• Phonetics and Speech Sciences
• /
• v.15 no.4
• /
• pp.109-118
• /
• 2023

Cardiac arrest is a critical medical emergency where immediate response is essential for patient survival. This is especially true for Out-of-Hospital Cardiac Arrest (OHCA), for which the actions of emergency medical services in the early stages significantly impact outcomes. However, in Korea, a challenge arises due to a shortage of dispatcher who handle a large volume of emergency calls. In such situations, the implementation of a machine learning-based OHCA detection program can assist responders and improve patient survival rates. In this study, we address this challenge by developing a machine learning-based OHCA detection program. This program analyzes transcripts of conversations between responders and callers to identify instances of cardiac arrest. The proposed model includes an automatic transcription module for these conversations, a text-based cardiac arrest detection model, and the necessary server and client components for program deployment. Importantly, The experimental results demonstrate the model's effectiveness, achieving a performance score of 79.49% based on the F1 metric and reducing the time needed for cardiac arrest detection by 15 seconds compared to dispatcher. Despite working with a limited dataset, this research highlights the potential of a cardiac arrest detection program as a valuable tool for responders, ultimately enhancing cardiac arrest survival rates.

• Journal of the Society of Disaster Information
• /
• v.16 no.1
• /
• pp.203-209
• /
• 2020

Purpose: This study aims to support the dispatcher to analysis the architecture type of fire. Method: Analysis the dispatch protocol guideline (released by gyunggi fire brigade) and make the dispatch scenario by site, combustibles, evacuation, fire extinguish systems. Result: After making scenario, develop the system (for dispatcher), is based on the tablet PC. Conclusion: Dispatch systems apply not only fire but rescue and disaster. This study focus on the fire, but It is need to expend the rescue and disaster. in korea, Fire Safety Evaluation and Multishop DB are possible to link to this system.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.16-21
• /
• 2021

소방 본부의 119 종합상황실에서는 24시간 국민의 안전을 위해 긴급 신고를 접수한다. 수보사 분들은 24시간 교대 근무를 하며 신고 전화에 접수 및 응대 뿐만 아니라 출동, 지휘, 관제 업무를 함께 수행한다. 이 논문에서는 이 같은 수보사의 업무 지원을 위해 우리가 구축한 음성 인식과 결합된 실시간 텍스트 분석 시스템에 대해서 소개하고, 출동 지령서 자동 작성을 위한 키워드 검출 및 대화 요약 및 개체명 인식에 기반한 대화 상태 추척 방법에 대해 설명하고자 한다. 대화 요약 기술은 음성 인식 결과를 실시간으로 분석하여 중요한 키워드의 검출 및 지령서 자동 작성을 위한 후처리를 수행하며, 문장 수준에서 개체명 인식 및 관계 분석을 통한 목적 대화의 대화 상태 추적을 수행한다. 이 같은 응용 시스템은 딥러닝 및 기계학습 기반의 자연어 처리 시스템이 실시간으로 텍스트 분석을 수행할 수 있는 기술 수준이 되었음을 보여주며, 긴급한 상황에서 많은 신고 전화를 접수하는 수보사의 업무 효율 증진 뿐만 아니라, 정확하고 신속한 위치 파악으로 신고자를 도와주어 국민안전 증진에 도움을 줄 수 있을 것으로 기대된다.

• Journal of Fashion Business
• /
• v.26 no.2
• /
• pp.95-109
• /
• 2022

This study was aimed at developing a new textile design based on the authentic and cultural resources of the Gangneung Subo pattern and applying the textile design to knitted fashion products. Gangneung has been recognized for its outstanding artistry in the field of Gyubang art. Gangneung Subo is an embroidered wrapping cloth. The discovered and preserved Subo at this time was from the Kwandong region centered in Gangeung, and is regarded as the product of the indigenous native culture in Kwandong. Therefore, as a representative cultural resource of Gangneung, the Gangneung Subo has sufficient value as a material for the development of cultural products with uniqueness, distinctiveness, and historicality. As a research method, the background of Gangneung Subo was investigated. A total of 12 motifs were created while preserving the authentic originality of the Gangneung Subo pattern and minimizing unwanted deformations of the pattern during the developing process. The created motifs were repeatedly applied to the pattern and new textile designs were created. Eighteen knit fashion products, including narrow and wide-width mufflers and neck warmers, were developed by applying the new textile designs. As a significant cultural resource for cultural goods development, this study ascertained the value of Gangneung Subo, preserving its unique distinction and history. This study was especially significant since the Gangneung cultural goods developed used knitted material and extended the development to producing real products.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.8 no.3
• /
• pp.57-65
• /
• 1984

This is to study some female court costumes, Jamgsam and Sooboro etc. (장삼, 수보노), which seem to had been used as ceremonial robes. There is no remaines, and only a little written materials can be used. The Kook-Chang-Dogam Eui Gues(국장도감의구) give us some know ledges on the shapes, materials, embroideries and the usages of them. After surveying the provisions of the Eui-Gues, Auther arrived at conclusions as follow; 1. Jangsam(장삼) set is the counterpart of the Myunbok(면복) set. 2. Sooboro(수보노), worn over the Sang(상), is short, divided into three parts from the middle of the length, and the peonies(목단) are embroidered at the bottom of the three parts. 3. Jangsam(장삼) is accompanied by susik(수식), which seems to be a kind of headband, and a pair of gloves(수의).

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1345-1347
• /
• 2015

본 논문에서는 응급상황이 신고되는 상황에서 수보자에게 전달되는 신고자의 주변음향신호로부터 신고자의 주변상황을 추정하기 위하여 음향의 주파수적 특성 및 변화특성의 모델링 성능이 뛰어난 Gabor 필터뱅크 기반의 특징벡터 추출 기술 및 분류 성능이 뛰어난 심화신경망을 도입한다. 제안하는 Gabor 필터뱅크 기반의 특징벡터 추출 기법은 비음성 구간 검출기를 통하여 음성/비음성을 구분한 후에 비음성 구간에서 23차의 Mel-filter bank 계수를 추출한 후에 이로부터 Gabor 필터를 이용하여 주변상황 추정을 위한 특징벡터를 추출하고, 이로부터 학습된 심화신경망을 통하여 신고자의 장소적 정보를 추정한다. 제안된 기법은 여러 가지 시나리오 환경에서 평가되었으며, 우수한 분류성능을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1348-1349
• /
• 2015

본 논문에서는 응급구조의 신고 상황에서의 수보자의 보다 정확하고 신속한 대응를 위하여 수화자의 음향환경을 분석하여 주변상황에 대한 정보를 알고자 심화 신경망 기반의 음성 부재구간 검출 기법을 제안한다. 제안한 알고리즘은 음성 신호에서의 23차의 Mel-filter bank를 추출하고 이를 심화 신경망 기법을 이용하여 음성 부재구간을 검출한다. 객관적인 성능 평가를 위해 제안된 기법은 실제 응급구조 상황에서 평가되었으며, 기존의 음성검출기를 이용한 음성 부재구간 검출 성능에 비하여 향상된 성능을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.889-891
• /
• 2019

전화 상담 과정에서, 상담원은 고객의 요청에 적절히 대응해야 하는 의무를 갖고 있지만, 고객의 요청은 상담원의 수보 범위를 자주 벗어난다. 그런 범위 이외의 질문과 요청에 대해서도 일단은 성실히 응대하는 것이 상담원의 역할이고, 이 부분에서 상담 업무의 어려움이 존재한다. 이러한 어려움을 해결하기 위해서, 상담원에게 고객의 요청을 응대하기 위해 필요한 정보를 실시간으로 제공해줄 수 있는 시스템이 필요하다. 본 연구는, 이상의 기능을 수행하기 위한 시스템 구조를 설계하고, 그 프로토타입을 구현하는 것으로 이루어졌다.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.33 no.12
• /
• pp.1883-1896
• /
• 2009

This paper explores the use of Korean wrapping cloths (bojagi) in the late Joseon period and the types of decorations applied to them. Korean wrapping cloths called bojagi are pieces of cloths used by households of all social classes for practical purposes such as wrapping presents and covering food. In addition to the basic purposes, the making of bojagi was also an activity to express the down-to-earth wishes and the satisfaction of creation by the designer. With regard to the decorative feature of Korean wrapping cloths, five types of, patchwork, embroidered, painted, printed, and oiled-paper wrapping cloths, were examined. The patchwork wrapping cloths (jogakbo) show the frugality of Joseon women in addition to the well-developed composition skill of lines and colors. The embroidered wrapping cloths were prepared for special rituals and ceremonies such as weddings. Painted wrapping cloths were decorated with a Chinese-colors technique (called dangchae) or sometimes with black ink painting. For printed wrapping cloths, various sizes of woodblock printings and roller printings were used. Although monotone black ink was the main color applied to the printing, there was also wrapping cloths made from chintz having brilliant fast colors. Oiled-paper wrapping cloths called sikjibo were in use only for covering food. Cut-out work was employed to decorate it.

• Fire Science and Engineering
• /
• v.32 no.4
• /
• pp.103-109
• /
• 2018

The call-takers in the 119 General Situation Room are playing important roles in recognizing the first crisis situation such as fire, rescue, and emergency, and in starting up the response system. In particular, with regard to the emergency calls, the prompt and accurate surveillance can determine the patient's life as well as the prognosis. Based on April 8-December 31, 2014 Prehospital Care Reports in a metropolitan city, we analyzed the conversation turns and the conversation time between the agent and the caller, and the time of the conversation structure and sequence according to the reception routes and the severity of symptoms. The conversation analysis between the agent and the caller will be useful for the development and improvement of the action manual in the future.