• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.123-138
• /
• 2017

Since the stock market is driven by the expectation of traders, studies have been conducted to predict stock price movements through analysis of various sources of text data. In order to predict stock price movements, research has been conducted not only on the relationship between text data and fluctuations in stock prices, but also on the trading stocks based on news articles and social media responses. Studies that predict the movements of stock prices have also applied classification algorithms with constructing term-document matrix in the same way as other text mining approaches. Because the document contains a lot of words, it is better to select words that contribute more for building a term-document matrix. Based on the frequency of words, words that show too little frequency or importance are removed. It also selects words according to their contribution by measuring the degree to which a word contributes to correctly classifying a document. The basic idea of constructing a term-document matrix was to collect all the documents to be analyzed and to select and use the words that have an influence on the classification. In this study, we analyze the documents for each individual item and select the words that are irrelevant for all categories as neutral words. We extract the words around the selected neutral word and use it to generate the term-document matrix. The neutral word itself starts with the idea that the stock movement is less related to the existence of the neutral words, and that the surrounding words of the neutral word are more likely to affect the stock price movements. And apply it to the algorithm that classifies the stock price fluctuations with the generated term-document matrix. In this study, we firstly removed stop words and selected neutral words for each stock. And we used a method to exclude words that are included in news articles for other stocks among the selected words. Through the online news portal, we collected four months of news articles on the top 10 market cap stocks. We split the news articles into 3 month news data as training data and apply the remaining one month news articles to the model to predict the stock price movements of the next day. We used SVM, Boosting and Random Forest for building models and predicting the movements of stock prices. The stock market opened for four months (2016/02/01 ~ 2016/05/31) for a total of 80 days, using the initial 60 days as a training set and the remaining 20 days as a test set. The proposed word - based algorithm in this study showed better classification performance than the word selection method based on sparsity. This study predicted stock price volatility by collecting and analyzing news articles of the top 10 stocks in market cap. We used the term - document matrix based classification model to estimate the stock price fluctuations and compared the performance of the existing sparse - based word extraction method and the suggested method of removing words from the term - document matrix. The suggested method differs from the word extraction method in that it uses not only the news articles for the corresponding stock but also other news items to determine the words to extract. In other words, it removed not only the words that appeared in all the increase and decrease but also the words that appeared common in the news for other stocks. When the prediction accuracy was compared, the suggested method showed higher accuracy. The limitation of this study is that the stock price prediction was set up to classify the rise and fall, and the experiment was conducted only for the top ten stocks. The 10 stocks used in the experiment do not represent the entire stock market. In addition, it is difficult to show the investment performance because stock price fluctuation and profit rate may be different. Therefore, it is necessary to study the research using more stocks and the yield prediction through trading simulation.

• The Transactions of the Korea Information Processing Society
• /
• v.1 no.2
• /
• pp.225-236
• /
• 1994

Many research result conducted by neural network researchers claimed that the degree of generalization of the neural network system is higher or at least equal to that of statistical methods. However, those successful results could be brought only if the neural network was trained by appropriately sound data, having a little of noisy data and being large enough to control noisy data. Real data used in a lot of fields, especially business fields, were not so sound that the network have frequently failed to obtain satisfactory prediction accuracy, the degree of generalization. Enhancing the degree of generalization with noisy data is discussed in this study. The suggestion, which was obtained through a series of experiments, to enhance the degree of generalization is to remove inconsistent data by checking overlapping and inconsistencies. Furthermore, the previous conclusion by other reports is also confirmed that the learning mechanism of neural network takes average value of two inconsistent data included in training set［2］. The interim results of on-going research project are reported in this paper These are ann architecture of the neural network adopted in this project and the whole idea of developing on-line credit evaluation system,being intergration of the expert(resoning)system and the neural network(learning system.Another definite result is corroborated through this study that quickprop,being agopted as a learing algorithm, also has more speedy learning process than does back propagation even in very noisy environment.

• Journal of the Korea Concrete Institute
• /
• v.19 no.6
• /
• pp.803-810
• /
• 2007

An analytical method capable of predicting various stress-strain responses in axially loaded concrete confined with FRP (fiber reinforced polymers) composites in a rational manner is presented. Its underlying idea is that the volumetric expansion due to progressive microcracking in mechanically loaded concrete is an important measure of the extent of damage in the material microstructure, and can be utilized to estimate the load-carrying capacity of concrete by considering the corresponding accumulated damage. Following from this, an elastic modulus expressed as a function of area strain and concrete porosity, the energy-balance equation relating the dilating concrete to the confining device interactively, the varying confining pressure, and an incremental calculation algorithm are included in the solution procedure. The proposed method enables the evaluation of lateral strains consecutively according to the related mechanical model and the energy-balance equation, rather than using an empirically derived equation for Poisson's ratio or dilation rate as in other analytical methods. Several existing analytical methods that can predict the overall response were also examined and discussed, particularly focusing on the way of considering the volumetric expansion. The results predicted by the proposed and Samaan's bilinear equation models correlated with observed results with a reasonable degree, however it can be judged that the latter is not capable of predicting the response of lateral strains correctly due to incorporating the initial Poisson's ratio and the final converged dilation rate only. Further, the proposed method seems to have greater benefits in other applications by the use of the fundamental principles of mechanics.

• Journal of Broadcast Engineering
• /
• v.14 no.5
• /
• pp.589-600
• /
• 2009

This paper is ready to change a trend of a ultra high definition (UHD) video image, and it will contribute to improve the performance of the latest H.264 through the Uni-directional $8{\times}8$ intra-prediction idea which is based on developing a intra prediction compression. The Uni-directional $8{\times}8$ intra prediction is focused on a $8{\times}8$ block intra prediction using $4{\times}4$ block based prediction which is using the same direction of intra prediction. This paper describes that the uni-directional $8{\times}8$ intra-prediction gets a improvement around 7.3% BDBR only in the $8{\times}8$ block size, and it gets a improvement around 1.3% BDBR in the H.264 applied to the multi block size structures. In the case of a larger image size, it can be changed to a good algorithm. Because the video codec which is optimized for UHD resolution can be used a different block size which is bigger than before(currently a minimum of $4{\times}4$ blocks of units).

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.2
• /
• pp.301-314
• /
• 2016

Juels and Sudan's fuzzy vault scheme has been applied to various researches due to its error-tolerance property. However, the fuzzy vault scheme does not consider the difference between people's preferences, even though the authors instantiated movie lover' case in their paper. On the other hand, to make secure and high performance face authentication system, Nyang and Lee introduced a face authentication system, so-called fuzzy face vault, that has a specially designed association structure between face features and ordinary fuzzy vault in order to let each face feature have different weight. However, because of optimizing intra/inter class difference of underlying feature extraction methods, we can easily expect that the face authentication system does not successfully decrease the face authentication failure. In this paper, for ensuring the flexible use of the fuzzy vault scheme, we introduce the bucket structure, which differently implements the weighting idea of Nyang and Lee's face authentication system, and three distribution functions, which formalize the relation between user's weight of preferences and system implementation. In addition, we suggest a matchmaker scheme based on them and confirm its computational performance through the movie database.

• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.1
• /
• pp.30-43
• /
• 2008

Memory reference instructions such as loads or stores are critical factors that limit the processing power of processor. The prefetching technique is an effective way to reduce the latency caused from memory access. However, excessively aggressive prefetch leads to cache pollution so as to cancel out the advantage of prefetch. In this study, four filtering schemes have been compared and evaluated which dynamically decide whether to begin prefetch after referring a filtering table to decrease cache pollution. First, A bi-states scheme has been shown to analyze the lock problem of the conventional scheme, this scheme such as conventional scheme used to be N:1 mapping, but it has the two state to 1bit value of each entries. A complete state scheme has been introduced to be used as a reference for the comparative study. A block address lookup scheme has been proposed as the main idea of this paper which exhibits the most exact filtering performance. This scheme has a length of the table the same as the bi-states scheme, the contents of each entry have the fields the same as the complete state scheme recently, never referenced data block address has been 1:1 mapping a entry of the filter table. Experimental results from commonly used general benchmarks and multimedia programs show that average cache miss ratio have been decreased by 10.5% for the block address lookup scheme(BAL) compare to conventional dynamic filter scheme(2-bitSC).

• The KIPS Transactions:PartB
• /
• v.9B no.2
• /
• pp.245-254
• /
• 2002

IC package marking inspection system using machine vision locates and identifies the target elements from input image, and decides the quality of marking by comparing the extracted target elements with the standard patterns. This paper proposes an adaptive multi-level thresholding (AMLT) method which is suitable for a series of operations such as locating the target IC package, extracting the characters, and detecting the Pinl dimple. It also proposes a dynamic matching unit selection (DMUS) method which is robust to noises as well as effective to catch out the local marking errors. The main idea of the AMLT method is to restrict the inputs of Otsu's thresholding algorithm within a specified area and a partial range of gray values. Doing so, it can adapt to the specific domain. The DMUS method dynamically selects the matching unit according to the result of character extraction and layout analysis. Therefore, in spite of the various erroneous situation occurred in the process of character extraction and layout analysis, it can select minimal matching unit in any environment. In an experiment with 280 IC package images of eight types, the correct extracting rate of IC package and Pinl dimple was 100% and the correct decision rate of marking quality was 98.8%. This result shows that the proposed methods are effective to IC package marking inspection.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.4
• /
• pp.93-101
• /
• 2004

A face boundary can be approximated by an ellipse with five-dimensional parameters. This property allows an ellipse detection algorithm to be adapted to detecting faces. However, the construction of a huge five-dimensional parameter space for a Hough transform is quite unpractical. Accordingly, we Propose a selectively attentional Hough transform method for detecting faces from a symmetric contour in an image. The idea is based on the use of a constant aspect ratio for a face, gradient information, and scan-line-based orientation decomposition, thereby allowing a 5-dimensional problem to be decomposed into a two-dimensional one to compute a center with a specific orientation and an one-dimensional one to estimate a short axis. In addition, a two-point selection constraint using geometric and gradient information is also employed to increase the speed and cope with a cluttered background. After detecting candidate face regions using the proposed Hough transform, a multi-layer perceptron verifier is adopted to reject false positives. The proposed method was found to be relatively fast and promising.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.49-58
• /
• 2011

Typically, vision-based AR systems operate on the basis of prior knowledge of the environment such as a square marker. The traditional marker-based AR system has a limitation that the marker has to be located in the sensing range. Therefore, there have been considerable research efforts for the techniques known as real-time camera tracking, in which the system attempts to add unknown 3D features to its feature map, and these then provide registration even when the reference map is out of the sensing range. In this paper, we describe a real-time camera tracking framework specifically designed to track a monocular camera in a desktop workspace. Basic idea of the proposed scheme is that a real-time camera tracking is achieved on the basis of a plane tracking algorithm. Also we suggest a method for re-detecting features to maintain registration of virtual objects. The proposed method can cope with the problem that the features cannot be tracked, when they go out of the sensing range. The main advantage of the proposed system are not only low computational cost but also convenient. It can be applicable to an augmented reality system for mobile computing environment.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.1
• /
• pp.31-38
• /
• 2011

A RAM-based Neural Net is a weightless neural network based on binary neural network. 3-D neural network using this paper is binary neural network with multiful information bits and store counts of training. Recognition method by MRD technique is based on the supervised learning. Therefore neural network by itself can not distinguish between the categories and well-separated categories of training data can achieve only through the performance. In this paper, unsupervised learning algorithm is proposed which is trained existing 3-D neural network without distinction of data, to distinguish between categories depending on the only input training patterns. The training data for proposed unsupervised learning provided by the NIST handwritten digits of MNIST which is consist of 0 to 9 multi-pattern, a randomly materials are used as training patterns. Through experiments, neural network is to determine the number of discriminator which each have an idea of the handwritten digits that can be interpreted.