• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.673-687
• /
• 2023

Convolutional neural network-based deep learning technology is the most commonly used in image identification, but it requires large-scale data for training. Therefore, application in specific fields in which data acquisition is limited, such as in the military, may be challenging. In particular, the identification of ground weapon systems is a very important mission, and high identification accuracy is required. Accordingly, various studies have been conducted to achieve high performance using small-scale data. Among them, the ensemble method, which achieves excellent performance through the prediction average of the pre-trained models, is the most representative method; however, it requires considerable time and effort to find the optimal combination of ensemble models. In addition, there is a performance limitation in the prediction results obtained by using an ensemble method. Furthermore, it is difficult to obtain the ensemble effect using models with imbalanced classification accuracies. In this paper, we propose a transfer learning-based feature fusion technique for heterogeneous models that extracts and fuses features of pre-trained heterogeneous models and finally, fine-tunes hyperparameters of the fully connected layer to improve the classification accuracy. The experimental results of this study indicate that it is possible to overcome the limitations of the existing ensemble methods by improving the classification accuracy through feature fusion between heterogeneous models based on transfer learning.

• The korean journal of orthodontics
• /
• v.40 no.2
• /
• pp.106-114
• /
• 2010

Objective: The aim of this experimental study was to evaluate the effects of direct electrical current stimulation (DECS) on bone regeneration in response to an expansion of the inter-premaxillary suture in the rat. Methods: Sixteen 50 - 60 days old Wistar male rats were separated into two equal groups (control and experimental). Both groups were subjected to expansion, and 30-gram of force was applied to the maxillary incisors with helical-spring. In the experimental group, two metallic-screws were placed at lateral parts of the maxillary segments. Electrodes were connected to the screws. The device was activated with current adjustment to measure $10{\mu}A$ continuously and the current was monitored daily during the expansion and early-retention phase. Bone regeneration in the sutural area was histomorphometrically evaluated including new-bone area (${\mu}m^2$), bone perimeter (${\mu}m$), feret's diameter (${\mu}m$) and newly formed bone (%) parameters. Kruskal-Wallis rank and Mann-Whitney U tests were used for statistical evaluation at p < 0.05 level. Results: Statistical analysis showed significant differences between groups for all investigated histomorphometric parameters. New bone area (p = 0.002), bone perimeter (p = 0.004), feret's diameter (p = 0.002) and newly formed bone percentage (p = 0.002) measurements were significantly higher in the experimental group than the control group. Bone histomorphometric measurements revealed that bone architecture in the DECS group was improved. Conclusions: The application of DECS to an orthopedically expanded inter-premaxillary suture area during the early retention phase stimulated the formation of new bone.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.31 no.6 s.165
• /
• pp.837-847
• /
• 2007

1,098 pieces of photographs($1995{\sim}2002$) of men's suit style have been classified according to fashion images in order to examine features and change aspects with statistical analysis. The findings of examining features of the trend by year with test of homogeneity, correspondence analysis, biplots, correlation analysis and regression analysis are as follows: (a) there are significant differences on fashion images as the trend by yew with test of homogeneity, (b) there are remarkable differences on the fashion trend by year with correspondence analysis and biplots. (c) There are significant correlations for appearance among fashion images by its frequency through correlation analysis, and (d) it is assumed that fashion images are going to be gradually outstanding according to regression analysis.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.2
• /
• pp.209-216
• /
• 2018

High-resolution satellite imagery is used in diverse fields such as meteorological observation, topography observation, remote sensing (RS), military facility monitoring and protection of cultural heritage. In satellite imagery, low-resolution imagery can take place depending on the conditions of hardware (e.g., optical system, satellite operation altitude, image sensor, etc.) even though the images were obtained from the same satellite imaging system. Once a satellite is launched, the adjustment of the imaging system cannot be done to improve the resolution of the degraded images. Therefore, there should be a way to improve resolution, using the satellite imagery. In this study, a super resolution (SR) algorithm was adopted to improve resolution, using such low-resolution satellite imagery. The SR algorithm is an algorithm which enhances image resolution by matching multiple low-resolution images. In satellite imagery, however, it is difficult to get several images on the same region. To take care of this problem, this study performed the SR algorithm by calibrating geometric changes on images after applying automatic extraction of feature points and projection transform. As a result, a clear edge was found just like the SR results in which feature points were manually obtained.

• Journal of Fashion Business
• /
• v.2 no.3
• /
• pp.121-136
• /
• 1998

The purpose of this study was to present a new research method of stage costume by designing and making the stage costume of Yean-GaeSoMoon(淵蓋蘇文) in Peking Opera Du Mu Guan (Korean; Dog Mog Guan, 獨木關). The stage costume of Peking Opera was formed on the basis of the Chinese traditional stage costume in the Qing period, however the style of stage costume was beautified the costume of Ming period and here contained the factors of successive costumes. But the stage costume of Peking Opera didn't have the same rank system with real history costume and didn't have demarcation according to period and history. In the stage costume of Peking Opera, the color is cultural language that can inform spectators of sex, age, personality, position of characters. The pattern of decoration also symboled the personality and characteristic of the character. Yean-GaeSoMoon in the play wore green armour (Chinese; ru ying kao 綠硬靠), red pants (Chinese; hong ku 紅褲), red mustache (Chinese; hong ran kou 紅髥口), crown (Chinese; da e zi 大額子), shoes (Chinese; hou di xue 厚底靴) and Xue RenGui wore white armour (Chinese; baikao 白靠), red pants (Chinese; hong ku 紅褲), shoes (Chinese; hou di xue 厚底靴), hat (Chinese; za jin 扎巾). By historical materials, Yean-GaeSoMoon was a nationalist who uphold national sprit and the greatest hero of the age and a charismatic politician who combines literatural arts with military arts. Considering these reviews, defined the thema of his new costumes' image as "the flying bird which has three legs"(三足鳥), the bird which symbolized the sun and immortality in Koguryo fresco. On the basis of this image, presented three types of Yean-GaeSoMoon's stage costume. Yean-GaeSoMoon as the minister in the court wore black gown (Chinese; mang pao 蟒袍) of dargon pattern which symbolizes harisma who opening the heaven. He as the general who directs war wore red mantle (Chinese; dou peng 斗蓬) which symbolizes the blue dragon that soaring into the sky, as the officer who fights the enemy's general wore green armour (Chinese; gai liang jia 改良甲), red pants (Chinese; hong ku 紅褲) which symbolizes the flying Sward that blowing violently. By wearing these stage costumes, the image of Yean-GaeSoMoon could changed from the fierce general of minority race who likes to fight, to the Koguryo general who fights against enemy at the risk of his life for Koguryo's autonomy. Through this study once again we could realized that stage costume played very mportant part In outstnding the characteristic of actor in the Peking Opera.

• International Commerce and Information Review
• /
• v.15 no.1
• /
• pp.185-206
• /
• 2013

Recent studies validate the idea that consumer judgment of products can affect consumer purchase intentions. Consumers judge products based on product quality, after sales satisfaction, and other visible values, but consumers also judge products on country-of-origin image, brand image and such intangible values. In this paper, we will examine consumer ethnocentrism and animosity, which are frequently responsible for country-of-origin prejudices, because the offending (i.e. exporting) nation has engaged in economic, political, or even military activities that the consumer finds difficult to forgive. The results of the study show a positive effect of product judgment on consumer purchase intentions, but consumer ethnocentrism and animosity negatively affect product judgment and consumer purchase intentions of foreign products. In the Chinese market, ethnocentric Chinese consumers have negative perceptions of foreign products with negative intentions to buy them. Chinese consumers have strong animosity for Japanese products, which negatively affect product judgments and purchase intentions to buy; therefore, Japanese corporations should increase cooperation with Chinese corporations. Conversely, for Korean companies, product judgment primarily affects consumers' intentions to buy; consequently, Korean companies should improve their product quality, after-sales satisfaction, brand image and other tangible aspects to improve consumer judgment.

• Convergence Security Journal
• /
• v.21 no.1
• /
• pp.191-200
• /
• 2021

Artificial intelligence technology is developing in an environment where a lot of data is produced due to the development of computing technology, a cloud environment that can store data, and the spread of personal mobile phones. Among these artificial intelligence technologies, the deep neural network provides excellent performance in image recognition and image classification. There have been many studies on image detection for forest fires and fire prevention using such a deep neural network, but studies on detection of cigarette smoking were insufficient. Meanwhile, military units are establishing surveillance systems for various facilities through CCTV, and it is necessary to detect smoking near ammunition stores or non-smoking areas to prevent fires and explosions. In this paper, by reflecting experimentally optimized numerical values such as activation function and learning rate, we did the detection of smoking pictures and non-smoking pictures in two cases. As experimental data, data was constructed by crawling using pictures of smoking and non-smoking published on the Internet, and a machine learning library was used. As a result of the experiment, when the learning rate is 0.004 and the optimization algorithm Adam is used, it can be seen that the accuracy of 93% and F1-score of 94% are obtained.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.4
• /
• pp.179-184
• /
• 2021

Along with the development of the fourth industry, the public sector has increasingly paid more attention to search using drones and real-time monitoring, for various goals. The drones are used and researched to complete a variety of searching and monitoring missions, including search for missing persons, security, coastal patrol and monitoring, speed enforcement, highway and urban traffic monitoring, fire and wildfire monitoring, monitoring of illegal fishing in reservoirs and protest rally monitoring. Police stations, fire departments and military authorities, however, concentrate on the hardware part, so there are little research on efficient communication systems for the real-time monitoring of data collected from high-performance resolution and infrared thermal imagining cameras, and analysis programs suitable for special missions. In order to increase the efficiency of drones with the searching mission, this paper, therefore, attempts to propose an image analysis technique to increase the precision of search by producing image data suitable for searching missions, based on images obtained from drones and provide the foundation for improving relevant policies and establishing proper platforms, based on actual field cases and experiments.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.45 no.3
• /
• pp.9-20
• /
• 2017

Camp Page, which has been located in front of Chuncheon Station for about 50 years since 1958, recently opened to the public. Chuncheon City is currently struggling to construct a park on this site due to an uncertainty of general plans and financial difficulties. Accordingly, this research conducted a cognitive survey about site usage with Camp Page users in order to clarify directions for efficient establishment of parks within the former military base. The course of research includes analytical methods such as a survey targeting Chuncheon citizens and tourists both in the field and online, a frequency analysis of 1,360 index samples, a cross analysis and t-test. As a result, firstly, Chuncheon citizens recognized the image of Chuncheon as a city with a fresh, clean lakeshore whereas tourists think of it as a city for sightseeing and leisure. Hence, it was justifiable to conclude that the city should organize various programs for people to enjoy leisure activities while at the same time protecting the environment. Second, the awareness of tourists about Camp Page was relatively low and both citizens and tourists recognize that it was not sufficient enough for enjoyment of free time. The majority answered "space for culture and art and for experiencing the natural environment" when asked about the direction of space creation at Camp Page, which indicates that the site will need to be available both for cultural art and nature experiences. Lastly, it was thought that the direction of developing leisure facilities in Chuncheon city should include the improvement of worn out installations and developing chain products among programs. This research will be able to use fundamental data for the efficient utilization of the returned U.S. military camps that are constantly merging.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.10
• /
• pp.109-119
• /
• 2013

An unmanned ground vehicle(UGV) today plays a significant role in both civilian and military areas. Predominantly these systems are used to replace humans in hazardous situations. To take unmanned ground vehicles systems to the next level and increase their capabilities and the range of missions they are able to perform in the combat field, new technologies are needed in the area of command and control. For this reason, we present war field simulator based on information fusion technology to efficiently control UGV. In this paper, we present the war field simulator which is made of critical components, that is, simulation controller, virtual image viewer, and remote control device to efficiently control UGV in the future combat fields. In our information fusion technology, improved methods of target detection, recognition, and location are proposed. In addition, time reduction method of target detection is also proposed. In the consequence of the operation test, we expect that our war field simulator based on information fusion technology plays an important role in the future military operation significantly.