• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2129-2147
• /
• 2019

This paper introduces an adaptive face recognition method based on a Novel Incremental Kernel Nonparametric Discriminant Analysis (IKNDA) that is able to learn through time. More precisely, the IKNDA has the advantage of incrementally reducing data dimension, in a discriminative manner, as new samples are added asynchronously. Thus, it handles dynamic and large data in a better way. In order to perform face recognition effectively, we combine the Gabor features and the ordinal measures to extract the facial features that are coded across local parts, as visual primitives. The variegated ordinal measures are extraught from Gabor filtering responses. Then, the histogram of these primitives, across a variety of facial zones, is intermingled to procure a feature vector. This latter's dimension is slimmed down using PCA. Finally, the latter is treated as a facial vector input for the advanced IKNDA. A comparative evaluation of the IKNDA is performed for face recognition, besides, for other classification endeavors, in a decontextualized evaluation schemes. In such a scheme, we compare the IKNDA model to some relevant state-of-the-art incremental and batch discriminant models. Experimental results show that the IKNDA outperforms these discriminant models and is better tool to improve face recognition performance.

• 말소리와 음성과학
• /
• 제12권4호
• /
• pp.19-25
• /
• 2020

This study examined thirty-one Korean students' pronunciation of an English passage using a speech recognition application, Speechnotes, and two Canadian raters' evaluations of their speech according to the International English Language Testing System (IELTS) band criteria to assess the possibility of using the application as a teaching aid for pronunciation education. The results showed that the grand average percentage of correctly recognized words was 77.7%. From the moderate recognition rate, the pronunciation level of the participants was construed as intermediate and higher. The recognition rate varied depending on the composition of the content words and the function words in each given sentence. Frequency counts of unrecognized words by group level and word type revealed the typical pronunciation problems of the participants, including fricatives and nasals. The IELTS bands chosen by the two native raters for the rainbow passage had a moderately high correlation with each other. A moderate correlation was reported between the number of correctly recognized content words and the raters' bands, while an almost a negligible correlation was found between the function words and the raters' bands. From these results, the author concludes that the speech recognition application could constitute a partial aid for diagnosing each individual's or the group's pronunciation problems, but further studies are still needed to match human raters.

• 문화기술의 융합
• /
• 제10권3호
• /
• pp.909-914
• /
• 2024

본 연구에서는 로봇 비전용 영상 인식을 비롯한 다양한 AI 분야에서 널리 활용되는 전이학습에 대한 정량적 평가를 제시하였다. 전이학습을 적용한 연구 결과에 대한 정량적, 정성적 분석은 제시되나, 전이학습 자체에 대해서는 논의되지 않는다. 따라서 본 연구에서는 전이학습 자체에 대한 정량적 평가를 숫자 손글씨 데이터베이스인 MNIST를 기반으로 제안한다. 기준 네트워크를 대상으로 전이학습 동결층의 깊이 및 전이학습 데이터와 사전 학습 데이터의 비율에 따른 정확도 변화를 추적하였다. 이를 통해 첫번째 레이어까지 동결할 때 전이학습 데이터의 비율이 3% 이상일 경우, 90% 이상의 정확도를 안정적으로 유지할 수 있음이 확인되었다. 본 연구의 전이학습 정량 평가 방법은 향후 네트워크 구조와 데이터의 종류에 따라 최적화된 전이학습을 구현하는데 활용 가능하며, 다양한 환경에서 로봇 비전 및 이미지 분석 AI의 활용 범위를 확대할 것이다.

• 한국멀티미디어학회논문지
• /
• 제15권9호
• /
• pp.1174-1183
• /
• 2012

본 연구는 다변화된 정보 인터페이스 환경에서 사용자의 시각 몰입과 재인 과정에 시각단서가 어떠한 역할을 하는지와, 시각정보 구조와의 관련성을 분석하기 위하여 실시되었다. 그리하여 최신 그래픽 정보 사용자 트렌드를 고려하여 과학적인 도구와 주관적 내면 평가를 활용한 평가모형을 설계하고, 보다 체계적인 실험과정을 통하여 획득한 몰입과 재인의 사용자 경험 데이터를 분석하였다. 이를 토대로 향후 최신의 디바이스에 광범위하게 적용 가능한 그래픽 정보 사용자의 기초설계모형과 표준 평가 모형을 구축하는 데 기여할 수 있을 것이다.

• 말소리와 음성과학
• /
• 제10권4호
• /
• pp.111-119
• /
• 2018

This paper proposes a method to improve speech recognition performance by extracting various pronunciations of the pseudo-morpheme unit from an eojeol unit corpus and generating a new recognition unit considering pronunciation variations. In the proposed method, we first align the pronunciation of the eojeol units and the pseudo-morpheme units, and then expand the pronunciation dictionary by extracting the new pronunciations of the pseudo-morpheme units at the pronunciation of the eojeol units. Then, we propose a new recognition unit that relies on pronunciation by tagging the obtained phoneme symbols according to the pseudo-morpheme units. The proposed units and their extended pronunciations are incorporated into the lexicon and language model of the speech recognizer. Experiments for performance evaluation are performed using the Korean speech recognizer with a trigram language model obtained by a 100 million pseudo-morpheme corpus and an acoustic model trained by a multi-genre broadcast speech data of 445 hours. The proposed method is shown to reduce the word error rate relatively by 13.8% in the news-genre evaluation data and by 4.5% in the total evaluation data.

• 대한감각통합치료학회지
• /
• 제5권1호
• /
• pp.21-30
• /
• 2007

Objective: This study was to provide a standard for the evaluation of The Korean version of Adolescent/Adult Sensory Profile(K-ASP) for University students and to investigate the difference of the subjective sense recognition regarding the characteristics of sensory processing. Method: The subjects consisted of 84 University students. A researcher examined subjective sense recognition and K-ASP for subjects. Visual Analog Scale used to evaluate subjective sense recognition and K-ASP was utilized to evaluate the characteristics of sensory processing. Results: 1. The average scores and standard deviation of K-ASP were $32.93{\pm}7.88$ for low registration group, $39.39{\pm}6.55$ for sensory seeking group, $38.94{\pm}9.13$ for sensory sensitivity group, and $34.24{\pm}7.85$ for sensory avoiding group. 2. The correlation between the total score on an each quadrant and the subjective sense recognition are -.27 for low registration group, .11 for sensory seeking group, .09 for sensory sensitivity group and .12 for sensory avoiding group. It showed the statistically significant correlation between the total score of low registration and the subjective sense recognition group(p<.05). 3. The average scores and standard deviation of the subjective sense recognition were $5.22{\pm}1.56$ for high threshold and $7.28{\pm}1.70$ for low threshold. The subjective sense recognition according to the characteristics of sensory processing showed the statistically significant difference. Conclusions: This study supports the theory that there is the difference of sensory recognition according to each individual and we found that people with difficulties of sensory processing acknowledge their characteristics of sensory processing well. Evaluation of sensory processing ability through interview or questionnaire supports the fact which it is reliable.

• 대한임베디드공학회논문지
• /
• 제8권3호
• /
• pp.179-184
• /
• 2013

A voice recognition technology as a technology fundament plays an important role in medical devices with smart functions. This paper describes the implementation of a control system that can be utilized as a part of illumination equipment for medical applications (IEMA) based on a voice recognition. The control system can essentially be divided into five parts, the microphone, training part, recognition part, memory part, and control part. The system was implemented using the RSC-4x evaluation board which is included the micro-controller for voice recognition. To investigate the usefulness of the implemented control system, the experiments of the recognition rate was carried out according to the input distance for voice recognition. As a result, the recognition rate of the control system was more than 95% within a distance between 0.5 and 2m. The result verified that the implemented control system performs well as the smart control system based for an IEMA.

• 한국콘텐츠학회논문지
• /
• 제14권5호
• /
• pp.44-54
• /
• 2014

본 연구는 한류 확산의 진원지이자 한국 드라마 수출의 주요국인 일본을 대상으로 일본 시청자들의 한국 드라마 시청과 한국에 대한 태도 형성 관계를 고찰하고자 하였다. 한국과 일본은 과거 지배-피지배라는 역사적 특수성을 가지고 있는바, 일본 시청자들의 한일 역사 인식에 따른 한국 드라마 시청성과의 관계를 살펴보았다. 한국 드라마 주시청자층인 일본 여성 10~60대 250명을 대상으로 현지 서베이를 실시한 결과, 긍정적인 한일 역사 인식은 한국 드라마 시청의 높은 몰입행위를 나타냈고, 높은 몰입행위는 전체적인 한국 드라마 평가와 한국에 대한 태도에 긍정적인 영향을 미치는 것으로 나타났다. 한일 역사 인식이 한국 드라마 수용의 주요 영향 요인임을 밝힌 연구결과는 발전적인 한국 드라마 유통을 위해 일본 시청자의 왜곡 없는 한일 역사 인식이 선행되어야 하며, 이를 위한 상호 문화외교적 정책방안이 재고되어야 함을 시사하는 것이다.

• 한국주거학회논문집
• /
• 제28권1호
• /
• pp.63-72
• /
• 2017

The purpose of this study is to investigate the overall recognition on attitudes of well-dying and evaluation the importance of planning factors of well-dying space in college students. This will serve as a basis to accumulate materials on the recognition of well-dying and well-dying spaces of various generations of South Korea. This study conducted a survey from October 4th to 8th, 2016 with 119 college students from U University and K University. As the contents of the survey, were comprised of general socio-demographic elements, subjective recognition and attitudes toward well-dying, and the importance of the planning factors of the physical, emotional, social and spiritual environments of the well-dying space. The main results are as follows. (1) The interest of university students on death education is high, and there was a preference for 'home' where they could be comfortable and be with loved ones as the space for dying. Also, in case of events of bereaving them after death, formal grieving ceremonies were undesired. The funeral was desired to be simple, serene, and not too sad. (2) In evaluation of the importance of physical, emotional, and spiritual environmental planning factors, physical environmental factors were considered to be the most important overall, and the recognition of importance of the planning factors of spiritual environment was low.

• 벤처창업연구
• /
• 제12권3호
• /
• pp.135-146
• /
• 2017

가치 있는 기회를 기반으로 한 창업은 국가 경제의 장기적인 성장에 긍정적인 영향을 미친다. 본 연구는 서민경제의 근간을 이루는 소상공인들의 기회형 창업에 대한 정부의 교육적 지원의 개선점과 방향성을 제언하기 위해 현재 소상공인들에게 제공되는 창업교육을 기회형 창업의 관점에서 검증하였다. 본 연구를 위해 정부의 소상공인 창업교육을 수료한 전국의 소상공인들을 대상으로 온라인 설문을 실시하고, 345명의 온라인 설문 데이터를 실증분석에 사용하였다. 연구결과 소상공인들을 위한 창업교육과 지원제도는 창업효능감에 모두 양(+)의 영향을 미치는 것으로 나타났으며 창업효능감은 기회인식과 기회평가 역량은 물론 향상초점과 예방초점에도 양(+)의 영향을 미치는 것으로 나타났다. 이론과 실습교육이 포함된 소상공인 창업교육은 향상초점과 예방초점에 모두 양(+)의 영향을 미치는 것으로 나타났다. 소상공인들의 향상초점은 기회인식에는 양(+)의 영향을 미치는 것으로 나타났지만 기회평가에는 유의한 영향이 없는 것으로 나타났으며 소상공인들의 예방초점은 기회인식과 기회평가에 유의한 영향을 미치지 않는 것으로 나타났다. 본 연구결과에 의하면 현 소상공인 창업교육은 소상공인들의 기회인식과 기회평가 역량에 유의한 영향을 미치지 않는 것으로 나타나 소상공인들의 기회형 창업율을 높이기 위해 현 창업교육에 개선이 필요함을 시사한다.