• Journal of Intelligence and Information Systems
• /
• v.21 no.3
• /
• pp.101-116
• /
• 2015

Recently, due to the development of smart devices and social media, vast amounts of information with the various forms were accumulated. Particularly, considerable research efforts are being directed towards analyzing unstructured big data to resolve various social problems. Accordingly, focus of data-driven decision-making is being moved from structured data analysis to unstructured one. Also, in the field of recommendation system, which is the typical area of data-driven decision-making, the need of using unstructured data has been steadily increased to improve system performance. Approaches to improve the performance of recommendation systems can be found in two aspects- improving algorithms and acquiring useful data with high quality. Traditionally, most efforts to improve the performance of recommendation system were made by the former approach, while the latter approach has not attracted much attention relatively. In this sense, efforts to utilize unstructured data from variable sources are very timely and necessary. Particularly, as the interests of users are directly connected with their needs, identifying the interests of the user through unstructured big data analysis can be a crew for improving performance of recommendation systems. In this sense, this study proposes the methodology of improving recommendation system by measuring interests of the user. Specially, this study proposes the method to quantify interests of the user by analyzing user's internet usage patterns, and to predict user's repurchase based upon the discovered preferences. There are two important modules in this study. The first module predicts repurchase probability of each category through analyzing users' purchase history. We include the first module to our research scope for comparing the accuracy of traditional purchase-based prediction model to our new model presented in the second module. This procedure extracts purchase history of users. The core part of our methodology is in the second module. This module extracts users' interests by analyzing news articles the users have read. The second module constructs a correspondence matrix between topics and news articles by performing topic modeling on real world news articles. And then, the module analyzes users' news access patterns and then constructs a correspondence matrix between articles and users. After that, by merging the results of the previous processes in the second module, we can obtain a correspondence matrix between users and topics. This matrix describes users' interests in a structured manner. Finally, by using the matrix, the second module builds a model for predicting repurchase probability of each category. In this paper, we also provide experimental results of our performance evaluation. The outline of data used our experiments is as follows. We acquired web transaction data of 5,000 panels from a company that is specialized to analyzing ranks of internet sites. At first we extracted 15,000 URLs of news articles published from July 2012 to June 2013 from the original data and we crawled main contents of the news articles. After that we selected 2,615 users who have read at least one of the extracted news articles. Among the 2,615 users, we discovered that the number of target users who purchase at least one items from our target shopping mall 'G' is 359. In the experiments, we analyzed purchase history and news access records of the 359 internet users. From the performance evaluation, we found that our prediction model using both users' interests and purchase history outperforms a prediction model using only users' purchase history from a view point of misclassification ratio. In detail, our model outperformed the traditional one in appliance, beauty, computer, culture, digital, fashion, and sports categories when artificial neural network based models were used. Similarly, our model outperformed the traditional one in beauty, computer, digital, fashion, food, and furniture categories when decision tree based models were used although the improvement is very small.

• Journal of Intelligence and Information Systems
• /
• v.18 no.1
• /
• pp.125-141
• /
• 2012

These days, the malicious attacks and hacks on the networked systems are dramatically increasing, and the patterns of them are changing rapidly. Consequently, it becomes more important to appropriately handle these malicious attacks and hacks, and there exist sufficient interests and demand in effective network security systems just like intrusion detection systems. Intrusion detection systems are the network security systems for detecting, identifying and responding to unauthorized or abnormal activities appropriately. Conventional intrusion detection systems have generally been designed using the experts' implicit knowledge on the network intrusions or the hackers' abnormal behaviors. However, they cannot handle new or unknown patterns of the network attacks, although they perform very well under the normal situation. As a result, recent studies on intrusion detection systems use artificial intelligence techniques, which can proactively respond to the unknown threats. For a long time, researchers have adopted and tested various kinds of artificial intelligence techniques such as artificial neural networks, decision trees, and support vector machines to detect intrusions on the network. However, most of them have just applied these techniques singularly, even though combining the techniques may lead to better detection. With this reason, we propose a new integrated model for intrusion detection. Our model is designed to combine prediction results of four different binary classification models-logistic regression (LOGIT), decision trees (DT), artificial neural networks (ANN), and support vector machines (SVM), which may be complementary to each other. As a tool for finding optimal combining weights, genetic algorithms (GA) are used. Our proposed model is designed to be built in two steps. At the first step, the optimal integration model whose prediction error (i.e. erroneous classification rate) is the least is generated. After that, in the second step, it explores the optimal classification threshold for determining intrusions, which minimizes the total misclassification cost. To calculate the total misclassification cost of intrusion detection system, we need to understand its asymmetric error cost scheme. Generally, there are two common forms of errors in intrusion detection. The first error type is the False-Positive Error (FPE). In the case of FPE, the wrong judgment on it may result in the unnecessary fixation. The second error type is the False-Negative Error (FNE) that mainly misjudges the malware of the program as normal. Compared to FPE, FNE is more fatal. Thus, total misclassification cost is more affected by FNE rather than FPE. To validate the practical applicability of our model, we applied it to the real-world dataset for network intrusion detection. The experimental dataset was collected from the IDS sensor of an official institution in Korea from January to June 2010. We collected 15,000 log data in total, and selected 10,000 samples from them by using random sampling method. Also, we compared the results from our model with the results from single techniques to confirm the superiority of the proposed model. LOGIT and DT was experimented using PASW Statistics v18.0, and ANN was experimented using Neuroshell R4.0. For SVM, LIBSVM v2.90-a freeware for training SVM classifier-was used. Empirical results showed that our proposed model based on GA outperformed all the other comparative models in detecting network intrusions from the accuracy perspective. They also showed that the proposed model outperformed all the other comparative models in the total misclassification cost perspective. Consequently, it is expected that our study may contribute to build cost-effective intelligent intrusion detection systems.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.39-54
• /
• 2013

Recent explosive increase of electronic commerce provides many advantageous purchase opportunities to customers. In this situation, customers who do not have enough knowledge about their purchases, may accept product recommendations. Product recommender systems automatically reflect user's preference and provide recommendation list to the users. Thus, product recommender system in online shopping store has been known as one of the most popular tools for one-to-one marketing. However, recommender systems which do not properly reflect user's preference cause user's disappointment and waste of time. In this study, we propose a novel recommender system which uses data mining and multi-model ensemble techniques to enhance the recommendation performance through reflecting the precise user's preference. The research data is collected from the real-world online shopping store, which deals products from famous art galleries and museums in Korea. The data initially contain 5759 transaction data, but finally remain 3167 transaction data after deletion of null data. In this study, we transform the categorical variables into dummy variables and exclude outlier data. The proposed model consists of two steps. The first step predicts customers who have high likelihood to purchase products in the online shopping store. In this step, we first use logistic regression, decision trees, and artificial neural networks to predict customers who have high likelihood to purchase products in each product group. We perform above data mining techniques using SAS E-Miner software. In this study, we partition datasets into two sets as modeling and validation sets for the logistic regression and decision trees. We also partition datasets into three sets as training, test, and validation sets for the artificial neural network model. The validation dataset is equal for the all experiments. Then we composite the results of each predictor using the multi-model ensemble techniques such as bagging and bumping. Bagging is the abbreviation of "Bootstrap Aggregation" and it composite outputs from several machine learning techniques for raising the performance and stability of prediction or classification. This technique is special form of the averaging method. Bumping is the abbreviation of "Bootstrap Umbrella of Model Parameter," and it only considers the model which has the lowest error value. The results show that bumping outperforms bagging and the other predictors except for "Poster" product group. For the "Poster" product group, artificial neural network model performs better than the other models. In the second step, we use the market basket analysis to extract association rules for co-purchased products. We can extract thirty one association rules according to values of Lift, Support, and Confidence measure. We set the minimum transaction frequency to support associations as 5%, maximum number of items in an association as 4, and minimum confidence for rule generation as 10%. This study also excludes the extracted association rules below 1 of lift value. We finally get fifteen association rules by excluding duplicate rules. Among the fifteen association rules, eleven rules contain association between products in "Office Supplies" product group, one rules include the association between "Office Supplies" and "Fashion" product groups, and other three rules contain association between "Office Supplies" and "Home Decoration" product groups. Finally, the proposed product recommender systems provides list of recommendations to the proper customers. We test the usability of the proposed system by using prototype and real-world transaction and profile data. For this end, we construct the prototype system by using the ASP, Java Script and Microsoft Access. In addition, we survey about user satisfaction for the recommended product list from the proposed system and the randomly selected product lists. The participants for the survey are 173 persons who use MSN Messenger, Daum Caf$\acute{e}$, and P2P services. We evaluate the user satisfaction using five-scale Likert measure. This study also performs "Paired Sample T-test" for the results of the survey. The results show that the proposed model outperforms the random selection model with 1% statistical significance level. It means that the users satisfied the recommended product list significantly. The results also show that the proposed system may be useful in real-world online shopping store.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.44 no.4
• /
• pp.45-56
• /
• 2016

In this study, an analysis has been conducted on the evaluation criteria of current G-SEED(Green Standard for Energy and Environmental Design) and on the 78 buildings, certified by G-SEED, for 3 years from November, 2012 to November, 2015. Based on the results of this analysis, four issues are driven and proposed hereinafter. Issue 1 : Nowadays, the psychological proportion of landscape architecture in building is getting greater than ever so that it shows reliable reduction of carbon dioxide. Therefore, so far as the eight kinds of buildings are concerned, the evaluation items of G-SEED must include those of landscape architecture mandatorily through its enlargement. Issue 2 : It is undesirable factor that inhibits precise evaluation on landscaping area to let other areas appraise landscape architecture because it requires outstanding professionalism. So, G-SEED should not only ensure landscaping professionalism for the correct evaluation but also let landscape area participate in assessing other areas. Issue 3 : Many previous researches turned out that landscape planting technique has excellent effect on saving energy and reducing temperature of buildings. Thus, landscape planting technique of landscape area is required to be one of the evaluation items of energy sector. Issue 4 : Tree management also has to be newly included as one of the evaluation factor for the maintenance relating to the landscape architecture. G-SEED, enacted and enforced by the Green Building Creation Support Act in 2013, surely is effective system to reduce carbon dioxide in buildings. This is a special Act in its nature that is superior to Construction Law and must be observed by all means to construct buildings. Under the umbrella of this legal system, various of researches and products are contributing to creating new jobs in construction area. However, it is a well-known fact that landscape architecture area has shown less interest on this Act than that of construction area. In conclusion, it is necessary that landscape industry should conduct continuous researches on G-SEED and pay more attention to the Act enough to harvest related products and enlarge its work area.

• Korean Journal of Soil Science and Fertilizer
• /
• v.36 no.3
• /
• pp.163-179
• /
• 2003

Multifunctionality of agriculture which is not traded on the market now has been an important international issue in that it environmental and public benefits. We carried out to modify and to update the function of upland farming on flood prevention and fostering water resources. Economic values of environmental benefits were evaluated by replacement cost methods. Models to evaluate the function of preventing flood were selected as: (1)precipitation(flood-inducing) - runoff(A), (2) soil depth ${\times}$ soil air phase, (3) precipitation (flood-inducing) - runoff(B), (4) soil depth ${\times}$ effective porosity of soil. Models to estimate the function of fostering water resources were (1) saturated hydraulic conductivity (Ks) ${\times}$ duration of saturation(days) ${\times}$ (1-ratio of water flow directly into river), (2) precipitation ${\times}$ ratio of water fostered by rain resources ${\times}$ (area of upland/total land area), and (3) soil water retention quantity(under standing crop or tree) - SWRQ(in bare soil). Function of preventing flood was $883Mg\;ha^{-1}$ of water per year and 645 million Mg for the whole upland area. Function of fostering water resources was $94.1Mg\;ha^{-1}$ of water per year and 69 million Mg for the whole upland area. The value of flood-preventing function evaluated by replacement cost methods was estimated 1,428 billion won per year as compared to the cost for dam construction. The value of water resource fostering were estimated 8.6 billion won in the price of living water.

• Journal of Korean Society of Forest Science
• /
• v.110 no.3
• /
• pp.341-354
• /
• 2021

A large part of Gapyeong is occupied by Korean pine (Pinus koraiensis) and Japanese larch (Larix kaempferi) plantations. Abies holophylla stands are scattered throughout Gapyeong, but little information on their distribution is available. This study explored the potential of succession from planted species to native A. holophylla in plantations. Trees were inventoried and regeneration of A. holoplhylla and stand management history were examined in Korean pine, Japanese larch, and A. holophylla-dominated stands. The importance percentage of A. holophylla was the highest among species with a range of 36.1% to 79.1% in all stands and the density of A. holophylla in understory (DBH <2 cm or <1.3 m height) ranged from 50 to 5,820 trees ha^-1. Non-metric multidimensional scaling classified stands into four types, AN, AP, AM, and P. The AN type showed a reverse J-shape DBH distribution, which was similar to that in natural A. holophylla stands. Both AP and AM types included Korean pine plantations with A. holophylla seed trees within stands. For AP, A. holophylla competed with planted species in overstory and deciduous broadleaved species in understory. The AM type was once thinned from below, thus stem density in the mid DBH classes was lower than upper or lower DBH classes. The P type consisted of plantations without A. holophylla seed trees. However, understory regeneration of A. holophylla was abundant through seed supply from A. holophylla in adjacent stands. Plantations with A. holophylla seed trees within or in adjacent stands showed vigorous natural regeneration of A. holophylla, highlighting the potential for succession from planted species to native A. holophylla in the Gapyeong area. Further studies can help develop techniques to restore plantations to native species-dominated natural stands using ecological succession.

• Journal of Bio-Environment Control
• /
• v.28 no.1
• /
• pp.66-77
• /
• 2019

The present study investigated pine trees, which forms a major plantation species in Korea, with the objective of improving the survival rate of pine trees after planting. Growth responses and characteristics were assessed by controlling the level of fertilizer application, which is a basic controlling the growth of pine seedlings, to identify the optimal fertilization treatment. Pine tree seedlings were grown in 104 containers and were examined 8 weeks after planting. Stem height and were measured at 4-week intervals. In terms of fertilization treatment for 1-0 pine seedlings, the treatment group with gradually-increasing fertilizer concentration ($500{\rightarrow}1000{\rightarrow}1000{\rightarrow}1000mg{\cdot}L^{-1}$) had the biggest increase in stem height and diameter at the root. The survey results indicated that the increased concentration treatment group and the gradually-increasing concentration treatment group had more growth compared with that in the fixed concentration treatment group. The gradually-increasing concentration treatment group ($500{\rightarrow}1000{\rightarrow}1000{\rightarrow}1000mg{\cdot}L^{-1}$) had the highest total dry matter production. Nine weeks after fertilization, the tips of the pine leaves turned yellow in the fixed concentration treatment group ($3000mg{\cdot}L^{-1}$). The same phenomenon was observed in the treatment group in which the concentration was increased to $2000mg{\cdot}L^{-1}$, and in the gradually-increasing concentration treatment group, when the concentration was raised up to $2000mg{\cdot}L^{-1}$. We concluded that the optimal fertilization conditions for producing healthy pine 1-0 seedlings involve fertilizing once a week with Multifeed 19 at $500mg{\cdot}L^{-1}$ during the seedling period, Multifeed 19 at $1000mg{\cdot}L^{-1}$ during the rapid growth period, and Multifeed 32 at $1000mg{\cdot}L^{-1}$ during the maturation period.

• Journal of Korean Society of Forest Science
• /
• v.110 no.2
• /
• pp.198-209
• /
• 2021

This study evaluated the effects of the dimensional characteristics of containers on the nitrogen status of Quercus serrata, Fraxinus rhynchophylla, and Zelkova serrata in the container nursery stage. Seedlings were grown using 16 container types [four growing densities (100, 144, 196, and 256 seedlings/m²) × four cavity volumes (220, 300, 380, and 460 cm³/cavity)]. Two-way ANOVA was performed to test the differences in nitrogen concentration and seedling content among container types. Additionally, we performed multiple regression analyses to correlate container dimensions and nitrogen content. Container types had a strong influence on nitrogen concentration and the content of the seedling species, with a significant interaction effect between growing density and cavity volume. Cavity volumes were positively correlated with the nitrogen content of the three seedling species, whereas growing density negatively affected those of F. rhynchophylla. Further, nutrient vector analysis revealed that the seedling nutrient loading capacities of the three species, such as efficiency and accumulation, were altered because of the different fertilization effects by container types. The optimal ranges of container dimension by each tree species, obtained multiple regression analysis with nitrogen content, were found to be approximately 180-210 seedlings/m² and 410-460 cm³/cavity for Q. serrata, 100-120 seedlings/m² and 350-420 cm³/cavity for F. rhynchophylla, and 190-220 seedlings/m² and 380-430 cm³/cavity for Z. serrata. This study suggests that an adequate type of container will improve seedling quality with higher nutrient loading capacity production in nursery stages and increase seedling growth in plantation stages.

• Korean Journal of Environment and Ecology
• /
• v.34 no.6
• /
• pp.503-514
• /
• 2020

Climate change leads to changes in phenological response and movement of plant habitats. Korea's evergreen broad-leaved forest has widened its distribution area compared for the past 20 years, and the range of its native habitats is moving northward. We analyzed climate indices such as the warmth index, the cold index, the lowest temperature in the coldest month, and the annual average temperature, which are closely related to vegetation distribution, to predict the change in the native habitat of Lauraceae evergreen broad-leaved trees. We also analyzed the change and spatial distribution to identify the habitat climate characteristics of 8 species of Lauraceae evergreen broad-leaved trees distributed in the warm temperate zone in Korea. Moreover, we predicted the natural habitat change in the 21st century according to the climate change scenario (RCP 4.5/8.5), applying the MaxEnt species distribution model. The monthly average climate index of the 8 species of Lauraceae evergreen broad-leaved trees was 116.9±10.8℃ for the temperate index, the cold index 3.9±3.8℃, 1495.7±455.4mm for the annual precipitation, 11.7±3.5 for the humidity index, 14.4±1.1℃ for the annual average temperature, and 1.0±2.1℃ for the lowest temperature of winter. Based on the climate change scenario RCP 4.5, the distribution of the Lauraceae evergreen broad-leaved trees was analyzed to expand to islands of Jeollanam-do and Gyeongsangnam-do, adjacent areas of the west and south coasts, and Goseong, Gangwon-do on the east coast. In the case of the distribution based on the climate change scenario RCP 8.5, it was analyzed that the distribution would expand to all of Jeollanam-do and Gyeongsangnam-do, and most regions except for some parts of Jeollabuk-do, Chungcheongnam-do, Gyeongsangbuk-do, and the capital region. For the conservation of Lauraceae evergreen broad-leaved trees to prepare for climate change, it is necessary to establish standards for conservation plans such as in-situ and ex-situ conservation and analyze various physical and chemical characteristics of native habitats. Moreover, it is necessary to preemptively detect changes such as distribution, migration, and decline of Lauraceae evergreen broad-leaved trees following climate change based on phenological response data based on climate indicators and establish conservation management plans.

• Korean Journal of Environment and Ecology
• /
• v.36 no.2
• /
• pp.118-138
• /
• 2022

This study was conducted to identify the vegetation structure of major vegetation by region and elevation in the subalpine zone of Seoraksan National Park and prepare an inventory of flora. We reviewed the results of the previous subalpine studies and, through a preliminary survey, determined that the first appearance point of subalpine vegetation was about 800 m based on the south. Then we conducted a site survey by installing a total of 77 plots, including 12 plots on the northern Baekdamsa-Madeungnyeong trail (BD), 13 plots on the west Hangyeryeong-Kkeutcheong trail (HG), 13 plots on the east side of Sinheungsa-Socheongbong trail (SA), and 39 plots in the southern Osaek-Kkeutcheong, Osaek-Daecheongbong trail (OS), in an interval of 50 m above sea level. The analysis classified 7 communities, including Qercus mongolica-Abies holophylla-Acer pseudosieboldianumcommunity, Q. mongolica-Tilia amurensiscommunity, Q. mongolica-Pinus koraiensiscommunity, Q. mongolica-A. pseudosieboldianumcommunity, Betula ermanii-A. nephrolepiscommunity, P. koraiensis-A. nephrolepiscommunity, and mixed deciduous broad-leaf tree community according to the species composition based on the appearance of the major subalpine plants such as Quercus mongolica, Betula ermanii, and Abies nephrolepis, region, and elevation. 10.68±2.98 species appeared per plot (100 m²), and 110.87±63.89 individuals were identified. The species diversity analysis showed that the subalpine vegetation community of Seoraksan National Park was a mixed forest in which various species appeared as important species. Although there was a difference in the initial elevation for the appearance of major subalpine plants by region, they were distributed intensively in the elevation range of 1,100 to 1,300 m. In the Seoraksan National Park, 322 taxa, 83 families, 193 genera, 196 species, 1 subspecies, 26 varieties, and 4 forms of vascular plants were identified. One taxon of Trientalis europaeavar.arcticawas identified as the protected species. The endemic plants were 19 taxa, and 58 taxa were identified as subalpine plants.