• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.1-17
• /
• 2019

Because stock price forecasting is an important issue both academically and practically, research in stock price prediction has been actively conducted. The stock price forecasting research is classified into using structured data and using unstructured data. With structured data such as historical stock price and financial statements, past studies usually used technical analysis approach and fundamental analysis. In the big data era, the amount of information has rapidly increased, and the artificial intelligence methodology that can find meaning by quantifying string information, which is an unstructured data that takes up a large amount of information, has developed rapidly. With these developments, many attempts with unstructured data are being made to predict stock prices through online news by applying text mining to stock price forecasts. The stock price prediction methodology adopted in many papers is to forecast stock prices with the news of the target companies to be forecasted. However, according to previous research, not only news of a target company affects its stock price, but news of companies that are related to the company can also affect the stock price. However, finding a highly relevant company is not easy because of the market-wide impact and random signs. Thus, existing studies have found highly relevant companies based primarily on pre-determined international industry classification standards. However, according to recent research, global industry classification standard has different homogeneity within the sectors, and it leads to a limitation that forecasting stock prices by taking them all together without considering only relevant companies can adversely affect predictive performance. To overcome the limitation, we first used random matrix theory with text mining for stock prediction. Wherever the dimension of data is large, the classical limit theorems are no longer suitable, because the statistical efficiency will be reduced. Therefore, a simple correlation analysis in the financial market does not mean the true correlation. To solve the issue, we adopt random matrix theory, which is mainly used in econophysics, to remove market-wide effects and random signals and find a true correlation between companies. With the true correlation, we perform cluster analysis to find relevant companies. Also, based on the clustering analysis, we used multiple kernel learning algorithm, which is an ensemble of support vector machine to incorporate the effects of the target firm and its relevant firms simultaneously. Each kernel was assigned to predict stock prices with features of financial news of the target firm and its relevant firms. The results of this study are as follows. The results of this paper are as follows. (1) Following the existing research flow, we confirmed that it is an effective way to forecast stock prices using news from relevant companies. (2) When looking for a relevant company, looking for it in the wrong way can lower AI prediction performance. (3) The proposed approach with random matrix theory shows better performance than previous studies if cluster analysis is performed based on the true correlation by removing market-wide effects and random signals. The contribution of this study is as follows. First, this study shows that random matrix theory, which is used mainly in economic physics, can be combined with artificial intelligence to produce good methodologies. This suggests that it is important not only to develop AI algorithms but also to adopt physics theory. This extends the existing research that presented the methodology by integrating artificial intelligence with complex system theory through transfer entropy. Second, this study stressed that finding the right companies in the stock market is an important issue. This suggests that it is not only important to study artificial intelligence algorithms, but how to theoretically adjust the input values. Third, we confirmed that firms classified as Global Industrial Classification Standard (GICS) might have low relevance and suggested it is necessary to theoretically define the relevance rather than simply finding it in the GICS.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_4
• /
• pp.1319-1326
• /
• 2019

The KARI(Korea Aerospace Research Institute) operates the government satellite information application consultation to cope with ever-increasing demand for satellite images in the public sector, and carries out various support projects including the generation and provision of mosaic images on the Korean Peninsula every year to enhance user convenience and promote the use of satellite images. In particular, the government has wanted to increase the utilization of mosaic images on the Korean Peninsula and seek to classify and update mosaic images so that users can use them in their businesses easily. However, it is necessary to test and verify whether the classification results of the mosaic images can be utilized in the field since the original spectral information is distorted during pan-sharpening and color balancing, and there is a limitation that only R, G, and B bands are provided. Therefore, in this study, the reliability of the classification result of the mosaic image was compared to the result of KOMPSAT-3 image. The study found that the accuracy of the classification result of KOMPSAT-3 image was between 81~86% (overall accuracy is about 85%), while the accuracy of the classification result of mosaic image was between 69~72% (overall accuracy is about 72%). This phenomenon is interpreted not only because of the distortion of the original spectral information through pan-sharpening and mosaic processes, but also because NDVI and NDWI information were extracted from KOMPSAT-3 image rather than from the mosaic image, as only three color bands(R, G, B) were provided. Although it is deemed inadequate to distribute classification results extracted from mosaic images at present, it is believed that it will be necessary to explore ways to minimize the distortion of spectral information when making mosaic images and to develop classification techniques suitable for mosaic images as well as the provision of NIR band information. In addition, it is expected that the utilization of images with limited spectral information could be increased in the future if related research continues, such as the comparative analysis of classification results by geomorphological characteristics and the development of machine learning methods for image classification by objects of interest.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.7
• /
• pp.1216-1221
• /
• 2022

Ships tend to be larger to increase the efficiency of cargo transportation. Larger ships lead to increased travel time for ship workers, increased work intensity, and reduced work efficiency. Problems such as increased work intensity are reducing the influx of young people into labor, along with the phenomenon of avoidance of high intensity labor by the younger generation. In addition, the rapid aging of the population and decrease in the young labor force aggravate the labor shortage problem in the maritime industry. To overcome this, the maritime industry has recently introduced technologies such as an intelligent production design platform and a smart production operation management system, and a smart autonomous logistics system in one of these technologies. The smart autonomous logistics system is a technology that delivers various goods using intelligent mobile robots, and enables the robot to drive itself by using sensors such as lidar and camera. Therefore, in this paper, it was checked whether the mobile robot could autonomously drive to the stop sign by detecting the passage way of the ship deck. The autonomous driving was performed by detecting the passage way of the ship deck through the camera mounted on the mobile robot based on the data learned through Nvidia's End-to-end learning. The mobile robot was stopped by checking the stop sign using SSD MobileNetV2. The experiment was repeated five times in which the mobile robot autonomously drives to the stop sign without deviation from the ship deck passage way at a distance of about 70m. As a result of the experiment, it was confirmed that the mobile robot was driven without deviation from passage way. If the smart autonomous logistics system to which this result is applied is used in the marine industry, it is thought that the stability, reduction of labor force, and work efficiency will be improved when workers work.

• The Journal of Korean Society for Radiation Therapy
• /
• v.12 no.1
• /
• pp.91-104
• /
• 2000

Recently linear accelerator in radiation therapy in asymmetric field has been easily used since the improvement and capability of asymmetrical field adjustment attached to the machine. It has been thought there have been some significant errors in dose calculation when asymmetrical radiation fields have been utilized in practice of radiation treatments if the fundamental data for dose calculation have been measured in symmetrical standard fields. This study investigated how much the measured data of dose distributions and their isodose curves are different between in asymmetrical and symmetrical standard fields, and how much there difference affect the error in dose calculation in conventional method measured in symmetrical standard field. The distributions of radiation dose were measured by photon diode detector in the water phantom (RFA-300P, Scanditronix, Sweden) as tissue equivalent material on utilization of 6 MV linear accelerator with source surface distance (SSD) 1000 mm. The photon diode detector has the velocity of 1 mm per second from water surface to 250 mm depth in the field size of $40mm{\times}40mm\;to\;250mm{\times}250mm\;symmetric\;field\;and\;40mm{\times}20mm\;to\;250mm{\times}125mm$ asymmetrical fields. The measurements of percent depth dose (PDD) and subsequent plotting of their isodose curves were performed from water surface to 250mm dmm from Y-center axis in $100mm{\times}50mm$ field in order to absence the variability of depth dose according to increasing field sizes and their affects to plotted isodose curves. The difference of PDD between symmetric and asymmetric field was maximum $4.1\%\;decrease\;in\;40mm{\times}20mm\;field,\;maximum\;6.6\%\;decrease\;in\;100mm{\times}50mm\;and\;maximum\;10.2\%\;decrease\;200mm{\times}100mm$, the larger decrease difference of PDD as the greater field size and as greater the depth, The difference of PDD between asymmetrical field and equivalent square field showed maximum $2.4\%\;decrease\;in\;60mm{\times}30mm\;field,\;maximum\;4.8\%\;decrease\;in\;150mm{\times}75mm\;and\;maximum\;6.1\%\;decrease\;in\;250mm{\times}125mm$, and the larger decreased differenced PDD as the greater field size and as greater the depth, these differences of PDD were out of $5\%$ of dose calculation as defined by international Commission on radiation unit and Measurements(ICRU). In the dose distribution of asymmetrical field (half beam) the plotted isodose curves were observed to have deviations by decreased PDD as greater as the blocking of the beam moved closer to the central axis, and as the asymmetrical field increased by moving the block 10 mm keeping away from the central axis, the PDD increased and plotted isodose curves were gradually more flattened, due to reduced amount of the primary beam and the fraction of low energy soft radiations by passing thougepth in asymmetrical field by moving independent jaw each 10 h beam flattening filter. As asymmetrical radiation field as half beam radiation technique is used, the radiation dosimetry calculated in utilizing the fundamental data which measured in standard symmetrical field should be converted on bases of nearly measured data in asymmetrical field, measured beam data flies of various asymmetrical field in various energy and be necessary in each institution.

• The Journal of Korean Academy of Prosthodontics
• /
• v.38 no.5
• /
• pp.583-594
• /
• 2000

Dislodgement of a crown or extension bridge and the loosening of a retainer of a bridge is a serious clinical problem in fixed restoration. Generally these problems are considered to be associated with deformation of the restoration. During biting, the restoration is subjected to complex forces and deforms considerably within the limit of its elasticity. Deformation of the restoration under the occlusal force induces excessive stress in the cement film, which then leads to the cement fracture. Such a fracture may eventually cause loss of the restoration. Because most of the past retention tests for full veneer crown were done without fatigue loading, they were not exactly simulating intraoral environment. And the purpose of this study was to evaluate the effect of cyclic cantilever loading on the retentive strength of full veneer crowns depending on different type of cements and taper of prepared abutment. Steel dies with $8^{\circ}\;or\;16^{\circ}$ convergence angle were fabricated through milling and crowns with the same method. These dies and crowns were divided into 8 groups. Group 1 : $16^{\circ}$ taper die, cementation with zinc phosphate cement, without loading Group 2 : $16^{\circ}$ taper die, cementation with zinc phosphate cement, with loading Group 3 : $8^{\circ}$ taper die, cementation with zinc phosphate cement, without loading Group 4 : $8^{\circ}$ taper die, cementation with zinc phosphate cement, with loading Group 5 : $16^{\circ}$ taper die, cementation with Panavia 21, without loading Group 6 : $16^{\circ}$ taper die, cementation with Panavia 21, with loading Group 7 : $8^{\circ}$ taper die, cementation with Panavia 21 without loading Group 8 : $8^{\circ}$ taper die, cementation with Panavia 21, with loading After checking the fit of die and crown, the luting surface of dies and inner surface of crowns were air-abraded for 10 seconds. The crowns were cemented to the dies, with cements mixed according to the manufacturer's recommendations. A static load of 5kg was then applied for 10 minutes with static loading device. Twenty-four hours later, group 1, 3, 5, 7 were only thermocycled, group 2, 4, 6, 8 were subjected to cyclic loading after thermocycling. Retentive tests were performed on the Instron machine. From the finding of this study, the following conclusions were obtained 1. Panavia 21 showed significantly higher retentive strength than zinc phosphate cement for all groups (p<0.05). 2. There was a significant difference in the retentive strength between $8^{\circ}\;and\;16^{\circ}$ taper for zinc phosphate cement(p<0.05), but no significant difference for Panavia 21 (p>0.05). 3. Cyclic loading significantly decreased the retentive strength for all groups(p<0.05). 4. For zinc phosphate cement, there was 35% reduction of the retentive strength after loading in the $16^{\circ}$ taper die, 25% in the $8^{\circ}$ taper die, and for Panavia 21, 21% in the $16^{\circ}$ taper die, 18% in the $8^{\circ}$ taper die.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.6-7
• /
• 2021

Vegetation development in rivers is one of the important issues not only in academic fields such as geomorphology, ecology, hydraulics, etc., but also in river management practices. The problem of river vegetation is directly connected to the harmony of conflicting values of flood management and ecosystem conservation. In Korea, since the 2000s, the issue of river vegetation and land formation has been continuously raised under various conditions, such as the regulating rivers downstream of the dams, the small eutrophicated tributary rivers, and the floodplain sites for the four major river projects. In this background, this study proposes a method for classifying the distribution of vegetation in rivers based on remote sensing data, and presents the results of applying this to the Naeseong Stream. The Naeseong Stream is a representative example of the river landscape that has changed due to vegetation development from 2014 to the latest. The remote sensing data used in the study are images of Sentinel 1 and 2 satellites, which is operated by the European Aerospace Administration (ESA), and provided by Google Earth Engine. For the ground truth, manually classified dataset on the surface of the Naeseong Stream in 2016 were used, where the area is divided into eight types including water, sand and herbaceous and woody vegetation. The classification method used a random forest classification technique, one of the machine learning algorithms. 1,000 samples were extracted from 10 pre-selected polygon regions, each half of them were used as training and verification data. The accuracy based on the verification data was found to be 82~85%. The model established through training was also applied to images from 2016 to 2020, and the process of changes in vegetation zones according to the year was presented. The technical limitations and improvement measures of this paper were considered. By providing quantitative information of the vegetation distribution, this technique is expected to be useful in practical management of vegetation such as thinning and rejuvenation of river vegetation as well as technical fields such as flood level calculation and flow-vegetation coupled modeling in rivers.

• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.71-89
• /
• 2016

Sentiment analysis is used for identifying emotions or sentiments embedded in the user generated data such as customer reviews from blogs, social network services, and so on. Various research fields such as computer science and business management can take advantage of this feature to analyze customer-generated opinions. In previous studies, the star rating of a review is regarded as the same as sentiment embedded in the text. However, it does not always correspond to the sentiment polarity. Due to this supposition, previous studies have some limitations in their accuracy. To solve this issue, the present study uses a supervised sentiment classification model to measure a more accurate sentiment polarity. This study aims to propose an advanced sentiment classifier and to discover the correlation between movie reviews and box-office success. The advanced sentiment classifier is based on two supervised machine learning techniques, the Support Vector Machines (SVM) and Feedforward Neural Network (FNN). The sentiment scores of the movie reviews are measured by the sentiment classifier and are analyzed by statistical correlations between movie reviews and box-office success. Movie reviews are collected along with a star-rate. The dataset used in this study consists of 1,258,538 reviews from 175 films gathered from Naver Movie website (movie.naver.com). The results show that the proposed sentiment classifier outperforms Naive Bayes (NB) classifier as its accuracy is about 6% higher than NB. Furthermore, the results indicate that there are positive correlations between the star-rate and the number of audiences, which can be regarded as the box-office success of a movie. The study also shows that there is the mild, positive correlation between the sentiment scores estimated by the classifier and the number of audiences. To verify the applicability of the sentiment scores, an independent sample t-test was conducted. For this, the movies were divided into two groups using the average of sentiment scores. The two groups are significantly different in terms of the star-rated scores.

• The korean journal of orthodontics
• /
• v.33 no.2 s.97
• /
• pp.103-111
• /
• 2003

The Purpose of this study was to evaluate the effect of occlusion on the mechanical strength of periodontal fibers during retention periods after experimental tooth movement. In the Sprague-Dawley male rats weighing 200g or more, the ntraoral elastics were inserted into the both right and left interproximal space between upper first and second molars for tooth movement. kiter 4 days later, the left lower first, second, and third molars were extracted for differentiating the non-occlusal side from the occlusal side in the same mouth. At the same time the elastics were removed and then light cured resin was Placed in the space between upper first and second molars following undercut was made for retention bilaterally. From the beginning of retention, 7 rats were sacrificed at 0, 4, 8, 12, 16, 20 days respectively. For evaluating of magnitude on the mechanical strength of periodontal tissue, the maximal shear load of the upper first molars were measured bilateraly during extraction using Instron Universal Testing Machine. The results of this study were obtained as follows : 1. In the occlusal side, the maximal shear load was increased from no retention to retention 20 days group as time was going and statistically difference was shown from retention 12 days group (p<0.05). 2. In the non-occlusal side, the maximal shear load was increased slightly from no retention to 20 days group as time was going but there was no statistically difference (p>0.05). 3. The result compared with the maximal shear load between occlusal and nonocclusal side showed no statistically difference until retention 8 day group (p>0.05), but showed statistically difference from retention 12 day to 20day group (P<0.05). These results show that occlusion had an effect on mechanical strength of the periodontal fibers during retention periods after experimental tooth movement; therefore, it is suggested that occlusion should be considered while the retainer types and retention period are planned.

• Science of Emotion and Sensibility
• /
• v.21 no.1
• /
• pp.59-70
• /
• 2018

With the breakthrough of speech recognition technology, conversational agents have become pervasive through smartphones and smart speakers. The recognition accuracy of speech recognition technology has developed to the level of human beings, but it still shows limitations on understanding the underlying meaning or intention of words, or understanding long conversation. Accordingly, the users experience various errors when interacting with the conversational agents, which may negatively affect the user experience. In addition, in the case of smart speakers with a voice as the main interface, the lack of feedback on system and transparency was reported as the main issue when the users using. Therefore, there is a strong need for research on how users can better understand the capability of the conversational agents and mitigate negative emotions in error situations. In this study, we applied social strategies, "forewarning" and "apology", to conversational agent and investigated how these strategies affect users' perceptions of the agent in breakdown situations. For the study, we created a series of demo videos of a user interacting with a conversational agent. After watching the demo videos, the participants were asked to evaluate how they liked and trusted the agent through an online survey. A total of 104 respondents were analyzed and found to be contrary to our expectation based on the literature study. The result showed that forewarning gave a negative impression to the user, especially the reliability of the agent. Also, apology in a breakdown situation did not affect the users' perceptions. In the following in-depth interviews, participants explained that they perceived the smart speaker as a machine rather than a human-like object, and for this reason, the social strategies did not work. These results show that the social strategies should be applied according to the perceptions that user has toward agents.

• Restorative Dentistry and Endodontics
• /
• v.14 no.1
• /
• pp.41-56
• /
• 1989

The purpose of this study was to examine the effect of temperature dependence of the behavior on the physical properties of posterior composite resins. Three light cure posterior composite resins (Heliomolar, Litefil-P, and P-50) and one chemical cure posterior composite resin (Bisfil-II) were used as experimental materials. Composite resin was placed in a cylindrical brass mold (2.5 mm high and 6.5 mm inside diameter) that was rested on a glass plate. Another flat glass was placed on top of the mold, and the plate was tightly clamped together. After the mold had been filled with the light cure composite material, the top surface was cured for 30 seconds with a light source. Chemical cure resin specimens were made in the same manner as above. Three hundreds and twenty composite resin specimens were constructed from the four composite materials. One hundred and sixty specimens of them were placed in a heater at $50^{\circ}C$, $75^{\circ}C$, $100^{\circ}C$, $125^{\circ}C$, $150^{\circ}C$, $175^{\circ}C$ and $200^{\circ}C$ for 5 minutes or 10 minutes respectively before compressive strengths were measured. Another one hundred and sixty specimens were tested for the diametral tensile strengths in the same way as above. They were randomly divided into eight groups according to the mode of heating methods as follows and stored in distilled water at $37^{\circ}C$ for 24 hours. Group $37^{\circ}C$ - specimens were stored at $37^{\circ}C$ in distilled water for 24 hours. Group $50^{\circ}C$ - specimens were heated at $50^{\circ}C$ after curing. Group $75^{\circ}C$ - specimens were heated at $75^{\circ}C$ after curing. Group $100^{\circ}C$ - specimens were heated at $100^{\circ}C$ after curing. Group $125^{\circ}C$ - specimens were heated at $125^{\circ}C$ after curing. Group $150^{\circ}C$ - specimens were heated at $150^{\circ}C$ after curing. Group $175^{\circ}C$ - specimens were heated at $175^{\circ}C$ after curing. Group $200^{\circ}C$ - specimens were heated at $200^{\circ}C$ after curing. Twenty specimens of each of four composite resins were respectively made by insertion of materials into same mold for examining the dimensional changes between before and after heating. The final eighty specimens were stored in distilled water at $37^{\circ}C$ for 24 hours before testing the dimensional changes. Compressive and diametral tensile strengths were measured crosshead speed 1mm/minute and 500Kg in full scale with a mechanical testing machine (DLC 500 Type, Shimadzu Co., Japan). Dimensional changes were determined by measuring the diametral changes of eighty specimens with micrometer (Mitutoyo Co., Japan). Results were as follows: 1. Diametral tensile strengths of specimens in all groups were increased with time heated compared with control group except for that in group $50^{\circ}C$ and the maximum diametral tensile strength was appeared in the specimen of Litefil-P heated for 10 minutes at $100^{\circ}C$. In heliomolar and P-50, it could be seen in the specimen heated for 10 minutes at $150^{\circ}C$, but in Bisfil-II, it could be found in the specimen heated for 5 minutes at $150^{\circ}C$. 2. Compressive strengths of specimens in all groups was tended to be also increased with time heated but that in group $50^{\circ}C$ and the maximum compressive strengths were showed in the same specimens conditioned as the diametral tensile strengths of four composite materials tested. 3. In Heliomolar, Litefil-P, and Bisfil-II, it was decreased in diameters of resin specimens between before heating and increased in diameters of resin specimens after storing in distilled water, but it was not in P-50. 4. There is little difference in diametral tensile strengths, compressive strengths, and dimensional changes followed by heating the resin specimens for 5 minutes and 10 minutes, but there is no statistical significances.