• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.551-552
• /
• 2021

인공지능 기술의 발달로 현대사회 사람들은 일상생활에 편리함을 제공받고 업무의 효율성과 생산성이 향상되었다. 대한민국 보육교사들은 수많은 업무로 인해 근무시간 대비 휴식시간과 점심시간이 턱없이 부족하다. 본 논문에서는 보육교사가 일일이 아동들의 사진을 분류하는 업무에 편의성을 제공하여 보다 많은 휴식시간을 보장받고 활용할 수 있도록 전이학습을 통한 아동 이미지 자동 분류 시스템에 대해 기술하고자 한다. 이 시스템을 통해 분류된 아동들의 사진을 매년 제작하는 유아 포토북 제작에도 활용할 수 있을 것으로 기대된다.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.144-151
• /
• 2021

딥러닝의 등장으로 자동 음성 인식 (Automatic Speech Recognition) 기술은 인간과 컴퓨터의 상호작용을 위한 가장 중요한 요소로 자리 잡았다. 그러나 아직까지 유사 발음 오류, 띄어쓰기 오류, 기호부착 오류 등과 같이 해결해야할 난제들이 많이 존재하며 오류 유형에 대한 명확한 기준 정립이 되고 있지 않은 실정이다. 이에 본 논문은 음성 인식 시스템의 오류 유형 분류 기준을 한국어에 특화되게 설계하였으며 이를 다양한 상용화 음성 인식 시스템을 바탕으로 질적 분석 및 오류 분류를 진행하였다. 실험의 경우 도메인과 어투에 따른 분석을 각각 진행하였으며 이를 통해 각 상용화 시스템별 강건한 부분과 약점인 부분을 파악할 수 있었다.

• Journal of Industrial Convergence
• /
• v.20 no.8
• /
• pp.77-84
• /
• 2022

This study aims to present a method for implementing a decision support system that can be used for selecting emerging technologies by applying a machine learning-based automatic classification technique. To conduct the research, the architecture of the entire system was built and detailed research steps were conducted. First, emerging technology candidate items were selected and trend data was automatically generated using a big data system. After defining the conceptual model and pattern classification structure of technological development, an efficient machine learning method was presented through an automatic classification experiment. Finally, the analysis results of the system were interpreted and methods for utilization were derived. In a DTW-kNN-based classification experiment that combines the Dynamic Time Warping(DTW) method and the k-Nearest Neighbors(kNN) classification model proposed in this study, the identification performance was up to 87.7%, and particularly in the 'eventual' section where the trend highly fluctuates, the maximum performance difference was 39.4% points compared to the Euclidean Distance(ED) algorithm. In addition, through the analysis results presented by the system, it was confirmed that this decision support system can be effectively utilized in the process of automatically classifying and filtering by type with a large amount of trend data.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.5
• /
• pp.432-441
• /
• 2002

Though many services offer useful information on internet, computer users are not so familiar with such services that they need an assistant system to use the services easily In the case of web sites, for example, the operators answer the users e-mail questions, but the increasing number of users makes it hard to answer the questions efficiently. In this paper, we propose an assistant system which responds to the users questions automatically and helps them browse the Hanmail Net FAQ (Frequently Asked Question) conceptually. This system uses two-level self-organizing map (SOM): the keyword clustering SOM and document classification SOM. The keyword clustering SOM reduces a variable length question to a normalized vector and the document classification SOM classifies the question into an answer class. Experiments on the 2,206 e-mail question data collected for a month from the Hanmail net show that this system is able to find the correct answers with the recognition rate of 95% and also the browsing based on the map is conceptual and efficient.

• Convergence Security Journal
• /
• v.18 no.4
• /
• pp.19-25
• /
• 2018

In this paper, we propose an user-centered integrated lost-goods management system through a ranking system based on weight and a hierarchical image classification system based on Deep Learning. The proposed system consists of a hierarchical image classification system that automatically classifies images through deep learning, and a ranking system modules that listing the registered lost property information on the system in order of weight for the convenience of the query process.In the process of registration, various information such as category classification, brand, and related tags are automatically recognized by only one photograph, thereby minimizing the hassle of users in the registration process. And through the ranking systems, it has increased the efficiency of searching for lost items by exposing users frequently visited lost items on top. As a result of the experiment, the proposed system allows users to use the system easily and conveniently.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.445-447
• /
• 2001

본 논문에서는 콜센터를 위하여 설계 및 구현된 전자메일 자동응답 및 관리 시스템 주에서 서버 시스템에 해당하는 뿐을 기술하였다. 본 연구에서는 도메인에 특성화된 표현 형식 개발을 개발하여 보다 효율적인 3단계 매칭방법을 가진 자동응답기, 학습에 기반한 도메인 비의존적인 자동분류기 및 적용방법의 재배열이 가능한 담당자 분배기를 구현하였다.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.527-534
• /
• 2016

The emergent information society requires the talent for creative thinking based on problem-solving skills and comprehensive thinking rather than simple memorization. Therefore, the Korean curriculum has also changed into the direction of the creative thinking through increasing short-answer questions that can determine the overall thinking of the students. However, their scoring results are a little bit inconsistency because scoring short-answer questions depends on the subjective scoring of human raters. In order to alleviate this point, an automated scoring system using a machine learning has been used as a scoring tool in overseas. Linguistically, Korean and English is totally different in the structure of the sentences. Thus, the automated scoring system used in English cannot be applied to Korean. In this paper, we introduce an automated scoring system for Korean short-answer questions using predictability and unanimity. We also verify the practicality of the automatic scoring system through the correlation coefficient between the results of the automated scoring system and those of human raters. In the experiment of this paper, the proposed system is evaluated for constructed-response items of Korean language, social studies, and science in the National Assessment of Educational Achievement. The analysis was used Pearson correlation coefficients and Kappa coefficient. Results of the experiment had showed a strong positive correlation with all the correlation coefficients at 0.7 or higher. Thus, the scoring results of the proposed scoring system are similar to those of human raters. Therefore, the automated scoring system should be found to be useful as a scoring tool.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.581-584
• /
• 2002

본 논문에서는 범주 내의 키워드 빈도에 의해 문서를 자동으로 분류하는 방법을 제안한다. 문서 자동분류 시스템에서는 문서와 문서를 비교하기 위해서 분류 자질(feature)에 적절한 가중치를 부여할 필요가 있다. 본 논문에서는 수작업으로 분류된 신문기사를 이용하여 자질의 가중치를 학습하는 방법을 사용하였다. 기존의 용어가중치 방법은 각 범주별로 가장 많이 등장한 명사부터 순서대로 추출하여 가중치를 주는 방법을 사용한 것에 비해 본 논문에서는 명사의 출현 횟수뿐만 아니라 출현위치를 함께 고려하여 가중치를 계산하는 방법을 제안한다. 또한 단어 빈도 가중치 방법의 변형된 방식을 사용함으로써 기존의 단어 빈도 가중치 방법과 비교하여 분류 정확도 측면에서 9%이상 성능 향상을 있음을 보인다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.4
• /
• pp.386-391
• /
• 2015

This paper proposed the optimal attributes for text classification based on Korean and Chinese linguistic features. The experiments committed to discover which is the best feature among n-grams which is known as language independent, morphemes that have language dependency and some other feature sets consisted with n-grams and morphemes showed best results. This paper used SVM classifier and Internet news for text classification. As a result, bi-gram was the best feature in Korean text categorization with the highest F1-Measure of 87.07%, and for Chinese document classification, 'uni-gram+noun+verb+adjective+idiom', which is the combined feature set, showed the best performance with the highest F1-Measure of 82.79%.

• The Journal of the Korea Contents Association
• /
• v.5 no.4
• /
• pp.169-179
• /
• 2005

Standard industry and occupation code are usually assigned manually in Korean census. The manual coding is very labor intensive and expensive task. Furthermore, inconsistent coding is resulted from the ability of human experts and their working environments. This paper proposes an automatic code classification system which converts natural language responses on survey questionnaires into corresponding numeric codes by using manually constructed rule base and example-based machine learning. The system was trained with 400,000 records of which standard codes was assigned. It was evaluated with 10-fold cross validation and was tested with three code sets: population occupation set, industry set, and industry survey set. The proposed system showed 76.63%, 82.24 and 99.68% accuracy for each code set.