• Journal of the Microelectronics and Packaging Society
• /
• v.27 no.2
• /
• pp.53-58
• /
• 2020

Analysis of electric semiconductor packaging technology for electric vehicles was performed. Topic modeling using LDA technique was performed by collecting valid patents by deriving valid patents. It was classified into 20 topics, and the definition of technology was defined through extracted words for each topic. In order to analyze the trend of each topic, the trend of power semiconductor packaging technology was analyzed by deriving hot and cold topics by topic through regression analysis on frequency by year. The package structure technology according to the withstand voltage, the input/output-related control technology and the heat dissipation technology were derived as the hot topic technology, and the inductance reduction technology was derived as the cold topic technology.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.07a
• /
• pp.431-434
• /
• 2012

시간 흐름에 따라 TV 프로그램 스케줄은 변화하고 스케줄의 변화는 사용자 선호에 영향을 미친다. 이러한 스케줄 변화에 따른 토픽의 흐름이 사용자 선호도에 미치는 영향 외에도, 개성에 따른 선호도의 변화는 개인별 차이가 크다. 본 논문은 사용자 선호도 변화에 적응적으로 대응하면서 시간 변화에도 일정한 관심을 보이는 사용자의 선호도에는 가중치를 더한 모델을 목표로 한다. 따라서 제안 모델은 현재의 시청 데이터를 기준으로 한 사용자별 선호도의 선행 정보(prior)로 이전 시청선호를 두었고, 선호도 변화와 일관성을 고려하여 하나의 시청길이에 대한 선호도뿐만 아니라 여러 시청 길이의 선호도를 결합한 선호도를 구성할 수 있는 확장성 있는 모델을 제시한다. 선호도의 일관성에 대한 가중치 연산에 있어 전체 확률모델의 확률을 향상시키는 연산을 통해 정교성을 더한 모델을 제시한다. 실제 사용자들이 시청한 데이터인 2011 TNMS데이터를 기준으로 제안 모델의 성능을 확인한 결과, 기존의 LDA, MDTM모델 보다 나은 성능을 보임을 확인할 수 있었으며, 1주일 단위 추천결과, 5개 추천 시, 최대 67.9%의 추천 정확도를 확인할 수 있었다.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.9
• /
• pp.229-236
• /
• 2016

In the past, crime prediction methods utilized previous records to accurately predict crime occurrences. Yet these crime prediction models had difficulty in updating immense data. To enhance the crime prediction methods, some approaches used social network service (SNS) data in crime prediction studies, but the relationship between SNS data and crime records has not been studied thoroughly. Hence, in this paper, we analyze the relationship between SNS data and criminal occurrences in the perspective of crime prediction. Using Latent Dirichlet Allocation (LDA), we extract tweets that included any words regarding criminal occurrences and analyze the changes in tweet frequency according to the crime records. We then calculate the number of tweets including crime related words and investigate accordingly depending on crime occurrences. Our experimental results demonstrate that there is a difference in crime related tweet occurrences when criminal activity occurs. Moreover, our results show that SNS data analysis will be helpful in crime prediction model as there are certain patterns in tweet occurrences before and after the crime.

• Korea Trade Review
• /
• v.48 no.1
• /
• pp.29-53
• /
• 2023

This study analyzes the statements made by representatives of member countries at the WTO Ministerial Conference (MC), the highest decision-making body of the WTO, to examine the position and attitude that Korea has shown at the WTO during the last 27 years. After constructing text dataset by extracting about 1,800 statement documents made by member countries from the WTO document database, the text mining technique is applied to figure out the characteristics of Korea's statements compared to other member countries. Through formal characteristics such as the number of remarks and length of speech, basic attitudes such as continuity of Korea's interest in the WTO and the level of interest in the WTO are measured. In terms of substantive characteristics, the topics in the statements of Korea are categorized through the LDA topic model, and the keywords of Korea for each session are analyzed through comparative analysis with statements by other member countries.

• Knowledge Management Research
• /
• v.23 no.2
• /
• pp.123-142
• /
• 2022

The non-face-to-face environment accelerated by COVID-19 has speeded up the dissemination of digital virtual ecosystems and metaverse. In order for the metaverse to be sustainable, digital twins that are compatible with the real world are key, and critical technology for that is AR (Augmented Reality). In this study, we examined research trends about AR, and will propose the directions for future AR research. We conducted LDA based topic modeling on 11,049 abstracts of published domestic and foreign AR related papers from 2009 to Mar 2022, and then looked into AR that was comprehensive research trends, comparison of domestic and foreign research trends, and research trends before and after the popularity of metaverse concepts. As a result, the topics of AR related research were deduced from 11 topics such as device, network communication, surgery, digital twin, education, serious game, camera/vision, color application, therapy, location accuracy, and interface design. After popularity of metaverse, 6 topics were deduced such as camera/vision, training, digital twin, surgical/surgical, interaction performance, and network communication. We will expect, through this study, to encourage active research on metaverse AR with convergent characteristics in multidisciplinary fields and contribute to giving useful implications to practitioners.

• Journal of Industrial Convergence
• /
• v.21 no.8
• /
• pp.23-33
• /
• 2023

Consumer review analysis is important for product development, customer satisfaction, competitive advantage, and effective marketing. Increased use of wireless earphones is expected to reach $45.7 billion by 2026 with growth in lifestyle. Therefore, in consideration of the growth and importance of the market, consumer reviews of wireless earphones from Apple and Samsung were analyzed. In this study, 11,320 wireless earphone reviews from Apple and Samsung sold on Coupang were collected to analyze consumers' purchase intentions and analyze consumer satisfaction through analysis of the frequency, sensitivity, and LDA topic model of text mining. As a result of topic modeling, 16 topics were derived and classified into sound quality, connection, shopping mall service, purchase intention, battery, delivery, and price. As a result of brand comparison, Samsung purchased a lot for gift purposes, had a high positive sentiment for price, and Apple had a high positive sentiment for battery, sound quality, connection, service, and delivery. The results of this study can be used as data for related industries as a result of research that can obtain improvements and insights on customer satisfaction, quality and market trends, including manufacturing, retail, marketers, and consumers.

• Information Systems Review
• /
• v.24 no.1
• /
• pp.21-37
• /
• 2022

Drug repositioning, one of the methods of developing new drugs, is a useful way to discover new indications by allowing drugs that have already been approved for use in people to be used for other purposes. Recently, with the development of machine learning technology, the case of analyzing vast amounts of biological information and using it to develop new drugs is increasing. The use of machine learning technology to drug repositioning will help quickly find effective treatments. Currently, the world is having a difficult time due to a new disease caused by coronavirus (COVID-19), a severe acute respiratory syndrome. Drug repositioning that repurposes drugsthat have already been clinically approved could be an alternative to therapeutics to treat COVID-19 patients. This study intends to examine research trends in the field of drug repositioning using machine learning techniques. In Pub Med, a total of 4,821 papers were collected with the keyword 'Drug Repositioning'using the web scraping technique. After data preprocessing, frequency analysis, LDA-based topic modeling, random forest classification analysis, and prediction performance evaluation were performed on 4,419 papers. Associated words were analyzed based on the Word2vec model, and after reducing the PCA dimension, K-Means clustered to generate labels, and then the structured organization of the literature was visualized using the t-SNE algorithm. Hierarchical clustering was applied to the LDA results and visualized as a heat map. This study identified the research topics related to drug repositioning, and presented a method to derive and visualize meaningful topics from a large amount of literature using a machine learning algorithm. It is expected that it will help to be used as basic data for establishing research or development strategies in the field of drug repositioning in the future.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06a
• /
• pp.274-277
• /
• 2011

최근 많은 연구들이 사람들의 삶을 예측하기 위해 개인의 일상적인 패턴을 표현하는 구조를 찾아내는 것을 목표로 하고 있다. 이러한 목표를 위해 사용되는 데이터 중에서 핸드폰을 통해 수집된 데이터는 사용자가 항상 소지하고 있다는 점에서 그 가치가 높다. 그 중에서도 GPS 데이터는 다른 로그 데이터에 비해 가시적이기 때문에 개인의 일상을 표현하는데 더 효율적이다. 본 연구는 핸드폰에서 수집한 GPS 데이터를 Latent Dirichlet Allocation (LDA) 모델에 적용하여 사용자의 행동을 분석하는 주제를 다루려고 한다. 특히 이 논문에서는 개인의 현재 장소가 행동에 영향을 크게 미치는 요소라 가정하고 사용자가 특정 지역을 찾아갔을 때 방문 목적을 찾는 것으로 행동 분석을 구체화하였다. 아래의 내용에서 인사동에서 수집한 GPS 데이터를 이 모델에 적용하여 사용자에게 중요한 위치들로 이루어진 '주제들'을 발견하고, 인사동 방문 목적을 추론하는 실험을 설명할 것이다.

• Journal of Technology Innovation
• /
• v.26 no.4
• /
• pp.199-232
• /
• 2018

There are increasing needs for understanding and fathoming of business management environment through big data analysis at industrial and corporative level. The research using the company disclosure information, which is comprehensively covering the business performance and the future plan of the company, is getting attention. However, there is limited research on developing applicable analytical models leveraging such corporate disclosure data due to its unstructured nature. This study proposes a text-mining-based analytical model for industrial and firm level analyses using publicly available company disclousre data. Specifically, we apply LDA topic model and word2vec word embedding model on the U.S. SEC data from the publicly listed firms and analyze the trends of business topics at the industrial and corporate levels. Using LDA topic modeling based on SEC EDGAR 10-K document, whole industrial management topics are figured out. For comparison of different pattern of industries' topic trend, software and hardware industries are compared in recent 20 years. Also, the changes of management subject at firm level are observed with comparison of two companies in software industry. The changes of topic trends provides lens for identifying decreasing and growing management subjects at industrial and firm level. Mapping companies and products(or services) based on dimension reduction after using word2vec word embedding model and principal component analysis of 10-K document at firm level in software industry, companies and products(services) that have similar management subjects are identified and also their changes in decades. For suggesting methodology to develop analysis model based on public management data at industrial and corporate level, there may be contributions in terms of making ground of practical methodology to identifying changes of managements subjects. However, there are required further researches to provide microscopic analytical model with regard to relation of technology management strategy between management performance in case of related to various pattern of management topics as of frequent changes of management subject or their momentum. Also more studies are needed for developing competitive context analysis model with product(service)-portfolios between firms.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.2
• /
• pp.99-107
• /
• 2009

This paper presents an enhanced hybrid model based on Independent Component Analysis(ICA) in order to features of numeric characters in license plates. ICA which is used only in high dimensional statistical features doesn't consider statistical features in low dimension and correlation between numeric characters. To overcome the drawbacks of ICA, we propose an improved ICA with the hybrid model using both Principle Component Analysis(PCA) and Linear Discriminant Analysis(LDA). Experiment results show that the proposed model has a superior performance in feature extraction and recognition compared with ICA only as well as other hybrid models.