• The Transactions of the Korea Information Processing Society
• /
• v.3 no.5
• /
• pp.1273-1280
• /
• 1996

In order perform high accuracy recognition of text recognition systems, the recognized text must be processed through a post-processing stage using contextual information. We present a system that combines multiple knowledge sources to post-process the output of an optical character recognition(OCR) system. The multiple knowledge sources include characteristics of word, wrongly recognized types of Hangul characters, and Hangul word learning In this paper, the wrongly recognized characters which are made by OCR systems are collected and analyzed. We imput a Korean dictionary with approximately 15 0,000 words, and Korean language texts of Korean elementary/middle/high school. We found that only 10.7% words in Korean language texts of Korean elementary/middle /high school were used in a Korean dictionary. And we classified error types of Korean character recognition with OCR systems. For Hangul word learning, we utilized indexes of texts. With these multiple knowledge sources, we could predict a proper word in large candidate words.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.4
• /
• pp.91-98
• /
• 2012

A group key exchange (GKE) protocol is designed to allow a group of parties communicating over a public network to establish a common secret key. As group-oriented applications gain popularity over the Internet, a number of GKE protocols have been suggested to provide those applications with a secure multicast channel. Among the many protocols is Yi et al.'s password-based GKE protocol in which each participant is assumed to hold their individual password registered with a trusted server. A fundamental requirement for password-based key exchange is security against off-line dictionary attacks. However, Yi et al.'s protocol fails to meet the requirement. In this paper, we report this security problem with Yi et al.'s protocol and show how to solve it.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.6
• /
• pp.1598-1606
• /
• 1996

In order to achieve high accuracy of off-line character recognition(OCR) systems, the recognized text must be processed through a post-processing stage using contextual information. In this paper, we reclassify Korean word classes in terms of OCR word correction. And we collect combinations of Korean particles(approximately 900) linguistic verbal from(around 800). We aggregate 9 Korean irregular verbal phrases defined from a Korean linguistic point of view. Using these Korean word information and a Head-tail method, we can correct misrecognized words. A Korean character recognizer demonstrates 93.7% correct character recognition without a post-processing stage. The entire recognition rate of our system with a post-processing stage exceeds 97% correct character recognition.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.6
• /
• pp.1251-1259
• /
• 2017

One-time password has been proposed for the purpose of addressing the security problems of the simple password system: fixed passwords and pre-shared passwords. Since it employs the consecutive hash values after a root hash value is registered at the server, the security weakness of the fixed passwords has been addressed. However, it has a shortcoming of re-registering a new root hash value when the previous hash chain's hash values are exhausted. Even though several one-time password systems not requiring re-registration have been proposed, they all have several problems in terms of constraint conditions and efficiency. In this paper, we propose the one - time password scheme based on a hash chain that generates one - time passwords using only two cryptographic hash functions at each authentication and satisfies the existing constraints without re-registration, Security requirements and efficiency.

• Journal of the Korea Convergence Society
• /
• v.12 no.3
• /
• pp.1-7
• /
• 2021

Since Neural Machine Translation (NMT) uses only a limited number of words, there is a possibility that words that are not registered in the dictionary will be entered as input. The proposed method to alleviate this Out of Vocabulary (OOV) problem is Subword Tokenization, which is a methodology for constructing words by dividing sentences into subword units smaller than words. In this paper, we deal with general subword tokenization algorithms. Furthermore, in order to create a vocabulary that can handle the infinite conjugation of Korean adjectives and verbs, we propose a new methodology for subword tokenization training by separating the Jongsung(coda) from Korean syllables (consisting of Chosung-onset, Jungsung-neucleus and Jongsung-coda). As a result of the experiment, the methodology proposed in this paper outperforms the existing subword tokenization methodology.

• The Korean Society of Law and Medicine
• /
• v.15 no.1
• /
• pp.335-373
• /
• 2014

According to one Medicare report, in the US, total federal spending on health care expends almost 18 percent of the nation's GDP, about double what most industrialized nations spend on health care. And in 2011, Medicare spending reached close to $554 billion, which amounted to 21 percent of the total spent on U.S. health care in that year. Of that $554 billion, Medicare spent 28 percent, or about $170 billion, on patients' last six months of life. So what are the reasons of this high cost in EOL care and its possible solutions? Much spendings of Medicare on End-of-Life care for the terminally ill/chronically ill in the US has led health economics experts to assess the characteristics of the care. Decades of study shows that EOL care is usually supply-sensitive and poor in cost-effectiveness. The volume of care is sensitively depending on the supply of resources, rather than the severity of illness or preferences of patients. This means at the End-of-Life care, the medical resources are being overused. On the other hand, opposed to the common assumption, "The more care the better utility", the study shows that the outcome is very poor. Actually the patient preference and concerns are quite the opposite from what intense EOL care would bring about. This study analyzes the reasons for the supply-sensitiveness of EOL care. It can be resulted from the common misconception about the intense care and the outcome, physicians' mission for patients, lack of End-of-Life Care Decision which helps the patients choose their own preferred treatment intensity. It also could be resulted from physicians' fear of legal liabilities, and the management strategy since the hospitals are also seeking for financial benefits. This study suggests the possible solutions for over-treatment at the End-of-Life resulting from supply-sensitiveness. Solutions can be sought in two aspects, legal implementation and management strategy. In order to implement advance directive properly, active ethics education for physicians to change their attitude toward EOL care and more conversations about end-of-life care between physicians and patients is crucial, and incentive system for the physicians who actively have the conversations with patients will also help. Also, the general education towards the public is also important in the long run, and easy and official advance directive registry system-such as online registry-has to be built and utilized more widely. Alternative strategies in management are also needed. For example, the new strategic cost management and management education, such as cutting unnecessary costs and resetting values as medical providers have to be considered. In order to effectively resolve the problem in EOL care for the terminally ill/chronically ill and provide better experience to the patients, first of all, the misconception and the wrong conventional wisdom among doctors, patients, and the government have to be overcome. And then there should be improvements in systems and cultures of the EOL care.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.292-294
• /
• 2018

Recently, damage caused by natural disasters such as fire, earthquake, heavy rains and heavy snow is increasing. In addition, traffic accidents due to freezing, fog and fire in tunnels and bridges are frequently occurring. In such a disaster situation, it is very important to take prompt action by the person in charge of managing the facility and area.To this end, a disaster broadcasting system is used, but in the existing system, the broadcasting room and the speaker are connected by a wired connection. Also, the person in charge has to be in the broadcasting room to broadcast, which has a problem of delaying the time. In this paper, we design a disaster broadcasting system using LTE modem. The designed system enables a broadcasting person to make a call to a broadcasting system from anywhere using a cellular phone and a public telephone. Broadcasting via telephone is possible only with the telephone number pre-registered in the system and can be registered / deleted by the administrator. The registered telephone number, incoming voice file, and announcement voice for automatic broadcasting are stored in the system internal SD memory for convenient management. This disaster broadcasting system is expected to contribute to quick and convenient disaster broadcasting.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.437-442
• /
• 2006

최근 많은 관심을 끌고 있는 지문인식시스템은 사용자의 지문영상을 입력 받아 사전에 등록된 템플릿과 비교하여 사용자 여부를 확인하는 사용자 인증 도구이다. 지문을 입력 받기 위한 센서와 매칭 알고리즘 등이 활발히 개발되고 있으며, 실제로 전자상거래나 출입통제시스템 등의 많은 분야에 적용되고 있다. 지문인식시스템에 대한 기존의 평가는 수집된 지문 DB 에 대해 인식 성능이 얼마인지, 쌍둥이들을 잘 구분하는지, 위조 지문을 파악할 수 있는지 등 주로 지문인식 자체의 성능에 초점이 맞추어져 있었다. 하지만 지문인식은 사용자나 환경과 관련된 많은 요인에 영향을 받기 때문에, 시스템을 효과적으로 적용하기 위해서는 이들에 대한 분석이 필요하다. 지문인식시스템에 대한 사용성 평가는 시스템이 대상환경에 효과적으로 적용되도록 하고, 사용성 분석을 통해 보다 편리하고 효율적인 사용자 인터페이스의 개발을 유도한다. 본 논문에서는 지문인식에 영향을 주는 요인을 사용자와 시스템 측면에서 분석하고, 사용성 평가를 통해 효과적인 지문인식시스템 인터페이스 구축을 위한 가이드라인을 제시한다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.1
• /
• pp.35-40
• /
• 2013

The messages on mobile terminal may contain context information such as user's location, time and preference. This paper proposes message forwarding system based on user's context. The server stores the predefined target addresses which may be mobile phone number, web server address and email address. On request for message transmission, the server tries to find a target address matching a user's context. Thus, a sender transmits messages to a representative address without knowing various receiver's addresses and a receiver can retrieve classified messages according to subject/location.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.659-662
• /
• 2008

In sports videos, text provides valuable information about the game such as scores and information about the players. This paper proposed a robust recognition method of player name in golf videos. In golf, most of users want to search the scenes which contain the play shots of favorite players. We use text information in golf videos for robust extraction of player information, By using OCR, we have obtained the text information, and then recognized the player information from player name DB. We can search the scenes of favorite players by using this player information. By conducting experiments on several golf videos, we demonstrate that our method achieves impressive performance with respect to the robustness.