• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2011년도 춘계학술대회 논문집
• /
• pp.1735-1741
• /
• 2011

The safety of station structures among railway infrastructures should be considered as a top priority because hundreds of thousands passengers a day take a subway. The station structures, which have been being operated since the 1970s, are especially vulnerable to the earthquake and long-term vibrations such as ambient train vibrations as well. This is why the structural-health monitoring system of station structures should be required. For these reason, Korean government has made an effort to develop the structural health-monitoring system of them, which can evaluate the health-state of station structures as well as can monitor the vulnerable structural members in real-time. Then, through the monitoring system, the vulnerable structural members could be retrofitted. For the development of health-state evaluation method for station structures with the real-time sensing data measured in the fields, authors carried out the numerical simulations to develop evaluation algorithms based on statistical pattern recognition techniques. In this study, the dynamic behavior of Chungmuro station in Seoul was numerically analyzed and then critical members were chosen. Damages were artificially simulated at the selected critical members of the numerical model. And, the supervised and unsupervised learning based pattern recognition algorithms were applied to quantify and localize the structural defects.

• 한국정보처리학회논문지
• /
• 제7권11호
• /
• pp.3584-3591
• /
• 2000

본 논문에서는 국내의 대표적인 상용인식기들의 성능을 평가하기 위한 평가 방법과 평가 기준을 제안한다. 제안한 평가 기준으로 상용화된 오프라인 문자인식기들과 실험실 인식기를 비교해본 후 각각의 특성을 분석해 보았다. 인식에 필요한 대상 문서는 400 DPI로 스캔한 1000여개의 문서영상과 수작업으로 작성한 원문이 존재하는 KT 테스트 컬렉션을 사용하였다. 본 논문에서 인식기의 성능을 평가하기 위해 문자단위 인식률 측정 방법을 제안하였다. 비교를 위한 문서의 유형을 제안하여, 단일 특성을 가지는 문서, 복합 특성을 가지는 문서 등으로 비교·분석하였다.

• Journal of Welding and Joining
• /
• 제16권5호
• /
• pp.108-118
• /
• 1998

This study proposes th analysis and evaluation method of time series ultrasonic signal using the chaos feature extraction for ultrasonic pattern recognition. Features extracted from time series data using the chaos time series signal analyze quantitatively weld defects. For this purpose, analysis objective in this study is fractal dimension and Lyapunov exponent. Trajectory changes in the strange attractor indicated that even same type of defects carried substantial difference in chaosity resulting from distance shifts such as 0.5 and 1.0 skip distance. Such differences in chaosity enables the evaluation of unique features of defects in the weld zone. In quantitative chaos feature extraction, feature values of 4.511 and 0.091 in the case of side hole and 4.539 and 0.115 in the case of vertical hole were proposed on the basis of fractal dimension and Lyapunov exponent. Proposed chaos feature extraction in this study can enhances ultrasonic pattern recognition results from defect signals of weld zone such as side hole and vertical hole.

• 한국콘텐츠학회논문지
• /
• 제10권5호
• /
• pp.1-9
• /
• 2010

이 논문은 특징 선택에 사용되는 개미 군락 최적화의 수렴 특성을 개선하기 위해 선택적 평가라는 새로운 기법을 제시한다. 이 방법은 불필요하거나 가능성이 덜한 후보 해를 배제함으로써 계산량을 줄인다. 이 방법은, 그런 해를 찾아내는데 사용할 수 있는 페로몬 정보 때문에 구현이 가능하다. 문제 크기에 따른 알고리즘의 적용가능성을 판단할 목적으로, 특징 선택에 사용되는 세 가지 알고리즘인 탐욕 알고리즘, 유전 알고리즘, 그리고 개미 군락 최적화의 계산 시간을 분석한다. 엄밀한 분석을 위해 원자 연산이라는 개념을 사용한다. 실험 결과는 선택적 평가를 채택한 개미 군락 최적화가 계산 시간과 인식 성능 모두에서 우수함을 보여준다.

• 벤처창업연구
• /
• 제18권3호
• /
• pp.45-60
• /
• 2023

본 연구에서는 창업기회평가를 매개하여 중장년 직장인의 창업 개인역량과 창업기회인식이 창업의도에 미치는 영향을 분석하였다. 창업 개인역량의 하위변수로는 사전지식, 긍정적 태도, 사회적 네트워크로 구분하였다. 본 연구의 실증분석을 위하여 창업에 관심이 있는 전국의 직장인을 대상으로 약 15일간(2023.02.06.~2023.02.20.) 네이버 오피스를 이용한 온라인 설문조사를 실시하였으며, 총 262부를 수집하여 결측치 12부를 제외한 250부를 대상으로 SPSS Ver.24.0과 PROCESS MACRO Model 4.0을 실증분석에 사용하였다. 분석결과는 첫째, 창업자 개인역량의 사전지식과 사회적 네트워크 및 창업기회인식은 높을수록 창업기회평가와 창업의도가 증가하는 유의한 정(+)의 영향력을 미치는 것으로 나타났다. 반면 창업자 개인역량 중 긍정적 태도는 창업기회평가 및 창업의도에 영향을 미치지 않는 것으로 나타났다. 또한 창업기회평가 및 창업의도에 미치는 영향력의 크기는 창업기회인식, 사전지식, 사회적 네트워크 순으로 나타났다. 이는 중장년 직장인의 창업에 대한 긍정적태도는 COVID-19로 인한 창업환경 위축, 창업준비 부족으로 인한 실패의 두려움, 과잉자신감에 따른 인지편향의 오류로 인한 창업실패 사례 속출 등으로 창업이 부정적인 이미지를 가지고 있다는 것을 시사하고 있다. 둘째, 창업자 개인역량과 창업기회인식이 통제된 상황에서 창업기회평가는 창업의도에 유의한 정(+)의 영향을 미치는 것으로 나타났다. 셋째, 창업기회평가는 창업자 개인역량의 사전지식, 사회적 네트워크 및 창업기회인식과 창업의도 간을 매개하는 것으로 나타났지만, 긍정적 태도와 창업의도 간은 매개하지 않는 것으로 나타났다. 넷째, 창업기회평가 및 창업의도에 미치는 영향요인 중 창업자 개인역량보다 창업기회인식이 더 크게 나타나 창업기회인식의 중요함이 확인하였다. 다섯째, 창업자 개인역량인 사전지식과 네트워크가 창업기회평가 및 창업의도에 영향을 미치는 것으로 나타나 창업사전지식 함양 및 경험의 중요성을 인식하도록 창업교육을 강화하면 중장년 직장인들의 창업을 활성화할 수 있다는 점을 확인하였다.

• 한국의류산업학회지
• /
• 제13권2호
• /
• pp.173-185
• /
• 2011

This study aimed to clarify the difference between consumers and hands-on staff in evaluation of the attributes importance of asset evaluation attributes and the relationship between difference from consumers and hands-on staff in evaluation of the attributes and the performance. Subjects for the quantitative research, quota sampling was adopted in the areas where the subject brands were in place, and 452 questionnaires (141 of hands-on staff, 311 of consumers) were analyzed. The results were as follows; 1. The factors that hands-on staff and consumers regarded as most important as to asset evaluation attributes of department store-exclusive importation brands included preference and product quality in the order, and then image, recognition, reliability, and country of origin in the case of hands-on staff, and reliability, image, recognition, and country of origin in the case of consumers in the order. 2. As a result of examining the effect of the difference between hands-on staff and consumers regarding exclusive importation brands(GAP, ZARA) of certain department stores on business achievement and consumer attitude, it turned out that the smaller the difference between the two groups with regard to evaluation, the higher the business achievement and consumer attitude.

• 대한음성학회지:말소리
• /
• 제59호
• /
• pp.27-51
• /
• 2006

For speech recognition systems, rejection function as well as decoding function is necessary to improve the reliability. There have been many research efforts on out-of-vocabulary word rejection, however, little attention has been paid on non-target sentence rejection. Recently pronunciation approaches using speech recognition increase the need for non-target sentence rejection to provide more accurate and robust results. In this paper, we proposed filler model method and word/phoneme detection ratio method to implement non-target sentence rejection system. We made performance evaluation of filler model along to word-level, phoneme-level, and sentence-level filler models respectively. We also perform the similar experiment using word-level and phoneme-level word/phoneme detection ratio method. For the performance evaluation, the minimized average of FAR and FRR is used for comparing the effectiveness of each method along with the number of words of given sentences. From the experimental results, we got to know that word-level method outperforms the other methods, and word-level filler mode shows slightly better results than that of word detection ratio method.

• 한국음향학회지
• /
• 제19권1호
• /
• pp.11-15
• /
• 2000

RM 음성 Corpus를 이용한 화자 적응 연속 음성 인식을 수행하였다. RM Corpus의 훈련용 데이터를 이용해서 기준화자에 대한 HMM 학습을 실시하고 평가용 데이터를 이용하여 화자 적응 인식에 대한 평가를 실시하였다. 화자 적응을 위해서는 훈련용 데이터의 일부가 사용되었다. DTW를 이용하여 인식 대상화자의 데이터를 기준화자의 데이터와 시간적으로 일치시키고 오차 역전파 신경회로망을 사용하여 인식 대상화자의 스펙트럼이 기준화자의 스펙트럼 특성을 지니도록 변환시켰다. 최적의 화자 적응이 이루어지도록 하기 위해 신경회로망의 여러 요소들을 변화시키면서 실험을 실시하고 그 결과를 제시하였다. 학습을 거쳐 적절한 가중치를 지닌 신경회로망을 이용하여 기준화자에 적응시킨 결과 단어 인식율이 최대 2.1배, 단어 정인식율이 최대 4.7배 증가하였다.

• 한국환경교육학회지:환경교육
• /
• 제11권2호
• /
• pp.14-25
• /
• 1998

The Quality of human living depends on the environmental quality of the region sustaining the life. The environmental deterioration of the modern society is due to mechanical environmentalism. For the better quality of the life, The changes of recognition and attitude on the environments are required. These changes of mind are also important in environmental education for teenagers. The 7th national curriculum, officially anounced December 1998, focuses on the change of attitude to environments and practical behavior in real life for “Environments”, the environmental education curriculum in middle school. Basic elements of the curriculum are cultivation of the pro-environmental thinking, multi-levelling of teaching materials and methods, and encouraging of student participating activity. Actually, the curriculum construction is composed of stepped-levelling of teaching and learning, reasonable contents volume, encouraging of student practice, and suggesting of evaluation standards of textbook writing. Three main subjects of environmental education for middle school consist of (1) man and environment, (2) recognition of environmental problem, and (3) protection activity for environment. Methodology of environmental education can include multi-disciplinary approaches, variable teaching methods, and continuing evaluation of student practice and participation attitude. Environmental education for teenagers relating to the 7th national curriculum focuses on recognition of the environmental problems and practice activity in daily life. The recognition includes considering relationship of human life to environment, solving environmental problems in regional context, and development of comprehensive understanding concept of the environments. For the practice education, variable teaching methods, such as field survey and application of multi-media, are needed.

• Bulletin of the Korean Chemical Society
• /
• 제31권11호
• /
• pp.3371-3381
• /
• 2010

In this study, quantitative and pattern recognition analysis for the quality evaluation of Magnoliae Flos using HPLC/UV was developed. For quantitative analysis, eleven major bioactive lignan compounds were determined. The separation conditions employed for HPLC/UV were optimized using ODS $C_{18}$ column ($250{\times}4.6\;mm$, $5\;{\mu}m$) with isocratic elution of acetonitrile and water with 1% acetic acid as the mobile phase at a flow rate of 1.0 mL/min and a detection wavelength of 278 nm. These methods were fully validated with respect to the linearity, accuracy, precision, recovery, and robustness. The HPLC/UV method was applied successfully to the quantification of eleven major compounds in the extract of Magnoliae Flos. The HPLC analytical method for pattern recognition analysis was validated by repeated analysis of twenty one reference samples corresponding to seven different species of Magnoliae Flos and nine samples purchased from market. The results indicate that the established HPLC/UV method is suitable for the quantitative analysis and quality control of multi-components in Magnoliae Flos.