• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.5
• /
• pp.217-228
• /
• 2023

Video instance segmentation is an intelligent visual task with high complexity because it not only requires object instance segmentation for each image frame constituting a video, but also requires accurate tracking of instances throughout the frame sequence of the video. In special, human instance segmentation in drama videos has an unique characteristic that requires accurate tracking of several main characters interacting in various places and times. Also, it is also characterized by a kind of the class imbalance problem because there is a significant difference between the frequency of main characters and that of supporting or auxiliary characters in drama videos. In this paper, we introduce a new human instance datatset called MHIS, which is built upon drama videos, Miseang, and then propose a novel video data augmentation method, CDVA, in order to overcome the data imbalance problem between character classes. Different from the previous video data augmentation methods, the proposed CDVA generates more realistic augmented videos by deciding the optimal location within the background clip for a target human instance to be inserted with taking rich spatio-temporal context embedded in videos into account. Therefore, the proposed augmentation method, CDVA, can improve the performance of a deep neural network model for video instance segmentation. Conducting both quantitative and qualitative experiments using the MHIS dataset, we prove the usefulness and effectiveness of the proposed video data augmentation method.

• Journal of Intelligence and Information Systems
• /
• v.19 no.4
• /
• pp.21-37
• /
• 2013

Recently, as the advent of the knowledge-based society, there are more people getting interested in the intellectual property. Especially, the ICT companies leading the high-tech industry are working hard to strive for systematic management of intellectual property. As we know, the patent information represents the intellectual capital of the company. Also now the quantitative analysis on the continuously accumulated patent information becomes possible. The analysis at various levels becomes also possible by utilizing the patent information, ranging from the patent level to the enterprise level, industrial level and country level. Through the patent information, we can identify the technology status and analyze the impact of the performance. We are also able to find out the flow of the knowledge through the network analysis. By that, we can not only identify the changes in technology, but also predict the direction of the future research. In the field using the network analysis there are two important analyses which utilize the patent citation information; citation indicator analysis utilizing the frequency of the citation and network analysis based on the citation relationships. Furthermore, this study analyzes whether there are any impacts between the size of the company and patent citation relationships. 74 S&P 500 registered companies that provide IT and communication services are selected for this study. In order to determine the relationship of patent citation between the companies, the patent citation in 2009 and 2010 is collected and sociomatrices which show the patent citation relationship between the companies are created. In addition, the companies' total assets are collected as an index of company size. The distance between companies is defined as the absolute value of the difference between the total assets. And simple differences are considered to be described as the hierarchy of the company. The QAP Correlation analysis and MR-QAP analysis is carried out by using the distance and hierarchy between companies, and also the sociomatrices that shows the patent citation in 2009 and 2010. Through the result of QAP Correlation analysis, the patent citation relationship between companies in the 2009's company's patent citation network and the 2010's company's patent citation network shows the highest correlation. In addition, positive correlation is shown in the patent citation relationships between companies and the distance between companies. This is because the patent citation relationship is increased when there is a difference of size between companies. Not only that, negative correlation is found through the analysis using the patent citation relationship between companies and the hierarchy between companies. Relatively it is indicated that there is a high evaluation about the patent of the higher tier companies influenced toward the lower tier companies. MR-QAP analysis is carried out as follow. The sociomatrix that is generated by using the year 2010 patent citation relationship is used as the dependent variable. Additionally the 2009's company's patent citation network and the distance and hierarchy networks between the companies are used as the independent variables. This study performed MR-QAP analysis to find the main factors influencing the patent citation relationship between the companies in 2010. The analysis results show that all independent variables have positively influenced the 2010's patent citation relationship between the companies. In particular, the 2009's patent citation relationship between the companies has the most significant impact on the 2010's, which means that there is consecutiveness regarding the patent citation relationships. Through the result of QAP correlation analysis and MR-QAP analysis, the patent citation relationship between companies is affected by the size of the companies. But the most significant impact is the patent citation relationships that had been done in the past. The reason why we need to maintain the patent citation relationship between companies is it might be important in the use of strategic aspect of the companies to look into relationships to share intellectual property between each other, also seen as an important auxiliary of the partner companies to cooperate with.

• The Korean Journal of Applied Statistics
• /
• v.28 no.6
• /
• pp.1047-1061
• /
• 2015

Stratified random sampling is a powerful sampling strategy to reduce variance of the estimators by incorporating useful auxiliary information to stratify the population. Sample allocation is the one of the important decisions in selecting a stratified random sample. There are two common methods, the proportional allocation and Neyman allocation if we could assume data collection cost for different observation units equal. Theoretically, Neyman allocation considering the size and standard deviation of each stratum, is known to be more effective than proportional allocation which incorporates only stratum size information. However, if the information on the standard deviation is inaccurate, the performance of Neyman allocation is in doubt. It has been pointed out that Neyman allocation is not suitable for multi-purpose sample survey that requires the estimation of several characteristics. In addition to sampling error, non-response error is another factor to evaluate sampling strategy that affects the statistical precision of the estimator. We propose new sample allocation methods using the available information about stratum response rates at the designing stage to improve stratified random sampling. The proposed methods are efficient when response rates differ considerably among strata. In particular, the method using population sizes and response rates improves the Neyman allocation in multi-purpose sample survey.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.2 no.2
• /
• pp.11-21
• /
• 2000

Tunnelling has been created as a great extent in view of less land space available because the growth of population in metropolitan has been accelerated at a faster pace than the development of the cities. In tunnelling, it is often faced that measures are obliged to be taken without confirmation for such abnormality as diverged movement of surrounding rock mass, growing crack of shotcrete and yielding of rockbolts. In this case, it is usually said that the judgments of experienced engineers for the selection of measure are importance and allowed us to get over the situations in many construction sites. But decrease of such experienced engineers need us to develop the new system to assist the selection of measures for the abnormality without any experiences of similar tunnelling sites. In this study, After a lot of tunnelling reinforcement methods were surveyed and the detail application were studied, an expert system was developed to predict the safety of tunnel and choose proper tunnel reinforcement system using fuzzy quantification theory and fuzzy inference rule based on tunnel information database. The expert system developed in this study have two main parts named pre-module and post-module. Pre-module decides tunnel information imput items based on the tunnel face mapping information which can be easily obtained in-situ site. Then, using fuzzy quantification theory II, fuzzy membership function is composed and tunnel safety level is inferred through this membership function. The comparison result between the predicted reinforcement system level and measured ones was very similar. In-situ data were obtained in three tunnel sites including subway tunnel under Han river. This system will be very helpful to make the most of in-situ data and suggest proper applicability of tunnel reinforcement system developing more resonable tunnel support method from dependance of some experienced experts for the absent of guide.

• The Korean Journal of Air & Space Law and Policy
• /
• v.33 no.2
• /
• pp.345-366
• /
• 2018

Article 37 of the International Convention on Civil Aviation requires that rules should be adopted to keep in compliance with international standards and recommended practices established by ICAO. As SARPs are revised annually, each ICAO Member State needs to reflect the new content in its national aviation Acts in a timely manner. In recent years, data-driven international standards have been developed because of the important roles of aviation safety data and information-based legislation in accident prevention based on human factors. The Safety Management System and crew Fatigue Risk Management Systems were reviewed as examples of the result of data-driven rulemaking. The safety management system was adopted in 2013 with the introduction of Annex 19 and Chapter 5 of the relevant manual describes safety data collection and analysis systems. Through analysis of safety data and information, decision makers can make informed data-driven decisions. The Republic of Korea introduced Safety Management System in accordance with Article 58 of the Aviation Safety Act for all airlines, maintenance companies, and airport corporations. To support the SMS, both mandatory reporting and voluntary safety reporting systems need to be in place. Up until now, the standard of administrative penal dispensation for violations of the safety management system has been very weak. Various regulations have been developed and implemented in the United States and Europe for the proper legislation of the safety management system. In the wake of the crash of the Colgan aircraft, the US Aviation Safety Committee recommended the US Federal Aviation Administration to establish a system that can identify and manage pilot fatigue hazards. In 2010, a notice of proposed rulemaking was issued by the Federal Aviation Administration and in 2011, the final rule was passed. The legislation was applied to help differentiate risk based on flight according to factors such as the pilot's duty starting time, the availability of the auxiliary crew, and the class of the rest facility. Numerous amounts data and information were analyzed during the rulemaking process, and reflected in the resultant regulations. A cost-benefit analysis, based on the data of the previous 10 year period, was conducted before the final legislation was reached and it was concluded that the cost benefits are positive. The Republic of Korea also currently has a clause on aviation safety legislation related to crew fatigue risk, where an airline can choose either to conform to the traditional flight time limitation standard or fatigue risk management system. In the United States, specifically for the purpose of data-driven rulemaking, the Airline Rulemaking Committee was formed, and operates in this capacity. Considering the advantageous results of the ARC in the US, and the D4S in Europe, this is a system that should definitely be introduced in Korea as well. A cost-benefit analysis is necessary, and can serve to strengthen the resulting legislation. In order to improve the effectiveness of data-based legislation, it is necessary to have reinforcement of experts and through them prepare a more detailed checklist of relevant variables.

• Korean Journal of Remote Sensing
• /
• v.30 no.1
• /
• pp.61-73
• /
• 2014

This study reviewed an application of water quality estimation using an Airborne Hyperspectral Imagery (A-HSI) and tested a part of Han River water quality (especially suspended solid) estimation with available in-situ data. The estimation of water quality was processed two methods. One is using observation data as downwelling radiance to water surface and as scattering and reflectance into water body. Other is linear regression analysis with water quality in-situ measurement and upwelling data as at-sensor radiance (or reflectance). Both methods drive meaningful results of RS estimation. However it has more effects on the auxiliary dataset as water quality in-situ measurement and water body scattering measurement. The test processed a part of Han River located Paldang-dam downstream. We applied linear regression analysis with AISA eagle hyperspectral sensor data and water quality measurement in-situ data. The result of linear regression for a meaningful band combination shows $-24.847+0.013L_{560}$ as 560 nm in radiance (L) with 0.985 R-square. To comparison with Multispectral Imagery (MSI) case, we make simulated Landsat TM by spectral resampling. The regression using MSI shows -55.932 + 33.881 (TM1/TM3) as radiance with 0.968 R-square. Suspended Solid (SS) concentration was about 3.75 mg/l at in-situ data and estimated SS concentration by A-HIS was about 3.65 mg/l, and about 5.85mg/l with MSI with same location. It shows overestimation trends case of estimating using MSI. In order to upgrade value for practical use and to estimate more precisely, it needs that minimizing sun glint effect into whole image, constructing elaborate flight plan considering solar altitude angle, and making good pre-processing and calibration system. We found some limitations and restrictions such as precise atmospheric correction, sample count of water quality measurement, retrieve spectral bands into A-HSI, adequate linear regression model selection, and quantitative calibration/validation method through the literature review and test adopted general methods.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.26 no.4
• /
• pp.551-556
• /
• 2012

The database for the oriental medicine had been existed in documentation in past times and it has been developed to the database type for random accesses in the information society. However, the aspects of the database are not so diversified and the database for the bio herbal material exists in widened type dictionary style. It is a situation that the database which handles the in-depth raw herbal medicines is not sufficient in its quantity and quality. Korean wild grape is a deciduous plant categorized into the Vitaceae and it was found experimentally that it has various medical effects. It is one of the medical materials with higher potentiality of academic study and commercialization recently because it has a bigger possibility to be applied into diverse industrial fields including the medical product for health, food and beauty. We constituted the cooperative system among the Muju cluster business group for Korean mountain wild grapes, Physiology Laboratory in Kyung Hee University Oriental Medicine and Medical Classics Laboratory in Kyung Hee University Oriental Medicine with a view to focusing on such potentiality and a database for Korean wild grapes was made a touchstone for establishing the in-depth database for the single bio medical materials. First of all, the literatures based on the North East Asia in ancient times had been categorized into the classical literature (Korean literature published by government organization, Korean classical literature, Chinese classical literature and classical literature fro Korean and Chinese oriental medicine) and modern literature (Modern literature for oriental medicine, modern literature for domestic and foreign herbal medicine) to cover the eastern and western research records and writings related to Korean wild grapes and the text-mining work has been performed through the cooperation system with the Medical Classics Laboratory in Kyung Hee University Oriental Medicine. First of all, the data for the experiment and theory for Korean wild grape were collected for the Medline database controlled by the Parliament Library of USA to arrange the domestic and foreign theses with topic for Korean wild grapes and the network hyperlink function and down load function were mounted for self-thesis searching function and active view based on the collected data. The thesis searching function provides various auxiliary functions and the searching is available according to the diverse searching/queries such as the name of sub species of Korean wild grape, the logical intersection index for the active ingredients, efficacy and elements. It was constituted for the researchers who design the Korean wild grape study to design of easier experiment. In addition, the data related to the patents for Korean wild grape which were collected from European Patent Office in response to the commercialization possibility and the system available for searching and view was established in the same viewpoint. Perl was used for the query programming and MS-SQL for database establishment and management in the designing of this database. Currently, the data is available for free use and the address is as follows. http://163.180.41.43:8011/index.html

• Journal of KIISE:Computing Practices and Letters
• /
• v.6 no.2
• /
• pp.135-149
• /
• 2000

Most of prior works on testing parallel programs have concentrated on how to guarantee the reproducibility by employing event traces exercised during executions of a program. Consequently, little work has been done to generate test cases, especially, from specifications produced from software development process. In this research work, we devise the techniques for deriving test cases automatically from the specifications written in Message Sequence Charts(MSCs) which are widely used in telecommunication areas and develop the testing environment for performing module testing of parallel programs with derived test cases. For deriving test cases from MSCs, we have to uncover the causality relations among events embedded implicitly in MSCs. For this, we devise the methods for adapting vector time stamping to MSCs, Then, valid event sequences, satisfying the causality relations, are generated and these are used as test cases. The generated test cases, written in TTCN, are translated into CHILL source codes, which interact with a target module to be tested and test the validity of behaviors of the module. Since the testing method developed in this research work extracts test cases from the MSC specifications produced front telecommunications software development process, it is not necessary to describe auxiliary specifications for testing. In audition adapting vector time stamping generates automatically the event sequences, the generated event sequences that are ones for whole system can be used for individual testing purpose.

• Journal of Internet Computing and Services
• /
• v.22 no.1
• /
• pp.109-135
• /
• 2021

his study classified the development process of artificial intelligence (AI) speakers through analysis of the news text of artificial intelligence (AI) speakers shown in traditional news reports, and identified the characteristics of each product by period. The theoretical background used in the analysis are news frames and topic frames. As analysis methods, topic modeling and semantic network analysis using the LDA method were used. The research method was a content analysis method. From 2014 to 2019, 2710 news related to AI speakers were first collected, and secondly, topic frames were analyzed using Nodexl algorithm. The result of this study is that, first, the trend of topic frames by AI speaker provider type was different according to the characteristics of the four operators (communication service provider, online platform, OS provider, and IT device manufacturer). Specifically, online platform operators (Google, Naver, Amazon, Kakao) appeared as a frame that uses AI speakers as'search or input devices'. On the other hand, telecommunications operators (SKT, KT) showed prominent frames for IPTV, which is the parent company's flagship business, and 'auxiliary device' of the telecommunication business. Furthermore, the frame of "personalization of products and voice service" was remarkable for OS operators (MS, Apple), and the frame for IT device manufacturers (Samsung) was "Internet of Things (IoT) Integrated Intelligence System". The econd, result id that the trend of the topic frame by AI speaker development period (by year) showed a tendency to develop around AI technology in the first phase (2014-2016), and in the second phase (2017-2018), the social relationship between AI technology and users It was related to interaction, and in the third phase (2019), there was a trend of shifting from AI technology-centered to user-centered. As a result of QAP analysis, it was found that news frames by business operator and development period in AI speaker development are socially constituted by determinants of media discourse. The implication of this study was that the evolution of AI speakers was found by the characteristics of the parent company and the process of co-evolution due to interactions between users by business operator and development period. The implications of this study are that the results of this study are important indicators for predicting the future prospects of AI speakers and presenting directions accordingly.

• Conservation Science in Museum
• /
• v.26
• /
• pp.161-182
• /
• 2021

A jungwangu, a type of medium-sized mortar, is a firearm with a barrel and a bowl-shaped projectileloading component. A bigyeokjincheonroe (bombshell) or a danseok (stone ball) could be used as a projectile. According to the Hwaposik eonhae (Korean Translation of the Method of Production and Use of Artillery, 1635) by Yi Seo, mortars were classified into four types according to its size: large, medium, small, or extra-small. A total of three mortars from the Joseon period have survived, including one large mortar (Treasure No. 857) and two medium versions (Treasure Nos. 858 and 859). In this study, the production method for medium mortars was investigated based on scientific analysis of the two extant medium mortars, respectively housed in the Jinju National Museum (Treasure No. 858) and the Korea Naval Academy Museum (Treasure No. 859). Since only two medium mortars remain in Korea, detailed specifications were compared between them based on precise 3D scanning information of the items, and the measurements were compared with the figures in relevant records from the period. According to the investigation, the two mortars showed only a minute difference in overall size but their weight differed by 5,507 grams. In particular, the location of the wick hole and the length of the handle were distinct. The extant medium mortars are highly similar to the specifications listed in the Hwaposik eonhae. The composition of the medium mortars was analyzed and compared with other bronze gunpowder weapons. The surface composition analysis showed that the medium mortars were made of a ternary alloy of Cu-Sn-Pb with average respective proportions of (wt%) 85.24, 10.16, and 2.98. The material composition of the medium mortars was very similar to the average composition of the small gun from the Joseon period analyzed in previous research. It also showed a similarity with that of bronze gun-metal from medieval Europe. The casting technique was investigated based on a casting defect on the surface and the CT image. Judging by the mold line on the side, it appears that they were made in a piece-mold wherein the mold was halved and using a vertical design with molten metal poured through the end of the chamber and the muzzle was at the bottom. Chaplets, an auxiliary device that fixed the mold and the core to the barrel wall, were identified, which may have been applied to maintain the uniformity of the barrel wall. While the two medium mortars (Treasure Nos. 858 and 859) are highly similar to each other in appearance, considering the difference in the arrangement of the chaplets between the two items it is likely that a different mold design was used for each item.