• 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.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.63-83
• /
• 2019

Investors prefer to look for trading points based on the graph shown in the chart rather than complex analysis, such as corporate intrinsic value analysis and technical auxiliary index analysis. However, the pattern analysis technique is difficult and computerized less than the needs of users. In recent years, there have been many cases of studying stock price patterns using various machine learning techniques including neural networks in the field of artificial intelligence(AI). In particular, the development of IT technology has made it easier to analyze a huge number of chart data to find patterns that can predict stock prices. Although short-term forecasting power of prices has increased in terms of performance so far, long-term forecasting power is limited and is used in short-term trading rather than long-term investment. Other studies have focused on mechanically and accurately identifying patterns that were not recognized by past technology, but it can be vulnerable in practical areas because it is a separate matter whether the patterns found are suitable for trading. When they find a meaningful pattern, they find a point that matches the pattern. They then measure their performance after n days, assuming that they have bought at that point in time. Since this approach is to calculate virtual revenues, there can be many disparities with reality. The existing research method tries to find a pattern with stock price prediction power, but this study proposes to define the patterns first and to trade when the pattern with high success probability appears. The M & W wave pattern published by Merrill(1980) is simple because we can distinguish it by five turning points. Despite the report that some patterns have price predictability, there were no performance reports used in the actual market. The simplicity of a pattern consisting of five turning points has the advantage of reducing the cost of increasing pattern recognition accuracy. In this study, 16 patterns of up conversion and 16 patterns of down conversion are reclassified into ten groups so that they can be easily implemented by the system. Only one pattern with high success rate per group is selected for trading. Patterns that had a high probability of success in the past are likely to succeed in the future. So we trade when such a pattern occurs. It is a real situation because it is measured assuming that both the buy and sell have been executed. We tested three ways to calculate the turning point. The first method, the minimum change rate zig-zag method, removes price movements below a certain percentage and calculates the vertex. In the second method, high-low line zig-zag, the high price that meets the n-day high price line is calculated at the peak price, and the low price that meets the n-day low price line is calculated at the valley price. In the third method, the swing wave method, the high price in the center higher than n high prices on the left and right is calculated as the peak price. If the central low price is lower than the n low price on the left and right, it is calculated as valley price. The swing wave method was superior to the other methods in the test results. It is interpreted that the transaction after checking the completion of the pattern is more effective than the transaction in the unfinished state of the pattern. Genetic algorithms(GA) were the most suitable solution, although it was virtually impossible to find patterns with high success rates because the number of cases was too large in this simulation. We also performed the simulation using the Walk-forward Analysis(WFA) method, which tests the test section and the application section separately. So we were able to respond appropriately to market changes. In this study, we optimize the stock portfolio because there is a risk of over-optimized if we implement the variable optimality for each individual stock. Therefore, we selected the number of constituent stocks as 20 to increase the effect of diversified investment while avoiding optimization. We tested the KOSPI market by dividing it into six categories. In the results, the portfolio of small cap stock was the most successful and the high vol stock portfolio was the second best. This shows that patterns need to have some price volatility in order for patterns to be shaped, but volatility is not the best.

• Proceedings of the Korea Environmental Mutagen Society Conference
• /
• 2003.10a
• /
• pp.34-63
• /
• 2003

Occupational and environmental exposure to manganese continue to represent a realistic public health problem in both developed and developing countries. Increased utility of MMT as a replacement for lead in gasoline creates a new source of environmental exposure to manganese. It is, therefore, imperative that further attention be directed at molecular neurotoxicology of manganese. A Need for a more complete understanding of manganese functions both in health and disease, and for a better defined role of manganese in iron metabolism is well substantiated. The in-depth studies in this area should provide novel information on the potential public health risk associated with manganese exposure. It will also explore novel mechanism(s) of manganese-induced neurotoxicity from the angle of Mn-Fe interaction at both systemic and cellular levels. More importantly, the result of these studies will offer clues to the etiology of IPD and its associated abnormal iron and energy metabolism. To achieve these goals, however, a number of outstanding questions remain to be resolved. First, one must understand what species of manganese in the biological matrices plays critical role in the induction of neurotoxicity, Mn(II) or Mn(III)? In our own studies with aconitase, Cpx-I, and Cpx-II, manganese was added to the buffers as the divalent salt, i.e., $MnCl_2$. While it is quite reasonable to suggest that the effect on aconitase and/or Cpx-I activites was associated with the divalent species of manganese, the experimental design does not preclude the possibility that a manganese species of higher oxidation state, such as Mn(III), is required for the induction of these effects. The ionic radius of Mn(III) is 65 ppm, which is similar to the ionic size to Fe(III) (65 ppm at the high spin state) in aconitase (Nieboer and Fletcher, 1996; Sneed et al., 1953). Thus it is plausible that the higher oxidation state of manganese optimally fits into the geometric space of aconitase, serving as the active species in this enzymatic reaction. In the current literature, most of the studies on manganese toxicity have used Mn(II) as $MnCl_2$ rather than Mn(III). The obvious advantage of Mn(II) is its good water solubility, which allows effortless preparation in either in vivo or in vitro investigation, whereas almost all of the Mn(III) salt products on the comparison between two valent manganese species nearly infeasible. Thus a more intimate collaboration with physiochemists to develop a better way to study Mn(III) species in biological matrices is pressingly needed. Second, In spite of the special affinity of manganese for mitochondria and its similar chemical properties to iron, there is a sound reason to postulate that manganese may act as an iron surrogate in certain iron-requiring enzymes. It is, therefore, imperative to design the physiochemical studies to determine whether manganese can indeed exchange with iron in proteins, and to understand how manganese interacts with tertiary structure of proteins. The studies on binding properties (such as affinity constant, dissociation parameter, etc.) of manganese and iron to key enzymes associated with iron and energy regulation would add additional information to our knowledge of Mn-Fe neurotoxicity. Third, manganese exposure, either in vivo or in vitro, promotes cellular overload of iron. It is still unclear, however, how exactly manganese interacts with cellular iron regulatory processes and what is the mechanism underlying this cellular iron overload. As discussed above, the binding of IRP-I to TfR mRNA leads to the expression of TfR, thereby increasing cellular iron uptake. The sequence encoding TfR mRNA, in particular IRE fragments, has been well-documented in literature. It is therefore possible to use molecular technique to elaborate whether manganese cytotoxicity influences the mRNA expression of iron regulatory proteins and how manganese exposure alters the binding activity of IPRs to TfR mRNA. Finally, the current manganese investigation has largely focused on the issues ranging from disposition/toxicity study to the characterization of clinical symptoms. Much less has been done regarding the risk assessment of environmenta/occupational exposure. One of the unsolved, pressing puzzles is the lack of reliable biomarker(s) for manganese-induced neurologic lesions in long-term, low-level exposure situation. Lack of such a diagnostic means renders it impossible to assess the human health risk and long-term social impact associated with potentially elevated manganese in environment. The biochemical interaction between manganese and iron, particularly the ensuing subtle changes of certain relevant proteins, provides the opportunity to identify and develop such a specific biomarker for manganese-induced neuronal damage. By learning the molecular mechanism of cytotoxicity, one will be able to find a better way for prediction and treatment of manganese-initiated neurodegenerative diseases.

• Journal of Korea Water Resources Association
• /
• v.55 no.10
• /
• pp.723-736
• /
• 2022

In this study, monthly precipitation forecasting models that can predict up to 12 months in advance were constructed for the Geum River basin, and two statistical techniques, multiple linear regression (MLR) and artificial neural network (ANN), were applied to the model construction. As predictor candidates, a total of 47 climate indices were used, including 39 global climate patterns provided by the National Oceanic and Atmospheric Administration (NOAA) and 8 meteorological factors for the basin. Forecast models were constructed by using climate indices with high correlation by analyzing the teleconnection between the monthly precipitation and each climate index for the past 40 years based on the forecast month. In the goodness-of-fit test results for the average value of forecasts of each month for 1991 to 2021, the MLR models showed -3.3 to -0.1% for the percent bias (PBIAS), 0.45 to 0.50 for the Nash-Sutcliffe efficiency (NSE), and 0.69 to 0.70 for the Pearson correlation coefficient (r), whereas, the ANN models showed PBIAS -5.0~+0.5%, NSE 0.35~0.47, and r 0.64~0.70. The mean values predicted by the MLR models were found to be closer to the observation than the ANN models. The probability of including observations within the forecast range for each month was 57.5 to 83.6% (average 72.9%) for the MLR models, and 71.5 to 88.7% (average 81.1%) for the ANN models, indicating that the ANN models showed better results. The tercile probability by month was 25.9 to 41.9% (average 34.6%) for the MLR models, and 30.3 to 39.1% (average 34.7%) for the ANN models. Both models showed long-term predictability of monthly precipitation with an average of 33.3% or more in tercile probability. In conclusion, the difference in predictability between the two models was found to be relatively small. However, when judging from the hit rate for the prediction range or the tercile probability, the monthly deviation for predictability was found to be relatively small for the ANN models.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_1
• /
• pp.1449-1463
• /
• 2020

As recent global warming and climate changes become more serious, the importance of CO2 absorption by forests is increasing to cope with the greenhouse gas issues. According to the UN Framework Convention on Climate Change, it is required to calculate national CO2 absorptions at the local level in a more scientific and rigorous manner. This paper presents the gridded expansion of forest flux observations and mapping of daily CO2 absorption by the forests in Korea using numerical weather prediction data and satellite images. To consider the sensitive daily changes of plant photosynthesis, we built a machine learning model to retrieve the daily RACA (reference amount of CO2 absorption) by referring to the climax forest in Gwangneung and adopted the NIFoS (National Institute of Forest Science) lookup table for the CO2 absorption by forest type and age to produce the daily AACA (actual amount of CO2 absorption) raster data with the spatial variation of the forests in Korea. In the experiment for the 1,095 days between Jan 1, 2013 and Dec 31, 2015, our RACA retrieval model showed high accuracy with a correlation coefficient of 0.948. To achieve the tier 3 daily statistics for AACA, long-term and detailed forest surveying should be combined with the model in the future.

• Journal of Korea Water Resources Association
• /
• v.56 no.5
• /
• pp.311-323
• /
• 2023

In order to reduce disaster damage by localized heavy rains, floods, and urban inundation, it is important to know in advance whether natural disasters occur. Currently, heavy rain watch and heavy rain warning by the criteria of the Korea Meteorological Administration are being issued in Korea. However, since this one criterion is applied to the whole country, we can not clearly recognize heavy rain damage for a specific region in advance. Therefore, in this paper, we tried to reset the current criteria for a special weather report which considers the regional characteristics and to predict the damage caused by rainfall after 1 hour. The study area was selected as Gyeonggi-province, where has more frequent heavy rain damage than other regions. Then, the rainfall inducing disaster or hazard-triggering rainfall was set by utilizing hourly rainfall and heavy rain damage data, considering the local characteristics. The heavy rain damage prediction model was developed by a decision tree model and a random forest model, which are machine learning technique and by rainfall inducing disaster and rainfall data. In addition, long short-term memory and deep neural network models were used for predicting rainfall after 1 hour. The predicted rainfall by a developed prediction model was applied to the trained classification model and we predicted whether the rain damage after 1 hour will be occurred or not and we called this as 1ST-Model. The 1ST-Model can be used for preventing and preparing heavy rain disaster and it is judged to be of great contribution in reducing damage caused by heavy rain.

• Journal of Korea Water Resources Association
• /
• v.56 no.12
• /
• pp.981-992
• /
• 2023

Due to recent global climate change, the scale of flood damage is increasing as rainfall is concentrated and its intensity increases. Rain on a scale that has not been observed in the past may fall, and long-term rainy seasons that have not been recorded may occur. These damages are also concentrated in ASEAN countries, and many people in ASEAN countries are affected, along with frequent occurrences of flooding due to typhoons and torrential rains. In particular, the Bandung region which is located in the Upper Chitarum River basin in Indonesia has topographical characteristics in the form of a basin, making it very vulnerable to flooding. Accordingly, through the Official Development Assistance (ODA), a flood forecasting and warning system was established for the Upper Citarium River basin in 2017 and is currently in operation. Nevertheless, the Upper Citarium River basin is still exposed to the risk of human and property damage in the event of a flood, so efforts to reduce damage through fast and accurate flood forecasting are continuously needed. Therefore, in this study an artificial intelligence-based river flood water level forecasting model for Dayeu Kolot as a target station was developed by using 10-minute hydrological data from 4 rainfall stations and 1 water level station. Using 10-minute hydrological observation data from 6 stations from January 2017 to January 2021, learning, verification, and testing were performed for lead time such as 0.5, 1, 2, 3, 4, 5 and 6 hour and LSTM was applied as an artificial intelligence algorithm. As a result of the study, good results were shown in model fit and error for all lead times, and as a result of reviewing the prediction accuracy according to the learning dataset conditions, it is expected to be used to build an efficient artificial intelligence-based model as it secures prediction accuracy similar to that of using all observation stations even when there are few reference stations.

• Journal of the Korea Concrete Institute
• /
• v.24 no.4
• /
• pp.481-490
• /
• 2012

Evaluation of chloride penetration is very important, because induced chloride ion causes corrosion in embedded steel. Diffusion coefficient obtained from rapid chloride penetration test is currently used, however this method cannot provide a correct prediction of chloride content since it shows only ion migration velocity in electrical field. Apparent diffusion coefficient of chloride ion based on simple Fick's Law can provide a total chloride penetration magnitude to engineers. This study proposes an analysis technique to predict chloride penetration using apparent diffusion coefficient of chloride ion from neural network (NN) algorithm and time-dependent diffusion phenomena. For this work, thirty mix proportions with the related diffusion coefficients are studied. The components of mix proportions such as w/b ratio, unit content of cement, slag, fly ash, silica fume, and fine/coarse aggregate are selected as neurons, then learning for apparent diffusion coefficient is trained. Considering time-dependent diffusion coefficient based on Fick's Law, the technique for chloride penetration analysis is proposed. The applicability of the technique is verified through test results from short, long term submerged test, and field investigations. The proposed technique can be improved through NN learning-training based on the acquisition of various mix proportions and the related diffusion coefficients of chloride ion.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.1
• /
• pp.77-85
• /
• 2020

Currently, life-cycle cost analysis methods are introduced to maintain large infrastructure facilities in Korea. However, there are not many cases in which maintenance models are applied that reflect conditions such as the location of a facility and its surroundings. In order to establish an appropriate maintenance strategy, a cost prediction, deterioration model, and a decision model reflecting uncertainty should be established. In this study, an economic analysis model was developed for long-term cost planning and management based on user decisions based on maintenance methods and judgment criteria for painting specifications applied to power generation structures. The performance of the paintwork was assessed through the paint deterioration test for the application of the economic analysis model, and the results of the economic analysis according to the applied paint specifications (Urethan, polysiloxane, fluorine) were verified by applying the proposed economic analysis model. In this study, it is believed that the selection of the repair cycle and evaluation methods applied with the development model rather than the performance of the painting can be expected to be used as basic data for the maintenance cycle, even if it is not limited to the painting.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.19 no.3
• /
• pp.120-129
• /
• 2017

Agrometeorological advisories for farms and orchards are issued when daily weather exceeds a predefined range of the local reference climate, which is a long-term average of daily weather for the location. The reference climate at local scales is prepared by various simplification methods, resulting in uncertainty in the agrometeorological advisories. We restored daily weather data for the 1981-2010 period and analyzed the differences in prediction results of weather risk by comparing with the temporal and spatial simplified normal climate values. For this purpose, we selected the agricultural drought index (ADI) among various disaster related indices because ADI requires many kinds of weather data to calculate it. Ten rural counties within the Seomjin River Basin were selected for this study. The normal value of 'temporal simplification' was calculated by using the daily average value for 30 years (1981-2010). The normal value of 'spatial simplification' is the zonal average of the temporally simplified normal values falling within a standard watershed. For residual moisture index, temporal simplification normal values were overestimated, whereas spatial simplification normal values were underestimated in comparison with non-simplified normal values. The ADI's calculated from January to July 2017 showed a significant deviation in terms of the extent of drought depending on the normal values used. Through this study, we confirmed that the result of weather risk calculation using normal climatic values from 'simplified' methods can affect reliability of the agrometeorological advisories.