• Journal of the Korea Convergence Society
• /
• v.11 no.8
• /
• pp.165-171
• /
• 2020

Most of the stock price prediction research using text mining uses news and SNS data. However, there is a weakness that it is difficult to get honest and vivid information about companies from them. This paper deals with the problem of the prediction for the direction of stock price by doing text mining the online company reviews of internal staff indicating employee satisfaction. The comparative analysis of the prediction models for the direction of stock price showed the prediction model, which adds internal employee reviews, has better performance than those that did not. This paper presents the convergence study using natural language processing in financial engineering. In the field of stock price prediction, This paper pursued a new methodology that used employee satisfaction. In practice, it is expected to provide useful information in the field of forecasting stock price direction.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.7
• /
• pp.1501-1509
• /
• 2011

Current identity management 1.0 model, which is service provider-centric and isolated, has several problems such as low usability, high cost structure, difficulty in privacy protection, and lack of trust infrastructure. Though various SSO-based identity management 2.0 models including Passport/Live ID, Liberty Alliance/SAML, CardSpace, and OpenID have been recently developed in order to overcome those problems, they are not widely accepted in real Internet environment so as to replace the existing identity management 1.0 model. This paper firstly analyzes the widely-known identity 2.0 models in a comparative way, and then presents a perspective on the development direction of identity management 3.0 model for future Internet.

• Journal of the Korean Society of Safety
• /
• v.31 no.6
• /
• pp.121-128
• /
• 2016

Social Media transformed the mass media based information traffic, and it has become a key resource for finding value in enterprises and public institutions. Particularly, in regards to disaster management, the necessity for public participation policy development through the use of social media is emphasized. National Disaster Management Research Institute developed the Social Big Board, which is a system that monitors social Big Data in real time for purposes of implementing social media disaster management. Social Big Board collects a daily average of 36 million tweets in Korean in real time and automatically filters disaster safety related tweets. The filtered tweets are then automatically categorized into 71 disaster safety types. This real time tweet monitoring system provides various information and insights based on the tweets, such as disaster issues, tweet frequency by region, original tweets, etc. The purpose of using this system is to take advantage of the potential benefits of social media in relations to disaster management. It is a first step towards disaster management that communicates with the people that allows us to hear the voice of the people concerning disaster issues and also understand their emotions at the same time. In this paper, Korean language text mining based Social Big Board will be briefly introduced, and disaster issue detection model, which is key algorithms, will be described. Disaster issues are divided into two categories: potential issues, which refers to abnormal signs prior to disaster events, and occurrence issues, which is a notification of disaster events. The detection models of these two categories are defined and the performance of the models are compared and evaluated.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.24
• /
• pp.10797-10801
• /
• 2015

Background: To explore the molecular mechanisms of metastatic osteosarcoma (OS) by using the microarray expression profiles of metastatic and non-metastatic OS samples. Materials and Methods: The gene expression profile GSE37552 was downloaded from Gene Expression Omnibus database, including 2 human metastatic OS cell line models and 2 two non-metastatic OS cell line models. The differentially expressed genes (DEGs) were identified by Multtest package in R language. In addition, functional enrichment analysis of the DEGs was performed by WebGestalt, and the protein-protein interaction (PPI) networks were constructed by Hitpredict, then the signal pathways of the genes involved in the networks were performed by Kyoto Encyclopaedia of Genes and Genomes (KEGG) automatic annotation server (KAAS). Results: A total of 237 genes were classified as DEGs in metastatic OS. The most significant up- and down-regulated genes were A2M (alpha-2-macroglobulin) and BCAN (brevican). The DEGs were significantly related to the response to hormone stimulus, and the PPI network of A2M contained IL1B (interleukin), LRP1 (low-density lipoprotein receptor-related protein 1) and PDGF (platelet-derived growth factor). Furthermore, the MAPK signaling pathway and focal adhesion were significantly enriched. Conclusions: A2M and its interactive proteins, such as IL1B, LRP1 and PDGF may be candidate target molecules to monitor, diagnose and treat metastatic OS. The response to hormone stimulus, MAPK signaling pathway and focal adhesion may play important roles in metastatic OS.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.1
• /
• pp.24-31
• /
• 1994

In this paper, we report on the development of a speaker independent continuous speech recognition system using continuous hidden Markov models. The continuous hidden Markov model consists of mean and covariance matrices and directly models speech signal parameters, therefore does not have quantization error. Filter bank coefficients with their 1st and 2nd-order derivatives are used as feature vectors to represent the dynamic features of speech signal. We use the segmental K-means algorithm as a training algorithm and triphone as a recognition unit to alleviate performance degradation due to coarticulation problems critical in continuous speech recognition. Also, we use the one-pass search algorithm that Is advantageous in speeding-up the recognition time. Experimental results show that the system attains the recognition accuracy of $83\%$ without grammar and $94\%$ with finite state networks in speaker-indepdent speech recognition.

• Journal of Korea Multimedia Society
• /
• v.4 no.6
• /
• pp.524-533
• /
• 2001

Efficient continuous speech recognition system for practical applications requires that the processing be carried out in real time and high recognition accuracy. In this paper, we study the acoustic models by adopting the PDT-SSS algorithm and the language models by iterative learning so as to improve the speech recognition accuracy. And the adaptive pruning algorithm is applied to the continuous speech. To verify the effectiveness of proposed method, we carried out the continuous speech recognition for the Korean air flight reservation task. Experimental results show that the adopted algorithm has the average 90.9% for continuous speech recognition and the average 90.7% for word recognition accuracy including continuous speech. And in case of adopting the adaptive pruning algorithm to continuous speech, it reduces the recognition time of about 1.2 seconds(15%) without any loss of accuracy. From the result, we proved the effectiveness of the PDT-SSS algorithm and the adaptive pruning algorithm.

• The Journal of the Korea Contents Association
• /
• v.15 no.12
• /
• pp.204-211
• /
• 2015

This study made fundamental approaches on the significance of social enterprises on minority protection policies. In particular, it offered discussions focused on the relationship between social enterprises and North Korean defectors which greatly affect minority policies. Study results can be summed up as follows. First, the greatest difficulties for North Korean defectors in their adjustment to Korean society are economic activities and a sense of social differences and social enterprises are a policy which can resolve these problems in the most effective way. Second, existing social enterprises were excessively run by the central government and they were support models which lacked creativity and development. To resolve such problems, a lesson was learned that these must change into policy models with local coproduction. Third, a lesson was learned that social enterprises offer more than simple economic activity, offering the proper functions of society, culture, living, and language, and thus the participation of North Korean defectors in social enterprises should be made mandatory in certain sectors. Such research results will contribute to theoretically explaining the relationship between North Korean defectors and social enterprises as minority policies.

• Journal of Information Technology Services
• /
• v.16 no.3
• /
• pp.167-183
• /
• 2017

The rapid growth of information technology and mobile service platforms, i.e., internet, google, and facebook, etc. has led the abundance of data. Due to this environment, the world is now facing a revolution in the process that data is searched, collected, stored, and shared. Abundance of data gives us several opportunities to knowledge discovery and data mining techniques. In recent years, data mining methods as a solution to discovery and extraction of available knowledge in database has been more popular in e-commerce service fields such as, in particular, movie recommendation. However, most of the classification approaches for predicting the movie popularity have used only several types of information of the movie such as actor, director, rating score, language and countries etc. In this study, we propose a classification-based support vector machine (SVM) model for predicting the movie popularity based on movie's genre data and social network data. Social network analysis (SNA) is used for improving the classification accuracy. This study builds the movies' network (one mode network) based on initial data which is a two mode network as user-to-movie network. For the proposed method we computed degree centrality, betweenness centrality, closeness centrality, and eigenvector centrality as centrality measures in movie's network. Those four centrality values and movies' genre data were used to classify the movie popularity in this study. The logistic regression, neural network, $na{\ddot{i}}ve$ Bayes classifier, and decision tree as benchmarking models for movie popularity classification were also used for comparison with the performance of our proposed model. To assess the classifier's performance accuracy this study used MovieLens data as an open database. Our empirical results indicate that our proposed model with movie's genre and centrality data has by approximately 0% higher accuracy than other classification models with only movie's genre data. The implications of our results show that our proposed model can be used for improving movie popularity classification accuracy.

• Journal of Internet Computing and Services
• /
• v.8 no.6
• /
• pp.135-144
• /
• 2007

Feature models are widely used in domain engineering phase of software product lines development to model the common and variable concepts among products. From the feature model, the feature configurations are generated by selecting the features to be included in target product. The feature configuration represents the requirements for the specific product to be implemented. Although there are a lot of researches on how to build and use the feature models and feature configurations, the researches on the formal semantics and reasoning of them are rather inactive. This paper proposes the feature configuration verification approach based on JESS, java-based rule-base system. The Graph Product Line, a standard problem for evaluating the software product line technologies, is used throughout the paper to illustrate this approach. The approach in this paper has advantage of presenting the exact reason causing inconsistency in the feature configuration. In addition, this approach should be easily applied into other software product lines development environments because JESS system can be easily integrated with Java language.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.23 no.3
• /
• pp.315-323
• /
• 2010

Five concrete compressive stress-strain models have been analyzed to check the validity of the strength method for determining the nominal moment of strengthened members using commercially available computer language. The results show that the concrete stress-strain models do not influence on the flexural analysis. The moment of a strengthened member obtained from the flexural analysis at concrete compressive strain reaching 0.003 is well agreed with nominal moment using the strength method. The flexural analysis results show that when the steel reinforcement, FRP ratio, FRP failure strain, and concrete failure compressive strain are relatively lower, the strength method overestimates the flexural capacity of the strengthened members.