• Journal of Intelligence and Information Systems
• /
• v.16 no.4
• /
• pp.159-172
• /
• 2010

The recommender system is one of the possible solutions to assist customers in finding the items they would like to purchase. To date, a variety of recommendation techniques have been developed. One of the most successful recommendation techniques is Collaborative Filtering (CF) that has been used in a number of different applications such as recommending Web pages, movies, music, articles and products. CF identifies customers whose tastes are similar to those of a given customer, and recommends items those customers have liked in the past. Numerous CF algorithms have been developed to increase the performance of recommender systems. Broadly, there are memory-based CF algorithms, model-based CF algorithms, and hybrid CF algorithms which combine CF with content-based techniques or other recommender systems. While many researchers have focused their efforts in improving CF performance, the theoretical justification of CF algorithms is lacking. That is, we do not know many things about how CF is done. Furthermore, the relative performances of CF algorithms are known to be domain and data dependent. It is very time-consuming and expensive to implement and launce a CF recommender system, and also the system unsuited for the given domain provides customers with poor quality recommendations that make them easily annoyed. Therefore, predicting the performances of CF algorithms in advance is practically important and needed. In this study, we propose an efficient approach to predict the performance of CF. Social Network Analysis (SNA) and Artificial Neural Network (ANN) are applied to develop our prediction model. CF can be modeled as a social network in which customers are nodes and purchase relationships between customers are links. SNA facilitates an exploration of the topological properties of the network structure that are implicit in data for CF recommendations. An ANN model is developed through an analysis of network topology, such as network density, inclusiveness, clustering coefficient, network centralization, and Krackhardt's efficiency. While network density, expressed as a proportion of the maximum possible number of links, captures the density of the whole network, the clustering coefficient captures the degree to which the overall network contains localized pockets of dense connectivity. Inclusiveness refers to the number of nodes which are included within the various connected parts of the social network. Centralization reflects the extent to which connections are concentrated in a small number of nodes rather than distributed equally among all nodes. Krackhardt's efficiency characterizes how dense the social network is beyond that barely needed to keep the social group even indirectly connected to one another. We use these social network measures as input variables of the ANN model. As an output variable, we use the recommendation accuracy measured by F1-measure. In order to evaluate the effectiveness of the ANN model, sales transaction data from H department store, one of the well-known department stores in Korea, was used. Total 396 experimental samples were gathered, and we used 40%, 40%, and 20% of them, for training, test, and validation, respectively. The 5-fold cross validation was also conducted to enhance the reliability of our experiments. The input variable measuring process consists of following three steps; analysis of customer similarities, construction of a social network, and analysis of social network patterns. We used Net Miner 3 and UCINET 6.0 for SNA, and Clementine 11.1 for ANN modeling. The experiments reported that the ANN model has 92.61% estimated accuracy and 0.0049 RMSE. Thus, we can know that our prediction model helps decide whether CF is useful for a given application with certain data characteristics.

• Journal of Distribution Research
• /
• v.15 no.1
• /
• pp.25-47
• /
• 2010

CS is one of the major concerns of managers in the world because it is well known to be a key medium construct for firms' superior outcome. One of the major agents for CS management is retailers. Firms try to manage not only employees but also retailers to promote CS behaviors. And so diverse incentives are used to promote their CS behaviors under diverse channel setting such as multi-channel. However in spite of the rising needs there has been scarce studies on the optimal incentive structure for a manufacturer to offer competing retailers at the multi-channel. In this paper, we try to find better way for a manufacturer to promote the competing retailers' CS behaviors. We investigated how to promote the retailers' CS behavior via game-theoretic modeling. Especially, we focus on the possible incentive, CS bonus type reward introduced in the studies of Hauser, Simester, and Wernerfelt(1994) and Chu and Desai(1995). We build up a multi stage complete information game and derive a subgame perfect equilibrium using backward induction. Stages of the game are as following. (Stage 1) Manufacturer sets wholesale price(w) and CS bonus($\eta$). (Stage 2) Both retailers in competition set CS effort level($e_i$) and retail price($p_i$) simultaneously. (Stage 3) Consumers make purchasing decisions based on the manufacturer's initial reputation and retailers' CS efforts.

• Journal of Korean Society of Forest Science
• /
• v.82 no.3
• /
• pp.235-245
• /
• 1993

This study was carried out to understand the stand structure based on the compositional characteristics of natural deciduous forest dominated by Quercus species, which will provide with fundamental ecological and silvicultural information for effective forest management. Of two tracts selected from the Seoul National University Research Forests, one is located in Kwangju-Gun Kyunggi-Do, and the other in Kwangyang-Gun Chollanam-Do. Point-quarter sampling method w-as employed to survey woody vegetation confined to larger than 6cm in DBH. The numbers of sample points were 152 and 187, in Kwangju-Gun and Kwangyang-Gun, respectively. Comparative analysis for two forest tracts was made as follows ; 1) species composition by calculation of importance values ; 2) number of stems per hectare for major tree species ; 3) species diversity for the forests in two locations ; 4) inter-species association based on $X^2$ test. The relative dominate of Quercus speices showed 88% at Kwangju-Gun, Kyunggi-Do and 50% at Kwangy-ang-Gun. Chollanam-Do. Such high dominance occurred due to high importance values of Quercus variahilis and Q. mortgolica in both locations. Quercus serrata showed low value at Kwangju-Gun. Kyunggi-Do whereas Q. acutissirna, Q. dentata and Q. aliena did none at Kwangyang-Gun. Chollanam-Do. The species diversity and evenness in oak communities exhibited 0.82 and 0.61, respectively at Kwangju-Gun. Kyunggi-Do, while those did 1.09 and 0.73 at Kwangyang-Gun, Chollanam-Do. Therefore, it was considered that Ku-angju-Gun region was disturbed severely by human activities but Kwangyang-Gun region eras less disturbed. Frequent appearance of Carpinus and Acer species indicates increase in diversities and better development of succession at Kwangyang-Gun region.

• KDI Journal of Economic Policy
• /
• v.13 no.4
• /
• pp.91-116
• /
• 1991

Market liberalization progressing simultaneously with high and rapidly rising domestic wages has created an adverse business environment for domestic firms. Korean firms are losing their international competitiveness in comparison to firms from LDC(Less Developed Countries) in low-tech industries. In high-tech industries, domestic firms without government protection (which is impossible due to the liberalization policy and the current international status of the Korean economy) are in a disadvantaged position relative to firms from advanced countries. This paper examines the division of roles between the private sector and the government in order to achieve a successful structural adjustment, which has become the impending industrial policy issue caused by high domestic wages, on the one hand, and the opening of domestic markets, on the other. The micro foundation of the economy-wide structural adjustment is actually the restructuring of business portfolios at the firm level. The firm-level business restructuring means that firms in low-value-added businesses or with declining market niches establish new major businesses in higher value-added segments or growing market niches. The adjustment of the business structure at the firm level can only be accomplished by accumulating firm-specific managerial assets necessary to establish a new business structure. This can be done through learning-by-doing in the whole system of management, including research and development, manufacturing, and marketing. Therefore, the voluntary cooperation among the people in the company is essential for making the cost of the learning process lower than that at the competing companies. Hence, firms that attempt to restructure their major businesses need to induce corporate-wide participation through innovations in organization and management, encourage innovative corporate culture, and maintain cooperative labor unions. Policy discussions on structural adjustments usually regard firms as a black box behind a few macro variables. But in reality, firm activities are not flows of materials but relationships among human resources. The growth potential of companies are embodied in the human resources of the firm; the balance of interest among stockholders, managers, and workers of the company' brings the accumulation of the company's core competencies. Therefore, policymakers and economists shoud change their old concept of the firm as a technological black box which produces a marketable commodities. Firms should be regarded as coalitions of interest groups such as stockholders, managers, and workers. Consequently the discussion on the structural adjustment both at the macroeconomic level and the firm level should be based on this new paradigm of understanding firms. The government's role in reducing the cost of structural adjustment and supporting should the creation of new industries emphasize the following: First, government must promote the competition in domestic markets by revising laws related to antitrust policy, bankruptcy, and the promotion of small and medium-sized companies. General consensus on the limitations of government intervention and the merit of deregulation should be sought among policymakers and people in the business world. In the age of internationalization, nation-specific competitive advantages cannot be exclusively in favor of domestic firms. The international competitiveness of a domestic firm derives from the firm-specific core competencies which can be accumulated by internal investment and organization of the firm. Second, government must build up a solid infrastructure of production factors including capital, technology, manpower, and information. Structural adjustment often entails bankruptcies and partial waste of resources. However, it is desirable for the government not to try to sustain marginal businesses, but to support the diversification or restructuring of businesses by assisting in factor creation. Institutional support for venture businesses needs to be improved, especially in the financing system since many investment projects in venture businesses are highly risky, even though they are very promising. The proportion of low-value added production processes and declining industries should be reduced by promoting foreign direct investment and factory automation. Moreover, one cannot over-emphasize the importance of future-oriented labor policies to be based on the new paradigm of understanding firm activities. The old laws and instititutions related to labor unions need to be reformed. Third, government must improve the regimes related to money, banking, and the tax system to change business practices dependent on government protection or undesirable in view of the evolution of the Korean economy as a whole. To prevent rational business decisions from contradicting to the interest of the economy as a whole, government should influence the business environment, not the business itself.

• Korean Journal of Ecology and Environment
• /
• v.34 no.1 s.93
• /
• pp.30-44
• /
• 2001

In this study limnological characteristics of Lake Juam was surveyed from June 1993 to May 1994 in order to provides important information regarding water resources. Secchi disc transparency, epilimnetic chlorophyll a (chi-a), total nitrogen (TN), total phosphorus (TP) concentration and primary productivity were in the range of $2.0{\sim}4.5\;m$, $0.9{\sim}13.6\;mgChl/m^3$, 0.78$\{sim}$2.32 mgN/l, $11{\sim}56\;mgP/m^3$, $270{\sim}2.160\;mgCm^{-2}\;day^{-1}$, respectively. On the basis of TP, Chl-a and Secchi disc depth, the trophic state of Lake Juam can be classied as mesotrophic lake. The phosphorus inputs from non-point sources are concentrated in heavy rain episodes during the monsoon season. As a result, phosphorus concentration are higher in summer than in winter. TP loading from the watershed were estimated to be $0.9\;gPm^{-2}yr^{-1}$, which correspond to a boundary of the critical loading ($1.0\;gPm^{-2}yr^{-1}$) for eutrophication. From the results of the algal assay, both phosphous and nitrogen act as limiting nutrients in algal growth. The seasonal succession of phytoplankton community structure in Lake Juam was similar to that observed in other temperate lakes. Diatoms (Asterionella formosa and Aulacoseira granulate var. angustissima)fujacofeira BraHuJafa uar. aHgusHrsiaia) weredominant in spring and winter, cyanobacteria) were dominant in warm season. The organic carbon, nitrogen and phosphorus content of lake sediment were $9.5{\sim}14.0\;mgC/g$, $1.01{\sim}1.82\;mgN/g$ and $0.51{\sim}0.65\;mgP/g$, respectively. The allochthonous organic carbon loading from the watershed and autochthonous organic carbon loading by primary production of phytoplankton were determined to be 1,122 tC/yr and 6,718 tC/yr, respectively. To prevent eutrophication of Lake Juam, nutrient management of watershed should be focus on reduction of fertilizer application, proper treatment of manure, and conservation of topsoil as well as point source.

• Journal of Agricultural Extension & Community Development
• /
• v.20 no.4
• /
• pp.1045-1078
• /
• 2013

The purpose of the present study is to improve the effectiveness of Korea's ODA projects on agricultural technology transfer to Africa. This study investigates agricultural extension system of African countries and provides a direction of the systematic strategies of the Korean ODAs on agricultural technology. This study pays particular attention on Africanization of agricultural technology transfer of the Korean ODA strategies. Unlike the previous studies focusing mainly on micro level investigation on the ODA strategy development, the present study incorporates the agricultural technology dissemination system of Ethiopia and Uganda in a macro perspective to develop a desirable form of the ODA strategy. The findings illustrate that the technology dissemination systems of the case countries have different characteristics depending on the function and organization of extension agency. And their functional capability and role segmentation by the extension agency are differently configured, too. In case of Ethiopia, top-down structure for the agricultural extension system has been built. Farmers' group and field agent of the information delivery system has expanded their participation into the system. However, we also find that the system of Ethiopia still lacks effective use of its existing technology, since it puts more emphasis on management aspects than improvement of agricultural productivity for farmers. On the other hand, even though Uganda has established participatory extension system that encompasses the entire agencies of the extension system, government efforts to enhance the extension system are still concentrated on expanding research functions rather than technical dissemination. The results imply that promoting and strengthening localization of the ODA strategy has to be developed to make localization policy of the Korean ODA. The present study concludes with some specific policy implications for necessary conditions of the agricultural development in African countries.

• Korean Journal of Ecology and Environment
• /
• v.33 no.3 s.91
• /
• pp.187-196
• /
• 2000

This paper describes a simple method that uses differences among Carlson's (1977) trophic state index (TSI) values based on total phosphorus (TP), chlorophyll a (CHL) and Secchi depth (SD) to draw inferences regarding the factors that are limiting to phytoplankton growth and the composition of lake seston. Examples are provided regarding seasonal and spatial patterns in a large subtropical lake (Lake Okeechobee, Florida, USA) and inter- and intra-lake variations from a multilake data set developed from published studies. Once an investigator has collected routine water quality data and established TSI values based on TP, CHL, and SD, a number of inferences can be made. Additional information can be provided where it also is possible to calculate a TSI based on total nitrogen (TN). Where TSI (CHL)<>TSI (SD), light attenuating particles are large (large filaments or colonies of algae), and the phytoplankton may be limited by zooplankton grazing. Other limiting conditions are inferred by different relationships between the TSI values. Results of this study indicate that the analysis is quite robust, and that it generally gives good agreement with conclusions based on more direct methods (e.g., nutrientaddition bioassays, zooplankton size data, zooplankton removal experiments). The TSI approach, when validated periodically with these more costly and time-intensive methods, provides an effective, low cost method for tracking long-term changes in pelagic structure and function with potential value in monitoring lake ecology and responses to management.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.34 no.4
• /
• pp.57-65
• /
• 2016

Maeul-soop(Village forest) is a key element of Korean traditional village landscape historically and culturally. However, a number of Maeul-soops have been lost or declined due to various influences since the modern age. For this Maeul-soop that has a variety of conservation values including historical, cultural and ecological ones, attention and efforts for a systematic conservation and restoration of Maeul-soop are needed. The purpose of the present study is to provide information on ecological restoration and sustainable use and management of Maeul-soops based on component plant species, habitat and location characteristics of 499 Maeul-soops spread throughout Korea. Major six categories of threat factors to Maeul-soop ecosystem were identified and the influence of each factor was evaluated. For the evaluation of weight by threat factors for the influence on the vulnerability of Maeul-soop ecosystem, more three-dimensional analysis was conducted using Analytic Hierarchy Process (AHP) analysis method. In the results of evaluation using AHP analysis method, reduction of area, among six categories, was spotted as the biggest threat to existence of Maeul-soops. Next, changes in topography and soil environment were considered as a threat factor of qualitative changes in Maeul-soop ecosystem. Influence of vegetation structure and its qualitative changes on the loss or decline of Masul-soop was evaluated to be lower than that of changes in habitat. Based on weight of each factor, the figures were converted with 100 points being the highest score and the evaluation of vulnerability of Maeul-soop was conducted with the converted figures. In the result of evaluation of vulnerability of Maeul-soops, grade III showed the highest frequency and a normal distribution was formed from low grade to high grade. 38 Maeul-soops were evaluated as grade I which showed high naturality and 10 Maeul-soops were evaluated as grade V as their maintenance was threatened. Also in the results of evaluation of vulnerability of each Maeul-soop, restoration of Maeul-soop's own area was found as top priority to guarantee the sustainability of Maeul-soops. It was confirmed that there was a need to prepare a national level ecological response strategy for each vulnerability factor of Maeul-soop, which was important national ecological resources.

• Korean Chemical Engineering Research
• /
• v.60 no.3
• /
• pp.347-355
• /
• 2022

The safety valve (PSV) is a safety device that automatically releases a spring when the pressure generated by various causes reaches the set pressure, and is restored to a normal state when the pressure falls below a certain level. Periodic inspection and monitoring of safety valves are essential so that they can operate normally in abnormal conditions such as pressure rise. However, as the current safety inspection is performed only at a set period, it is difficult to ensure the safety of normal operation. Therefore, evaluation items were developed by finding failure modes and causative factors of safety valves required for safety management. In addition, it is intended to provide decision-making information for securing safety by deriving the priority of items. To this end, a Delphi survey was conducted three times to derive evaluation factors that were judged to be important in relation to the Failure Mode Cause Factor (FMCFs) of the safety valve (PSV) targeting 15 experts. As a result, 6 failure modes of the safety valve and 22 evaluation factors of its sub-factors were selected. In order to analyze the priorities of the evaluation factors selected in this way, the hierarchical structure was schematized, and the hierarchical decision-making method (AHP) was applied to the priority calculation. As a result of the analysis, the failure mode priorities of FMCFs were 'Leakage' (0.226), 'Fail to open' (0.201), 'Fail to relieve req'd capacity' (0.152), 'Open above set pressure' (0.149), 'Spuriously' 'open' (0.146) and 'Stuck open' (0.127) were confirmed in the order. The lower priority of FMCFs is 'PSV component rupture' (0.109), 'Fail to PSV size calculation' (0.068), 'PSV Spring aging' (0.065), 'Erratic opening' (0.059), 'Damage caused by improper installation and handling' (0.058), 'Fail to spring' (0.053), etc. were checked in the order. It is expected that through efficient management of FMCFs that have been prioritized, it will be possible to identify vulnerabilities of safety valves and contribute to improving safety.

• 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.