• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.1-12
• /
• 2019

As Artificial Intelligence (AI) technology develops, it is applied to various fields such as image, voice, and text. AI has shown fine results in certain areas. Researchers have tried to predict the stock market by utilizing artificial intelligence as well. Predicting the stock market is known as one of the difficult problems since the stock market is affected by various factors such as economy and politics. In the field of AI, there are attempts to predict the ups and downs of stock price by studying stock price patterns using various machine learning techniques. This study suggest a way of predicting stock price patterns based on the Convolutional Neural Network(CNN) among machine learning techniques. CNN uses neural networks to classify images by extracting features from images through convolutional layers. Therefore, this study tries to classify candlestick images made by stock data in order to predict patterns. This study has two objectives. The first one referred as Case 1 is to predict the patterns with the images made by the same-day stock price data. The second one referred as Case 2 is to predict the next day stock price patterns with the images produced by the daily stock price data. In Case 1, data augmentation methods - random modification and Gaussian noise - are applied to generate more training data, and the generated images are put into the model to fit. Given that deep learning requires a large amount of data, this study suggests a method of data augmentation for candlestick images. Also, this study compares the accuracies of the images with Gaussian noise and different classification problems. All data in this study is collected through OpenAPI provided by DaiShin Securities. Case 1 has five different labels depending on patterns. The patterns are up with up closing, up with down closing, down with up closing, down with down closing, and staying. The images in Case 1 are created by removing the last candle(-1candle), the last two candles(-2candles), and the last three candles(-3candles) from 60 minutes, 30 minutes, 10 minutes, and 5 minutes candle charts. 60 minutes candle chart means one candle in the image has 60 minutes of information containing an open price, high price, low price, close price. Case 2 has two labels that are up and down. This study for Case 2 has generated for 60 minutes, 30 minutes, 10 minutes, and 5minutes candle charts without removing any candle. Considering the stock data, moving the candles in the images is suggested, instead of existing data augmentation techniques. How much the candles are moved is defined as the modified value. The average difference of closing prices between candles was 0.0029. Therefore, in this study, 0.003, 0.002, 0.001, 0.00025 are used for the modified value. The number of images was doubled after data augmentation. When it comes to Gaussian Noise, the mean value was 0, and the value of variance was 0.01. For both Case 1 and Case 2, the model is based on VGG-Net16 that has 16 layers. As a result, 10 minutes -1candle showed the best accuracy among 60 minutes, 30 minutes, 10 minutes, 5minutes candle charts. Thus, 10 minutes images were utilized for the rest of the experiment in Case 1. The three candles removed from the images were selected for data augmentation and application of Gaussian noise. 10 minutes -3candle resulted in 79.72% accuracy. The accuracy of the images with 0.00025 modified value and 100% changed candles was 79.92%. Applying Gaussian noise helped the accuracy to be 80.98%. According to the outcomes of Case 2, 60minutes candle charts could predict patterns of tomorrow by 82.60%. To sum up, this study is expected to contribute to further studies on the prediction of stock price patterns using images. This research provides a possible method for data augmentation of stock data.

• Journal of Korean Society of Transportation
• /
• v.35 no.4
• /
• pp.360-373
• /
• 2017

The BTO-a projects is the types, which has a demand risk among the type of PPP projects in Korea. When demand risk is realized, private investor encounters financial difficulties due to lower revenue than its expectation and the government may also have a problem in stable infrastructure operation. In this regards, the government has applied various risk sharing policies in response to demand risk. However, the amount of government's risk sharing is the government's contingent liabilities as a result of demand uncertainty, and it fails to be quantified by the conventional NPV method of expressing in the text of the concession agreement. The purpose of this study is to estimate the value of investment risk sharing by the government considering the demand risk in the profit sharing system (BTO-a) introduced in 2015 as one of the demand risk sharing policy. The investment risk sharing will take the form of options in finance. Private investors have the right to claim subsidies from the government when their revenue declines, while the government has the obligation to pay subsidies under certain conditions. In this study, we have established a methodology for estimating the value of investment risk sharing by using the Black - Scholes option pricing model and examined the appropriateness of the results through case studies. As a result of the analysis, the value of investment risk sharing is estimated to be 12 billion won, which is about 4% of the investment cost of the private investment. In other words, it can be seen that the government will invest 12 billion won in financial support by sharing the investment risk. The option value when assuming the traffic volume risk as a random variable from the case studies is derived as an average of 12.2 billion won and a standard deviation of 3.67 billion won. As a result of the cumulative distribution, the option value of the 90% probability interval will be determined within the range of 6.9 to 18.8 billion won. The method proposed in this study is expected to help government and private investors understand the better risk analysis and economic value of better for investment risk sharing under the uncertainty of future demand.

• The Journal of Korean Academy of Prosthodontics
• /
• v.33 no.4
• /
• pp.753-768
• /
• 1995

For accurate impression taking of dental patient and esthetic denture treatment of ednetulous patient, measuring between intraoral anatomic landmarks is useful.In this study the subjects selected at a random were two-jundred forty persons with a mean age 22.5(range 21-24) and were taken impression of by irreversible hydrocolloid impression material(Alginate). On the study model made by dental stone, each individual tray was made and final impresion was taken by border moilding. On final model measurings were performed with 3-dimensional measuring device and the values were analyzed by t-test The results is following : ABOUT THE MEASURED VALUES. 1. The width between maxillary right and left canine cusp tip was average 36.44mm(s.d. 2.48), man 36.67mm, woman 35.83mm(p<0.05). 2. The width between labial height of contour of maxillary right and left canine was average 40.08mm(s.d. 2.42), man 40.29mm, woman 39.52mm(p<0.05). 3. The width between mesio-lingual cusps of maxillary first molar was average 43.14mm(s.d. 3.33), man 43.56mm, woman 42.05mm(p<0.05). 4. The width between buccal alveolar ridge on axis of mesiolingual cusp of right and left maxillary first molar was average 64.89mm(s.d. 3.88), man 65.58mm, woman 62.92mm(p<0.05). 5. The width between buccal alveolar ridge on axis of mesiolingual cusp of right and left maxillary second molar was average 68.58mm(s.d. 3.91), man 69.29mm, woman 66.30mm (p<0.05). 6. The width between right and left hamular notch was average 49.80mm(s.d. 3.96), man 50.70mm, woman 48.20mm(p<0.05). 7. The length from labial heigth of contour of maxillary central incisor to center of incisive papilla was average 9.52mm(s.d. 1.18), man 9.46mm, woman 9.63mm(p>0.05). 8. The length from labial heigth of contour of maxillary central incisor to palatine fovea was average 53.27mm(s.d. 2.93), man 53.93mm, woman 52.08mm(p<0.05). 9. The center of incisive papilla ws located posterior to intercanine line at 0.40mm(s.d. 1.16), man 0.51mm, woman 0.11mm(p<0.05). 10. The height from incisal edge of maxillary central incisor to the labial vestibule was average 21.84mm(s.d. 1.38), man 22.01mm, woman 21.00mm(p<0.05). 11. The height from mesiolingual cusp of maxillary first molar to buccalvestible was average 17.45mm(s.d. 1.42), man 17.56mm, woman 17.08mm(p>0.05). 12. The height from hamular notch to standard occlusal plane was average 6.84mm(s.d. 1.06), man 6.91mm, woman 6.70mm(p>0.05). 13. The height from the deepest point of palatal vault to standard occlsalplane was average 19.95 mm(s.d. 2.03), man 20.19mm, woman 19.12mm(p<0.05). ABOUT THE ARCH FORM 1. The arch form was able to classify into four typr by the rate of the measured values. Each arch form distribution was that the 1 group had 32.46% the 2 group 2.19%, the 3 group 52.83%, the 4 group 12.72%. The sexual composition was that in 1 group man had 73.5%, woman 26.5%, in 2 group man had 40.0%, woman 60.0%, in 3 group man had 83.3%, woman 16.7%, and in 4 group man had 55.17%, woman 44.83%. 2. When canine cusp tip was marked as point O, the intersection point between labial height of contour of maxillary central incisor and intermaxillary suture as point A, height of contour of maxillary second molar buccal alveolar ridge as B point, ${\angle}$AOB was measured $133.8^{\circ}$for the 1 group, $133.0^{\circ}$for the 2 group, $132.3^{\circ}$for the 3 group, $128.9^{\circ}$for the 4 group.

• Journal of Animal Science and Technology
• /
• v.46 no.4
• /
• pp.509-516
• /
• 2004

This study is to investigate the amount of biased estimates for heritability and genetic correlation according to data structure on marbling scores in Korean cattle. Breeding population with 5 generations were simulated by way of selection for carcass weight, Longissimus muscle area and latent values of marbling scores and random mating. Latent variables of marbling scores were categorized into five by the thresholds of 0, I, 2, and 3 SD(DSI) or seven by the thresholds of -2, -1, 0,1I, 2, and 3 SD(DS2). Variance components and genetic pararneters(Heritabilities and Genetic correlations) were estimated by restricted maximum likelihood on multivariate linear mixed animal models and by Gibbs sampling algorithms on multivariate threshold mixed animal models in DS1 and DS2. Simulation was performed for 10 replicates and averages and empirical standard deviation were calculated. Using REML, heritabilitis of marbling score were under-estimated as 0.315 and 0.462 on DS1 and DS2, respectively, with comparison of the pararneter(0.500). Otherwise, using Gibbs sampling in the multivariate threshold animal models, these estimates did not significantly differ to the parameter. Residual correlations of marbling score to other traits were reduced with comparing the parameters when using REML algorithm with assuming linear and normal distribution. This would be due to loss of information and therefore, reduced variation on marbling score. As concluding, genetic variation of marbling would be well defined if liability concepts were adopted on marbling score and implemented threshold mixed model on genetic parameter estimation in Korean cattle.

• Korean Journal of Plant Resources
• /
• v.28 no.1
• /
• pp.101-110
• /
• 2015

Parameters of mating system and pollen flow of a Pinus densiflora population in Buan, South Korea, were estimated using seven nuclear microsatellite markers. The expected heterozygosity ($H_e$) was 0.614 in mother trees and 0.624 in seeds. Fixation index (F) was 0.018 and 0.087 in each generation. There was no significant genetic difference between the generations (P > 0.05). From MLTR, the outcrossing rate ($t_m$), the biparental inbreeding ($t_m-t_s$), and the correlation of paternity ($r_p$) were 0.967, 0.057, and 0.012, respectively. tm was larger but $t_m-t_s$ and $r_p$ were smaller than those of allozyme markers in Pinus densiflora. These values were similar to those of microsatellite markers in other pine species. The optimal pollen dispersal model from TwoGener was the normal dispersal model with the effective density of 220 trees/ha and its level of genetic differentiation in pollen pool structure (${\Phi}_{ft}$) was 0.021. The average radial distance of pollen flow (${\delta}$) was calculated as 11.42 m, but no correlation between the pairwise-${\Phi}_{ft}$ and the geographical distance among mother trees was at Mantel test (r = -0.141, P > 0.05). Although the effective pollen dispersal in the population seems to be restricted, the amount of genetic variation might be maintained in each generation without a loss of genetic diversity. It might be because the genetic diversity in pollen pool was high but the genetic difference between pollen donors was small under the complete random mating condition in the Pinus densiflora population in Buan.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.105-122
• /
• 2019

Dimensionality reduction is one of the methods to handle big data in text mining. For dimensionality reduction, we should consider the density of data, which has a significant influence on the performance of sentence classification. It requires lots of computations for data of higher dimensions. Eventually, it can cause lots of computational cost and overfitting in the model. Thus, the dimension reduction process is necessary to improve the performance of the model. Diverse methods have been proposed from only lessening the noise of data like misspelling or informal text to including semantic and syntactic information. On top of it, the expression and selection of the text features have impacts on the performance of the classifier for sentence classification, which is one of the fields of Natural Language Processing. The common goal of dimension reduction is to find latent space that is representative of raw data from observation space. Existing methods utilize various algorithms for dimensionality reduction, such as feature extraction and feature selection. In addition to these algorithms, word embeddings, learning low-dimensional vector space representations of words, that can capture semantic and syntactic information from data are also utilized. For improving performance, recent studies have suggested methods that the word dictionary is modified according to the positive and negative score of pre-defined words. The basic idea of this study is that similar words have similar vector representations. Once the feature selection algorithm selects the words that are not important, we thought the words that are similar to the selected words also have no impacts on sentence classification. This study proposes two ways to achieve more accurate classification that conduct selective word elimination under specific regulations and construct word embedding based on Word2Vec embedding. To select words having low importance from the text, we use information gain algorithm to measure the importance and cosine similarity to search for similar words. First, we eliminate words that have comparatively low information gain values from the raw text and form word embedding. Second, we select words additionally that are similar to the words that have a low level of information gain values and make word embedding. In the end, these filtered text and word embedding apply to the deep learning models; Convolutional Neural Network and Attention-Based Bidirectional LSTM. This study uses customer reviews on Kindle in Amazon.com, IMDB, and Yelp as datasets, and classify each data using the deep learning models. The reviews got more than five helpful votes, and the ratio of helpful votes was over 70% classified as helpful reviews. Also, Yelp only shows the number of helpful votes. We extracted 100,000 reviews which got more than five helpful votes using a random sampling method among 750,000 reviews. The minimal preprocessing was executed to each dataset, such as removing numbers and special characters from text data. To evaluate the proposed methods, we compared the performances of Word2Vec and GloVe word embeddings, which used all the words. We showed that one of the proposed methods is better than the embeddings with all the words. By removing unimportant words, we can get better performance. However, if we removed too many words, it showed that the performance was lowered. For future research, it is required to consider diverse ways of preprocessing and the in-depth analysis for the co-occurrence of words to measure similarity values among words. Also, we only applied the proposed method with Word2Vec. Other embedding methods such as GloVe, fastText, ELMo can be applied with the proposed methods, and it is possible to identify the possible combinations between word embedding methods and elimination methods.

• Journal of Life Science
• /
• v.31 no.9
• /
• pp.840-848
• /
• 2021

This study was conducted to estimate annual trends and the environmental effects in the racing records of Jeju horses. The Korean Racing Authority (KRA) collected 48,645 observations for 2,167 Jeju horses from 2002 to 2019. Racing records were preprocessed to eliminate errors that occur during the data collection. Racing times were adjusted for comparison between race distances. A stepwise Akaike information criterion (AIC) variable selection method was applied to select appropriate environment variables affecting racing records. The annual improvement of the race time was -0.242 seconds. The model with the lowest AIC value was established when variables were selected in the following order: year, budam classification, jockey ranking, trainer ranking, track condition, weather, age, and gender. The most suitable model was constructed when the jockey ranking and age variables were considered as random effects. Our findings have potential for application as basic data when building models for evaluating genetic abilities of Jeju horses.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.933-948
• /
• 2023

Atmospheric aerosols not only have adverse effects on human health but also exert direct and indirect impacts on the climate system. Consequently, it is imperative to comprehend the characteristics and spatiotemporal distribution of aerosols. Numerous research endeavors have been undertaken to monitor aerosols, predominantly through the retrieval of aerosol optical depth (AOD) via satellite-based observations. Nonetheless, this approach primarily relies on a look-up table-based inversion algorithm, characterized by computationally intensive operations and associated uncertainties. In this study, a novel high-resolution AOD direct retrieval algorithm, leveraging machine learning, was developed using top-of-atmosphere reflectance data derived from the Geostationary Ocean Color Imager-II (GOCI-II), in conjunction with their differences from the past 30-day minimum reflectance, and meteorological variables from numerical models. The Light Gradient Boosting Machine (LGBM) technique was harnessed, and the resultant estimates underwent rigorous validation encompassing random, temporal, and spatial N-fold cross-validation (CV) using ground-based observation data from Aerosol Robotic Network (AERONET) AOD. The three CV results consistently demonstrated robust performance, yielding R²=0.70-0.80, RMSE=0.08-0.09, and within the expected error (EE) of 75.2-85.1%. The Shapley Additive exPlanations(SHAP) analysis confirmed the substantial influence of reflectance-related variables on AOD estimation. A comprehensive examination of the spatiotemporal distribution of AOD in Seoul and Ulsan revealed that the developed LGBM model yielded results that are in close concordance with AERONET AOD over time, thereby confirming its suitability for AOD retrieval at high spatiotemporal resolution (i.e., hourly, 250 m). Furthermore, upon comparing data coverage, it was ascertained that the LGBM model enhanced data retrieval frequency by approximately 8.8% in comparison to the GOCI-II L2 AOD products, ameliorating issues associated with excessive masking over very illuminated surfaces that are often encountered in physics-based AOD retrieval processes.

• Phonetics and Speech Sciences
• /
• v.15 no.4
• /
• pp.81-90
• /
• 2023

Auditory perceptual assessment and acoustic analysis are commonly used in clinical practice for voice evaluation. This study aims to explore the effects of speech task context on auditory perceptual assessment and acoustic measures in patients with voice disorders. Sustained vowel phonations (/a/, /e/, /i/, /o/, /u/, /ɯ/, /ʌ/) and connected speech (a standardized paragraph 'kaeul' and nine sub-sentences) were obtained from a total of 22 patients with voice disorders. GRBAS ('G', 'R', 'B', 'A', 'S') and CAPE-V ('OS', 'R', 'B', 'S', 'P', 'L') auditory-perceptual assessment were evaluated by two certified speech language pathologists specializing in voice disorders using blind and random voice samples. Additionally, spectral and cepstral measures were analyzed using the analysis of dysphonia in speech and voice model (ADSV).When assessing voice quality with the GRBAS scale, it was not significantly affected by the vowel type except for 'B', while the 'OS', 'R' and 'B' in CAPE-V were affected by the vowel type (p<.05). In addition, measurements of CPP and L/H ratio were influenced by vowel types and sentence positions. CPP values in the standard paragraph showed significant negative correlations with all vowels, with the highest correlation observed for /e/ vowel (r=-.739). The CPP of the second sentence had the strongest correlation with all vowels. Depending on the speech stimulus, CAPE-V may have a greater impact on auditory-perceptual assessment than GRBAS, vowel types and sentence position with consonants influenced the 'B' scale, CPP, and L/H ratio. When using vowels in the voice assessment of patients with voice disorders, it would be beneficial to use not only /a/, but also the vowel /i/, which is acoustically highly correlated with 'breathy'. In addition, the /e/ vowel was highly correlated acoustically with the standardized passage and sub-sentences. Furthermore, given that most dysphonic signals are aperiodic, 2nd sentence of the 'kaeul' passage, which is the most acoustically correlated with all vowels, can be used with CPP. These results provide clinical evidence of the impact of speech tasks on auditory perceptual and acoustic measures, which may help to provide guidelines for voice evaluation in patients with voice disorders.

• 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.