• Title/Summary/Keyword: 수용 후 이용

Search Result 757, Processing Time 0.028 seconds

Transition of Rice Culture Practices during Chosun Dynasty through Old References V. Cultivation and Cropping Patterns (주요 고농서를 통한 조선시대의 도작기술 전개 과정 연구 V. 재배양식)

  • Lee, Sung-Kyum;Guh, Ja-Ok;Lee, Eun-Woong;Lee, Hong-Suk
    • KOREAN JOURNAL OF CROP SCIENCE
    • /
    • v.37 no.1
    • /
    • pp.104-115
    • /
    • 1992
  • The rice culture techniques included 'Jodosukyungbeob'(旱稻水耕法 : culture techniques of early-ripening paddy rice), 'Mandosukyungbeob' (晩稻水耕法) : culture techniques of late-Ripening paddy rice 'Handobeob'(旱稻<山稻>法 : culture techniques of upland rice), 'Myojongbeob'(苗種法 : culture techniques of paddy rice by transplanting), 'Kunangbeob'(乾秧法 : culture techniques of rice by transplanting which rears seeding in dry paddy) and 'Sudogunpanongbeob'(水稻乾播農法 : culture techniques of paddy rice seeding in dry field). Especially, 'Kunangbeob' and 'Sudogunpanongbeob' were originally developed in Korea as seen in 1600s(Kyoungje : 經濟) and early 1800s (Yoji : 要旨). In 'Jodosukyungbeob' it took 9 days for seed dipping, water-sprouting and prevent damage by birds, each for 3 days in China, but in Korea seed dipping in water took 3 days and the rest of the procedures were flexibly established. In matured soils, practices were fall plowing right after harvest, recognition of effective tillering and additional fertilization use of human manure, and stimulation of sprouting by lime application. The unique culture techniques adequate for Korean situations were practiced, which included weed control after draining accurately for 3 to 4 times, draining at mid season for improving wind and drought tolerance, rice harvesting at appropriate time for preventing grain shattering, and seeding in rows. 'Mandosukyungbeob' was improved techniques contrast to those of China, and the major contents were selection of proper varieties, good stand establishment by seeding high rates, induction of vigorous tillers, and adoption of 'Jokjongbeob'(足種法 : seeding method by foot). Also, one of the most prominent rice cultures by our ancestors was 'Kunpanongbeob' that was systemized form habitual practice of Pyongan Province. The unique technique actualized was 'Hando [旱稻(山稻)]' culture technique which was the combinations of 'Jokjongbeob', root stimulation method, and disaster-tolerant mixture cropping with adoptation of variety theory, although it was originated from China. The transplanting techniques has come before 'Jikseol'($\ulcorner$直說$\lrcorner$) and its merits were sufficiently realized. However, this method was basically prohibited from the early Chosun dynasty because extremely bad harvest was expected under drought conditions and insufficient conditions of water storage. But, it was permitted in the areas that contained water all the times and in case of large-scale farming especially. Most of rice culture was transplanted in the end of the Chosun dynasty because transplanting was continuously spreaded in the three southern provinces of Korea. Under these circumstances, transplanting technique was improved from the early to the end of the Chosun dynasty by weed control, fertilizing, water management, and quadratic transplanting. Based on these techniques, agricultural productivity was improved 5 times by that time. 'Kunpanongbeob' was created and developed properly for Korean conditions that is dry in early season and flooding in late season. This was successively developed and established into transplanting technique of nursery seedling.

  • PDF

A study on the simulation method for the flushing flowrate and velocity in the watermain using a hydrant and a drain valve (소화전과 이토변을 이용한 플러싱 적용 시 관 내 세척유량과 유속 모의 방안에 관한 연구)

  • Gim, ARin;Lee, Eunhwan;Lee, SongI;Kim, kwang hyun;Jun, Hwandon
    • Journal of Korea Water Resources Association
    • /
    • v.55 no.spc1
    • /
    • pp.1251-1260
    • /
    • 2022
  • Recently, due to the deterioration of watermains and the detachment of scale which is accumulated on the watermain surface, water quality accidents in a water supply network occur frequently. As scale accumulated on watermains is stabilized, it may not cause water quality accidents under the normal operating condition. However, due to water hammer or transient flow caused by the abrupt velocity and/or direction of flow change, it can be detached from the watermain surface resulting in water quality accidents. To prevent these kinds of water quality accidents, it is required to remove scale by watermain cleaning regularly. Many researches about flushing which is the most popular water cleaning method are focused on the desirable velocity criteria and the cleaning condition to accomplish the effect of flushing whereas less amount of research effort is given to develop a method to consider whether the desirable velocity for flushing can be obtained before flushing is performed. During flushing, the major and minor headloss is occurred when flushing water flows through a hydrant or drain valve. These headloss may slow down the velocity of flushing water so that it can reduce the flushing effect. Thus, in this study, we suggest a method to simulate the flow velocity of flushing water using "MinorLoss Coefficient" and "Emitter Coefficient" in EPANET. The suggested method is applied to a sample network and the water supply network of "A" city in Korea to compare the flushing effect between "flushing through a hydrant" and "flushing through a drain valve". In case of "flushing through a hydrant", if the hydraulic condition ocurring from a watermain pipe connecting to the inlet pipe of a hydrant to the outlet of a hydrant is not considered, the actual flowrate and velocity of a flow is less than the simulated flowrate and velocity of a flow. In case of "flushing through a drain valve", the flushing velocity and flowrate can be easily simulated and the difference between the simulated and the actual velocity and flowrate is not significant. Also, "flushing through a drain valve" is very effective to flushing a long-length pipe section because of its efficiency to obtain the flushing velocity. However, the number and location of a drain valve is limited compared to a hydrant so that "flushing through a drain valve" has a limited application in the field. For this reason, the engineer should consider various field conditions to come up with a proper flushing plan.

Development of a Simultaneous Analytical Method for Determination of Insecticide Broflanilide and Its Metabolite Residues in Agricultural Products Using LC-MS/MS (LC-MS/MS를 이용한 농산물 중 살충제 Broflanilide 및 대사물질 동시시험법 개발)

  • Park, Ji-Su;Do, Jung-Ah;Lee, Han Sol;Park, Shin-min;Cho, Sung Min;Kim, Ji-Young;Shin, Hye-Sun;Jang, Dong Eun;Jung, Yong-hyun;Lee, Kangbong
    • Journal of Food Hygiene and Safety
    • /
    • v.34 no.2
    • /
    • pp.124-134
    • /
    • 2019
  • An analytical method was developed for the determination of broflanilide and its metabolites in agricultural products. Sample preparation was conducted using the QuEChERS (Quick, Easy, Cheap, Effective, Rugged and Safe) method and LC-MS/MS (liquid chromatograph-tandem mass spectrometer). The analytes were extracted with acetonitrile and cleaned up using d-SPE (dispersive solid phase extraction) sorbents such as anhydrous magnesium sulfate, primary secondary amine (PSA) and octadecyl ($C_{18}$). The limit of detection (LOD) and quantification (LOQ) were 0.004 and 0.01 mg/kg, respectively. The recovery results for broflanilide, DM-8007 and S(PFP-OH)-8007 ranged between 90.7 to 113.7%, 88.2 to 109.7% and 79.8 to 97.8% at different concentration levels (LOQ, 10LOQ, 50LOQ) with relative standard deviation (RSD) less than 8.8%. The inter-laboratory study recovery results for broflanilide and DM-8007 and S (PFP-OH)-8007 ranged between 86.3 to 109.1%, 87.8 to 109.7% and 78.8 to 102.1%, and RSD values were also below 21%. All values were consistent with the criteria ranges requested in the Codex guidelines (CAC/GL 40-1993, 2003) and the Food and Drug Safety Evaluation guidelines (2016). Therefore, the proposed analytical method was accurate, effective and sensitive for broflanilide determination in agricultural commodities.

Experimental Studies on the Antitumor Effects of Jinryungtang Gagambang Extract (진령탕가감방의 항종양효과(抗腫瘍效果)에 관(關)한 실험적(實驗的) 연구(硏究))

  • Jeong, Jun-Tak;Moon, Goo;Moon, Suk-Jae
    • THE JOURNAL OF KOREAN ORIENTAL ONCOLOGY
    • /
    • v.4 no.1
    • /
    • pp.37-53
    • /
    • 1998
  • The sprig of Jinryungtang Gagambang has been used for curing as a traditional medicine without any experimental evidence to support the rational basis for their clinical use. This experiment was carried out to evaluate the possible therapeutic or antitumoral effects of Jinryungtang Gagambang extract against cancer, and to study some mechanisms responsible for its effect. The cytotoxic and antitumor effects were evaluated on human cell liens (A549, hep3B, Caki-1, Sarcoma 180) after exposure to Jinryungtang Gagambang extract using in ILS, colony forming efficency and SRB assay which were regarded as a valuable method for cytotoxic and antitumor effects of unknown compound on tumor cell lines. The results obtained in this studies were as follows. 1. As a result of exposure to Jinryungtang Gagambang extract, the proliferation of A549, hep3B, Caki-1, good correlations were shown from the results of SRB assay and those of clogenetic assay. 2. The oral administration of Jinryungtang Gagambang extract showed significant effects of increase of MST(mean survival time) and ILS(increased life span) depending on the increasing concentration. 3. Against squamous cell carcinoma induced by MCA, Jinryungtang Gagambang decreased not only the frequency of tumor production but also the number and weight of tumors per tumor bearing mice(TBM). Jinryungtang Gagambang also significantly suppressed the development of 3LL cell-implanted tumors by frequency and their size, and some developed tumors were regressed by the continuous treatment of Jinryungtang Gagambang extract into TBM. 4. Jinryungtang Gagambang extract also increased NK cell activities. According to the above results, it could be suggested that Jinryungtang Gagambang extract has prominent antiutmor effect.

  • PDF

A Study on the Forest Land System in the YI Dynasty (이조시대(李朝時代)의 임지제도(林地制度)에 관(關)한 연구(硏究))

  • Lee, Mahn Woo
    • Journal of Korean Society of Forest Science
    • /
    • v.22 no.1
    • /
    • pp.19-48
    • /
    • 1974
  • Land was originally communized by a community in the primitive society of Korea, and in the age of the ancient society SAM KUK-SILLA, KOKURYOE and PAEK JE-it was distributed under the principle of land-nationalization. But by the occupation of the lands which were permitted to transmit from generation to generation as Royal Grant Lands and newly cleared lands, the private occupation had already begun to be formed. Thus the private ownership of land originated by chiefs of the tribes had a trend to be gradually pervaded to the communal members. After the, SILLA Kingdom unified SAM KUK in 668 A.D., JEONG JEON System and KWAN RYO JEON System, which were the distribution systems of farmlands originated from the TANG Dynasty in China, were enforced to established the basis of an absolute monarchy. Even in this age the forest area was jointly controlled and commonly used by village communities because of the abundance of area and stocked volume, and the private ownership of the forest land was prohibited by law under the influence of the TANG Dynasty system. Toward the end of the SILLA Dynasty, however, as its centralism become weak, the tendency of the private occupancy of farmland by influential persons was expanded, and at the same time the occupancy of the forest land by the aristocrats and Buddhist temples began to come out. In the ensuing KORYO Dynasty (519 to 1391 A.D.) JEON SI KWA System under the principle of land-nationalization was strengthened and the privilege of tax collection was transferred to the bureaucrats and the aristocrats as a means of material compensation for them. Taking this opportunity the influential persons began to expand their lands for the tax collection on a large scale. Therefore, about in the middle of 11th century the farmlands and the forest lands were annexed not only around the vicinity of the capital but also in the border area by influential persons. Toward the end of the KORYO Dynasty the royal families, the bureaucrats and the local lords all possessed manors and occupied the forest lands on a large scale as a part of their farmlands. In the KORYO Dynasty, where national economic foundation was based upon the lands, the disorder of the land system threatened the fall of the Dynasty and so the land reform carried out by General YI SEONG-GYE had led to the creation of ensuing YI Dynasty. All systems of the YI Dynasty were substantially adopted from those of the KORYO Dynasty and thereby KWA JEON System was enforced under the principle of land-nationalization, while the occupancy or the forest land was strictly prohibited, except the national or royal uses, by the forbidden item in KYEONG JE YUK JEON SOK JEON, one of codes provided by the successive kings in the YI Dynasty. Thus the basis of the forest land system through the YI Dynasty had been established, while the private forest area possessed by influential persons since the previous KORYO Dynasty was preserved continuously under the influence of their authorities. Therefore, this principle of the prohibition was nothing but a legal fiction for the security of sovereign powers. Consequently the private occupancy of the forest area was gradually enlarged and finally toward the end of YI Dynasty the privately possessed forest lands were to be officially authorized. The forest administration systems in the YI Dynasty are summarized as follows: a) KEUM SAN and BONG SAN. Under the principle of land-nationalization by a powerful centralism KWA JEON System was established at the beginning of the YI Dynasty and its government expropriated all the forests and prohibited strictly the private occupation. In order to maintain the dignity of the royal capital, the forests surounding capital areas were instituted as KEUM SAN (the reserved forests) and the well-stocked natural forest lands were chosen throughout the nation by the government as BONG SAN(national forests for timber production), where the government nominated SAN JIK(forest rangers) and gave them duties to protect and afforest the forests. This forest reservation system exacted statute labors from the people of mountainious districts and yet their commons of the forest were restricted rigidly. This consequently aroused their strong aversion against such forest reservation, therefore those forest lands were radically spoiled by them. To settle this difficult problem successive kings emphasized the preservation of the forests repeatedly, and in KYEONG KUK DAI JOEN, the written constitution of the YI Dynasty, a regulation for the forest preservation was provided but the desired results could not be obtained. Subsequently the split of bureaucrats with incessant feuds among politicians and scholars weakened the centralism and moreover, the foreign invasions since 1592 made the national land devasted and the rural communities impoverished. It happned that many wandering peasants from rural areas moved into the deep forest lands, where they cultivated burnt fields recklessly in the reserved forest resulting in the severe damage of the national forests. And it was inevitable for the government to increase the number of BONG SAN in order to solve the problem of the timber shortage. The increase of its number accelerated illegal and reckless cutting inevitably by the people living mountainuos districts and so the government issued excessive laws and ordinances to reserve the forests. In the middle of the 18th century the severe feuds among the politicians being brought under control, the excessive laws and ordinances were put in good order and the political situation became temporarily stabilized. But in spite of those endeavors evil habitudes of forest devastation, which had been inveterate since the KORYO Dynasty, continued to become greater in degree. After the conclusion of "the Treaty of KANG WHA with Japan" in 1876 western administration system began to be adopted, and thereafter through the promulgation of the Forest Law in 1908 the Imperial Forests were separated from the National Forests and the modern forest ownership system was fixed. b) KANG MU JANG. After the reorganization of the military system, attaching importance to the Royal Guard Corps, the founder of the YI Dynasty, TAI JO (1392 to 1398 A.D.) instituted the royal preserves-KANG MU JANG-to attain the purposes for military training and royal hunting, prohibiting strictly private hunting, felling and clearing by the rural inhabitants. Moreover, the tyrant, YEON SAN (1495 to 1506 A.D.), expanded widely the preserves at random and strengthened its prohibition, so KANG MU JANG had become the focus of the public antipathy. Since the invasion of Japanese in 1592, however, the innovation of military training methods had to be made because of the changes of arms and tactics, and the royal preserves were laid aside consequently and finally they had become the private forests of influential persons since 17th century. c) Forests for official use. All the forests for official use occupied by government officies since the KORYO Dynasty were expropriated by the YI Dynasty in 1392, and afterwards the forests were allotted on a fixed standard area to the government officies in need of firewoods, and as the forest resources became exhausted due to the depredated forest yield, each office gradually enlarged the allotted area. In the 17th century the national land had been almost devastated by the Japanese invasion and therefore each office was in the difficulty with severe deficit in revenue, thereafter waste lands and forest lands were allotted to government offices inorder to promote the land clearing and the increase in the collections of taxes. And an abuse of wide occupation of the forests by them was derived and there appeared a cause of disorder in the forest land system. So a provision prohibiting to allot the forests newly official use was enacted in 1672, nevertheless the government offices were trying to enlarge their occupied area by encroaching the boundary and this abuse continued up to the end of the YI Dynasty. d) Private forests. The government, at the bigninning of the YI Dynasty, expropriated the forests all over the country under the principle of prohibition of private occupancy of forest lands except for the national uses, while it could not expropriate completely all of the forest lands privately occupied and inherited successively by bureaucrats, and even local governors could not control them because of their strong influences. Accordingly the King, TAI JONG (1401 to 1418 A.D.), legislated the prohibition of private forest occupancy in his code, KYEONG JE YUK JEON (1413), and furthermore he repeatedly emphasized to observe the law. But The private occupancy of forest lands was not yet ceased up at the age of the King, SE JO (1455 to 1468 A.D.), so he prescribed the provision in KYEONG KUK DAI JEON (1474), an immutable law as a written constitution in the YI Dynasty: "Anyone who privately occupy the forest land shall be inflicted 80 floggings" and he prohibited the private possession of forest area even by princes and princesses. But, it seemed to be almost impossible for only one provsion in a code to obstruct the historical growing tendecy of private forest occupancy, for example, the King, SEONG JONG (1470 to 1494 A.D.), himself granted the forests to his royal families in defiance of the prohibition and thereafter such precedents were successively expanded, and besides, taking advantage of these facts, the influential persons openly acquired their private forest lands. After tyrannical rule of the King, YEON SAN (1945 to 1506 A.D.), the political disorder due to the splits to bureaucrats with successional feuds and the usurpations of thrones accelerated the private forest occupancy in all parts of the country, thus the forbidden clause on the private forest occupancy in the law had become merely a legal fiction since the establishment of the Dynasty. As above mentioned, after the invasion of Japanese in 1592, the courts of princes (KUNG BANGG) fell into the financial difficulties, and successive kings transferred the right of tax collection from fisherys and saltfarms to each KUNG BANG and at the same time they allotted the forest areas in attempt to promote the clearing. Availing themselves of this opportunity, royal families and bureaucrats intended to occupy the forests on large scale. Besides a privilege of free selection of grave yard, which had been conventionalized from the era of the KORYO Dynasty, created an abuse of occuping too wide area for grave yards in any forest at their random, so the King, TAI JONG, restricted the area of grave yard and homestead of each family. Under the policy of suppresion of Buddhism in the YI Dynasty a privilege of taxexemption for Buddhist temples was deprived and temple forests had to follow the same course as private forests did. In the middle of 18th century the King, YEONG JO (1725 to 1776 A.D.), took an impartial policy for political parties and promoted the spirit of observing laws by putting royal orders and regulations in good order excessively issued before, thus the confused political situation was saved, meanwhile the government officially permittd the private forest ownership which substantially had already been permitted tacitly and at the same time the private afforestation areas around the grave yards was authorized as private forests at least within YONG HO (a boundary of grave yard). Consequently by the enforcement of above mentioned policies the forbidden clause of private forest ownership which had been a basic principle of forest system in the YI Dynasty entireely remained as only a historical document. Under the rule of the King, SUN JO (1801 to 1834 A.D.), the political situation again got into confusion and as the result of the exploitation from farmers by bureaucrats, the extremely impoverished rural communities created successively wandering peasants who cleared burnt fields and deforested recklessly. In this way the devastation of forests come to the peak regardless of being private forests or national forests, moreover, the influential persons extorted private forests or reserved forests and their expansion of grave yards became also excessive. In 1894 a regulation was issued that the extorted private forests shall be returned to the initial propriators and besides taking wide area of the grave yards was prohibited. And after a reform of the administrative structure following western style, a modern forest possession system was prepared in 1908 by the forest law including a regulation of the return system of forest land ownership. At this point a forbidden clause of private occupancy of forest land got abolished which had been kept even in fictitious state since the foundation of the YI Dynasty. e) Common forests. As above mentioned, the forest system in the YI Dynasty was on the ground of public ownership principle but there was a high restriction to the forest profits of farmers according to the progressive private possession of forest area. And the farmers realized the necessity of possessing common forest. They organized village associations, SONGE or KEUM SONGE, to take the ownerless forests remained around the village as the common forest in opposition to influential persons and on the other hand, they prepared the self-punishment system for the common management of their forests. They made a contribution to the forest protection by preserving the common forests in the late YI Dynasty. It is generally known that the absolute monarchy expr opriates the widespread common forests all over the country in the process of chainging from thefeudal society to the capitalistic one. At this turning point in Korea, Japanese colonialists made public that the ratio of national and private forest lands was 8 to 2 in the late YI Dynasty, but this was merely a distorted statistics with the intention of rationalizing of their dispossession of forests from Korean owners, and they took advantage of dead forbidden clause on the private occupancy of forests for their colonization. They were pretending as if all forests had been in ownerless state, but, in truth, almost all the forest lands in the late YI Dynasty except national forests were in the state of private ownership or private occupancy regardless of their lawfulness.

  • PDF

Studies on the Repeated Toxicity Test of Food Red No.2 for 4 Weeks Oral Administration in SD Rat (SD랫드에서 식용색소 적색2호의 4주간 경구투여에 따른 반복독성시험에 관한 연구)

  • Yoo, Jin-Gon;Jung, Ji-Youn
    • Journal of Food Hygiene and Safety
    • /
    • v.27 no.1
    • /
    • pp.42-49
    • /
    • 2012
  • This study was carried out to investigate the toxicity of food Red No.2 in the Sprague-Dawley (SD) female rat for 4 weeks. SD rats were orally administered for 28 days, with dosage of 500, 1,000, 2,000 mg/kg/day. Animals treated with food Red No.2 did not cause any death and show any clinical signs. They did not show any significant changes of body weight, feed uptake and water consumption. There were not significantly different from the control group in urinalysis, hematological, serum biochemical value and histopathological examination. In conclusion, 4 weeks of the repetitive oral medication of food Red No.2 has resulted no alteration of toxicity according to the test materials in the group of female rats with injection of 2,000 mg/kg. Therefore, food Red No.2 was not indicated to have any toxic effect in the SD rats, when it was orally administered below the dosage 2,000 mg/kg/day for 4 weeks.

Development of a complex failure prediction system using Hierarchical Attention Network (Hierarchical Attention Network를 이용한 복합 장애 발생 예측 시스템 개발)

  • Park, Youngchan;An, Sangjun;Kim, Mintae;Kim, Wooju
    • 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.