This is Mathcad

문광식 대한기계학회 2013 대한기계학회 춘추학술대회 Vol.2013 No.6

특목고의 연구 중심 프로그램 - 세종과학예술영재학교 정보과학 교육과정 -

문광식(Moon Kwangsik) 한국컴퓨터교육학회 2022 한국컴퓨터교육학회 학술발표대회논문집 Vol.26 No.1

세종과학예술영재학교는 영재교육진흥법에 따라 특수한 목적으로 설립된 고등학교 교육과정의 영재교육기관이다. 세종과학예술영재학교는 그 법적 지위에 따라 학교에서 정한 교육과정을 운영하고 있으며, 교육과정의 교과영역 편제에서 정보과학이 차지하는 비중이 일반고에 비해 매우 높은 수준이다. 또한 영재학교의 일반적인 특성에 따라 연구영역의 비중도 상당히 높다. 세종과학예술영재학교의 정보과학 교육과정과 정보과학과 관련한 연구영역의 내용 영역을 살펴봄으로써 디지털 대전환에 따른 정보과학 교육에 대한 ‘요구’와 이에 대응하는 교육과정 편성 및 적용을 통한 특목고의 연구 ‘중심 프로그램’이 선순환을 이루고 있음을 확인할 수 있다.

가변어휘 단어 인식에서의 미등록어 거절 알고리즘 성능 비교

김기태,문광식,김회린,이영직,정재호 한국음향학회 2001 韓國音響學會誌 Vol.20 No.2

발화 검증이란 등록된 단어 목록 이외의 단어가 입력되었을 때, 미등록된 단어는 인식할 수 없는 단어임을 알려주는 기능으로써 사용자에게 친숙한 음성 인식 시스템을 설계하는데 중요한 기술이다. 본 논문에서는 가변어휘 단어 인식기에서 최소 검증 오류를 나타낼 수 있는 발화 검증 시스템의 알고리즘을 제안한다. 우선, 한국전자통신연구원의 PBW(Phonetically Balanced Words) 445DB를 이용하여 가변어휘 단어 인식에서의 미등록어 거절 성능을 향상시키는 효과적인 발화 검증 방법을 제안하였다. 구체적으로 특별한 훈련 과정이 없이도 유사 음소 집합을 많이 포함시킨 반음소 모델을 제안하여 최소 검증 오류를 지니도록 하였다. 또한, 음소 단위의 null hypothesis와 alternate hypothesis의 비를 이용한 음소 단위의 신뢰도는 null hypothesis로 정규화해서 강인한 발화 검증 성능을 보여 주었으며, 음소 단위의 신뢰도를 이용한 단어 단위의 신뢰도는 등록어와 미등록어 사이의 분별력을 잘 표현해 주었다. 이와 같이 새로이 제안된 반음소 모델과 발화 검증 방법을 사용했을 때, CA (Correctly Accept for Keyword: 등록어를 제대로 인정한 경우)는 약 89%, CR (Correctly Reject for OOV (Out-of-Vocabulary): 미등록어에 대해 거절한 경우)은 약 90%로써, 기존 필터 모델을 이용한 방법보다 미등록어 거절 성능이 ERR (Error Reduction Rate) 측면에서 약 15-21% 향상됨을 알 수 있었다. Utterance verification is used in variable vocabulary word recognition to reject the word that does not belong to in-vocabulary word or does not belong to correctly recognized word. Utterance verification is an important technology to design a user-friendly speech recognition system. We propose a new utterance verification algorithm for no-training utterance verification system based on the minimum verification error. First, using PBW (Phonetically Balanced Words) DB (445 words), we create no-training anti-phoneme models which include many PLUs(Phoneme Like Units), so anti-phoneme models have the minimum verification error. Then, for OOV (Out-Of-Vocabulary) rejection, the phoneme-based confidence measure which uses the likelihood between phoneme model (null hypothesis) and anti-phoneme model (alternative hypothesis) is normalized by null hypothesis, so the phoneme-based confidence measure tends to be more robust to OOV rejection. And, the word-based confidence measure which uses the phoneme-based confidence measure has been shown to provide improved detection of near-misses in speech recognition as well as better discrimination between in-vocabularys and OOVs. Using our proposed anti-model and confidence measure, we achieve significant performance improvement; CA (Correctly Accept for In-Vocabulary) is about 89%, and CR (Correctly Reject for OOV) is about 90%, improving about 15-21% in ERR (Error Reduction Rate).

DP 알고리즘에 의한 발음사전 전처리와 문맥종속 자소별 MLP를 이용한 영어 발음사전 생성기의 개선

김회린,문광식,이영직,정재호 한국음향학회 1999 韓國音響學會誌 Vol.18 No.5

본 논문에서는 가변어휘 단어 인식기에 사용하기 위한 개선된 MLP 기반 영어 발음사전 생성기를 제안한다. 가변어휘 단어 인식기는 인식대상 도메인이 수시로 바뀌는 상황에서 현재의 인식 도메인에 의해 결정되는 임의의 한국어 어휘들에 대해 처리 할 수 있다. 이 시스템을 영어 단어에 대해서도 처리할 수 있도록 하기 위해서는 미리 정의된 사전에 포함할 수 없는 영어 고유명사와 같은 단어의 발음열을 구할 수 있는 방법이 필요하다. 영어 발음사전 생성기를 구현하기 위하여 본 연구에서는 각 자소를 음소로 변환해 주는 문맥종속 다층 퍼셉트론 구조를 제안한다. 각 자소별 다층 퍼셉트론을 훈련하기 위해서는 표준 발음사전으로부터 각 자소에 대응하는 음소 학습용 데이터를 준비해야 한다. 이를 위해 본 연구에서는 적절한 거리척도를 사용하는 동적 프로그래밍 알고리즘을 사용한다. 훈련 및 평가를 위한 데이터로는 116,191개 영어 단어의 발음사전을 사용하였다. 평가 결과 각각 30~50개의 히든 노드를 가지는 26개 자소별 MLP와 예외 자소 발음사전을 가지고 표준 발음사전에 대하여 72.8%의 단어 정확도를 얻었으며, 이것은 기존의 규칙 에 기반한 발음사전 생성의 정확도인 24.0% 보다 매우 우수한 결과임을 보여주었다. In this paper, we propose an improved MLP-based English pronunciation dictionary generator to apply to the variable vocabulary word recognizer. The variable vocabulary word recognizer can process any words specified in Korean word lexicon dynamically determined according to the current recognition task. To extend the ability of the system to task for English words, it is necessary to build a pronunciation dictionary generator to be able to process words not included in a predefined lexicon, such as proper nouns. In order to build the English pronunciation dictionary generator, we use context-dependent grapheme-to-phoneme multi-layer perceptron(MLP) architecture for each grapheme. To train each MLP, it is necessary to obtain grapheme-to-phoneme training data from general pronunciation dictionary. To automate the process, we use dynamic programming(DP) algorithm with some distance metrics. For training and testing the grapheme-to-phoneme MLPs, we use general English pronunciation dictionary with about 110 thousand words. With 26 MLPs each having 30 to 50 hidden nodes and the exception grapheme lexicon, we obtained the word accuracy of 72.8% for the 110 thousand words superior to rule-based method showing the word accuracy of 24.0%.

공사장 폴리우레탄폼의 화재 위험성 연구

장창훈,이윤칠,문광식 한국화재감식학회 2021 한국화재감식학회 학회지 Vol.12 No.3

Polyurethane foam is often used as an insulation material in modern society due to its excellent insulation function, light weight and low density. As a result, fires are occurring frequently at construction sites using polyurethane foam. Due to the characteristics of polyurethane foam, the spread of fire is fast and toxic gases erupt in large quantities, causing property damage and human damage Most of the causes of the fire are caused by carelessness of workers during heat of work around the area, such as welding spark and torch use, with polyurethane foam applied. In response, this study experimented with the possibility of direct ignition on polyurethane foam applied using welding spark, grinder, and torch, which are the heat of works mainly used in construction sites. Experiments show that the applied polyurethane foam was easily ignited by welding spark, torches, and oil vapor except grinder spark. The purpose of the project is to prevent fires by prohibiting heat work such as welding at polyurethane foam work places and thoroughly observing and supervising prescribed fire safety rules.

초음파검사 및 호르몬검사에 의한 젖소 번식검진과 발정유도 II. 황체가 존재하는 난소낭종의 진단과 치료

오기석,박상국,김방실,고진성,신종봉,백종환,홍기강,문광식,임원호 한국임상수의학회 2003 한국임상수의학회지 Vol.20 No.3

To establish the differential diagnosis and treatment method in bovine ovarian cysts, specially ovarian cysts with corpus luteum, serum progesterone concentration, rectal palpation and ultrasonography for measuring the cystic wall thickness and diameter of cyst and corpus luteum were investigated from 1,188 dairy cows with ovarian cysts. The plasma progesterone concentrations were 0.3$\pm$0.4 (mean$\pm$SD) ng/ml in 629 cows with follicular cysts, 3.7$\pm$1.1 ng/ml in 431 cows with luteal cysts, and 3.8$\pm$1.2 ng/ml in 128 cows with coexist of ovarian cysts and corpus luteum, respectively. The cystic wall thickness by ultrasonography were 1.6$\pm$0.4 mm in 629 cows with follicular cysts, 4.2$\pm$1.5 mm in 431 cows with luteal cysts, and 1.6$\pm$0.6 mm in 128 cows with coexist of ovarian cysts and corpus luteum, respectively. The days from initial treatment to insemination in follicular cysts were 28.1$\pm$6.9 days in treatment of GnRH alone, 15.9$\pm$2.9 days in combination of GnRH and dinoprost, and 15.1$\pm$3.1 days in combination of GnRH and cloprostenol. The percentages of cows conceived within 100 days after initial treatment were 61 %, 68% and 73% in treatment of GnRH alone, combination of GnRH and dinoprost, and combination of GnRH and cloprostenol, respectively. The days from initial treatment to insemination in luteal cysts were 3.8$\pm$0.6 days in treatment of dinoprost alone and 3.8$\pm$0.7 in cloprostenol alone. The percentages of cows conceived within 100 days after initial treatment were 69.5% and 68.5% in treatment of dinoprost and cloprostenol, respectively. The days from initial treatment to insemination in coexist of cysts and corpus luteum were 3.7$\pm$0.7 days in treatment of dinoprost alone and 3.8$\pm$0.6 in cloprostenol alone. The percentages of cows conceived within 100 days after initial treatment were 87% and 84% in treatment of dinoprost and cloprostenol, respectively. These results suggest that the best choice for treatment agents in ovarian cysts were combination of GnRH and PGF$_2$$\alpha$ in follicular cysts, and the PGF$_2$$\alpha$ in luteal cysts and in coexist of cysts and corpus luteum, respectively. In conclusion, it is suggest that ultrasonography is useful diagnostic tool for diagnosis and selection of treatment remedy in cystic ovaries of bovine.

초음파검사 및 호르몬검사에 의한 젖소 번식검진과 발정유도 III. $PGF_2{\alpha}$ 제제에 의한 발정유도

오기석,박상국,김방실,고진성,신종봉,백종환,홍기강,문광식,임원호 한국임상수의학회 2003 한국임상수의학회지 Vol.20 No.3

To establish the method of estrus induction using the injection of PGF$_2$$\alpha$ㆍ the 60 dairy cows treated by PGF$_2$$\alpha$ㆍ at 6, 8, 10, 12, 14, and 16 day of estrous cycle, recpectively. The plasma progesterone concentrations at day of injection of PGF$_2$$\alpha$ㆍ were $1.5\pm$1.3 (mean$\pm$SD) ng/ml at 6 days of estrous cycle, 3.7$\pm$1.4 ng/ml at 8 days, 6.5$\pm$1.8 ng/ml at 10 days, 7.9$\pm$2.0 ng/ml at 12 days, 6.5$\pm$2.5 ng/ml at 14 days, and 2.5$\pm$1.2 ng/m] at 16 days, respectively. The percentages of induction of estrus after PGF$_2$$\alpha$ㆍ treatment were 52.8% at 3th day after treatment, 21.7% at 4th day, 8.3% within 2th day, and ] 7.2% after 5th day, respectively. The percentages of cows conceived at first service after induction of estrus were 73.3% on 16 days of estrous cycle at treatment, 66.7% on 10 and 14 days, 63.3% on 8 and 12 days, and 53.3% on 6 day, respectively. The percentages of cows conceived on first service were 70.5% at 3th day after induction, 66.7% at 4th day and 65% at 5th day, respectively. These results suggest that the PGF$_2$$\alpha$ㆍ treatment at regressing stage of corpus luteum showed high induction of estrus and pregnancy rate, and there were high induction of estrus and pregnancy rate at 3th and 4th day after PGF$_2$$\alpha$ㆍ treatment.

초음파검사 및 호르몬검사에 의한 젖소 번식검진과 발정유도 I. 정기적인 번식검진 및 번식장애 치료

오기석,박상국,김방실,고진성,신종봉,백종환,홍기강,문광식,임원호 한국임상수의학회 2003 한국임상수의학회지 Vol.20 No.3

The ultrasonography was performed in 77,924 subestrous dairy cows from 680 dairy farms at 57 districts. The cows were examined for confirmation of resumption of ovaries and uterus after 30 days postpartum, for early pregnancy diagnosis after 30 days post-insemination, confirmation of pregnancy at 8 month post-insemination, and for diagnosis of reproductive dysfunctions, respectively. The results of reproductive examination by ultrasonography in 77,924 dairy cows were ovarian disorders 35,452 (46.8%), uterine disorders 10,721 (13.8%), pregnancy and pregnant failure 24,044 (30.8%), adhesion of reproductive tracts 167 (0.2%), freematins 13 (0.01%) and others 6,527 (8.4%) cows, respectively. The 13,732 (49.6%) cows out of 27,694 cows were treated for silent heat or error of estrus detection, 3,473 (12.5%) cows for follicular cysts, 815 (3.0%) cows for luteal cysts, 606 (2.2%) cows for inactive ovaries, 4 (0.01%) cows for granulosa cell tumors, and 6,455 (23.3%) cows for endometritis, respectively. The indices of reproductive efficiencies before (2001-08-10) and after (2003-07-20) periodical examination of reproductive status were as follows; the mean intercalving interval were shortened from 471 days to 383 days, the mean interval calving to conception were shortened from 187 days to 99 days, the mean interval calving to first service were shortened from 105 days to 67 days, the mean cows showing heat by 60 days postpartum were increased from 33% to 89%, the mean conception rate to first service were increased from 43% to 68%, and the mean service per conception were shortened from 2.6 times to 1.8 times, respectively. These results suggest that periodical examination of reproductive status would be useful for the improvement of the reproductive performance in dairy cows.

Kinect 기반 손 모양 인식을 위한 손 영역 검출에 관한 연구

박한훈(Hanhoon Park),최준영(Junyeong Choi),박종일(Jong-Il Park),문광식(Kwang-Seok Moon) 한국방송·미디어공학회 2013 방송공학회논문지 Vol.18 No.3