• 한국IT서비스학회지
• /
• 제6권2호
• /
• pp.161-175
• /
• 2007

Face recognition technology has lately attracted considerable attention because of its non-intrusiveness, usability and applicability. Related companies insist that their commercial products show the recognition rates more than 95% according to their self-testing. But, the rates cannot be admitted as official recognition rates. So, performance evaluation methods and tools are necessary to objectively measure the accuracy and performance of face recognition systems. In this paper, I propose a reference model for biometrics recognition evaluation tools, and implement an evaluation tool for the face recognition system based on the proposed reference model.

• 대한인간공학회지
• /
• 제18권3호
• /
• pp.105-125
• /
• 1999

As speech is the human being's most natural communication medium, using it gives many advantages. Currently, most user interfaces of a computer are using a mouse/keyboard type but the interface using speech recognition is expected to replace them or at least be used as a tool for supporting it. Despite the advantages, the speech recognition interface is not that popular because of technical difficulties such as recognition accuracy and slow response time to name a few. Nevertheless, it is important to optimize the human-computer system performance by improving the usability. This paper presents a set of guidelines for designing speech recognition interfaces and provides a method for evaluating the usability. A total of 113 guidelines are suggested to improve the usability of speech-recognition interfaces. The evaluation method consists of four major procedures: user interface evaluation; function evaluation; vocabulary estimation; and recognition speed/accuracy evaluation. Each procedure is described along with proper techniques for efficient evaluation.

• 디지털융복합연구
• /
• 제12권6호
• /
• pp.215-221
• /
• 2014

지문인식시스템은 사용자의 지문을 전자적으로 읽어 미리 입력된 데이터와 비교해 본인 여부를 판별하여 사용자의 신분을 확인하는 시스템이다. 지문인식시스템의 성능은 지문 인식에 걸리는 시간이나 정확도 등에 좌우된다. 본 논문에서는 지문인식시스템의 품질 수준을 평가하기 위해 ISO 품질평가 표준을 기반으로 효율성에 관한 평가모델을 구축하였다. 본 연구를 통해 표준에 입각한 평가기준 구축과 활용에 기여할 수 있을 것으로 기대한다.

• 한국멀티미디어학회논문지
• /
• 제13권4호
• /
• pp.487-495
• /
• 2010

바이오인식 (Biometrics) 시스템의 사용이 보편화 되면서 그들의 성능에 대해서 보다 정확하고 안정된 평가를 제공하는 방법이 요구된다. 다양한 바이오 인식 기술 중에서 얼굴인식 기술이 널리 사용되고 있으며 안정적인 얼굴인식 시스템의 개발을 위한 지표를 마련하고 얼굴인식 시스템이 제공해야 하는 성능에 대한 기준을 제시하기 위해서 얼굴인식 시스템의 성능을 평가해야 할 필요성이 커지게 되었다. 하지만 얼굴인식 시스템의 성능에 영향을 미치는 요소들이 매우 다양하고 복잡하기 때문에 얼굴인식 시스템의 성능을 평가하는 것은 어려운 일이다. 그렇기 때문에 이러한 환경요소에 대해서 개별적으로 평가하는 것보다 종합적으로 얼굴인식 시스템의 활용 시나리오를 기반으로 평가하는 것이 보다 효율적이고 효과적이다. 이 논문에서는 얼굴인식 시스템에 영향을 미치는 환경변수들을 분석하고 그 환경변수들을 고려하는 얼굴인식 시스템에 대한 평가방법을 제안하는 것을 목적으로 한다. 특별히 환경변수들을 개별적으로 평가하는 것이 아니고 그들의 조합을 고려하는 시나리오를 기반으로 평가하는 방법을 제안한다. 또한 일반적인 환경을 가정하는 시나리오 예시를 통해서 얼굴인식 시스템을 종합적인 환경변수를 고려하여 평가하는 것을 보여주었다.

• 한국소프트웨어감정평가학회 논문지
• /
• 제15권2호
• /
• pp.73-83
• /
• 2019

음성인식은 최근 인공지능 기술과 접목되면서 오인식률이 크게 개선되었고 사용자 관점에서 효과적이고 효율적인 HMI(Human Machine Interface)를 제공하고 있다. 이러한 추세는 방위산업 분야에서도 반영되고 있고 특히 항공분야에서 F-35에 적용이 되었다. 하지만 이러한 기술에 대해서 품질평가를 위해 방위산업 특히 항공분야에는 객관적이고 평가 가능한 정량적인 모델이 필요하다. 본 연구에서는 이러한 음성인식의 소프트웨어 측면에서 항공기에 적용하기 위한 정량적인 평가 모델을 제시한다. 평가 모델 제시를 위해 음성인식 적용 기술과 ISO/IEC 25000(SQuaRE) 제품 품질 속성을 이용해 평가 항목을 추출한다. 이러한 두 가지 항목의 연계를 통해 정량적인 평가 모델을 제시하고 사례 연구를 활용해 평가 결과를 확인한다.

• 성인간호학회지
• /
• 제20권5호
• /
• pp.731-742
• /
• 2008

Purpose: The purpose of this study was to analyze how a nursing student recognizes PBL with simulation education and its relationship to academic achievement. Methods: The study objects were the students in C college who learn through PBL using simulator for 15 weeks(September 2007 to December 2007). Learning element recognition was developed by Cho(2002) and three key evaluations(performance, self-evaluation, and colleague evaluation) were designed by professors. Results: Learning element recognition ranged from 2.37 to 4.83 with the average at 3.94. For Learning element recognition, students who preferred discussion score 4.15. This was statistically more significant than those who do not. Students who preferred presentations show significantly higher score in colleague evaluation. For Learning element recognition and academic achievement, self-evaluation and colleague evaluation showed relationship to PBL learning element. Conclusion: There was definitely a relationship with PBL learning element and academic achievement after learning the PBL with simulation education.

• ETRI Journal
• /
• 제46권1호
• /
• pp.48-58
• /
• 2024

This paper presents the development of language tutoring systems for nonnative speakers by leveraging advanced end-to-end automatic speech recognition (ASR) and proficiency evaluation. Given the frequent errors in non-native speech, high-performance spontaneous speech recognition must be applied. Our systems accurately evaluate pronunciation and speaking fluency and provide feedback on errors by relying on precise transcriptions. End-to-end ASR is implemented and enhanced by using diverse non-native speaker speech data for model training. For performance enhancement, we combine semisupervised and transfer learning techniques using labeled and unlabeled speech data. Automatic proficiency evaluation is performed by a model trained to maximize the statistical correlation between the fluency score manually determined by a human expert and a calculated fluency score. We developed an English tutoring system for Korean elementary students called EBS AI Peng-Talk and a Korean tutoring system for foreigners called KSI Korean AI Tutor. Both systems were deployed by South Korean government agencies.

• 한국산학기술학회논문지
• /
• 제13권1호
• /
• pp.87-98
• /
• 2012

교육과학기술부는 고등교육 프로그램 평가인증기관에 대한 정부 인정 사업을 추진해왔다. 이에 본 연구는 정부가 프로그램 평가인증기관을 인정하는 평가모형을 설정하고, 평가부문 및 평가항목, 평가지표를 개발하는데 목적이 있다. 이를 위해 본 연구는 프로그램 평가인증기관에 대한 정부인정의 개념을 설정하고, 프로그램 평가인증기관에 대한 정부인정 평가모형을 설계하였다. 평가 모형은 고등교육 프로그램 평가인증기관에 대한 정부인정사업의 절차를 반영하여 정부인정기관으로서의 기본적인 요건에 부합되는지 여부에 대한 적격성 검토를 수행하는 예비평가단계, 법령 및 관련 규정에 제시된 평가영역별 지정기준에 대한 충족 여부를 검증하는 본 평가단계의 과정으로 설정하였다. 아울러 평가영역에 따라 평가부문, 평가항목 및 평가지표들을 개발하였고, 심층적 검증을 위해 평가전문가들의 검토를 거쳐 2개 평가영역, 5개 평가부문, 24개 평가항목 및 33개 평가지표를 확정하였다.

• 복식문화연구
• /
• 제12권6호
• /
• pp.984-998
• /
• 2004

The purpose of this study was to analyze contents of clothing product evaluation statements in the internet shopping mall and to discover consumers' recognition and evaluation of it. The data were collected from 151 consumers' statements in the four internet apparel shopping malls and a questionnaire was developed to measure consumers' recognition of clothing product evaluation statements. The questionnaire was administrated 272 consumers over 18 years old. The results of this study were as follows; First, The contents of clothing product evaluation statements in the internet shopping blog, were divided into three categories which were product, service and consumer buying decision process. Product category include evaluation of clothing product, description of difference between real product and product on the screen, and advice of uses. Service category include quickness and kindness in delivery, store preference for good service. For consumer buying decision process, motivation of purchasing, perceived risk, expression of satisfaction from good buying and canvassing for purchasing were included. Second, consumer recognized that clothing product evaluation statements has function of furnishing information, confirmation of purchasing decision, risk reduction of internet shopping, and interesting entertainment. Consumers also were dependent on product evaluation statements for making purchasing decision. And it was trusted by consumers. This recognition & evaluation were correlated with consumer's clothing product knowledge, involvement, risk perception of internet shopping, experiences of internet shopping. Managerial implications are provided for internet shopping mall.

• The Journal of the Acoustical Society of Korea
• /
• 제23권3E호
• /
• pp.85-90
• /
• 2004

This paper presents two kinds of new approaches, one of which is concerned with recognition of emotional speech such as anger, happiness, normal, sadness, or surprise. The other is concerned with emotion recognition in speech. For the proposed speech recognition system handling human speech with emotional states, total nine kinds of prosodic features were first extracted and then given to prosodic identifier. In evaluation, the recognition results on emotional speech showed that the rates using proposed method increased more greatly than the existing speech recognizer. For recognition of emotion, on the other hands, four kinds of prosodic parameters such as pitch, energy, and their derivatives were proposed, that were then trained by discrete duration continuous hidden Markov models(DDCHMM) for recognition. In this approach, the emotional models were adapted by specific speaker's speech, using maximum a posteriori(MAP) estimation. In evaluation, the recognition results on emotional states showed that the rates on the vocal emotions gradually increased with an increase of adaptation sample number.