• Journal of Korean Society of Forest Science
• /
• v.97 no.4
• /
• pp.431-436
• /
• 2008

7 populations of rare endemic Berchemia berchemiaefolia were analysed using multivariate analysis for 9 characteristics of leaf morphology. The aim of this study was to examine geographic variation to support a genetic resource conservation plan of B. berchemiaefolia in Korea. In the morphological characters, nine characters of leaf were 10.25 cm (blade length), 4.10 cm (maximum width), 2.52 (blade length/maximum width), 3.22 cm (upper 1/3 width), 3.42 cm (lower 1/3 width), 0.95 (upper 1/3 width/lower 1/3 width), 1.24 cm (petiole length), 8.91 (blade length/petiole length), 8.16ea (vein number), respectively. Nested anova showed that were statistically significant differences among populations as well as among individuals within populations in all 9 quantitative characters. In 7 of 9 characters, variance components among individuals within populations were higher than those among populations. Cluster analysis using complete linkage method showed two groups (Chungbuk and Gyeongbuk districts) to Euclidean distance 1.2. Among principal components, primary 3 principal components appeared to be major variables because of the loading contribution of 87.3%. The first contribution was blade length, blade length/maximum width and blade length/petiole length; the second one was maximum width, upper 1/3 width and lower 1/3 width; the third one was petiole length, respectively.

• Korean Journal of Microbiology
• /
• v.51 no.2
• /
• pp.133-140
• /
• 2015

We have examined the correlation between the physicochemical and microbiological environment variables for the different layers of oak forest soil in Mt. Gyeryong, Korea. The result shows that there is a high correlation in the environment variables between the soil parameters of the fermented (F) layer and humus (H) layer. In particular, the pH level in the F layer shows a high correlation with C and N, while the various organic acids of the H layer turns out to be closely correlated with soil bacteria density. As we evaluated phylogenetic characteristics of bacterial populations by DGGE analysis with DNA extracted. Total of 175 bands including 43 bands from litter (L) layer, 42 bands from F layer, 43 bands from H layer and 47 bands from rhizosphere (A) layer were selected as the major DGGE band of oak forest soil. Based on the 16S rRNA gene sequences, 175 DGGE bands were classified into 32 orders in 7 phylum. The heat map was analyzed in order to compare the quantity of the base sequences of each order and based on the clustering of the different layers of oak forest soil, the result confirms that the F layer and H layer belong to a different cluster from that of L layer and A layer. Furthermore, it also showed that approximately 50% of the total microbial population in different layers is ${\alpha}$-proteobacteria, which indicates that they belong to the dominant system group. In particular, Rhizobiales, Burkholderiales and Actinobacteriales were observed in all the seasons and layers of oak forest soil, which confirms that they are the indigenous soil bacterial community in oak forest soil.

• Korean Journal of Environment and Ecology
• /
• v.15 no.4
• /
• pp.379-393
• /
• 2002

Thirty-six plots (each size 100m2) have been set up and surveyed to investigate the plant community structure and the ecological density of Pinus densiflora for. eracta(Chunyang-type) community in Seobyeok-ri, Chungyang-myeon, bonghwa-gun, Kyeongsangbuk-do. Four communities, Community I (large DBH class), Community II (large DBH class), Community III (middle DBH class), Community IV(small DBH class), were classified into by mean DBH and mean height. Pinus densiflora for. eracta dominate in canopy layer, Fraxinus sieboldiana and Quercus mongolica dominate in understory layer, Rhododendron Schlippenbachii and R. mucronulatum dominate in shrub layer. It turned out that thefour communiteis had low species diversity(0.4320~0.9487; unit: 400$m^2$) and high similarity. By the result of ecological density analysis. the mean basal area was proportionated to mean DBH (cm) size. By the result of simple regression analysis between mean DBH(cm), mean distance(m), and the number of individual were as follow: Ecological distance(m) = 0.0934$\times$ DBH(cm) +0.6117, Number of individual=242.47$\times$ DBH(cm)$^{-1.009}$, Ecological distance=9.643$\times$No. of individua $l^{-0.7016}$. In addition to four communities were suitable to the growth of Tricholoma matsutake because average species were about 30~50 years old, litter layer was 0.5~2.5cm and the ratio of coverage shrub was 20% .

• Korean Journal of Environment and Ecology
• /
• v.20 no.4
• /
• pp.407-414
• /
• 2006

This study was carried out to investigate soil properties, ordination, and vegetation of a forest wetland in Jangdo, Sinan-Gun. Peculiar species such as Epilobium pyrricholophum and Lycopus ramosissim us were found in the forest wetland of Jangdo, and Hosta yingeri and Carpinus turczaninovii for coreana that are an endemic species of Korea were also found. The vascular plants of 40 families 62 genera 57 species 9 varieties 1 form, total 67 taxa were accounted for. The communities were classified as Salix koreensis-Isachne globosa community, Isachne globosa community, and Miscathus sinensis var purpurascens community. Soil organic matter, total nitrogen, available phosphorous concentrations, and cation exchange capacity each ranged from 20.6 to 72.4%, 0.74 to 2.13%, 33.3 to 114.6 ppm, and 25.5 to 94.3 me/100g, respectively. Soil pH ranged from 5.10 to 5.42. Soil texture was clay loam. Results of the correlation between Jangdo forest community and environmental factor are as follows; Soil pH was the most effective factor for plant community distribution. The Salix koreensis-Isachne globosa community was found where it had the highest soil organic matter, nitrogen, and exchangeable Na, Ca, Mg concentration, ana CEC among the three communities. Miscathus sinensis var. purpurascens community was found where it had the lowest soil organic matter, nitrogen, and exchangeable Na, Ca, Mg concentration, and CEC among the three plant communities.

• The Journal of Society for e-Business Studies
• /
• v.23 no.3
• /
• pp.207-224
• /
• 2018

In this article, an empirical study was conducted by using public dataset from Lending Club Corporation, the largest online peer-to-peer (P2P) lending in the world. We explore significant predictor variables related to P2P lending default that housing situation, length of employment, average current balance, debt-to-income ratio, loan amount, loan purpose, interest rate, public records, number of finance trades, total credit/credit limit, number of delinquent accounts, number of mortgage accounts, and number of bank card accounts are significant factors to loan funded successful on Lending Club platform. We developed online P2P lending default prediction models using discriminant analysis, logistic regression, neural networks, and decision trees (i.e., CART and C5.0) in order to predict P2P loan default. To verify the feasibility and effectiveness of P2P lending default prediction models, borrower loan data and credit data used in this study. Empirical results indicated that neural networks outperforms other classifiers such as discriminant analysis, logistic regression, CART, and C5.0. Neural networks always outperforms other classifiers in P2P loan default prediction.

• Journal of the Korean GEO-environmental Society
• /
• v.20 no.1
• /
• pp.5-11
• /
• 2019

The main objective of this study was to analyse polycyclic aromatic hydrocarbons in surface sediments obtained from near Nakdong estuary, and to estimate ecological risks of PAHs using PAHs concentrations. The main constituents of sediments were $SiO_2$, $Al_2O_3$, CaO, $Fe_2O_3$, and ignition loss of sediments ranged from 2.97% and 8.39%. Total concentrations of PAHs ranged from $128.4ng\;g^{-1}$ and $507.4ng\;g^{-1}$, and the major PAHs were 2 ring and 4 ring aromatic hydrocarbons. Each concentrations of PAHs are all below effect range low, which indicated that each PAHs in 8 studying sites show low ecological risk. From M-ERM-Q analyses, M-ERM-Q values of 8 studying sites are below 0.1 indicating low ecological risk. From source apportionment analyses, PAHs come from grass, wood, charcoal combustion for N-1 and N-7, petroleum combustion for N-5 and N-6, petroleum pollution for N-2, N-3, N-4, N-8.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.23-46
• /
• 2021

Collaborative filtering, which is often used in personalization recommendations, is recognized as a very useful technique to find similar customers and recommend products to them based on their purchase history. However, the traditional collaborative filtering technique has raised the question of having difficulty calculating the similarity for new customers or products due to the method of calculating similaritiesbased on direct connections and common features among customers. For this reason, a hybrid technique was designed to use content-based filtering techniques together. On the one hand, efforts have been made to solve these problems by applying the structural characteristics of social networks. This applies a method of indirectly calculating similarities through their similar customers placed between them. This means creating a customer's network based on purchasing data and calculating the similarity between the two based on the features of the network that indirectly connects the two customers within this network. Such similarity can be used as a measure to predict whether the target customer accepts recommendations. The centrality metrics of networks can be utilized for the calculation of these similarities. Different centrality metrics have important implications in that they may have different effects on recommended performance. In this study, furthermore, the effect of these centrality metrics on the performance of recommendation may vary depending on recommender algorithms. In addition, recommendation techniques using network analysis can be expected to contribute to increasing recommendation performance even if they apply not only to new customers or products but also to entire customers or products. By considering a customer's purchase of an item as a link generated between the customer and the item on the network, the prediction of user acceptance of recommendation is solved as a prediction of whether a new link will be created between them. As the classification models fit the purpose of solving the binary problem of whether the link is engaged or not, decision tree, k-nearest neighbors (KNN), logistic regression, artificial neural network, and support vector machine (SVM) are selected in the research. The data for performance evaluation used order data collected from an online shopping mall over four years and two months. Among them, the previous three years and eight months constitute social networks composed of and the experiment was conducted by organizing the data collected into the social network. The next four months' records were used to train and evaluate recommender models. Experiments with the centrality metrics applied to each model show that the recommendation acceptance rates of the centrality metrics are different for each algorithm at a meaningful level. In this work, we analyzed only four commonly used centrality metrics: degree centrality, betweenness centrality, closeness centrality, and eigenvector centrality. Eigenvector centrality records the lowest performance in all models except support vector machines. Closeness centrality and betweenness centrality show similar performance across all models. Degree centrality ranking moderate across overall models while betweenness centrality always ranking higher than degree centrality. Finally, closeness centrality is characterized by distinct differences in performance according to the model. It ranks first in logistic regression, artificial neural network, and decision tree withnumerically high performance. However, it only records very low rankings in support vector machine and K-neighborhood with low-performance levels. As the experiment results reveal, in a classification model, network centrality metrics over a subnetwork that connects the two nodes can effectively predict the connectivity between two nodes in a social network. Furthermore, each metric has a different performance depending on the classification model type. This result implies that choosing appropriate metrics for each algorithm can lead to achieving higher recommendation performance. In general, betweenness centrality can guarantee a high level of performance in any model. It would be possible to consider the introduction of proximity centrality to obtain higher performance for certain models.

• Korean Journal of Social Welfare
• /
• v.60 no.1
• /
• pp.187-209
• /
• 2008

The authors developed 28 needs assessment tools for integrated assessment centered on needs, which is the core element in care management for the elderly in home. Also, the authors collected the assessment data of 676 elderly persons in home from 120 centers under the Korea Association of Senior Welfare Centers by using the needs assessment tools, and finally developed needs extraction algorithm through decision tree analysis in data mining to identify their actual needs and provide social welfare service suitable for such needs. The needs extraction algorithm for 28 needs of the elderly in home are summarized in