• Journal of Korea Multimedia Society
• /
• v.23 no.4
• /
• pp.595-602
• /
• 2020

We propose a generative probabilistic model with Dirichlet prior distribution for topic modeling and text similarity analysis. It assigns a topic and calculates text correlation between documents within a corpus. It also provides posterior probabilities that are assigned to each topic of a document based on the prior distribution in the corpus. We then present a Gibbs sampling algorithm for inference about the posterior distribution and compute text correlation among 50 abstracts from the papers published by IEEE. We also conduct a supervised learning to set a benchmark that justifies the performance of the LDA (Latent Dirichlet Allocation). The experiments show that the accuracy for topic assignment to a certain document is 76% for LDA. The results for supervised learning show the accuracy of 61%, the precision of 93% and the f1-score of 96%. A discussion for experimental results indicates a thorough justification based on probabilities, distributions, evaluation metrics and correlation coefficients with respect to topic assignment.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.5
• /
• pp.744-752
• /
• 2012

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as an one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problems. In data preprocessing part, Principal Component Analysis(PCA) which is generally used in face recognition, which is useful to express some classes using reduction, since it is effective to maintain the rate of recognition and to reduce the amount of data at the same time. However, because of there of the whole face image, it can not guarantee the detection rate about the change of viewpoint and whole image. Thus, to compensate for the defects, Linear Discriminant Analysis(LDA) is used to enhance the separation of different classes. In this paper, we combine the PCA&LDA algorithm and design the optimized pRBFNNs for recognition module. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNNs is represented as two kinds of polynomials such as constant, and linear. The coefficients of connection weight identified with back-propagation using gradient descent method. The output of the pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of Differential Evolution. The proposed pRBFNNs are applied to face image(ex Yale, AT&T) datasets and then demonstrated from the viewpoint of the output performance and recognition rate.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.3
• /
• pp.355-360
• /
• 2021

Recently Youtube has been more popular. As many studies show the comparative deprivation of the Social Medeia, this study looks into whether the comparative deprivation is expressed on the YouTube comments. It focuses on the Luxury Haul contents, videos about huge amounts of luxurious products, of which Youtubers'economic feature are demonstrative. The comments of the videos are analyzed with LDA TF-IDF and Word2Vec. Additionally, the comments were classified into positive and negative groups by the LSTM model as well. As a result of the study, even though many comments turned out positive, the negative keywords were indicated related to comparative deprivation. Also it was found that the viewers compared themselves with Youtubers. In particular, some YouTubers are more criticized if they are younger or does not seem to afford the luxurious products themselves. This study suggests that the users express the comparative deprivation on YouTube as well like on the other Social Media.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.6
• /
• pp.640-645
• /
• 2014

Many people use social network services as to communicate, to share an information and to build social relationships between others on the Internet. Twitter is such a representative service, where millions of tweets are posted a day and a huge amount of data collection has been being accumulated. Social mining that extracts the meaningful information from the massive data has been intensively studied. Typically, Twitter easily can deliver and retweet the contents using the following-follower relationships. Topic modeling in tweet data is a good tool for issue tracking in social media. To overcome the restrictions of short contents in tweets, we introduce a notion of reply graph which is constructed as a graph structure of which nodes correspond to users and of which edges correspond to existence of reply and retweet messages between the users. The LDA topic model, which is a typical method of topic modeling, is ineffective for short textual data. This paper introduces a topic modeling method that uses reply graph to reduce the number of short documents and to improve the quality of mining results. The proposed model uses the LDA model as the topic modeling framework for tweet issue tracking. Some experimental results of the proposed method are presented for a collection of Twitter data of 7 days.

• Communications for Statistical Applications and Methods
• /
• v.30 no.1
• /
• pp.75-94
• /
• 2023

The growing trend of cyber risk has put forward the importance of cyber risk management. Cyber risk is defined as an accidental or intentional risk related to information and technology assets. Although cyber risk is a subset of operational risk, it is reported to be handled differently from operational risk due to its different features of the loss distribution. In this study, we aim to detect the characteristics of cyber loss and find a suitable model by measuring value at risk (VaR). We use the loss distribution approach (LDA) and the time series model to describe cyber losses of financial and non-financial business sectors, provided in SAS^® OpRisk Global Data. Peaks over threshold (POT) method is also incorporated to improve the risk measurement. For the financial sector, the LDA and GARCH model with POT perform better than those without POT, respectively. The same result is obtained for the non-financial sector, although the differences are not significant. We also build a two-dimensional model reflecting the dependence structure between financial and non-financial sectors through a bivariate copula and check the model adequacy through VaR.

• Journal of Multimedia Information System
• /
• v.1 no.1
• /
• pp.55-67
• /
• 2014

Image topic and emotion analysis is an important component of online image retrieval, which nowadays has become very popular in the widely growing social media community. However, due to the gaps between images and texts, there is very limited work in literature to detect one image's Topics and Emotions in a unified framework, although topics and emotions are two levels of semantics that often work together to comprehensively describe one image. In this work, a unified model, Joint Topic/Emotion Multi-Modal Hierarchical Latent Dirichlet Allocation (JTE-MMHLDA) model, which extends previous LDA, mmLDA, and JST model to capture topic and emotion information at the same time from heterogeneous data, is proposed. Specifically, a two level graphical structured model is built to realize sharing topics and emotions among the whole document collection. The experimental results on a Flickr dataset indicate that the proposed model efficiently discovers images' topics and emotions, and significantly outperform the text-only system by 4.4%, vision-only system by 18.1% in topic detection, and outperforms the text-only system by 7.1%, vision-only system by 39.7% in emotion detection.

• Journal of Industrial Convergence
• /
• v.22 no.6
• /
• pp.51-59
• /
• 2024

The purpose of the paper is to suggest government policies that are practically helpful to small business owners in pandemic situations such as COVID-19. To this end, keyword frequency analysis and word cloud analysis of text mining analysis were performed by crawling news articles centered on the keywords "COVID-19 Support for Small Businesses", "The Impact of Small Businesses by Response System to COVID-19 Infectious Diseases", and "COVID-19 Small Business Economic Policy", and major issues were identified through LDA topic modeling analysis. As a result of conducting LDA topic modeling, the support policy for small business owners formed a topic label with government cash and financial support, and the impact of small business owners according to the COVID-19 infectious disease response system formed a topic label with a government-led quarantine system and an individual-led quarantine system, and the COVID-19 economic policy formed a topic label with a policy for small business owners to acquire economic crisis and self-sustainability. Focusing on the organized topic label, it was intended to provide basic data for small business owners to understand the damage reduction policy for small business owners and the policy for enhancing market competitiveness in the future pandemic situation.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.19-31
• /
• 2022

In Machine learning, we usually divide the entire data into training data and test data, train the model using training data, and use test data to determine the accuracy and generalization performance of the model. In the case of models with low generalization performance, the prediction accuracy of newly data is significantly reduced, and the model is said to be overfit. This study is about a method of generating training data based on central limit theorem and combining it with existed training data to increase normality and using this data to train models and increase generalization performance. To this, data were generated using sample mean and standard deviation for each feature of the data by utilizing the characteristic of central limit theorem, and new training data was constructed by combining them with existed training data. To determine the degree of increase in normality, the Kolmogorov-Smirnov normality test was conducted, and it was confirmed that the new training data showed increased normality compared to the existed data. Generalization performance was measured through differences in prediction accuracy for training data and test data. As a result of measuring the degree of increase in generalization performance by applying this to K-Nearest Neighbors (KNN), Logistic Regression, and Linear Discriminant Analysis (LDA), it was confirmed that generalization performance was improved for KNN, a non-parametric technique, and LDA, which assumes normality between model building.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.31 no.3
• /
• pp.42-49
• /
• 2023

Not only in aviation industry but also in other industries, safety data plays a key role to improve the level of safety performance. By analyzing safety data such as aviation safety report (text data), hazard can be identified and removed before it leads to a tragic accident. However, pre-processing of raw data (or natural language data) collected from each site should be carried out first to utilize proactive or predictive safety management system. As air traffic volume increases, the amount of data accumulated is also on the rise. Accordingly, there are clear limitation in analyzing data directly by manpower. In this paper, a topic prediction model for aviation safety mandatory report is proposed. In addition, the prediction accuracy of the proposed model was also verified using actual aviation safety mandatory report data. This research model is meaningful in that it not only effectively supports the current aviation safety mandatory report analysis work, but also can be applied to various data produced in the aviation safety field in the future.

• Journal of Korea Society of Industrial Information Systems
• /
• v.23 no.3
• /
• pp.87-95
• /
• 2018

Recently, with the technological development of artificial intelligence, related market is expanding rapidly. In the artificial intelligence technology field, which is still in the early stage but still expanding, it is important to reduce uncertainty about research direction and investment field. Therefore, this study examined technology trends using text mining and topic modeling among big data analysis methods and suggested trends of core technology and future growth potential. We hope that the results of this study will provide researchers with an understanding of artificial intelligence technology trends and new implications for future research directions.