• Journal of the Korea Society of Computer and Information
• /
• v.19 no.2
• /
• pp.193-200
• /
• 2014

Due to the advent of ubiquitous computing environment, it is becoming a part of our common life style. And tremendous information is cumulated rapidly. In these trends, it is becoming a very important technology to find out exact information in a large data to present users. Collaborative filtering is the method based on other users' preferences, can not only reflect exact attributes of user but also still has the problem of sparsity and scalability, though it has been practically used to improve these defects. In this paper, we propose clustering method by user's features based on SOM for predicting purchase pattern in u-Commerce. it is necessary for us to make the cluster with similarity by user's features to be able to reflect attributes of the customer information in order to find the items with same propensity in the cluster rapidly. The proposed makes the task of clustering to apply the variable of featured vector for the user's information and RFM factors based on purchase history data. To verify improved performance of proposing system, we make experiments with dataset collected in a cosmetic internet shopping mall.

• The KIPS Transactions:PartB
• /
• v.10B no.3
• /
• pp.287-296
• /
• 2003

There has been much research focused on collaborative filtering technique in Recommender System. However, these studies have shown the First-Rater Problem and the Sparsity Problem. The main purpose of this Paper is to solve these Problems. In this Paper, we suggest the user's predicting preference method using Bayesian estimated value and the associative user clustering for the recalculation of preference. In addition to this method, to complement a shortcoming, which doesn't regard the attribution of item, we use Representative Attribute-Neighborhood method that is used for the prediction when we find the similar neighborhood through extracting the representative attribution, which most affect the preference. We improved the efficiency by using the associative user's clustering analysis in order to calculate the preference of specific item within the cluster item vector to the collaborative filtering algorithm. Besides, for the problem of the Sparsity and First-Rater, through using Association Rule Hypergraph Partitioning algorithm associative users are clustered according to the genre. New users are classified into one of these genres by Naive Bayes classifier. In addition, in order to get the similarity value between users belonged to the classified genre and new users, and this paper allows the different estimated value to item which user evaluated through Naive Bayes learning. As applying the preference granted the estimated value to Pearson correlation coefficient, it can make the higher accuracy because the errors that cause the missing value come less. We evaluate our method on a large collaborative filtering database of user rating and it significantly outperforms previous proposed method.

• Horticultural Science & Technology
• /
• v.31 no.5
• /
• pp.598-606
• /
• 2013

Anther is the major organ of flower in responsible to reproduction and outward appearance. From anther-specific cDNA library of Lilium Oriental Hybrid 'Acapulco', 2000 expressed sequence tags were selected randomly. Differential slot blot analysis with cDNA probes from the anther and leaf was used to get anther-expressed clone and 570 non-redundant ESTs were obtained and sequenced. Compared to the GenBank database using BLASTX algorithm, 191 clones showed significant similarity but others (66.5%) did not measured to known sequence. Functional categories according to gene ontology (GO) annotation included sequence representing a significant portion of protein in cell and cell part respectively. A transcriptional analysis at 7 different organs and developmental stage was performed using northern blot with thirty ESTs as putative anther specific gene. This report suggest that selection of anther expressed clone using differential slot blot was considered as very effective tool and our current study can provide fundamental information on the lily anther including pollen furthermore.

• (The) Research of the performance art and culture
• /
• no.36
• /
• pp.103-135
• /
• 2018

The objective of this study is to re-examine the theory of Pansori (Korean musical storytelling genre) originating in Chinese tale-song literature. The said theory, first presented by Kim Hak-ju, succeeded in confirming the common points and association between Pansori and the Chinese tale-song literature, but failed to present the supporting ground for proving that Pansori originated in the said Chinese genre by comparing the contents of works and their performance type. In actuality, it was confirmed that the common factors of Pansori and the said Chinese genre naturally resulted from the performance situation where both genres should involve one singer chanting epics and simultaneously performing various roles and functions. In addition, it was confirmed that such identity of performance environment made the Pansori clown theory and the Gosagye tale-song(鼓詞系講唱) theory very similar. In addition, it was confirmed that, for one singer to present the wide spectrum of epic to the audience, the realistic description was the main part of literary style of both tale-song literature and Pansori, and furthermore it was revealed that, in the literary style of both tale-song literature and Pansori, the mixed use of time and temporal penetration were free. If a long performance of musical storytelling can be conceptualized in terms of 'tale-song' or 'oral epic', the Chinese tale-song literature and Pansori had similarity in the bigger frame of 'tale-song' or 'oral epic' and yet developed to have their own features.

• Journal of Broadcast Engineering
• /
• v.26 no.1
• /
• pp.39-60
• /
• 2021

In the field of deep learning, there are many algorithms mainly after GAN in research related to generation, but in terms of generation, there are similarities and differences with art. If the generation in the engineering aspect is mainly to judge the presence or absence of a quantitative indicator or the correct answer and the incorrect answer, the creation in the artistic aspect creates a creation that interprets the world and human life by cross-validating and doubting the correct answer and incorrect answer from various perspectives. In this paper, the video generation ability of deep learning was interpreted from the perspective of collage and compared with the results made by the artist. The characteristic of the experiment is to compare and analyze how much GAN reproduces the result of the creator made with the collage technique and the difference between the creative part, and investigate the satisfaction level by making performance evaluation items for the reproducibility of GAN. In order to experiment on how much the creator's statement and purpose of expression were reproduced, a deep learning algorithm corresponding to the statement keyword was found and its similarity was compared. As a result of the experiment, GAN did not meet much expectations to express the collage technique. Nevertheless, the image association showed higher satisfaction than human ability, which is a positive discovery that GAN can show comparable ability to humans in terms of abstract creation.

• The Korea Journal of Herbology
• /
• v.24 no.4
• /
• pp.115-120
• /
• 2009

Objectives : Due to the morphological similarity and frequent occurrence of intermediate forms as well as morphological variations of aerial part, the correct identification between Rhei Radix et Rhizoma and Rhei Undulatai Rhizoma is very difficult. To develop a reliable method for correct identification and improving the quality standards of Rhei Radix et Rhizoma and Rhei Undulatai Rhizoma, we analyzed RAPD and developed SCAR marker. Methods : To amplify target DNA at the genomic level, 32 Operon 10-mer random primers were applied with four Rheum species, R. officinale, R. palmatum, R. tanguticum and R. undulatum. The nucleotide sequences were determined and species-specific primers were prepared depending on the species-specific RAPD amplicons after subcloned into the pGEM-Teasy vector. To develop the SCAR markers, species-specific PCR amplification and multiplex-PCR were carried out using the single species-specific primer pairs and combinations of them, respectively. Results : We used RAPD analysis of four Rheum plant species to obtain several species-specific RAPD amplicons. From nucleotide sequences of these RAPD amplicons, we developed two SCAR markers that amplified 314 bp and 390 bp DNA fragments in only R. undulatum but not in R. officinale, R. palmatum, R. tanguticum and R. undulatum, for distinguishing Rhei Undulatai Rhizoma and Rhei Radix et Rhizoma. Furthermore, we established SCAR markers for the simultaneous discrimination of the three species within a single reaction by using multiplex-PCR. Conclusions : These genetic markers can be used for the efficient discrimination of plants species and commercial herbal medicines between Rhei Undulatai Rhizoma and Rhei Radix et Rhizoma, to ultimately prevent indiscriminate distribution and prescription of these herbal medicines.

• The Journal of the Korea Contents Association
• /
• v.22 no.5
• /
• pp.15-25
• /
• 2022

This study aims to identify the family and lineage of a part of a "Fish Tribe Conference" in the section Tokkijeon by utilizing computer literature analysis techniques. First of all, we encode the classification for a pairwise comparison's type of each paragraph to build a corpus, and based on this, we use the Hamming distance to calculate the distance matrix between each classification for a pairwise comparison's. We visualized classification for a pairwise comparison's clustering pattern by applying multidimensional scale method, and hierarchical clustering to explore the characteristics of the 'fish family' line and lineage compared to the existing cluster analysis study on entire paragraphs of "Tokkijeon". As a result, unlike the cluster analysis of the entire paragraph of "Tokkijeon", which consists of six categories, the "Fish Tribe Conference" section has five categories and some classification for a pairwise comparison's accesses. The results of this study are that the relative distance between Yibon was measured and systematic classification was performed in an objective and empirical way by calculation, and the characteristics of the line of the fish family were revealed compared to the analysis of the entire rabbit exhibition.

• Journal of Korea Water Resources Association
• /
• v.56 no.10
• /
• pp.641-653
• /
• 2023

As climate change and urbanization are causing unprecedented natural disasters in urban areas, it is crucial to have urban flood predictions with high fidelity and accuracy. However, conventional physically- and deep learning-based urban flood modeling methods have limitations that require a lot of computer resources or data for high-resolution flooding analysis. In this study, we propose and implement a method for improving the spatial resolution of urban flood analysis using a deep learning based super-resolution technique. The proposed approach converts low-resolution flood maps by physically based modeling into the high-resolution using a super-resolution deep learning model trained by high-resolution modeling data. When applied to two cases of retrospective flood analysis at part of City of Portland, Oregon, U.S., the results of the 4-m resolution physical simulation were successfully converted into 1-m resolution flood maps through super-resolution. High structural similarity between the super-solution image and the high-resolution original was found. The results show promising image quality loss within an acceptable limit of 22.80 dB (PSNR) and 0.73 (SSIM). The proposed super-resolution method can provide efficient model training with a limited number of flood scenarios, significantly reducing data acquisition efforts and computational costs.

• Journal of Korean Society of Forest Science
• /
• v.113 no.3
• /
• pp.327-338
• /
• 2024

Forest road construction can degrade the physical and biological environments of forest ecosystems. Although this degradation may be temporary, some research has shown the potential for the long-term recovery of the original ecosystem. This study investigated changes in communities' structures over time to understand the process of ecosystem change following road construction. Data were collected from 63 plots, each measuring 25m², in Buyeo-gun, Chungcheongnam-do, including plots from roads constructed in 1998 (25 years elapsed), 2021 (two years elapsed), and 2022 (one year elapsed), using phytosociological methods. The results showed that the importance of the values of Pinus densiflora an d Quercus variabilis in the tree and subtree layers of the 25-year-old cut slopes were similar to those of the control plots, indicating the significant recovery of the original ecosystem's structure and function after 25 years. Species diversity analysis revealed the higher evenness and lower dominance of the cut slopes and road surfaces attributed to the high dominance of species such as Arundinella hirta and Miscanthus sinensis. The community similarity index and detrended correspondence analysis (DCA) indicated that the control plots, all the edge plots, and the 25-year-old cut slopes could be considered part of the same community. In conclusion, forest roads in place for 25 years appear to have been restored to the level of the original ecosystem. These findings can serve as valuable ecological data for understanding the vegetation recovery process at future forest road construction sites.

• Korean Journal of Ecology and Environment
• /
• v.39 no.3 s.117
• /
• pp.340-351
• /
• 2006

To reveal physicochemical factors contributing to variation of phytoplankton communities, the study was carried out biweekly at 6 stations from Feb. 2004 to Feb. 2005 in the lower part of the Han River, Korea. As results, water temperature was changed from $0.3^{\circ}C$ to $26.6^{\circ}C$, pH: 6.6${\sim}$9.1, DO: 1.89${\sim}$22.23 mg $L^{-1}$, BOD: 0.38${\sim}$9.20 mg $L^{-1}$, COD: 1.4${\sim}$15.2 mg $L^{-1}$, Conductivity: $62.5{\sim}500.0\;{\mu}s\;cm^{-1}$, SS: 3.00${\sim}$159.3 mg $L^{-1}$, and Chl a $1.7{\sim}71.3\;{\mu}g\;L^{-1}$. Phytoplankton standing crops ranged from min. $3.6{\times}10^2\;cells\;mL^{-1}$ (July 2004, St. 3) to max. $2.3{\times}10^4\;cells\;mL^{-1}$ (Feb. 2005, St. 6), and mean of those varied from $5.9{\times}10^3\;cells\;mL^{-1}$in spring, $2.1{\times}10^3\;cells\;mL^{-1}$ in summer, $4.1{\times}10^3\;cells\;mL^{-1}$ in autumn and $8.5{\times}10^3\;cells\;mL^{-1}$ in winter, respectively. In order to investigate factors influencing the total phytoplankton standing crops a multiple regression analysis was adopted for the correlation between standing crops and environmental factors. The coefficient of determination ($R^2$) value of the regression was 0.465, it showed that environmental factors which predominantly influenced phytoplankton standing crops were water temperature, COD, $NO_2-N$, $PO_4-N$, Discharge and pH. six stations could be divided into 3 groups based on similarity index in terms of environmental factors. In ANOVA analysis for physicochemical and biological factors, water temperature, chlorophyll a, silicate, phytoplankton standing crops were the same group differed little from stations. However, Station 1and 2 were grouped followed in dissolved oxygen, conductivity, COD, nitrite, nitrate, ammonia and phosphate, and Station 3, 4 and 5 were followed in dissolved oxygen, conductivity, pH and phosphate.