• Journal of IKEEE
• /
• v.28 no.1
• /
• pp.53-64
• /
• 2024

With the advancement of NLP(Natural Language Processing) models, conversational AI such as ChatGPT is becoming increasingly popular. To enhance processing speed and reduce power consumption, it is important to implement the Transformer algorithm, which forms the basis of the latest natural language processing models, in hardware. In particular, the multi-head attention and feed-forward network, which analyze the relationships between different words in a sentence through matrix multiplication, are the most computationally intensive core algorithms in the Transformer. In this paper, we propose a new variable systolic array based on the number of input words to enhance matrix multiplication speed. Quantization maintains Transformer accuracy, boosting memory efficiency and speed. For evaluation purposes, this paper verifies the clock cycles required in multi-head attention and feed-forward network and compares the performance with other multipliers.

• 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.

• Tunnel and Underground Space
• /
• v.32 no.6
• /
• pp.502-517
• /
• 2022

As the use of TBM increases, research has recently increased to to analyze TBM data with machine learning techniques to predict the exchange cycle of disc cutters, and predict the advance rate of TBM. In this study, a regression prediction of disc cutte wear of slurry shield TBM site was made by combining machine learning based on the machine data and the geotechnical data obtained during the excavation. The data were divided into 7:3 for training and testing the prediction of disc cutter wear, and the hyper-parameters are optimized by cross-validated grid-search over a parameter grid. As a result, gradient boosting based on the ensemble model showed good performance with a determination coefficient of 0.852 and a root-mean-square-error of 3.111 and especially excellent results in fit times along with learning performance. Based on the results, it is judged that the suitability of the prediction model using data including mechanical data and geotechnical information is high. In addition, research is needed to increase the diversity of ground conditions and the amount of disc cutter data.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.135-149
• /
• 2020

Artificial intelligences are changing world. Financial market is also not an exception. Robo-Advisor is actively being developed, making up the weakness of traditional asset allocation methods and replacing the parts that are difficult for the traditional methods. It makes automated investment decisions with artificial intelligence algorithms and is used with various asset allocation models such as mean-variance model, Black-Litterman model and risk parity model. Risk parity model is a typical risk-based asset allocation model which is focused on the volatility of assets. It avoids investment risk structurally. So it has stability in the management of large size fund and it has been widely used in financial field. XGBoost model is a parallel tree-boosting method. It is an optimized gradient boosting model designed to be highly efficient and flexible. It not only makes billions of examples in limited memory environments but is also very fast to learn compared to traditional boosting methods. It is frequently used in various fields of data analysis and has a lot of advantages. So in this study, we propose a new asset allocation model that combines risk parity model and XGBoost machine learning model. This model uses XGBoost to predict the risk of assets and applies the predictive risk to the process of covariance estimation. There are estimated errors between the estimation period and the actual investment period because the optimized asset allocation model estimates the proportion of investments based on historical data. these estimated errors adversely affect the optimized portfolio performance. This study aims to improve the stability and portfolio performance of the model by predicting the volatility of the next investment period and reducing estimated errors of optimized asset allocation model. As a result, it narrows the gap between theory and practice and proposes a more advanced asset allocation model. In this study, we used the Korean stock market price data for a total of 17 years from 2003 to 2019 for the empirical test of the suggested model. The data sets are specifically composed of energy, finance, IT, industrial, material, telecommunication, utility, consumer, health care and staple sectors. We accumulated the value of prediction using moving-window method by 1,000 in-sample and 20 out-of-sample, so we produced a total of 154 rebalancing back-testing results. We analyzed portfolio performance in terms of cumulative rate of return and got a lot of sample data because of long period results. Comparing with traditional risk parity model, this experiment recorded improvements in both cumulative yield and reduction of estimated errors. The total cumulative return is 45.748%, about 5% higher than that of risk parity model and also the estimated errors are reduced in 9 out of 10 industry sectors. The reduction of estimated errors increases stability of the model and makes it easy to apply in practical investment. The results of the experiment showed improvement of portfolio performance by reducing the estimated errors of the optimized asset allocation model. Many financial models and asset allocation models are limited in practical investment because of the most fundamental question of whether the past characteristics of assets will continue into the future in the changing financial market. However, this study not only takes advantage of traditional asset allocation models, but also supplements the limitations of traditional methods and increases stability by predicting the risks of assets with the latest algorithm. There are various studies on parametric estimation methods to reduce the estimated errors in the portfolio optimization. We also suggested a new method to reduce estimated errors in optimized asset allocation model using machine learning. So this study is meaningful in that it proposes an advanced artificial intelligence asset allocation model for the fast-developing financial markets.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1285-1300
• /
• 2022

Turbidity, the measure of the cloudiness of water, is used as an important index for water quality management. The turbidity can vary greatly in small river systems, which affects water quality in national rivers. Therefore, the generation of high-resolution spatial information on turbidity is very important. In this study, a turbidity retrieval model using the Korea Multi-Purpose Satellite-3 and -3A (KOMPSAT-3/3A) images was developed for high-resolution turbidity mapping of Han River system based on eXtreme Gradient Boosting (XGBoost) algorithm. To this end, the top of atmosphere (TOA) spectral reflectance was calculated from a total of 24 KOMPSAT-3/3A images and 150 Landsat-8 images. The Landsat-8 TOA spectral reflectance was cross-calibrated to the KOMPSAT-3/3A bands. The turbidity measured by the National Water Quality Monitoring Network was used as a reference dataset, and as input variables, the TOA spectral reflectance at the locations of in situ turbidity measurement, the spectral indices (the normalized difference vegetation index, normalized difference water index, and normalized difference turbidity index), and the Moderate Resolution Imaging Spectroradiometer (MODIS)-derived atmospheric products(the atmospheric optical thickness, water vapor, and ozone) were used. Furthermore, by analyzing the KOMPSAT-3/3A TOA spectral reflectance of different turbidities, a new spectral index, new normalized difference turbidity index (nNDTI), was proposed, and it was added as an input variable to the turbidity retrieval model. The XGBoost model showed excellent performance for the retrieval of turbidity with a root mean square error (RMSE) of 2.70 NTU and a normalized RMSE (NRMSE) of 14.70% compared to in situ turbidity, in which the nNDTI proposed in this study was used as the most important variable. The developed turbidity retrieval model was applied to the KOMPSAT-3/3A images to map high-resolution river turbidity, and it was possible to analyze the spatiotemporal variations of turbidity. Through this study, we could confirm that the KOMPSAT-3/3A images are very useful for retrieving high-resolution and accurate spatial information on the river turbidity.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.1_2
• /
• pp.79-91
• /
• 2006

The intelligent disk can improve the overall performance of the I/O subsystem by processing the I/O operations in the disk side. At present time, however, realizing the intelligent disk seems to be impossible because of the limitation of the I/O subsystem and the lack of the backward compatibility with the traditional I/O interface scheme. In this paper, we proposed new model for the intelligent disk that dynamically optimizes the I/O subsystem using the information that is only related to the physical sector. In this way, the proposed model does not break the compatibility with the traditional I/O interface scheme. For these works, the boosting algorithm that upgrades a weak learner by repeating teaming is used. If the last learner classifies a recent I/O workload as the multimedia workload, the disk reads more sectors. Also, by embedding this functionality as a firmware or a embedded OS within the disk, the overall I/O subsystem can be operated more efficiently without the additional workload.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.3
• /
• pp.11-21
• /
• 2010

To aim at improving performance and reflecting user's needs of retrieval, the number of researches has been actively conducted in recent year as the quantity of information and generation of the web pages exceedingly increase. One of alternative approaches can be a tagging system. It makes users be able to provide a representation of metadata including writings, pictures, and movies etc. called tag and be convenient in use of retrieval of internet resources. Tags similar to keywords play a critical role in maintaining target pages. However, they still needs time consuming labors to annotate tags, which sometimes are found to be a hinderance caused by overuse of tagging. In this paper, we present an automatic tagging scheme for a solution of current tagging system conveying drawbacks and inconveniences. To realize the approach, face recognition-based tagging system on SNS is proposed by building a face area detection procedure, linear-based classification and boosting algorithm. The proposed novel approach of tagging service can increase possibilities that utilized SNS more efficiently. Experimental results and performance analysis are shown as well.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.713-722
• /
• 2013

This paper proposes a method of using depth information to detect the hand region in real-time based on the cascade method. In order to ensure stable and speedy detection of the hand region even under conditions of lighting changes in the test environment, this study uses only features based on depth information, and proposes a method of detecting the hand region by means of a classifier that uses boosting and cascading methods. First, in order to extract features using only depth information, we calculate the difference between the depth value at the center of the input image and the average of depth value within the segmented block, and to ensure that hand regions of all sizes will be detected, we use the central depth value and the second order linear model to predict the size of the hand region. The cascade method is applied to implement training and recognition by extracting features from the hand region. The classifier proposed in this paper maintains accuracy and enhances speed by composing each stage into a single weak classifier and obtaining the threshold value that satisfies the detection rate while exhibiting the lowest error rate to perform over-fitting training. The trained classifier is used to classify the hand region, and detects the final hand region in the final merger stage. Lastly, to verify performance, we perform quantitative and qualitative comparative analyses with various conventional AdaBoost algorithms to confirm the efficiency of the hand region detection algorithm proposed in this paper.

• Journal of Intelligence and Information Systems
• /
• v.22 no.1
• /
• pp.139-157
• /
• 2016

Bankruptcy involves considerable costs, so it can have significant effects on a country's economy. Thus, bankruptcy prediction is an important issue. Over the past several decades, many researchers have addressed topics associated with bankruptcy prediction. Early research on bankruptcy prediction employed conventional statistical methods such as univariate analysis, discriminant analysis, multiple regression, and logistic regression. Later on, many studies began utilizing artificial intelligence techniques such as inductive learning, neural networks, and case-based reasoning. Currently, ensemble models are being utilized to enhance the accuracy of bankruptcy prediction. Ensemble classification involves combining multiple classifiers to obtain more accurate predictions than those obtained using individual models. Ensemble learning techniques are known to be very useful for improving the generalization ability of the classifier. Base classifiers in the ensemble must be as accurate and diverse as possible in order to enhance the generalization ability of an ensemble model. Commonly used methods for constructing ensemble classifiers include bagging, boosting, and random subspace. The random subspace method selects a random feature subset for each classifier from the original feature space to diversify the base classifiers of an ensemble. Each ensemble member is trained by a randomly chosen feature subspace from the original feature set, and predictions from each ensemble member are combined by an aggregation method. The k-nearest neighbors (KNN) classifier is robust with respect to variations in the dataset but is very sensitive to changes in the feature space. For this reason, KNN is a good classifier for the random subspace method. The KNN random subspace ensemble model has been shown to be very effective for improving an individual KNN model. The k parameter of KNN base classifiers and selected feature subsets for base classifiers play an important role in determining the performance of the KNN ensemble model. However, few studies have focused on optimizing the k parameter and feature subsets of base classifiers in the ensemble. This study proposed a new ensemble method that improves upon the performance KNN ensemble model by optimizing both k parameters and feature subsets of base classifiers. A genetic algorithm was used to optimize the KNN ensemble model and improve the prediction accuracy of the ensemble model. The proposed model was applied to a bankruptcy prediction problem by using a real dataset from Korean companies. The research data included 1800 externally non-audited firms that filed for bankruptcy (900 cases) or non-bankruptcy (900 cases). Initially, the dataset consisted of 134 financial ratios. Prior to the experiments, 75 financial ratios were selected based on an independent sample t-test of each financial ratio as an input variable and bankruptcy or non-bankruptcy as an output variable. Of these, 24 financial ratios were selected by using a logistic regression backward feature selection method. The complete dataset was separated into two parts: training and validation. The training dataset was further divided into two portions: one for the training model and the other to avoid overfitting. The prediction accuracy against this dataset was used to determine the fitness value in order to avoid overfitting. The validation dataset was used to evaluate the effectiveness of the final model. A 10-fold cross-validation was implemented to compare the performances of the proposed model and other models. To evaluate the effectiveness of the proposed model, the classification accuracy of the proposed model was compared with that of other models. The Q-statistic values and average classification accuracies of base classifiers were investigated. The experimental results showed that the proposed model outperformed other models, such as the single model and random subspace ensemble model.

• 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.