• Phonetics and Speech Sciences
• /
• v.8 no.2
• /
• pp.31-39
• /
• 2016

In emergency dispatching at 119 Command & Dispatch Center, some inconsistencies between the 'standard emergency aid system' and 'dispatch protocol,' which are both mandatory to follow, cause inefficiency in the dispatcher's performance. If an emergency dispatch system uses automatic speech recognition (ASR) to process the dispatcher's protocol speech during the case registration, it instantly extracts and provides the required information specified in the 'standard emergency aid system,' making the rescue command more efficient. For this purpose, we have developed a Korean large vocabulary continuous speech recognition system for 400,000 words to be used for the emergency dispatch system. The 400,000 words include vocabulary from news, SNS, blogs and emergency rescue domains. Acoustic model is constructed by using 1,300 hours of telephone call (8 kHz) speech, whereas language model is constructed by using 13 GB text corpus. From the transcribed corpus of 6,600 real telephone calls, call logs with emergency rescue command class and identified major symptom are extracted in connection with the rescue activity log and National Emergency Department Information System (NEDIS). ASR is applied to emergency dispatcher's repetition utterances about the patient information. Based on the Levenshtein distance between the ASR result and the template information, the emergency patient information is extracted. Experimental results show that 9.15% Word Error Rate of the speech recognition performance and 95.8% of emergency response detection performance are obtained for the emergency dispatch system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.1
• /
• pp.123-129
• /
• 2017

New mobile phones with high tech-camera and a large size memory have been recently launched and people upload pictures of beautiful scenes or unknown flowers in SNS. This paper develops a flower recognition system that can get information on flowers in the place where mobile communication is not even available. It consists of a registration part for reference flowers and a recognition part based on OpenCV for Android platform. A new color classification method using RGB color channel and K-means clustering is proposed to reduce the recognition processing time. And ORB for feature extraction and Brute-Force Hamming algorithm for matching are used. We use 12 kinds of flowers with four color groups, and 60 images are applied for reference DB design and 60 images for test. Simulation results show that the success rate is 83.3% and the average recognition time is 2.58 s on Huawei ALEUL00 and the proposed system is suitable for a mobile phone without a network.

• Journal of The Korean Association of Information Education
• /
• v.16 no.1
• /
• pp.1-10
• /
• 2012

The purpose of this paper is a study of survey about teachers' attitude and recognition of education using newest information technology such as s-learning, social network and Web 3.0. We researched for elementary school teachers about recognition of the newest IT trend, educational necessity and effect of the newest IT. As a result, recognition and understanding of the newest IT is low but teachers think that effect of education using the newest IT is very high. Moreover, they have a lot of will for using the newest IT devices and training about the newest IT. However, it shows that they are diffident of taking charge of the newest IT and teaching for students using it. Also, the results showed different tendency as generations. This study would be a important role for deciding on direction of informatics education for 21C.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.904-906
• /
• 2016

In this paper, advertising and public relations services to provide kincet to implement a control system using face recognition and media. Traditionally, this unilateral system for delivering advertisements to consumers, is currently directed interactive ads. In other words, interactive advertising service that offers bi-directional communication. In the proposed system, the kincet using face recognition, to recognize faces with eyes, mouth, jaws and eyebrows. Presently used kinect version is the face of instability in the recognition and accurately is difficult to separate the three parts of the jaw, eyes, eyebrows only leverage. the classification has an easy immoyangProvide control services by separating the media, Hwanam-myeon, laughing. Also, consumers understand the expression of the control of the media and using picture for advertising to consumers through the transfer on both had indelibly imprinted by advertising.Effective are expected to appear.

• Journal of Information Technology Applications and Management
• /
• v.27 no.5
• /
• pp.69-80
• /
• 2020

Recently, luxury brands are selling their products to consumers using their own direct online channels. In the online channel, marketing strategy through storytelling is needed because consumers do not have enough product experience. Therefore, luxury brands are actively utilizing social media and delivering stories includes their birth and growth. Unlike mass media, social media communicates with consumers more quickly and frequently and delivers the story of brand naturally. This study classifies luxury brands into four groups based on story recognition of luxury brands and self-esteem, and analyzes and materializes each group of the propensities of luxury brand consumption. It also tries to draw strategic implications for effective SNS advertising by analyzing narrative transportation on SNS advertising, interests in videos, and the interests in story based on these typified groups of luxury consumption. The result of the analysis shows that there is a difference in consumption propensity among consumers who were classified into four groups according to story cognition of luxury brands and self-esteem. There is also a difference in the response to narrative images through SNSs, such as narrative transportation, interests in videos, and interests in brand stories.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.3
• /
• pp.199-206
• /
• 2020

The purpose of this study is to examine the relationship between intention to participation in sharing economy, digital cultural capital, and social connectedness and then analyze the variables affecting the intention to participate in sharing economy. This subjects were university students. Collected data were statistically processed by PASW 18.0 program using reliability, frequency analysis, T-test, one-way ANOVA, correlation and multiple regression analysis. The results were as follows. First, redistribution participation and cooperative lifestyle participation were relatively high. Second, intention to participate in sharing economy activities differs according to gender, age, monthly allowance, and SNS usage time. Third, intention to redistribution participation increases as the recognition of objectified digital culture capital, embodied digital culture capital, and social connectedness increases. And the intention to cooperative lifestyles participation and information sharing participation increased as digital culture capital increased. Forth, the most significant variable affecting the intention to participate in sharing economic activities was digital cultural capital.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.32 no.3
• /
• pp.67-91
• /
• 2021

The purposes of this study is to identify the perception of students' use of university libraries' public relations activities using Instagram and propose ways to improve the operation of university libraries' Instagram. To this end, the status of Instagram operations of domestic and foreign university libraries was investigated, and a survey was conducted on 292 students who used the library Instagram of their universities. Based on the research results, first, it is necessary to promote the use of libraries by using 'Library Events' information closely related to the use of Instagram by students, but planning ways to participate that can lead to practical use of libraries. Second, it is necessary to promote the role of librarians through Instagram and utilize daily communication information in order to positively affect library image recognition. Third, it is necessary to guide users on how to inquire on library Instagram and actively respond to communication with users through periodic post uploads and monitoring.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.375-377
• /
• 2012

스마트폰과 같은 모바일 기기가 발전함에 따라 SNS, 모바일 메신저, SMS와 같은 단문 기반 메시지는 자신의 감정을 가장 잘 표현하는 매체이다. 그럼에도 불구하고 기존 연구는 주로 장문의 텍스트로부터 긍정, 부정 분류나 문서의 성향을 분석하는 것에 그치는 경우가 많다. 의미지향(Semantic Orientation)방법은 검색엔진을 통해 감정 키워드와 인지하고자 하는 단어의 동시 빈출 정도를 PMI로 계산한 것으로 WordNet과 같은 의미 사전이 존재하지 않는 한국어의 특성에서 적용 가능한 방법이다. 본 논문에서는 의미 지향성 및 다른 텍스트 기반 감정 분류 기술에 대해 비교하고 이들을 활용하여 한국어로 구성된 단문 텍스트에서 효율적인 감정 분류 기법을 제안하고자 한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.671-673
• /
• 2020

정보화 시대에 살고 있는 우리는 인터넷 영상 매체를 떼놓을 수 없다. 어린아이들은 스마트폰의 유튜브를 보며 꿈꾸고, 어른들은 자신의 SNS에 취미나 장기를 뽐내고 공유하며 더 넓고 다양한 세상을 경험해 나간다. 인터넷 방송도 마찬가지로 이토록 다양한 경험과 재미를 주지만 정작 이 부분에 대해서 조사해 본 적은 없었다. 본 논문에서는 플랫폼, 인기 스트리머의 각각의 특징 조사하고 신규 스트리머에게 플랫폼 병행을 제안한다.

• Journal of KIISE:Software and Applications
• /
• v.36 no.8
• /
• pp.673-682
• /
• 2009

Recently, photo sharing and publishing based Social Network Sites(SNSs) are increasingly attracting the attention of academic and industry researches. Unlike the face recognition environment addressed by existing works, face annotation problem under SNSs is differentiated in terms of daily updated images database, a limited number of training set and millions of users. Thus, conventional approach may not deal with these problems. In this paper, we proposed a face annotation method for sharing and publishing photographs that contain faces under a social network service using random projection, non-linear regression and representational state transfer. Our experiments on several databases show that the proposed method records an almost constant execution time with comparable accuracy of the PCA-SVM classifier.