• 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.

• The Korean Journal of Health Service Management
• /
• v.11 no.4
• /
• pp.213-224
• /
• 2017

Objectives : The purpose of this study was to analyze representative topics and topic trends of papers in Korean Society and Health Service Management(KSHSM) Journal. Methods : We collected English abstracts and key words of 516 papers in KSHSM Journal from 2007 to 2017. We utilized Python web scraping programs for collecting the papers from Korea Citation Index web site, and RStudio software for topic analysis based on latent Dirichlet allocation algorithm. Results : 9 topics were decided as the best number of topics by perplexity analysis and the resultant 9 topics for all the papers were extracted using Gibbs sampling method. We could refine 9 topics to 5 topics by deep consideration of meanings of each topics and analysis of intertopic distance map. In topic trends analysis from 2007 to 2017, we could verify 'Health Management' and 'Hospital Service' were two representative topics, and 'Hospital Service' was prevalent topic by 2011, but the ratio of the two topics became to be similar from 2012. Conclusions : We discovered 5 topics were the best number of topics and the topic trends reflected the main issues of KSHSM Journal, such as name revision of the society in 2012.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.392-412
• /
• 2018

Due to the semantic gap problem across different modalities, automatically retrieval from multimedia information still faces a main challenge. It is desirable to provide an effective joint model to bridge the gap and organize the relationships between them. In this work, we develop a deep image annotation and classification by fusing multi-modal semantic topics (DAC_mmst) model, which has the capacity for finding visual and non-visual topics by jointly modeling the image and loosely related text for deep image annotation while simultaneously learning and predicting the class label. More specifically, DAC_mmst depends on a non-parametric Bayesian model for estimating the best number of visual topics that can perfectly explain the image. To evaluate the effectiveness of our proposed algorithm, we collect a real-world dataset to conduct various experiments. The experimental results show our proposed DAC_mmst performs favorably in perplexity, image annotation and classification accuracy, comparing to several state-of-the-art methods.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.7
• /
• pp.173-180
• /
• 2016

Since smartphones possess a variety of user information, we can derive useful data related to the case from app data analysis in the digital forensic perspective. However, it requires an appropriate forensic measure as smartphone has the property of high mobility and high possibility of data loss, forgery, and modulation. Especially the forged/modulated time-stamp impairs the credibility of digital proof and results in the perplexity during the timeline analysis. This paper provides traces of usage which could investigate whether the time-stamp has been forged/modulated or not within the range of iOS based devices.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.135-140
• /
• 2020

사전 학습된 Transformer 기반 언어 모델은 자연어처리 시스템에 적용되었을 시 광범위한 사례에서 큰 폭의 성능 향상을 보여준다. 여기서 사전 학습에 사용되는 언어 모델링 태스크는 비지도 학습에 속하는 기술이기 때문에 상대적으로 데이터의 확보가 쉬운 편이다. 하지만 몇 종의 주류 언어를 제외한 대부분 언어는 활용할 수 있는 언어 자원 자체가 희소하며, 따라서 이러한 사전 학습 기술의 혜택도 누리기 어렵다. 본 연구에서는 이와 같은 상황에서 발생할 수 있는 자원 희소성 문제를 극복하기 위해 이종 언어 간 전이 학습을 이용하는 방법을 제안한다. 본 방법은 언어 자원이 풍부한 언어에서 학습된 Transformer 기반 언어 모델에서 얻은 파라미터 중 재활용 가능한 부분을 이용하여 목표 언어의 모델을 초기화한 후 학습을 진행한다. 또한, 기존 언어와 목표 언어의 차이를 학습하는 역할을 하는 적응층들을 추가하여 이종 언어 간 전이 학습을 돕는다. 제안된 방법을 언어 자원이 희귀한 상황에 대하여 실험해본 결과, 전이 학습을 사용하지 않은 기준 모델 대비 perplexity와 단어 예측의 정확도가 큰 폭으로 향상됨을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.11
• /
• pp.2966-2986
• /
• 2023

Climate change is a constant threat to human life, and it is important to understand the public perception of this issue. Previous studies examining climate change have been based on limited survey data. In this study, the authors used big data such as news articles and social media data, within which the authors selected specific keywords related to climate change. Using these natural language data, topic modeling was performed for discourse analysis regarding climate change based on various topics. In addition, before applying topic modeling, sentiment analysis was adjusted to discover the differences between discourses on climate change. Through this approach, discourses of positive and negative tendencies were classified. As a result, it was possible to identify the tendency of each document by extracting key words for the classified discourse. This study aims to prove that topic modeling is a useful methodology for exploring discourse on platforms with big data. Moreover, the reliability of the study was increased by performing topic modeling in consideration of objective indicators (i.e., coherence score, perplexity). Theoretically, based on the social amplification of risk framework (SARF), this study demonstrates that the diffusion of the agenda of climate change in public news media leads to personal anxiety and fear on social media.

• KIISE Transactions on Computing Practices
• /
• v.22 no.7
• /
• pp.315-319
• /
• 2016

Recurrent neural network based language models (RNN LM) have shown improved results in language model researches. The RNN LMs are limited to post processing sessions, such as the N-best rescoring step of the wFST based speech recognition. However, it has considerable vocabulary problems that require large computing powers for the LM training. In this paper, we try to find the 1st pass N-gram model using word embedding, which is the simplified deep neural network. The class based language model (LM) can be a way to approach to this issue. We have built class based vocabulary through word embedding, by combining the class LM with word N-gram LM to evaluate the performance of LMs. In addition, we propose that part-of-speech (POS) tagging based LM shows an improvement of perplexity in all types of the LM tests.

• Journal of the Korean Society for information Management
• /
• v.32 no.1
• /
• pp.153-169
• /
• 2015

The combined approach of using ego-centric network analysis and dynamic citation network analysis for refining the result of LDA-based topic modeling was suggested and examined in this study. Tow datasets were constructed by collecting Web of Science bibliographic records of White LED and topic modeling was performed by setting a different number of topics on each dataset. The multi-assigned top keywords of each topic were re-assigned to one specific topic by applying an ego-centric network analysis algorithm. It was found that the topical cohesion of the result of topic modeling with the number of topic corresponding to the lowest value of perplexity to the dataset extracted by SPLC network analysis was the strongest with the best values of internal clustering evaluation indices. Furthermore, it demonstrates the possibility of developing the suggested approach as a method of multi-faceted research trend detection.

• The Journal of the Korea Contents Association
• /
• v.18 no.8
• /
• pp.178-186
• /
• 2018

Subject classification of thesis units is essential to serve scholarly information deliverables. However, to date, there is a journal-based topic classification, and there are not many article-level subject classification services. In the case of academic papers among domestic works, subject classification can be a more important information because it can cover a larger area of service and can provide service by setting a range. However, the problem of classifying themes by field requires the hands of experts in various fields, and various methods of verification are needed to increase accuracy. In this paper, we try to classify topics using the unsupervised learning algorithm to find the correct answer in the unknown state and compare the results of the subject classification algorithms using the coherence and perplexity. The unsupervised learning algorithms are a well-known Hierarchical Dirichlet Process (HDP), Latent Dirichlet Allocation (LDA) and Latent Semantic Indexing (LSI) algorithm.

• Journal of Computational Design and Engineering
• /
• v.3 no.1
• /
• pp.37-52
• /
• 2016

To injection mould polymers, designing mould is a key task involving several critical decisions with direct implications to yield quality, productivity and frugality. One prominent decision among them is specifying sprue-bush conduit expansion as it significantly influences overall injection moulding; abstruseness anguish in its design criteria deceives direct determination. Intuitively designers decide it wisely and then exasperate by optimising or manipulating processing parameters. To overwhelm that anomaly this research aims at proposing an ideal design criteria holistically for all polymeric materials also tend as a functional assessment metric towards perfection i.e., criteria to specify sprue conduit size before mould development. Accordingly, a priori analytical criterion was deduced quantitatively as expansion ratio from ubiquitous empirical relationships specifically a.k.a an exclusive expansion angle imperatively configured for injectant properties. Its computational intelligence advantage was leveraged to augment functionality of perfectly injecting into an impression gap, while synchronising both injector capacity and desired moulding features. For comprehensiveness, it was continuously sensitised over infinite scale as an explicit factor dependent on in-situ spatio-temporal injectant state perplexity with discrete slope and altitude for each polymeric character. In which congregant ranges of apparent viscosity and shear thinning index were conceived to characteristically assort most thermoplastics. Thereon results accorded aggressive conduit expansion widening for viscous incrust, while a very aggressive narrowing for shear thinning encrust; among them apparent viscosity had relative dominance. This important rationale would certainly form a priori design basis as well diagnose filling issues causing several defects. Like this the proposed generic design criteria, being simple would immensely benefit mould designers besides serve as an inexpensive preventive cliché to moulders. Its adaption ease to practice manifests a hope of injection moulding extremely alluring polymers. Therefore, we concluded that appreciating injectant's polymeric character to design exclusive sprue bush offers a definite a priori advantage.