• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.241-254
• /
• 2011

Financial time-series forecasting is one of the most important issues because it is essential for the risk management of financial institutions. Therefore, researchers have tried to forecast financial time-series using various data mining techniques such as regression, artificial neural networks, decision trees, k-nearest neighbor etc. Recently, support vector machines (SVMs) are popularly applied to this research area because they have advantages that they don't require huge training data and have low possibility of overfitting. However, a user must determine several design factors by heuristics in order to use SVM. For example, the selection of appropriate kernel function and its parameters and proper feature subset selection are major design factors of SVM. Other than these factors, the proper selection of instance subset may also improve the forecasting performance of SVM by eliminating irrelevant and distorting training instances. Nonetheless, there have been few studies that have applied instance selection to SVM, especially in the domain of stock market prediction. Instance selection tries to choose proper instance subsets from original training data. It may be considered as a method of knowledge refinement and it maintains the instance-base. This study proposes the novel instance selection algorithm for SVMs. The proposed technique in this study uses genetic algorithm (GA) to optimize instance selection process with parameter optimization simultaneously. We call the model as ISVM (SVM with Instance selection) in this study. Experiments on stock market data are implemented using ISVM. In this study, the GA searches for optimal or near-optimal values of kernel parameters and relevant instances for SVMs. This study needs two sets of parameters in chromosomes in GA setting : The codes for kernel parameters and for instance selection. For the controlling parameters of the GA search, the population size is set at 50 organisms and the value of the crossover rate is set at 0.7 while the mutation rate is 0.1. As the stopping condition, 50 generations are permitted. The application data used in this study consists of technical indicators and the direction of change in the daily Korea stock price index (KOSPI). The total number of samples is 2218 trading days. We separate the whole data into three subsets as training, test, hold-out data set. The number of data in each subset is 1056, 581, 581 respectively. This study compares ISVM to several comparative models including logistic regression (logit), backpropagation neural networks (ANN), nearest neighbor (1-NN), conventional SVM (SVM) and SVM with the optimized parameters (PSVM). In especial, PSVM uses optimized kernel parameters by the genetic algorithm. The experimental results show that ISVM outperforms 1-NN by 15.32%, ANN by 6.89%, Logit and SVM by 5.34%, and PSVM by 4.82% for the holdout data. For ISVM, only 556 data from 1056 original training data are used to produce the result. In addition, the two-sample test for proportions is used to examine whether ISVM significantly outperforms other comparative models. The results indicate that ISVM outperforms ANN and 1-NN at the 1% statistical significance level. In addition, ISVM performs better than Logit, SVM and PSVM at the 5% statistical significance level.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.21 no.5
• /
• pp.510-517
• /
• 2001

This paper describes an initial study for the application of eddy current pattern recognition approaches to more realistic flaw characterization in steam generator tubes. For this purpose, finite-element model-based theoretical eddy current testing (ECT) signals are simulated from 5 types of OD flaws with the variation in flaw size parameters and testing frequency. In addition, three kinds of software are developed for the convenience in the application of steps in pattern recognition approaches such as feature extraction feature selection and classification by probabilistic neural networks (PNNs). The cross point of the ECT signals simulated from flaws with non-symmetric cross-sections shows the deviation from the origin of the impedance plane. New features taking advantages of this phenomenon are added to complete the feature set with a total of 18 features. Then, classification with PNNs are performed based on this feature set. The PNN classifiers show high performance for the identification of symmetry in the cross-section of a flaw. However, they show very limited success in the interrogation of the sharpness of flaw tips.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.3
• /
• pp.59-66
• /
• 2016

This paper presents an empirical evaluation on dimensionality reduction strategies by which dissimilarity-based classifications (DBC) can be implemented efficiently. In DBC, classification is not based on feature measurements of individual objects (a set of attributes), but rather on a suitable dissimilarity measure among the individual objects (pair-wise object comparisons). One problem of DBC is the high dimensionality of the dissimilarity space when a lots of objects are treated. To address this issue, two kinds of solutions have been proposed in the literature: prototype selection (PS)-based methods and dimension reduction (DR)-based methods. In this paper, instead of utilizing the PS-based or DR-based methods, a way of performing DBC in Eigen spaces (ES) is considered and empirically compared. In ES-based DBC, classifications are performed as follows: first, a set of principal eigenvectors is extracted from the training data set using a principal component analysis; second, an Eigen space is expanded using a subset of the extracted and selected Eigen vectors; third, after measuring distances among the projected objects in the Eigen space using $l_p$-norms as the dissimilarity, classification is performed. The experimental results, which are obtained using the nearest neighbor rule with artificial and real-life benchmark data sets, demonstrate that when the dimensionality of the Eigen spaces has been selected appropriately, compared to the PS-based and DR-based methods, the performance of the ES-based DBC can be improved in terms of the classification accuracy.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.7
• /
• pp.532-539
• /
• 2004

In this Paper, we propose a content-based music information retrieval (MIR) system base on the query-by-example (QBE) method. The proposed system is implemented to retrieve queried music from a dataset where 60 music samples were collected for each of the four genres in Classical, Hiphop. Jazz. and Reck. resulting in 240 music files in database. From each query music signal, the system extracts 60 dimensional feature vectors including spectral centroid. rolloff. flux base on STFT and also the LPC. MFCC and Beat information. and retrieves queried music from a trained database set using Euclidean distance measure. In order to choose optimum features from the 60 dimension feature vectors, SFS method is applied to draw 10 dimension optimum features and these are used for the Proposed system. From the experimental result. we can verify the superior performance of the proposed system that provides success rate of 84% in Hit Rate and 0.63 in MRR which means near 10% improvements over the previous methods. Additional experiments regarding system Performance to random query Patterns (or portions) and query lengths have been investigated and a serious instability problem of system Performance is Pointed out.

• Korean Journal of Remote Sensing
• /
• v.15 no.3
• /
• pp.183-194
• /
• 1999

The Brightness, color and texture included in a multispectral satellite data are used as important factors to analyze and to apply the image data for a proper use. One of the most significant process in the satellite data analysis using texture or color information is to extract features effectively expressing the information of original image. It was described in this paper that six features were introduced to extract useful features from the analysis of the satellite data, and also a classification network using the back-propagation neural network was constructed to evaluate the classification ability of each vector feature in SPOT imagery. The vector features were adopted from the training set selection for the interesting region, and applied to the classification process. The classification results showed that each vector feature contained many merits and demerits depending on each vector's characteristics, and each vector had compatible classification ability. Therefore, it is expected that the color and texture features are effectively used not only in the classification process of satellite imagery, but in various image classification and application fields.

• 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.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.2
• /
• pp.165-172
• /
• 2010

In clinical data minig, choosing the optimal subset of features is such important, not only to reduce the computational complexity but also to improve the usefulness of the model constructed from the given data. Moreover the threshold values (i.e., cut-off points) of selected features are used in a clinical decision criteria of experts for differential diagnosis of diseases. In this paper, we propose a fuzzy discretization approach, which is evaluated by measuring the degree of separation of redundant attribute values in overlapping region, based on spatial distribution of data with continuous attributes. The weighted average of the redundant attribute values is then used to determine the threshold value for each feature and rough set theory is utilized to select a subset of relevant features from the overall features. To verify the validity of the proposed method, we compared experimental results, which applied to classification problem using 668 patients with a chief complaint of dyspnea, based on three discretization methods (i.e., equal-width, equal-frequency, and entropy-based) and proposed discretization method. From the experimental results, we confirm that the discretization methods with fuzzy partition give better results in two evaluation measures, average classification accuracy and G-mean, than those with hard partition.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.706-714
• /
• 2012

The Korea Meteorological Administration provided the recent four-years records of weather dataset for our very short-term heavy rainfall prediction. We divided the dataset into three parts: train, validation and test set. Through feature selection, we select only important features among 72 features to avoid significant increase of solution space that arises when growing exponentially with the dimensionality. We used a differential evolution algorithm and two classifiers as the fitness function of evolutionary computation to select more accurate feature subset. One of the classifiers is Support Vector Machine (SVM) that shows high performance, and the other is k-Nearest Neighbor (k-NN) that is fast in general. The test results of SVM were more prominent than those of k-NN in our experiments. Also we processed the weather data using undersampling and normalization techniques. The test results of our differential evolution algorithm performed about five times better than those using all features and about 1.36 times better than those using a genetic algorithm, which is the best known. Running times when using a genetic algorithm were about twenty times longer than those when using a differential evolution algorithm.

• Journal of IKEEE
• /
• v.8 no.2 s.15
• /
• pp.186-194
• /
• 2004

Due to the exponential growth of information on the internet, it is getting difficult to find and organize relevant informations. To reduce heavy overload of accesses to information, automatic text classification for handling enormous documents is necessary. In this paper, we describe structure and implementation of a document classification system for web documents. We utilize SVM for documentation classification model that is constructed based on training set and its representative terms in a directory. In our system, SVM is trained and is used for document classification by using word set that is extracted from information and communication related web documents. In addition, we use vector-space model in order to represent characteristics based on TFiDF and training data consists of positive and negative classes that are represented by using characteristic set with weight. Experiments show the results of categorization and the correlation of vector length.

• Phonetics and Speech Sciences
• /
• v.8 no.4
• /
• pp.103-113
• /
• 2016

This paper aims to propose articulatory features as novel predictors for automatic pronunciation assessment of English produced by Korean learners. Based on the distinctive feature theory, where phonemes are represented as a set of articulatory/phonetic properties, we propose articulatory Goodness-Of-Pronunciation(aGOP) features in terms of the corresponding articulatory attributes, such as nasal, sonorant, anterior, etc. An English speech corpus spoken by Korean learners is used in the assessment modeling. In our system, learners' speech is forced aligned and recognized by using the acoustic and pronunciation models derived from the WSJ corpus (native North American speech) and the CMU pronouncing dictionary, respectively. In order to compute aGOP features, articulatory models are trained for the corresponding articulatory attributes. In addition to the proposed features, various features which are divided into four categories such as RATE, SEGMENT, SILENCE, and GOP are applied as a baseline. In order to enhance the assessment modeling performance and investigate the weights of the salient features, relevant features are extracted by using Best Subset Selection(BSS). The results show that the proposed model using aGOP features outperform the baseline. In addition, analysis of relevant features extracted by BSS reveals that the selected aGOP features represent the salient variations of Korean learners of English. The results are expected to be effective for automatic pronunciation error detection, as well.