• The KIPS Transactions:PartB
• /
• v.10B no.1
• /
• pp.87-94
• /
• 2003

A study on the characteristics of server workloads based on user access pattern offers insights for the strategies on continuous media caching and network workloads distribution. This paper analyses characteristics of continuous media filet in each fervor and user access requests to each of them, using log data of three commercial sites, which are providing continuous media files in the form of real time streaming on the Internet. These servers have more continuous files than ones in the previously reported studies and are processing very large number of user access requests. We analyse the characteristics of continuous media files in each server by the size of files. playback time and encoding bandwidth. We also analyse the characteristics of user access requests by the distribution of user requests to continuous media files, user access time, access rate based on the popularity of the files and the number if access requests to serial continuous media files.

• Journal of The Korean Association of Information Education
• /
• v.25 no.5
• /
• pp.813-824
• /
• 2021

To improve educational performance by analyzing the learning trends of adult learners of Open High Schools, various algorithm models using artificial intelligence were designed and performance was evaluated by applying them to real data. We analyzed Log data of 115 adult learners in the cyber education system of Open High Schools. Most adult learners of Open High Schools learned more than recommended learning time, but at the end of the semester, the actual learning time was significantly reduced compared to the recommended learning time. In the second half of learning, the participation rate of VODs, formation assessments, and learning activities also decreased. Therefore, in order to improve educational performance, learning time should be supported to continue in the second half. In the latter half, we developed an artificial intelligence algorithm models using Tensorflow to predict learning time by data they started taking the course. As a result, when using CNN(Convolutional Neural Network) model to predict single or multiple outputs, the mean-absolute-error is lowest compared to other models.

• Journal of the Korea Convergence Society
• /
• v.13 no.4
• /
• pp.155-161
• /
• 2022

The outbreak of the Covid 19 increased the interest on the 'Virtual Tourism. In this research the key word related to "Virtual Tourism" was collected through the search engine and was analyzed through the data mining method such as Log-odds ratio, Frequency, and network analysis. It is clear that the information and communication dependency increased in the field of "Virtual Tourism" after Covid 19 and also the trend have changed from "securement of the contents diversity" to "project related to economic recovery." Since the demands for the "Virtual Reality" such as metaverse is increasing, there should be an economic and circular structure in which the government establishing a related policy and the funding plan based on the research, local government and the private companies planning and producing discriminate contents focusing on AISAS(Attension, Interest, Search, Action, Share) aand the research institutions and universities developing, applying, assessing and commercializing the technology.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.6
• /
• pp.489-495
• /
• 2020

The amount of data is increasing through various IT devices in a hyper-connected society where the 4th revolution is progressing, and new value can be created by analyzing that data. This paper was collected total 1,526 articles from 2017 to 2019 in central magazines, economic magazines, regional associations, and major broadcasting companies with the keyword "(East Coast Tourism or East Coast Travel) and Gangwon-do" through Bigkinds. It was performed the topic modeling using LDA algorithm implemented in the R language to analyze the collected 1,526 articles. It was extracted keywords for each year from 2017 to 2019, and classified and compared keywords with high frequency for each year. It was setted the optimal number of topics to 8 using Log Likelihood and Perplexity, and then inferred 8 topics using the Gibbs Sampling method. The inferred topics were Gangneung and Beach, Goseong and Mt.Geumgang, KTX and Donghae-Bukbu line, weekend sea tour, Sokcho and Unification Observatory, Yangyang and Surfing, experience tour, and transportation network infra. The changes of articles on East coast tourism was was analyzed using the proportion of the inferred eight topics. As the result, the proportion of Unification Observatory and Mt. Geumgang showed no significant change, the proportion of KTX and experience tour increased, and the proportion of other topics decreased in 2018 compared to 2017. In 2019, the proportion of KTX and experience tour decreased, but the proportion of other topics showed no significant change.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.317-320
• /
• 2016

The NH-NongHyup network and servers were paralyzed in 2011, in the 2013 3.20 cyber attack happened and Classified documents of Korea Hydro & Nuclear Power Co. Ltd were leaked on December in 2015. All of them were conducted by a foreign country. These attacks were planned for a long time compared to the script kids attacks and the techniques used were very complex and sophisticated. However, no successful solution has been implemented to defend an APT attack thus far. Therefore, we will use big data analytics to analyze whether or not APT attack has occurred in order to defend against the manipulative attackers. This research is based on the data collected through ISAC monitoring among 3 hierarchical Korean defense system. First, we will introduce related research about big data analytics and machine learning. Then, we design two big data analytics models to detect an APT attack and evaluate the models' accuracy and other results. Lastly, we will present an effective response method to address a detected APT attack.

• Genomics & Informatics
• /
• v.20 no.3
• /
• pp.27.1-27.13
• /
• 2022

Oral squamous cell carcinoma (OSCC) is the most prevalent head and neck malignancy, with frequent cervical lymph-node metastasis, leading to a poor prognosis in OSCC patients. The present study aimed to identify potential markers, including microRNAs (miRNAs) and genes, significantly involved in the etiology of early-stage OSCC. Additionally, the main OSCC's dysregulated Gene Ontology annotations and significant signaling pathways were identified. The dataset GSE45238 underwent multivariate statistical analysis in order to distinguish primary OSCC tissues from healthy oral epithelium. Differentially expressed miRNAs (DEMs) with the criteria of p-value < 0.001 and |Log2 fold change| > 1.585 were identified in the two groups, and subsequently, validated targets of DEMs were identified. A protein interaction map was constructed, hub genes were identified, significant modules within the network were illustrated, and significant pathways and biological processes associated with the clusters were demonstrated. Using the GEPI2 database, the hub genes' predictive function was assessed. Compared to the healthy controls, main OSCC had a total of 23 DEMs. In patients with head and neck squamous cell carcinoma (HNSCC), upregulation of CALM1, CYCS, THBS1, MYC, GATA6, and SPRED3 was strongly associated with a poor prognosis. In HNSCC patients, overexpression of PIK3R3, GIGYF1, and BCL2L11 was substantially correlated with a good prognosis. Besides, "proteoglycans in cancer" was the most significant pathway enriched in the primary OSCC. The present study results revealed more possible mechanisms mediating primary OSCC and may be useful in the prognosis of the patients with early-stage OSCC.

• The Journal of Society for e-Business Studies
• /
• v.27 no.1
• /
• pp.1-13
• /
• 2022

With the development of network technologies, the security to protect organizational resources from internal and external intrusions and threats becomes more important. Therefore in recent years, the anomaly detection algorithm that detects and prevents security threats with respect to various security log events has been actively studied. Security anomaly detection algorithms that have been developed based on rule-based or statistical learning in the past are gradually evolving into modeling based on machine learning and deep learning. In this study, we propose a deep-autoencoder model that transforms LSTM-autoencoder as an optimal algorithm to detect insider threats in advance using various machine learning analysis methodologies. This study has academic significance in that it improved the possibility of adaptive security through the development of an anomaly detection algorithm based on unsupervised learning, and reduced the false positive rate compared to the existing algorithm through supervised true positive labeling.

• Journal of Biomedical and Translational Research
• /
• v.19 no.4
• /
• pp.116-124
• /
• 2018

Korean Native Pig (KNP) has a uniform black coat color, excellent meat quality, white colored fat, solid fat structure and good marbling. However, its growth performance is low, while the western origin Yorkshire pig has high growth performance. To take advantage of the unique performance of the two pig breeds, we raised crossbreeds (KNP ${\times}$ Yorkshire to make use of the heterotic effect. We then analyzed the liver transcriptome as it plays an important role in fat metabolism. We sampled at two stages: 10 weeks and at 26 weeks. The stages were chosen to correspond to the change in feeding system. A total of 16 pigs (8 from each stage) were sampled and RNA sequencing was performed. The reads were mapped to the reference genome and differential expression analysis was performed with edgeR package. A total of 324 genes were found to be significantly differentially expressed (${\left|log2FC\right|}$ > 1 & q < 0.01), out of which 180 genes were up-regulated and 144 genes were down-regulated. Principal Component Analysis (PCA) showed that the samples clustered according to stages. Functional annotation of significant DEGs (differentially expressed genes) showed that GO terms such as DNA replication, cell division, protein phosphorylation, regulation of signal transduction by p53 class mediator, ribosome, focal adhesion, DNA helicase activity, protein kinase activity etc. were enriched. KEGG pathway analysis showed that the DEGs functioned in cell cycle, Ras signaling pathway, p53 signaling pathway, MAPK signaling pathway etc. Twenty-nine transcripts were also part of the DEGs, these were predominantly Cys2His2-like fold group (C2H2) family of zinc fingers. A protein-protein interaction (PPI) network analysis showed that there were three highly interconnected clusters, suggesting an enrichment of genes with similar biological function. This study presents the first report of liver tissue specific gene regulation in a cross-bred Korean pig.

• Journal of Korea Multimedia Society
• /
• v.7 no.8
• /
• pp.1066-1077
• /
• 2004

Dramatic increase in the number of Internet users want highly qualified service of continuous media contents on the web. To solve these problems, we present two network caching schemes(PPC, PPCwP) which consider the characteristics of continuous media objects and user access pattern in this paper. While there are plenty of reasons to create rich media contents, delivering this high bandwidth contents over the internet presents problems such as server overload, network congestion and client-perceived latency. PPC scheme periodically calculates the popularity of objects based on the playback quantity and determines the optimal size of the initial fraction of a continuous media object to be cached in proportion to the calculated popularity. PPCwP scheme calculates the expected popularity using the series information and prefetches the expected initial fraction of newly created continuous media objects. Under the PPCwP scheme, the initial client-perceived latency and the data transferred from a remote server can be reduced and limited cache storage space can be utilized efficiently. Trace-driven simulation have been performed to evaluate the presented caching schemes using the log-files of iMBC. Through these simulations, PPC and PPCwP outperforms LRU and LFU in terms of BHR and DSR.

• Journal of Internet Computing and Services
• /
• v.16 no.2
• /
• pp.57-66
• /
• 2015

Considerable research efforts are being directed towards analyzing unstructured data such as text files and log files using commercial and noncommercial analytical tools. In particular, researchers are trying to extract meaningful knowledge through text mining in not only business but also many other areas such as politics, economics, and cultural studies. For instance, several studies have examined national pending issues by analyzing large volumes of text on various social issues. However, it is difficult to provide successful information services that can identify R&D documents on specific national pending issues. While users may specify certain keywords relating to national pending issues, they usually fail to retrieve appropriate R&D information primarily due to discrepancies between these terms and the corresponding terms actually used in the R&D documents. Thus, we need an intermediate logic to overcome these discrepancies, also to identify and package appropriate R&D information on specific national pending issues. To address this requirement, three methodologies are proposed in this study-a hybrid methodology for extracting and integrating keywords pertaining to national pending issues, a methodology for packaging R&D information that corresponds to national pending issues, and a methodology for constructing an associative issue network based on relevant R&D information. Data analysis techniques such as text mining, social network analysis, and association rules mining are utilized for establishing these methodologies. As the experiment result, the keyword enhancement rate by the proposed integration methodology reveals to be about 42.8%. For the second objective, three key analyses were conducted and a number of association rules between national pending issue keywords and R&D keywords were derived. The experiment regarding to the third objective, which is issue clustering based on R&D keywords is still in progress and expected to give tangible results in the future.