• 한국멀티미디어학회논문지
• /
• 제21권11호
• /
• pp.1263-1270
• /
• 2018

Dynamic adaptation method is an effective technique to enhance the usability by personalizing the soft keyboard layout using the user's key input information. In this paper, we propose a dynamic adaptation method of a keyboard by automatically extracting typos from key input information and using adjacent-typo information classified through the relationship between typos. This technique does not limit a range of adaptation to the inside of the key but extends the range to the neighbor key so that the adaptation effect can be achieved in a wide range at a high speed, thereby the proposed method improves the usability of the keyboard with a small number of inputs. The proposed method showed 25% increase in usability compared to the existing method through experiment and it was confirmed that usability improves up to 33% when used with the existing method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• pp.2278-2291
• /
• 2023

Imported ornamental fish should be quarantined because they can have dangerous diseases depending on their habitat. The quarantine requires a lot of time because quarantine officers collect various information on the imported ornamental fish. Inefficient quarantine processes reduce its work efficiency and accuracy. Also, long-time quarantine causes the death of environmentally sensitive ornamental fish and huge financial losses. To improve existing quarantine systems, information on ornamental fish was collected and structured, and a server was established to develop quarantine performance support software equipped with a text search engine. However, the long names of ornamental fish in general can cause many typos and time bottlenecks when we type search words for the target fish information. Therefore, we need a technique that can correct typos. Typical typo character calibration compares input text with all characters in a calibrated candidate text dictionary. However, this approach requires computational power proportional to the number of typos, resulting in slow processing time and low calibration accuracy performance. Therefore, to improve the calibration accuracy of characters, we propose a fusion system of simple Artificial Neural Network (ANN) models and character preprocessing methods that accelerate the process by minimizing the computation of the models. We also propose a typo character generation method used for training the ANN models. Simulation results show that the proposed typo character correction system is about 6 times faster than the conventional method and has 10% higher accuracy.

• 한국문헌정보학회지
• /
• 제45권1호
• /
• pp.377-393
• /
• 2011

이 연구에서는 국내 주요 검색 포털인 네이버 이용자들의 검색 행태 추이를 조사, 분석하였다. 즉 1년 동안 분기별로 네이버에 입력된 질의들을 대상으로 질의의 입력 행태, 오타 입력 행태, 멀티미디어 검색 행태, 결과 문서 클릭 행태 등의 추이를 조사하였다. 이를 위하여 이용자들이 입력한 통합 검색 질의들로 구성된 질의 로그와 질의에 대한 검색 결과에서 이용자들이 조회한 문서를 기록한 클릭 로그를 분석하였다. 연구결과, 입력된 질의의 길이 및 주제, 멀티미디어 질의의 특징 및 비율, 오타의 비율 등에 있어서는 1년 동안 큰 변화 없이 일정한 것으로 나타났다. 반면, 질의별로 발생되는 클릭 횟수는 시간이 지남에 따라 점진적으로 증가하는 것으로 나타났다. 본 연구의 결과는 향후 포털의 효과적인 콘텐츠 구축 및 검색 알고리즘 개발에 활용될 수 있을 것으로 기대된다.

• 호남수학학술지
• /
• 제42권2호
• /
• pp.411-423
• /
• 2020

In this paper, we correct some errors and typos of [2] and introduce a new concept related to pseudo n-Jordan homomorphisms, that we call it pseudo n-homomorphism. We investigate automatic continuity and positivity of pseudo n-homomorphisms and pseudo n-Jordan homomorphisms on Banach algebras and C*-algebras. Moreover, we show that the sum of two pseudo n-Jordan homomorphisms is not a pseudo n-Jordan homomorphism and we show that under some conditions the sum of two pseudo n-Jordan homomorphisms is a pseudo n-Jordan homomorphism.

• 한국컴퓨터정보학회논문지
• /
• 제24권7호
• /
• pp.9-17
• /
• 2019

As the artificial intelligence technology has developed recently, researches on chatbots that provide information and contents desired by users through an interactive interface have become active. Since chatbots require a variety of natural language processing technology and domain knowledge including typos and slang, it is currently limited to develop chatbots that can carry on daily conversations in a general-purpose domain. In this study, we propose an artificial intelligence chatbot that can provide real-time public traffic information and route information. The proposed chatbot has an advantage that it can understand the intention and requirements of the user through the conversation on the messenger platform without map application.

• Journal of Information Processing Systems
• /
• 제17권1호
• /
• pp.203-212
• /
• 2021

To eliminate ambiguities in the existing methods to simplify Chinese pronunciation learning, we propose a model that can predict the pronunciation of Chinese characters automatically. The proposed model relies on a statistical machine translation (SMT) framework. In particular, we consider the components of Chinese characters as the basic unit and consider the pronunciation prediction as a machine translation procedure (the component sequence as a source sentence, the pronunciation, pinyin, as a target sentence). In addition to traditional features such as the bidirectional word translation and the n-gram language model, we also implement a component similarity feature to overcome some typos during practical use. We incorporate these features into a log-linear model. The experimental results show that our approach significantly outperforms other baseline models.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 제37회 하계학술대회 논문집 B
• /
• pp.679-680
• /
• 2006

Various different types of joining between High Tc superconducting(HTS) tapes were prepared and current-voltage(I-V) characteristic curves were investigated at 77 K, liquid nitrogen temperature. Two typos of HTS tapes wore used, one is no laminated tape(Sumitomo high strength type tape) and the other stainless steel laminated tape(AMSC(American Superconductors Inc.) 3ply tapes) Sample joints were lap-jointed with indium or solder. Joint resistances between Sumitomo tapes with 4-10 mm in length were estimated from I-V curves and in the range of $4-8n{\Omega}$ at 77 K. Joint resistances of AMSC tapes were in the range of $140-170n{\Omega}$, much higher than them of Sumitomo samples. The n-values of jointed HTS tapes were 50% of them with no joint. In AMSC tapes, indium is better than solder as the jointing material.

• 한국전자통신학회논문지
• /
• 제11권1호
• /
• pp.93-98
• /
• 2016

사건 및 사고로 다수의 피해자 또는 참고인들은 경찰서를 방문하고 진술 조서를 작성한다. 진술 조서 과정 중오기 또는 오타로 인하여 수정이 요청 되었을 때 수정 부분을 수정한 후 지문을 이용하여 수정되었음을 인정하는 불필요한 단계 과정에서 불편함과 위생적 문제점을 해결하고, 경찰의 내 수사 단계에서 진술조서 작성 시 KICS와 전자 수사자료표 시스템을 연동한 지문인식기 도입으로 원터치 신원 확인 및 간인 날인 절차를 간소화 할 수 있다.

• 국제학술발표논문집
• /
• The 1th International Conference on Construction Engineering and Project Management
• /
• pp.1262-1267
• /
• 2005

It is still difficult to share and utilize the information generated at each phase of a steel box girder production process due to the spatial gap and different level of management information. The physical distance results in the inefficiency of the information transmission, the accidental omission and typos of the relative information, and so on. Various levels of management information make it difficult to embody a new management system. Eventually, these factors incur the loss of cost and schedule and interrupt development of a new management system. This paper analyzes a current process and presents graphical process flow by using IDEF0. Based this analysis, the research for new production process and work breakdown structure (WBS) is conducted. At the end of this paper, the conceptual design of this system is suggested. Through new management system, it is expected that the model proposed in this study will improve the management process in the steel box production, and the improved process will reduce the redundant cost and schedule information, transmission and deposit generated by manual paper.

• Journal of Advanced Marine Engineering and Technology
• /
• 제34권6호
• /
• pp.871-879
• /
• 2010

본 논문은 뉴스 기사의 댓글에 대한 사용자의 감정을 분류하는 시스템을 제안한다. 제안된 시스템은 댓글의 문서 분류 시스템으로 기계학습에 기반을 두고 있다. 댓글은 일반적인 문서와 달리 본문을 가지고 있으며 본문의 내용이 독자의 감정에 영향을 줄 수 있다. 본 논문에서는 이와 같은 댓글의 특성과 여러 가지 자원을 이용하여 감정 분류를 위한 자질을 제안하고 이들의 가중치 설정 방법을 제안한다. 실험을 통해 이러한 가중치 설정 방법이 한글 뉴스의 댓글에 대한 감정을 분류하는데 효과적임을 알 수 있었다. 또한 댓글과 같이 많은 오류를 포함하는 문서에 대해서 문자 단위의 2음절과 3음절 자질도 충분히 이용 가치가 있음을 확인할 수 있었다. 향후에 뉴스 기사의 댓글뿐 아니라 상품 댓글 등 일반적인 감정 분석에 적용할 계획이다.