• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.916-917
• /
• 2023

본 연구는 사용자의 음성 패턴 분석과 텍스트 분류를 중심으로 이루어지는 한국어 감정 인식 작업을 개선하기 위해 Macaron Net 텍스트 모델의 결과와 MFCC 음성 모델의 결과 가중치 합을 분류하여 최종 감정을 판단하는 기존 82.9%였던 정확도를 텍스트 모델 기준 87.0%, Multi-Modal 모델 기준 88.0%로 개선한 모델을 제안한다. 해당 모델을 우울증 예방 플랫폼의 핵심 모델에 탑재하여 covid-19 팬데믹 이후 사회의 문제점으로 부상한 우울증 문제 해소에 기여 하고자 한다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2004.05a
• /
• pp.487-490
• /
• 2004

이메일과 같은 텍스트 기반의 서비스 둥이 점차 대중화되고 있지만, 이러한 텍스트 기반의 서비스에서는 메시지를 전달할 때 수신자가 필자의 감정 상태를 정확하게 파악하기 어려운 문제가 있다. 이러한 문제를 단편적으로 해결하기 위하여 감정 상태를 나타내는 이모티콘(emoticon)을 사용하기도 하지만 이는 보편적이지 않아서 사용하기에 불편한 점이 있다. 따라서 본 논문에서는 이러한 문제를 해결하기 위한 방안으로 일반 텍스트 문서에 감정 태그를 삽입하여 필자의 감정을 표현할 수 있도록 새로운 마크업 언어인 EmoXML(Emotion XML)을 정의한다. 그리고 문장 내에 포함되어 있는 감정 어휘를 인식하여, 관련 감정 태그를 자동으로 생성하고 처리할 수 있는 시스템을 설계한다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.6
• /
• pp.231-243
• /
• 2017

The purpose of this study is to improve the social acceptance of AVs by analyzing the citizen's perception using an emotional analysis technique which belongs to a type of text mining. The source of the data is originated from 3 year accumulated internet articles and comments on AV from 164 newspapers and Naver. According to the study results, there exists a positive perception on AVs, although negative ones are more frequent than the positive. Also most of people take neutral position on AV due to the unfamiliarity and lack of experience on AVs And these problems needs to be responded before AV's commercialization through continuous analyses on the perception and social acceptance.

• Korean small business review
• /
• v.42 no.4
• /
• pp.235-250
• /
• 2020

This study surveyed the perception of university students about employment in Small and Medium-sized Enterprises(SME) in the Chungbuk area to prepare improvement measures. In particular, the data were collected in descriptive questions along with the existing survey methods, and the perception of SME and decent work was identified using text-mining. As a result of the analysis, there are positive perceptions of jobs at SME such as various work experiences and low job competition rates, while there are generally many negative perceptions in pay, work and welfare. However, as a result of co-occurrence network analysis of responses to decent jobs, 'Information' was derived as a keyword. Currently, college students' negative perception of SME is affected by the lack of sufficient information, which needs to be improved first. To solve this problem, it was proposed to establish and operate a platform that can provide information on employment of SME and select necessary personnel.

• Journal of Korea Society of Industrial Information Systems
• /
• v.19 no.5
• /
• pp.51-56
• /
• 2014

In the digital world of the internet, steganography is introduced to hide the existence of the secret communication by concealing a secret message inside another unsuspicious cover medium. The third parties are unaware that a stego medium is being communicated. There exists a large variety of steganography methods based on texts. In this paper, analyzed the advantages and significant disadvantages of each existing text steganography method and how new approach could be proposed as a solution. The objective of this paper is to propose a method for hiding the secret messages in safer manner from external attacks by encryption rearrangement key.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.423-425
• /
• 2022

음성인식은 컴퓨터가 사람의 언어를 이해하여, 소리로 발화하는 사람의 음성을 인식하여 텍스트로 바꾸는 과정을 의미하며, 최근 활용도가 높아지고 있다. 음성인식 엔진은 얼마나 많은 학습데이터를 기반으로 훈련을 했느냐에 따라서 그 성능이 결정되기 때문에, 자신의 서비스 에 맞는 음성인식 엔진을 적절히 선택할 수 있어야 한다. 음성인식 엔진의 성능이 수시로 변경될 수 있기 때문에 표준 인터페이스를 빠른 개발을 진행할 수 있도록 표준 포맷을 제안하였다.

• Journal of The Korean Association of Information Education
• /
• v.26 no.1
• /
• pp.65-73
• /
• 2022

In this study, by using Entry text model learning, educational contents for artificial intelligence education of elementary school students are developed and applied to actual classes. Based on the elementary and secondary artificial intelligence content table, the achievement standards of practical software education and artificial intelligence education will be reconstructed.. Among text, images, and sounds capable of machine learning, "production of emotion recognition programs using text model learning" will be selected as the educational content, which can be easily understood while reducing data preparation time for elementary school students. Entry artificial intelligence is selected as an education platform to develop artificial intelligence education contents that create emotion recognition programs using text model learning and apply them to actual elementary school classes. Based on the contents of this study, As a result of class application, students showed positive responses and interest in the entry AI class. it is suggested that quantitative research on the effectiveness of classes for elementary school students is necessary as a follow-up study.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.3
• /
• pp.847-852
• /
• 2010

Text in natural images has a various and important feature of image. Therefore, to detect text and extraction of text, recognizing it is a studied as an important research area. Lately, many applications of various fields is being developed based on mobile phone camera technology. Detecting edge component form gray-scale image and detect an boundary of text regions by local standard deviation and get an connected components using Euclidean distance of RGB color space. Labeling the detected edges and connected component and get bounding boxes each regions. Candidate of text achieved with heuristic rule of text. Detected candidate text regions was merged for generation for one candidate text region, then text region detected with verifying candidate text region using ectilarity characterization of adjacency and ectilarity between candidate text regions. Experctental results, We improved text region detection rate using completentary of edge and color connected component.

• Annual Conference on Human and Language Technology
• /
• 2015.10a
• /
• pp.240-245
• /
• 2015

일반영역 음성인식은 n-gram 희소성 문제로 인해 대용량의 언어모델이 필요하다. 대용량 언어모델은 분산형 모델로 구현될 수 있고, 사용자 입력에 대한 동적 언어모델 보간 기술을 통해 음성인식 성능을 개선할 수 있다. 본 논문은 동적 언어모델 보간 기술에 대한 새로운 접근방법을 시도한다. 텍스트 군집화를 통해 주제별 언어모델을 생성한다. 여기서 주제는 사용자 입력 영역에 대응한다. 본 논문은 사용자 입력에 대하여 실시간으로 주제별 언어모델의 보간 가중치 값을 계산하는 접근 방법을 제시한다. 또한 언어모델의 보간 가중치 값 계산의 부담을 감소하기 위해 언어모델 군집화를 통해 대용량 언어모델 보간 접근 방법의 연산 부담을 해소하기 위한 시도를 한다. 주제별 언어모델에 기반하고 언어모델 군집화를 통한 동적 언어모델 보간 기술의 실험 결과 음성인식 오류 감소율 6.89%를 달성했다. 또한 언어모델 군집화 기술은 음성인식 정확도를 0.09% 저하시켰을 때 실행 시간을 17.6% 개선시키는 실험결과를 보였다.

• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.205-214
• /
• 2006

Texts in images have significant and detailed information about the scenes, and if we can automatically detect and recognize those texts in real-time, it can be used in various applications. In this paper, we propose a new text detection method that can find texts from the various camera-captured images and propose a text segmentation method from the detected text regions. The detection method proposes color variance as a detection feature in RGB color space, and the segmentation method suggests an improved K-means color clustering in RGB color space. We have tested the proposed methods using various kinds of document style and natural scene images captured by digital cameras and mobile-phone camera, and we also tested the method with a portion of ICDAR[1] contest images.