recently, researchers have used machine learning methodologies such as Support Vector Machine (SVM), Artificial Neural Network (ANN). Furthermore, fuzzy theory and genetic algorithms were used. Because of this change, many of bankruptcy models are developed. Also, performance has been improved. In general, the company's financial and accounting information will change over time. Likewise, the market situation also changes, so there are many difficulties in predicting bankruptcy only with information at a certain point in time. However, even though traditional research has problems that don't take into account the time effect, dynamic model has not been studied much. When we ignore the time effect, we get the biased results. So the static model may not be suitable for predicting bankruptcy. Thus, using the dynamic model, there is a possibility that bankruptcy prediction model is improved. In this paper, we propose RNN (Recurrent Neural Network) which is one of the deep learning methodologies. The RNN learns time series data and the performance is known to be good. Prior to experiment, we selected non-financial firms listed on the KOSPI, KOSDAQ and KONEX markets from 2010 to 2016 for the estimation of the bankruptcy prediction model and the comparison of forecasting performance. In order to prevent a mistake of predicting bankruptcy by using the financial information already reflected in the deterioration of the financial condition of the company, the financial information was collected with a lag of two years, and the default period was defined from January to December of the year. Then we defined the bankruptcy. The bankruptcy we defined is the abolition of the listing due to sluggish earnings. We confirmed abolition of the list at KIND that is corporate stock information website. Then we selected variables at previous papers. The first set of variables are Z-score variables. These variables have become traditional variables in predicting bankruptcy. The second set of variables are dynamic variable set. Finally we selected 240 normal companies and 226 bankrupt companies at the first variable set. Likewise, we selected 229 normal companies and 226 bankrupt companies at the second variable set. We created a model that reflects dynamic changes in time-series financial data and by comparing the suggested model with the analysis of existing bankruptcy predictive models, we found that the suggested model could help to improve the accuracy of bankruptcy predictions. We used financial data in KIS Value (Financial database) and selected Multivariate Discriminant Analysis (MDA), Generalized Linear Model called logistic regression (GLM), Support Vector Machine (SVM), Artificial Neural Network (ANN) model as benchmark. The result of the experiment proved that RNN's performance was better than comparative model. The accuracy of RNN was high in both sets of variables and the Area Under the Curve (AUC) value was also high. Also when we saw the hit-ratio table, the ratio of RNNs that predicted a poor company to be bankrupt was higher than that of other comparative models. However the limitation of this paper is that an overfitting problem occurs during RNN learning. But we expect to be able to solve the overfitting problem by selecting more learning data and appropriate variables. From these result, it is expected that this research will contribute to the development of a bankruptcy prediction by proposing a new dynamic model.

• Transactions of the Korean hydrogen and new energy society
• /
• v.25 no.5
• /
• pp.491-499
• /
• 2014

It is important to accurately measure and control the relative humidity of humidified gas entering a PEM (polymer electrolyte membrane) fuel cell stack because the level of humidification strongly affects the performance and durability of the stack. Humidity measurement devices can be used to directly measure the relative humidity, but they cost much to be equipped and occupy spaces in a fuel cell system. We present soft sensors for predicting the relative humidity without actual humidity measuring devices. By combining FIR (finite impulse response) model with PLS (partial least square) and SVM (support vector machine) regression models, DPLS (dynamic PLS) and DSVM (dynamic SVM) soft sensors were developed to correctly estimate the relative humidity of humidified gases exiting a planar-type membrane humidifier. The DSVM soft sensor showed a better prediction performance than the DPLS one because it is able to capture nonlinear correlations between the relative humidity and the input data of the soft sensors. Without actual humidity sensors, the soft sensors presented in this work can be used to monitor and control the humidity in operation of PEM fuel cell systems.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.1
• /
• pp.15-26
• /
• 2013

This paper proposes a classification method of parallel, vertical parking states and pillars for parking assist system using ultrasonic sensors. Since, in general parking space detection module, the compressed amplitude of ultrasonic data are received, the analysis of them is difficult. To solve these problems, in preprocessing state, symmetric transform and noise removal are performed. In feature extraction process, four features, standard deviation of distance, reconstructed peak, standard deviation of reconstructed signal and sum of width, are proposed. Gaussian fitting model is used to reconstruct saturated peak signal and discriminability of each feature is measured. To find the best combination among these features, multi-class SVM and subset generator are used for more accurate and robust classification. The proposed method shows 92 % classification rate and proves the applicability to parking space detection modules.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.10
• /
• pp.1516-1522
• /
• 2017

We propose a novel monitoring system for diagnosing crack faults of the wind turbine using image information. The proposed method classifies a normal state and a abnormal state for the blade parts of the wind turbine. Specifically, the images are input to the proposed system in various states of wind turbine rotation. according to the blade condition. Then, the video of rotating blades on the wind turbine is divided into several image frames. Motion vectors are estimated using the previous and current images using the motion estimation, and the change of the motion vectors is analyzed according to the blade state. Finally, we determine the final blade state using the Support Vector Machine (SVM) classifier. In SVM, features are constructed using the area information of the blades and the motion vector values. The experimental results showed that the proposed method had high classification performance and its $F_1$ score was 0.9790.

• Journal of Korea Multimedia Society
• /
• v.18 no.11
• /
• pp.1289-1301
• /
• 2015

Pedestrian detection (PD) is an essential task in various applications and sliding window-based methods utilizing HOG (Histogram of Oriented Gradients) or HOG-like descriptors have been shown to be very effective for accurate PD. However, due to exhaustive search across images, PD methods based on sliding window usually require heavy computational time. In this paper, we propose a real-time PD method for embedded visual surveillance with fixed backgrounds. The proposed PD method employs HOG descriptors as many PD methods does, but utilizes selective search so that it can save processing time significantly. The proposed selective search is guided by restricting searching to candidate regions extracted from Adaptive Gaussian Mixture Model (AGMM)-based background subtraction technique. Moreover, approximate computation of HOG descriptor and implementation in fixed-point arithmetic mode contributes to reduction of processing time further. Possible accuracy degradation due to approximate computation is compensated by applying an appropriate one among three offline trained SVM classifiers according to sizes of candidate regions. The experimental results show that the proposed PD method significantly improves processing speed without noticeable accuracy degradation compared to the original HOG-based PD and HOG with cascade SVM so that it is a suitable real-time PD implementation for embedded surveillance systems.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2003.10a
• /
• pp.133-138
• /
• 2003

The prediction of protein secondary structure has been an important bioinformatics tool that is an essential component of the template-based protein tertiary structure prediction process. It has been known that the predicted secondary structure information improves both the fold recognition performance and the alignment accuracy. In this paper, we describe several novel ideas that may improve the prediction accuracy. The main idea is motivated by an observation that the protein's structural information, especially when it is combined with the evolutionary information, significantly improves the accuracy of the predicted tertiary structure. From the non-redundant set of protein structures, we derive the 'potential' parameters for the protein secondary structure prediction that contains the structural information of proteins, by following the procedure similar to the way to derive the directional information table of GOR method. Those potential parameters are combined with the frequency matrices obtained by running PSI-BLAST to construct the feature vectors that are used to train the support vector machines (SVM) to build the secondary structure classifiers. Moreover, the problem of huge model file size, which is one of the known shortcomings of SVM, is partially overcome by reducing the size of training data by filtering out the redundancy not only at the protein level but also at the feature vector level. A preliminary result measured by the average three-state prediction accuracy is encouraging.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.1
• /
• pp.162-172
• /
• 2015

In this paper, we propose an adaptive detection algorithm of footstep and a classification algorithm for activities of the detected footstep. The proposed algorithm can detect and classify whole movement as well as individual and irregular activities, since it does not use continuous footstep signals which are used by most previous research. For classifying movement, we use feature vectors obtained from frequency spectrum from FFT, CWT, AR model and image of AR spectrogram. With SVM classifier, we obtain classification accuracy of single footstep activities over 90% when feature vectors using AR spectrogram image are used.

• Journal of Industrial Technology
• /
• v.38 no.1
• /
• pp.41-52
• /
• 2018

Recently, object detection is a critical function for any system that uses computer vision and is widely used in various fields such as video surveillance and self-driving cars. However, the conventional methods can not detect the objects clearly because of the dynamic background change in the beach. In this paper, we propose a new technique to detect humans correctly in the dynamic videos like shores. A new background modeling method that combines spatial GMM (Gaussian Mixture Model) and temporal GMM is proposed to make more correct background image. Also, the proposed method improve the accuracy of people detection by using SVM (Support Vector Machine) to classify people from the objects and KCF (Kernelized Correlation Filter) Tracker to track people continuously in the complicated environment. The experimental result shows that our method can work well for detection and tracking of objects in videos containing dynamic factors and situations.

• Journal of Korea Multimedia Society
• /
• v.20 no.7
• /
• pp.994-1003
• /
• 2017

Ground-glass opacity nodules(GGNs) in chest CT images are associated with lung cancer, and have a different malignant rate depending on existence of solid component in the nodules. In this paper, we propose a method to classify pure GGNs and part-solid GGNs using multiview images and texture analysis in pulmonary GGNs with solid components of 5mm or smaller. We extracted 1521 features from the GGNs segmented from the chest CT images and classified the GGNs using a SVM classification model with selected features that classify pure GGNs and part-solid GGNs through a feature selection method. Our method showed 85% accuracy using the SVM classifier with the top 10 features selected in the multiview images.