• Journal of the Korean Society of Radiology
• /
• v.17 no.3
• /
• pp.385-392
• /
• 2023

Caroli's disease is a fibrocystic liver disease. Autosomal recessive disorder is characterized by congenital multiple dilatation of the bile duct. Computerized tomography, magnetic resonance imaging, cholangiography and ultrasound are among the methods for diagnosing caroli disease. Computerized tomography is essential for detecting and distinguishing fibroplastic liver disease and is useful for determining intrahepatic bile duct dilatation. However, awareness of the possible side effects of using contrast mediums is necessary. A typical method of magnetic resonance cholangiography is used for magnetic resonance imaging. A non-invasive examination can reduce the pain of the patient, and the anatomical structure of the bile pancreatic duct and the presence or absence of lesions can be easily and quickly observed. Biliary contrast is an effective diagnostic method that can directly visualize various cystic dilatations throughout the enlarged bile duct. However, since this procedure is also an invasive procedure, it is recommended not for diagnosis but for treatment purposes. Ultrasonography can confirm similar findings to computerized tomography. The hepatic artery root is difficult to prove with conventional grayscale ultrasound. However, it is of clinical value in that it can not only describe dilated bile ducts with vascular roots in the tube but also easily identify color Doppler signals in the tube. With the development of video diagnostics, early diagnosis has become possible through computerized tomography, magnetic resonance imaging, cholangiography, and ultrasound. In order to further contribute to the development of video diagnostics so that long-term prognosis can be improved after treatment through early diagnosis, we examined what aspects of each test's caroli disease appear.

• Korean Journal of Culture and Social Issue
• /
• v.10 no.3
• /
• pp.103-129
• /
• 2004

This article examines the Korean adolescents and adults' social representation and trust of Korean society and people using indigenous psychological analysis. Respondents were asked to write in an open-ended questionnaire their perception of the following five aspects: Korean politics, economy, society, culture and people. They were then asked to report why they trust or distrust Korean society. A total of 1,064 respondents (218 middle school students, 200 university students, 218 fathers of the middle school students, 218 mothers of the middle school students, and 210 teachers) completed a questionnaire developed by the present researchers. The data were collected during April to June, 2003. The results indicate that 94.5% of Koreans view the existing political system and politicians as being corrupt, inept, factional, and lacking in integrity. A vast majority (84.9%) recognize the existence of systemic problems in the Korean economy. A total of 78.2% see problems in Korean society being dominated by selfishness, factionalism, conservatism, and social uncertainty. For Korean culture, a majority of respondents report being proud of its cultural tradition, accomplishment, and creativity. At the same time, 45.7% report loss of cultural identity and pride due to external influences. More than half of the respondents report negative aspects of Korean people (i.e., selfish, lack of morality, rushed, and overly focused on their social image), while nearly half of the respondents report positive aspects of Korean people as being compassionate, cooperative, good-natured and hard-working. As for reason for trusting Korean society, around a third report "because it is our country," followed by its future potential, and the good-nature and willingness of Korean people to work hard. The reasons for distrusting Korean society is the dishonesty politicians, corruption, institutional ineptness, and economic uncertainty. These results indicate a low level of collective efficacy in influencing and affecting change in Korean society.

• Journal of The Korean Association For Science Education
• /
• v.29 no.8
• /
• pp.990-1010
• /
• 2009

To derive brain-based evolutionary educational principles, this study examined the studies on the structural and functional characteristics of human brain, the biological evolution occurring between- and within-organism, and the evolutionary attributes embedded in science itself and individual scientist's scientific activities. On the basis of the core characteristics of human brain and the framework of universal Darwinism or universal selectionism consisted of generation-test-retention (g-t-r) processes, a Model of Brain-based Evolutionary Scientific Teaching for Learning (BEST-L) was developed. The model consists of three components, three steps, and assessment part. The three components are the affective (A), behavioral (B), and cognitive (C) components. Each component consists of three steps of Diversifying $\rightarrow$ Emulating (Executing, Estimating, Evaluating) $\rightarrow$ Furthering (ABC-DEF). The model is 'brain-based' in the aspect of consecutive incorporation of the affective component which is based on limbic system of human brain associated with emotions, the behavioral component which is associated with the occipital lobes performing visual processing, temporal lobes performing functions of language generation and understanding, and parietal lobes, which receive and process sensory information and execute motor activities of the body, and the cognitive component which is based on the prefrontal lobes involved in thinking, planning, judging, and problem solving. On the other hand, the model is 'evolutionary' in the aspect of proceeding according to the processes of the diversifying step to generate variants in each component, the emulating step to test and select useful or valuable things among the variants, and the furthering step to extend or apply the selected things. For three components of ABC, to reflect the importance of emotional factors as a starting point in scientific activity as well as the dominant role of limbic system relative to cortex of brain, the model emphasizes the DARWIN (Driving Affective Realm for Whole Intellectual Network) approach.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.205-225
• /
• 2018

Convolutional Neural Network (ConvNet) is one class of the powerful Deep Neural Network that can analyze and learn hierarchies of visual features. Originally, first neural network (Neocognitron) was introduced in the 80s. At that time, the neural network was not broadly used in both industry and academic field by cause of large-scale dataset shortage and low computational power. However, after a few decades later in 2012, Krizhevsky made a breakthrough on ILSVRC-12 visual recognition competition using Convolutional Neural Network. That breakthrough revived people interest in the neural network. The success of Convolutional Neural Network is achieved with two main factors. First of them is the emergence of advanced hardware (GPUs) for sufficient parallel computation. Second is the availability of large-scale datasets such as ImageNet (ILSVRC) dataset for training. Unfortunately, many new domains are bottlenecked by these factors. For most domains, it is difficult and requires lots of effort to gather large-scale dataset to train a ConvNet. Moreover, even if we have a large-scale dataset, training ConvNet from scratch is required expensive resource and time-consuming. These two obstacles can be solved by using transfer learning. Transfer learning is a method for transferring the knowledge from a source domain to new domain. There are two major Transfer learning cases. First one is ConvNet as fixed feature extractor, and the second one is Fine-tune the ConvNet on a new dataset. In the first case, using pre-trained ConvNet (such as on ImageNet) to compute feed-forward activations of the image into the ConvNet and extract activation features from specific layers. In the second case, replacing and retraining the ConvNet classifier on the new dataset, then fine-tune the weights of the pre-trained network with the backpropagation. In this paper, we focus on using multiple ConvNet layers as a fixed feature extractor only. However, applying features with high dimensional complexity that is directly extracted from multiple ConvNet layers is still a challenging problem. We observe that features extracted from multiple ConvNet layers address the different characteristics of the image which means better representation could be obtained by finding the optimal combination of multiple ConvNet layers. Based on that observation, we propose to employ multiple ConvNet layer representations for transfer learning instead of a single ConvNet layer representation. Overall, our primary pipeline has three steps. Firstly, images from target task are given as input to ConvNet, then that image will be feed-forwarded into pre-trained AlexNet, and the activation features from three fully connected convolutional layers are extracted. Secondly, activation features of three ConvNet layers are concatenated to obtain multiple ConvNet layers representation because it will gain more information about an image. When three fully connected layer features concatenated, the occurring image representation would have 9192 (4096+4096+1000) dimension features. However, features extracted from multiple ConvNet layers are redundant and noisy since they are extracted from the same ConvNet. Thus, a third step, we will use Principal Component Analysis (PCA) to select salient features before the training phase. When salient features are obtained, the classifier can classify image more accurately, and the performance of transfer learning can be improved. To evaluate proposed method, experiments are conducted in three standard datasets (Caltech-256, VOC07, and SUN397) to compare multiple ConvNet layer representations against single ConvNet layer representation by using PCA for feature selection and dimension reduction. Our experiments demonstrated the importance of feature selection for multiple ConvNet layer representation. Moreover, our proposed approach achieved 75.6% accuracy compared to 73.9% accuracy achieved by FC7 layer on the Caltech-256 dataset, 73.1% accuracy compared to 69.2% accuracy achieved by FC8 layer on the VOC07 dataset, 52.2% accuracy compared to 48.7% accuracy achieved by FC7 layer on the SUN397 dataset. We also showed that our proposed approach achieved superior performance, 2.8%, 2.1% and 3.1% accuracy improvement on Caltech-256, VOC07, and SUN397 dataset respectively compare to existing work.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.35 no.3
• /
• pp.41-66
• /
• 2017

The purpose of this research is to empirically trace the junctures of Yigye-gugok managed by Gwan-am Hong Gyeong-mo, a grandson of Yigye Hong Yang-ho who originally designed Yigye-gugok, while reviewing the features of the forms and patterns of gugok. The results of the research are as follows. 1. Ui-dong was part of the domain of the capital during the Chosun dynasty, which also is located in the city of Seoul as a matter of administrative zone. Likewisely, Yigye-gugok is taken as a special meaning for it was one and only gugok. Starting with Mangyeong Waterfall as the $1^{st}$ gok, Yigye follows through the $2^{nd}$ gok of Jeokchwibyeong Rock, the $3^{rd}$ gok of Chanunbong Peak, the $4^{th}$ gok of Jinuigang Rock, the $5^{th}$ gok of Okkyeongdae Rock, the $6^{th}$ gok of Wolyeongdam Pond, the $7^{th}$ gok of Tagyeongam Rock, the $8^{th}$ gok of Myeongoktan Stream, and the $9^{th}$ gok of Jaeganjeong Pavilion. Of these, Mangyeong Waterfall, Chanunbong Peak, and Okkyeongdae Rock are distinct for their locations in as much as their features, while estimated locations for Jinuigang Rock, Wolyeongdam Pond, Myeongoktan Stream, and Jaeganjeong Pavilion were discovered. However, Jeokchwibyeong Rock and Tagyeongam Rock demonstrated multiple locations in close resemblance to documentary literatures within secretive proximity, whereas geography, scenery, and sighted objects were considered to evaluate the 1st estimated location. Through these endeavored, it was possible to identify the shipping routes and structures for the total distance of 2.1km running from the $1^{st}$ gok to the $9^{th}$ gok, which nears Gwanam's description of 5ri(里), or approximately 1.96km for gugok. 2. Set towards the end of the $18^{th}$ century, Yigye-gugok originated from a series of work shaping the space of Hong Yang-ho's tomb into a space for the family. Comparing Yigye-gugok to other gugoks, numerous differences are apparent from beyond the rather more general format such as adjoining the $8^{th}$ gok while paving through the lower directions from the upper directions of the water. This gives rises to the interpretation such that Yigye-gugok was positioned to separate the doman of the family from those of the other families in power, thereby taking over Ui-dong. Yet, the aspect of the possession of the space lends itself to the determination that the location positioned at the $8^{th}$ gok above Mangyeongpok Waterfall representing Wooyi-dong was a consequence of the centrifugal space creation efforts. 3. While writings and poetic works were manufactured in such large quantities in Yigye-gugok whose products of setters and managers seemed intended towards gugok-do and letters carved on the rocks among others, there is yet a tremendous lack of visual media in the same respect. 'Yigye-gugok Daejacheop' Specimens of Handwriting offers the traces of Gwanam's attempts to engrave gakja at the food of Yigye-gugok. This research was able to ascertain that 'Yigye-gugok Daejacheop' Specimens of Handwriting was a product of Hong Yang-ho's collections maintained under the auspices of the National Central Museum, which are renowned for Song Shi-yeol's penmanship.

• Journal of Music and Human Behavior
• /
• v.5 no.1
• /
• pp.67-90
• /
• 2008

This case used MI techniques that give an imagery experience to depressed client's mental resource, and that makes in to verbalism. Also those images are supportive level therapy examples that apply to positive variation. MI is simple word of 'Music and Imagery' with one of psychology cure called GIM(Guided Imagery and Music). It makes client can through to the inner world and search, confront, discern and solve with suitable music. Supportive Level MI is only used from safety level music. Introduction of private session can associate specification feeling, subject, word or image. And those images are guide to positive experience. The First session step of MI program is a prelude that makes concrete goal like first interview. The Second step is a transition that can concretely express about client's story. The third step is induction and music listening. And it helps to associate imagery more easily by used tension relaxation. Also it can search and associate about various imagery from the music. The last step is process that process drawing imagery, talking about personal imagery experience in common with therapist that bring the power by expansion the positive experience. Client A case targets rapport forming(empathy, understanding and support), searching positive recourse(child hood, family), client's emotion and positive support. Music must be used simple tone, repetition melody, steady rhythm and organized by harmony music of what therapist and client's preference. The client used defense mechanism and couldn't control emotion by depression in 1 & 2 sessions. But the result was client A could experience about support and understanding after 3 sessions. After session 4 the client had stable, changed to positive emotion from the negative emotion and found her spontaneous. Therefore, at the session 6, the client recognized that she will have step of positive time at the future. About client B, she established rapport forming(empathy, understanding and support) and searching issues and positive recognition(child hood, family), expression and insight(present, future). The music was comfortable, organizational at the session 1 & 2, but after session 3, its development was getting bigger and the main melody changed variation with high and low of tune. Also it used the classic and romantic music. The client avoids bad personal relations to religious relationship. But at the session 1 & 2, client had supportive experience and empathy because of her favorite, supportive music. After session 3, client B recognized and face to face the present issue. But she had avoidance and face to face of ambivalence. The client B had a experience about emotion change according depression and face to face client's issues After session 4. At the session 5 & 6, client tried to have will power of healthy life and fairly attitude, train mental power and solution attitude in the future. On this wise, MI program had actuality and clients' issues solution more than GIM program. MI can solute the issue by client's based issue without approach to unconsciousness like GIM. Especially it can use variety music and listening time is shorter than GIM and structuralize. Also can express client's emotion very well. So it can use corrective and complement MI program to children, adolescent and adult.

• The Korean Journal of Air & Space Law and Policy
• /
• v.29 no.1
• /
• pp.127-160
• /
• 2014

The UN COPUOS was established in 1959 as a permanent committee of the UN General Assembly with the aims to promote international cooperation in peaceful uses of outer space, to formulate space-related programmes within the UN, to encourage research and dissemination of information on space, and to study legal problems arising from the outer space activities. Its members have been enlarged from 24 members in 1959 to 76 in 2014. The Legal Subcommittee, which has been established under COPUOS in 1962 to deal with legal problems associated with space activities, through its first three decades of work has set up a framework of international space law: the five treaties and agreements - namely the Outer Space Treaty, Rescue Agreement, Liability Convention, Registration Convention, Moon Agreement - and the five declarations and legal principles. However, some sceptical views on this legal framework has been expressed, concerning the applicability of existing international space law to practical issues and new kinds of emerging space activities. UNISPACE III, which took place in 1999, served as a momentum to revitalize the discussions of the legal issues faced by the international community in outer space activities. The agenda of the Legal Subcommittee is currently structured into three categories: regular items, single issue/items, and items considered under a multi-year workplan. The regular items, which deal with basic legal issues, include definition and delimitation of outer space, status and application of the five UN treaties on outer space, and national legislation relevant to the peaceful exploration and use of outer space. The single issues/items, which are decided upon the preceding year, are discussed only for one year in the plenary unless renewed. They include items related to the use of nuclear power sources in outer space and to the space debris mitigation. The agenda items considered under a multi-year work plan are discussed in working group. Items under this category deal with non-legally binding UN instruments on outer space and international mechanism for cooperation. In recent years, the Subcommittee has made some progress on agenda items related to nuclear power sources, space debris, and international cooperation by means of establishing non-legally binding instruments, or soft law. The Republic of Korea became the member state of COPUOS in 2001, after rotating seats every two years with Cuba and Peru since 1994. Korea's joining of COPUOS seems to be late, in considering that some countries with hardly any space activity, such Chad, Sierra Leone, Kenya, Lebanon, Cameroon, joined COPUOS as early as 1960s and 1970s and contributed to the drafting of the aforementioned treaties, declarations, and legal principles. Given the difficulties to conclude a treaty and un urgency to regulate newly emerging space activities, Legal Subcommittee now focuses its effort on developing soft law such as resolutions and guideline to be adopted by UN General Assembly. In order to have its own practices reflected in the international practices, one of the constituent elements of international customary law, Korea should analyse its technical capability, policy, and law related to outer space activities and participate actively in the formation process of the soft law.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.171-196
• /
• 2018

With the development of the web, two-way communication and evaluation became possible and marketing paradigms shifted. In order to meet the needs of consumers, web design trends are continuously responding to consumer feedback. As the web becomes more and more important, both academics and businesses are studying consumer emotions and satisfaction on the web. However, some consumer characteristics are not well considered. Demographic characteristics such as age and sex have been studied extensively, but few studies consider psychological characteristics such as regulatory focus (i.e., emotional regulation). In this study, we analyze the effect of web style on consumer emotion. Many studies analyze the relationship between the web and regulatory focus, but most concentrate on the purpose of web use, particularly motivation and information search, rather than on web style and design. The web communicates with users through visual elements. Because the human brain is influenced by all five senses, both design factors and emotional responses are important in the web environment. Therefore, in this study, we examine the relationship between consumer emotion and satisfaction and web style and design. Previous studies have considered the effects of web layout, structure, and color on emotions. In this study, however, we excluded these web components, in contrast to earlier studies, and analyzed the relationship between consumer satisfaction and emotional indexes of web-style only. To perform this analysis, we collected consumer surveys presenting 40 web style themes to 204 consumers. Each consumer evaluated four themes. The emotional adjectives evaluated by consumers were composed of 18 contrast pairs, and the upper emotional indexes were extracted through factor analysis. The emotional indexes were 'softness,' 'modernity,' 'clearness,' and 'jam.' Hypotheses were established based on the assumption that emotional indexes have different effects on consumer satisfaction. After the analysis, hypotheses 1, 2, and 3 were accepted and hypothesis 4 was rejected. While hypothesis 4 was rejected, its effect on consumer satisfaction was negative, not positive. This means that emotional indexes such as 'softness,' 'modernity,' and 'clearness' have a positive effect on consumer satisfaction. In other words, consumers prefer emotions that are soft, emotional, natural, rounded, dynamic, modern, elaborate, unique, bright, pure, and clear. 'Jam' has a negative effect on consumer satisfaction. It means, consumer prefer the emotion which is empty, plain, and simple. Regulatory focus shows differences in motivation and propensity in various domains. It is important to consider organizational behavior and decision making according to the regulatory focus tendency, and it affects not only political, cultural, ethical judgments and behavior but also broad psychological problems. Regulatory focus also differs from emotional response. Promotion focus responds more strongly to positive emotional responses. On the other hand, prevention focus has a strong response to negative emotions. Web style is a type of service, and consumer satisfaction is affected not only by cognitive evaluation but also by emotion. This emotional response depends on whether the consumer will benefit or harm himself. Therefore, it is necessary to confirm the difference of the consumer's emotional response according to the regulatory focus which is one of the characteristics and viewpoint of the consumers about the web style. After MMR analysis result, hypothesis 5.3 was accepted, and hypothesis 5.4 was rejected. But hypothesis 5.4 supported in the opposite direction to the hypothesis. After validation, we confirmed the mechanism of emotional response according to the tendency of regulatory focus. Using the results, we developed the structure of web-style recommendation system and recommend methods through regulatory focus. We classified the regulatory focus group in to three categories that promotion, grey, prevention. Then, we suggest web-style recommend method along the group. If we further develop this study, we expect that the existing regulatory focus theory can be extended not only to the motivational part but also to the emotional behavioral response according to the regulatory focus tendency. Moreover, we believe that it is possible to recommend web-style according to regulatory focus and emotional desire which consumers most prefer.

• Korean Journal of Heritage: History & Science
• /
• v.39
• /
• pp.95-130
• /
• 2006

Japanese government college researchers, including Sekino Tadashi(關野貞), have conducted research studies and collected data, on overall Korean cultural relics as well as Silla tumuli(新羅古墳) in the early modern times under the Japanese imperialistic rule. They were supported by the Meichi government in the early stage of research, by the Chosun government-general, and by their related organizations after Korea was coIonialized to carry out investigations on Korean antiquities, fine arts, architecture, anthropology, folklore, and so on. The objective for which they prosecuted inquiries into Korean cultural relics, including Silla tumuli, may be attributed to the purport to find out such data as needed for the theoretical foundation to justify their colonialization of Korea. Such a reason often showed locally biased or distorted views. Investigations and surveys had been incessantly carried out by those Japanese scholars who took a keen interest in Korean tumuli and excavated relics since 1886. 'Korea Architecture Survey Reports' conducted in 1904 by Sekino in Korea gives a brief introduction of the contents of Korean tumuli, including the Five Royal Mausoleums(五陵). And in 1906 Imanishi Ryu(今西龍) launched for the first time an excavation survey on Buksan Tumulus(北山古墳) in Sogeumgangsan(小金剛山) and on 'Namchong(南塚)' in Hwangnam-dong, which greatly contributed to the foundation of a basic understanding of Wooden chamber tombs with stone mound(積石木槨墳) and stone chambers with tunnel entrance(橫穴式石室墳). The ground plan and cross section of stone chambers made in 1909 at his excavation survey of seokchimchong(石枕塚) by Yazui Seiyichi(谷井第一) who majored in architecture made a drawing in excavation surveys for the first time in Korea, in which numerical expressions are sharply distinguished from the previous sketched ones. And even in the following excavation surveys this kind of drawing continued. Imanishi and Yazui elucidated that wooden chambers with stone mound chronologically differs from the stone chambers with tunnel entrance on the basis of the results of surveys of the locational characteristics of Silla tumuli, the forms and size of tomb entrance, excavated relics, and so forth. The government-general put in force 'the Historic Spots and Relics Preservation Rules' and 'the Historic Spots Survey Council Regulations' in 1916, establishing 'Historic Spots Survey Council and Museum Conference. When museums initiated their activities, they exhibited those relics excavated from tumuli and conducted surveys of relics with the permission of the Chosun government-general. A gold crown tomb(金冠塚) was excavated and surveyed in 1921 and a seobong tomb(瑞鳳塚) in 1927. Concomitantly with this large size wooden chamber tombs with stone mound attracted strong public attention. Furthermore, a variety of surveys of spots throughout the country were carried out but publication of tumuli had not yet been realized. Recently some researchers's endeavors led to publish unpublished reports. However, the reason why reports of such significant tumuli as seobong tomb had not yet been published may be ascribed to the critical point in those days. The Gyeongju Tumuli Distribution Chart made by Nomori Ken(野守健) on the basis of the land register in the late 1920s seems of much significance in that it specifies the size and locations of 155 tumuli and shows the overall shape of tumuli groups within the city, as used in today's distribution chart. In the 1930s Arimitsu Kyoichi(有光敎一) and Saito Tadashi(齋藤忠) identified through excavation surveys of many wooden chamber tombs with stone mound and stone chambers with tunnel entrance, that there were several forms of tombs in a tomb system. In particular, his excavation survey experience of those wooden chamber tombs with stone mound which were exposed in complicated and overlapped forms show features more developed than that of preceding excavation surveys and reports publication, and so on. The result of having reviewed the contents of many historic spots surveyed at that time. Therefore this reexamination is considered to be a significant project in arranging the history of archaeology in Korea.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.127-148
• /
• 2020

The data center is a physical environment facility for accommodating computer systems and related components, and is an essential foundation technology for next-generation core industries such as big data, smart factories, wearables, and smart homes. In particular, with the growth of cloud computing, the proportional expansion of the data center infrastructure is inevitable. Monitoring the health of these data center facilities is a way to maintain and manage the system and prevent failure. If a failure occurs in some elements of the facility, it may affect not only the relevant equipment but also other connected equipment, and may cause enormous damage. In particular, IT facilities are irregular due to interdependence and it is difficult to know the cause. In the previous study predicting failure in data center, failure was predicted by looking at a single server as a single state without assuming that the devices were mixed. Therefore, in this study, data center failures were classified into failures occurring inside the server (Outage A) and failures occurring outside the server (Outage B), and focused on analyzing complex failures occurring within the server. Server external failures include power, cooling, user errors, etc. Since such failures can be prevented in the early stages of data center facility construction, various solutions are being developed. On the other hand, the cause of the failure occurring in the server is difficult to determine, and adequate prevention has not yet been achieved. In particular, this is the reason why server failures do not occur singularly, cause other server failures, or receive something that causes failures from other servers. In other words, while the existing studies assumed that it was a single server that did not affect the servers and analyzed the failure, in this study, the failure occurred on the assumption that it had an effect between servers. In order to define the complex failure situation in the data center, failure history data for each equipment existing in the data center was used. There are four major failures considered in this study: Network Node Down, Server Down, Windows Activation Services Down, and Database Management System Service Down. The failures that occur for each device are sorted in chronological order, and when a failure occurs in a specific equipment, if a failure occurs in a specific equipment within 5 minutes from the time of occurrence, it is defined that the failure occurs simultaneously. After configuring the sequence for the devices that have failed at the same time, 5 devices that frequently occur simultaneously within the configured sequence were selected, and the case where the selected devices failed at the same time was confirmed through visualization. Since the server resource information collected for failure analysis is in units of time series and has flow, we used Long Short-term Memory (LSTM), a deep learning algorithm that can predict the next state through the previous state. In addition, unlike a single server, the Hierarchical Attention Network deep learning model structure was used in consideration of the fact that the level of multiple failures for each server is different. This algorithm is a method of increasing the prediction accuracy by giving weight to the server as the impact on the failure increases. The study began with defining the type of failure and selecting the analysis target. In the first experiment, the same collected data was assumed as a single server state and a multiple server state, and compared and analyzed. The second experiment improved the prediction accuracy in the case of a complex server by optimizing each server threshold. In the first experiment, which assumed each of a single server and multiple servers, in the case of a single server, it was predicted that three of the five servers did not have a failure even though the actual failure occurred. However, assuming multiple servers, all five servers were predicted to have failed. As a result of the experiment, the hypothesis that there is an effect between servers is proven. As a result of this study, it was confirmed that the prediction performance was superior when the multiple servers were assumed than when the single server was assumed. In particular, applying the Hierarchical Attention Network algorithm, assuming that the effects of each server will be different, played a role in improving the analysis effect. In addition, by applying a different threshold for each server, the prediction accuracy could be improved. This study showed that failures that are difficult to determine the cause can be predicted through historical data, and a model that can predict failures occurring in servers in data centers is presented. It is expected that the occurrence of disability can be prevented in advance using the results of this study.