• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.5
• /
• pp.482-488
• /
• 2014

This paper aims to analyze user's emotion automatically by analyzing Twitter, a representative social network service (SNS). In order to create sentiment analysis models by using machine learning techniques, sentiment labels that represent positive/negative emotions are required. However it is very expensive to obtain sentiment labels of tweets. So, in this paper, we propose a sentiment analysis model by using self-training technique in order to utilize "data without sentiment labels" as well as "data with sentiment labels". Self-training technique is that labels of "data without sentiment labels" is determined by utilizing "data with sentiment labels", and then updates models using together with "data with sentiment labels" and newly labeled data. This technique improves the sentiment analysis performance gradually. However, it has a problem that misclassifications of unlabeled data in an early stage affect the model updating through the whole learning process because labels of unlabeled data never changes once those are determined. Thus, labels of "data without sentiment labels" needs to be carefully determined. In this paper, in order to get high performance using self-training technique, we propose 3 policies for updating "data with sentiment labels" and conduct a comparative analysis. The first policy is to select data of which confidence is higher than a given threshold among newly labeled data. The second policy is to choose the same number of the positive and negative data in the newly labeled data in order to avoid the imbalanced class learning problem. The third policy is to choose newly labeled data less than a given maximum number in order to avoid the updates of large amount of data at a time for gradual model updates. Experiments are conducted using Stanford data set and the data set is classified into positive and negative. As a result, the learned model has a high performance than the learned models by using "data with sentiment labels" only and the self-training with a regular model update policy.

• The KIPS Transactions:PartC
• /
• v.10C no.6
• /
• pp.683-694
• /
• 2003

We present X-tree Diff, a change detection algorithm for tree-structured data. Our work is motivated by need to monitor massive volume of web documents and detect suspicious changes, called defacement attack on web sites. From this context, our algorithm should be very efficient in speed and use of memory space. X-tree Diff uses a special ordered labeled tree, X-tree, to represent XML/HTML documents. X-tree nodes have a special field, tMD, which stores a 128-bit hash value representing the structure and data of subtrees, so match identical subtrees form the old and new versions. During this process, X-tree Diff uses the Rule of Delaying Ambiguous Matchings, implying that it perform exact matching where a node in the old version has one-to one corrspondence with the corresponding node in the new, by delaying all the others. It drastically reduces the possibility of wrong matchings. X-tree Diff propagates such exact matchings upwards in Step 2, and obtain more matchings downwsards from roots in Step 3. In step 4, nodes to ve inserted or deleted are decided, We aldo show thst X-tree Diff runs on O(n), woere n is the number of noses in X-trees, in worst case as well as in average case, This result is even better than that of BULD Diff algorithm, which is O(n log(n)) in worst case, We experimented X-tree Diff on reat data, which are about 11,000 home pages from about 20 wev sites, instead of synthetic documets manipulated for experimented for ex[erimentation. Currently, X-treeDiff algorithm is being used in a commeercial hacking detection system, called the WIDS(Web-Document Intrusion Detection System), which is to find changes occured in registered websites, and report suspicious changes to users.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.6
• /
• pp.617-628
• /
• 2022

A ground support pattern should be designed by properly integrating various support materials in accordance with the rock mass grade when constructing a tunnel, and a technical decision must be made in this process by professionals with vast construction experiences. However, designing supports at the early stage of tunnel design, such as feasibility study or basic design, may be very challenging due to the short timeline, insufficient budget, and deficiency of field data. Meanwhile, the design of the support pattern can be performed more quickly and reliably by utilizing the machine learning technique and the accumulated design data with the rapid increase in tunnel construction in South Korea. Therefore, in this study, the design data and ground exploration data of 48 road tunnels in South Korea were inspected, and data about 19 items, including eight input items (rock type, resistivity, depth, tunnel length, safety index by tunnel length, safety index by rick index, tunnel type, tunnel area) and 11 output items (rock mass grade, two items for shotcrete, three items for rock bolt, three items for steel support, two items for concrete lining), were collected to automatically determine the rock mass class and the support pattern. Three machine learning models (S1, A1, A2) were developed using two machine learning algorithms (SVR, ANN) and organized data. As a result, the A2 model, which applied different loss functions according to the output data format, showed the best performance. This study confirms the potential of support pattern design using machine learning, and it is expected that it will be able to improve the design model by continuously using the model in the actual design, compensating for its shortcomings, and improving its usability.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_2
• /
• pp.1259-1268
• /
• 2021

The 2nd Geostationary Ocean Color Imager (GOCI-II) is the successor to the Geostationary Ocean Color Imager (GOCI), which employs one near-ultraviolet wavelength (380 nm) and eight visible wavelengths(412, 443, 490, 510, 555, 620, 660, 680 nm) and three near-infrared wavelengths(709, 745, 865 nm) to observe the marine environment in Northeast Asia, including the Korean Peninsula. However, the multispectral radiance image observed at satellite altitude includes both the water-leaving radiance and the atmospheric path radiance. Therefore, the atmospheric correction process to estimate the water-leaving radiance without the path radiance is essential for analyzing the ocean environment. This manuscript describes the GOCI-II standard atmospheric correction algorithm and its initial phase validation. The GOCI-II atmospheric correction method is theoretically based on the previous GOCI atmospheric correction, then partially improved for turbid water with the GOCI-II's two additional bands, i.e., 620 and 709 nm. The match-up showed an acceptable result, with the mean absolute percentage errors are fall within 5% in blue bands. It is supposed that part of the deviation over case-II waters arose from a lack of near-infrared vicarious calibration. We expect the GOCI-II atmospheric correction algorithm to be improved and updated regularly to the GOCI-II data processing system through continuous calibration and validation activities.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.4
• /
• pp.233-252
• /
• 2021

This paper is a study to improve the efficiency of mixing technology in the shield TBM chamber. Currently, the number of construction cases using the TBM method is increasing in Korea. According to the increasing use of TBM method, research on TBM method such as Disc Cutter, Cutter bit, and Segment also shows an increasing trend. However, there is little research on the mixing efficiency in chamber and chamber. In order to improve the smooth soil treatment and the behavior of the excavated soil, a study was conducted on the change of the mixing efficiency according to the effective mixing bar arrangement in the chamber. In the scale model experiment, the ground was composed using plastic materials of different colors for ease of identification. In addition, the mixing bar arrangement was different and classified into 4 cases, and the particle size distribution was classified into single particle size and multiple particle size, and the experiment was conducted with a total of 8 cases. The rotation speed of the cutter head of all cases was the same as 5 RPM, and the experiment time was also carried out in the same condition, 1 minute and 30 seconds. In order to check the mixing efficiency, samples at the upper, middle (left or right), and lower positions of each case were collected and analyzed. As a result of the scaled-down model experiment, the mixing efficiency of Case 4 and Case 4-1 increased compared to Case 1 and Case 1-1, which are actually used. Accordingly, it is expected that the mixing efficiency can be increased by changing the arrangement of the mixing bar in the chamber, and it is considered to be effective in saving air as the mixing efficiency increases. Therefore, this study is considered to be an important indicator for the use of shield TBM in Korea.

• Food Engineering Progress
• /
• v.21 no.1
• /
• pp.57-63
• /
• 2017

This study investigated the effects of 27.12 MHz radio frequency (RF) heating on heat transfer phenomena during the thawing process of frozen food. To determine the velocity of the RF thawing machine, samples were frozen at $-80^{\circ}C$ and subjected to different power treatments. The phase change times (-5 to $0^{\circ}C$) of frozen radish were 30, 26, 13, and 8 min; those of pork sirloin were 38, 25, 11, and 5 min; those of rump were 23, 17, 11, and 6 min; those of chicken breast were 42, 29, 13, and 9 min; and those of tuna were 25, 23, 10, and 5 min at 50, 100, 200, and 400 W, respectively. The heating limit temperatures of the radish, pork sirloin, rump, chicken breast, and tuna samples were 19.5, 9.2, 21.8, 8.8, and $16.8^{\circ}C$ at 50 W; 23.5, 15.5, 27.3, 12.3, and $19^{\circ}C$ at 100 W; 42, 26.9, 45.7, 22.1, and $39.4^{\circ}C$ at 200 W; and 48.5, 54.7, 63.6, 57.3, and $44.9^{\circ}C$ at 400 W. These results suggest that high-power RF improves thawing velocity and heating limit temperatures, and that an improvement on the operation of the RF thawing machine, according to food temperatures, is needed.

• Journal of Wetlands Research
• /
• v.21 no.2
• /
• pp.140-146
• /
• 2019

In order to manage non-point sources, the paradigm of the system should be changed so that the management of non-point sources will be systematized from the beginning of the use and development of the land. It is necessary to change the method of national subsidy support and poeration plan for the non-point source management area. In order to increase the effectiveness of the non-point source reduction project, it is necessary to provide a minimum support ratio and to provide additional support according to the performance of the local government. A new system should be established to evaluate the performance of non-point source reduction projects and to monitor the operational effectiveness. It is necessary to establish the related rules that can lead the local government to take responsible administration so that the local governments faithfully carry out the non-point source reduction project and achieve the planned achievement and become the sustainable maintenance. Alternative solutions are needed, such as problems with the use of $100{\mu}m$ filter in automatic sampling and analysis, timely acquisition of water sampling and analysis during rainfall, and effective management of non-point sources network operation management. As an alternative, it is necessary to consider improving the performance of sampling and analysis equipment, and operate the base station. In addition, countermeasures are needed if the amount of pollutant reduction according to the non-point source reduction facility promoted by the national subsidy is required to be used as the development load of the TMDLs. As an alternative, it is possible to consider supporting incentive type of part of the maintenance cost of the non-point source reduction facility depending on the amount of pollutants reduction.

• Journal of the Korean Society of International Agriculture
• /
• v.30 no.4
• /
• pp.292-299
• /
• 2018

In a survey in which farmers were asked about their levels of satisfaction with agricultural machines, Japanese products scored higher than local products by 1.2, 1.3, and 1.4 times for tractors, combine harvesters, and rice transplanter, respectively. Japanese products corresponded to generally high satisfaction levels in terms of operating performance, operability, frequency of breakdowns, and durability, excluding sales price and after-sales services. Effective countermeasures through quality improvement are therefore necessary for Korean products. Furthermore, a survey of dealers showed that the components and consumables for core agricultural machines had high frequencies of breakdowns and repairs. Four major components of tractors represented 85.3% of all breakdowns and repairs, five components of combine harvesters represented 89.6%, and three components of rice transplanters represented 80.5%. Moreover, a comparison of the technological levels between local and imported machines showed that the local machines' levels were at 60-100% for tractors, 70-100% for combine harvesters, and 70-95% for rice transplanters. Small and mid-sized tractors, 4 interrow combine harvesters, and 6 interrow rice transplanters showed similar levels of technology. The results of the analysis suggest that action is urgently needed at a policy level to establish an agricultural machinery component research center for the development, production, and supply of commonly-used components, with the participation of manufacturers of agricultural machines and components, in order to enhance the competitiveness of local manufacturers and to revitalize the agricultural machine market.

• Journal of Intelligence and Information Systems
• /
• v.27 no.2
• /
• pp.17-32
• /
• 2021

Speaker recognition is generally divided into speaker identification and speaker verification. Speaker recognition plays an important function in the automatic voice system, and the importance of speaker recognition technology is becoming more prominent as the recent development of portable devices, voice technology, and audio content fields continue to expand. Previous speaker recognition studies have been conducted with the goal of automatically determining who the speaker is based on voice files and improving accuracy. Speech is an important sociolinguistic subject, and it contains very useful information that reveals the speaker's attitude, conversation intention, and personality, and this can be an important clue to speaker recognition. The final ending used in the speaker's speech determines the type of sentence or has functions and information such as the speaker's intention, psychological attitude, or relationship to the listener. The use of the terminating ending has various probabilities depending on the characteristics of the speaker, so the type and distribution of the terminating ending of a specific unidentified speaker will be helpful in recognizing the speaker. However, there have been few studies that considered speech in the existing text-based speaker recognition, and if speech information is added to the speech signal-based speaker recognition technique, the accuracy of speaker recognition can be further improved. Hence, the purpose of this paper is to propose a novel method using speech style expressed as a sentence-final ending to improve the accuracy of Korean speaker recognition. To this end, a method called sentence sequencing that generates vector values by using the type and frequency of the sentence-final ending appearing in the utterance of a specific person is proposed. To evaluate the performance of the proposed method, learning and performance evaluation were conducted with a actual drama script. The method proposed in this study can be used as a means to improve the performance of Korean speech recognition service.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.103-128
• /
• 2021

Recently, investors' interest and the influence of stock-related information dissemination are being considered as significant factors that explain stock returns and volume. Besides, companies that develop, distribute, or utilize innovative new technologies such as artificial intelligence have a problem that it is difficult to accurately predict a company's future stock returns and volatility due to macro-environment and market uncertainty. Market uncertainty is recognized as an obstacle to the activation and spread of artificial intelligence technology, so research is needed to mitigate this. Hence, the purpose of this study is to propose a machine learning model that predicts the volatility of a company's stock price by using the internet search volume of artificial intelligence-related technology keywords as a measure of the interest of investors. To this end, for predicting the stock market, we using the VAR(Vector Auto Regression) and deep neural network LSTM (Long Short-Term Memory). And the stock price prediction performance using keyword search volume is compared according to the technology's social acceptance stage. In addition, we also conduct the analysis of sub-technology of artificial intelligence technology to examine the change in the search volume of detailed technology keywords according to the technology acceptance stage and the effect of interest in specific technology on the stock market forecast. To this end, in this study, the words artificial intelligence, deep learning, machine learning were selected as keywords. Next, we investigated how many keywords each week appeared in online documents for five years from January 1, 2015, to December 31, 2019. The stock price and transaction volume data of KOSDAQ listed companies were also collected and used for analysis. As a result, we found that the keyword search volume for artificial intelligence technology increased as the social acceptance of artificial intelligence technology increased. In particular, starting from AlphaGo Shock, the keyword search volume for artificial intelligence itself and detailed technologies such as machine learning and deep learning appeared to increase. Also, the keyword search volume for artificial intelligence technology increases as the social acceptance stage progresses. It showed high accuracy, and it was confirmed that the acceptance stages showing the best prediction performance were different for each keyword. As a result of stock price prediction based on keyword search volume for each social acceptance stage of artificial intelligence technologies classified in this study, the awareness stage's prediction accuracy was found to be the highest. The prediction accuracy was different according to the keywords used in the stock price prediction model for each social acceptance stage. Therefore, when constructing a stock price prediction model using technology keywords, it is necessary to consider social acceptance of the technology and sub-technology classification. The results of this study provide the following implications. First, to predict the return on investment for companies based on innovative technology, it is most important to capture the recognition stage in which public interest rapidly increases in social acceptance of the technology. Second, the change in keyword search volume and the accuracy of the prediction model varies according to the social acceptance of technology should be considered in developing a Decision Support System for investment such as the big data-based Robo-advisor recently introduced by the financial sector.