• Journal of the Korean Applied Science and Technology
• /
• v.18 no.3
• /
• pp.180-185
• /
• 2001

Antibiotics polymer prepared by chemical bonding and simple blending of antibacterial into polymers have attracted much interest because of their long-lasting and antibacterial activity. Antibiotics polymer can significantly reduce losses associated with dissolution, photolytic decomposition and volatillization. Further more, increased efficiency safety and selectivity are additional benefits which may be realized. In this study, Antibiotics polymer was synthesized by chemical reaction of polyacrylic acid with sulfamethazine by N,N'-dicyclohexylcarbodiimide(DCC) method. Antibacterial susceptibility was determined against Streptococcus pyrogenes[gram(+)] and Esherichia coli.[gram(-)] using a standardized disc test. As a result, the synthetic antibiotics polymer exhibited the broad susceptibilty against Streptococcus pyrogenes and Esherichia coli. Especially, the antibiotic effect of antibacterial polymer against Gram negative(Esherichia coli) was much stronger than that against Gram positive(Streptococcus pyrogenes).

• Microbiology and Biotechnology Letters
• /
• v.34 no.4
• /
• pp.306-310
• /
• 2006

For screening of the compounds exhibiting antimicrobial activities against the D-alanyl-D-alanine of Gram positive bacteria, approximately 2,500 actinomycetes isolated from soil were examined far antimicrobial activity. In consequence, we recently isolated the Streptomyces sp. G91353 strain produced an active compound, A91353, that inhibits the growth of Gram positive bacteria. A91353 was identified as N-acetyl-phenylalanine by various spectroscopic methods. The minimum inhibitory concentration (MIC) values of N-acetyl-phenylalanine on Gram positive bacteria such as Streptococcus pyogenes 308A, Streptococcus pyogenes 77A were determined as $50{\mu}g/ml$, respectively, but did not effect on Gram negative strains. These results indicate that N-acetyl-phenylalanine have an antimicrobial activity, which may be caused by the disturbance of D-alanyl-D-alanine synthesis.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.431-434
• /
• 2020

본 논문에서는 악성코드탐지 기법으로 n-grams를 사용한 특징 추출을 통해 이미지 인식 분야에서 널리 쓰이는 Convolutional Neural Network로 학습하는 프레임워크를 제안한다. 윈도우즈 실행 파일의 PE 포맷에서 특징을 추출하여 6-grams 확률을 구하고 grayscale 을 통해 이미지로 변환한다. 이것을 기존에 연구된 탐지방법과 비교하여 우수함을 보인다. 학습에 사용된 데이터는 총 55,000개로 5-folds 교차검증을 하였으며 예측 정확도는 98.87%였다.

• Journal of Veterinary Clinics
• /
• v.28 no.4
• /
• pp.348-351
• /
• 2011

The purpose of this study was to determine the distribution of gram-negative bacteria isolated from companion animals with sepsis, and to investigate the antimicrobial susceptibility patterns of the isolates. Bacterial pathogens were isolated from specimens of dogs and cats submitted to National Veterinary Research and Quarantine Service between 2008 and 2009. A total of 44 gram-negative pathogens were isolated from necropsied organs. The most common isolates were E. coli (n = 33), K. pneumoniae (n = 4) and B. bronchiseptica (n = 4). Most of gram-negative isolates were susceptible to ceftiofur (68.2%), colistin (84.1%), florfenicol (84.1%) and spectinomycin (61.4%). Most of those were resistant to ampicillin (77.3%), erythromycin (86.4%), flumequine (65.9%), lincomycin (97.7%), oxytetracycline (61.4%), penicillin (100%), streptomycin (63.6%), spiramycin (97.7%), sulfamethoxazole (90.9%), tylosin (97.7%) and tiamulin (100%). In conclusion, colistin and florfenicol could be useful against sepsis due to gram-negative bacteria.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.3
• /
• pp.274-284
• /
• 2002

Word segmentation errors occurring in text preprocessing often insert incorrect words into recognition vocabulary and cause poor language models for Korean large vocabulary continuous speech recognition. We propose an automatic word segmentation algorithm using Markov chains and syllable-based n-gram language models in order to correct word segmentation error in teat corpora. We assume that a sentence is generated from a Markov chain. Spaces and non-space characters are generated on self-transitions and other transitions of the Markov chain, respectively Then word segmentation of the sentence is obtained by finding the maximum likelihood path using syllable n-gram scores. In experimental results, the algorithm showed 91.58% word accuracy and 96.69% syllable accuracy for word segmentation of 254 sentence newspaper columns without any spaces. The algorithm improved the word accuracy from 91.00% to 96.27% for word segmentation correction at line breaks and yielded the decomposition accuracy of 96.22% for compound-noun decomposition.

• Annual Conference on Human and Language Technology
• /
• 2003.10d
• /
• pp.47-53
• /
• 2003

본 논문은 정제된 대용량 말뭉치로부터 얻은 음절 n-gram과 어절 통계를 이용한 한국어 자동 띄어쓰기 시스템을 제안한다. 한 문장 내에서 최적의 띄어쓰기 위치는 Viterbi 알고리즘에 의해 결정된다. 통계 기반 연구에 고유한 문제인 데이터 부족 문제, 학습 말뭉치 의존 문제를 개선하기 위하여 말뭉치를 확장하고 실험을 통해 얻은 매개변수를 사용하고 최장 일치 Viable Prefix를 찾아 어절 목록에 추가한다. 본 연구에 사용된 학습 말뭉치는 33,641,511어절로 구성되어 있으며 구어와 문어를 두루 포함한다.

• Annual Conference on Human and Language Technology
• /
• 1993.10a
• /
• pp.271-283
• /
• 1993

본 논문은 온라인 한글인식 시스템에서 오인식된 단어를 교정하는 알고리즘이다. 교정 기법으로는 N-gram 한글사전을 이용하였다. 오인식된 단어는 후보키의 선정과 선정된 후보문자중 가장 유사한 단어로 대체된다. 오인식 단어는 사전에 수록된 단어의 형태소 정보 즉, 사전의 표제어, 이의 품사 및 접속 규칙을 활용하여 교정된다. 본 논문은 오인식 교정에서 필요한 한글의 형태소 분석기에 관한 선행연구를 전제한다.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.83-86
• /
• 2003

This paper presents our style-based language model adaptation for Korean conversational speech recognition. Korean conversational speech is observed various characteristics of content and style such as filled pauses, word omission, and contraction as compared with the written text corpora. For style-based language model adaptation, we report two approaches. Our approaches focus on improving the estimation of domain-dependent n-gram models by relevance weighting out-of-domain text data, where style is represented by n-gram based tf*idf similarity. In addition to relevance weighting, we use disfluencies as predictor to the neighboring words. The best result reduces 6.5％ word error rate absolutely and shows that n-gram based relevance weighting reflects style difference greatly and disfluencies are good predictor.

• KIISE Transactions on Computing Practices
• /
• v.22 no.7
• /
• pp.315-319
• /
• 2016

Recurrent neural network based language models (RNN LM) have shown improved results in language model researches. The RNN LMs are limited to post processing sessions, such as the N-best rescoring step of the wFST based speech recognition. However, it has considerable vocabulary problems that require large computing powers for the LM training. In this paper, we try to find the 1st pass N-gram model using word embedding, which is the simplified deep neural network. The class based language model (LM) can be a way to approach to this issue. We have built class based vocabulary through word embedding, by combining the class LM with word N-gram LM to evaluate the performance of LMs. In addition, we propose that part-of-speech (POS) tagging based LM shows an improvement of perplexity in all types of the LM tests.

• Journal of KIISE:Software and Applications
• /
• v.35 no.12
• /
• pp.774-779
• /
• 2008

In this work, we describe comments classification system using topic signature. Topic signature is widely used for selecting feature in document classification and summarization. Comments are short and have so many word spacing errors, special characters. We firstly convert comments into 7-gram. We consider the 7-gram as sentence. We convert the 7-gram into 3-gram. We consider the 3-gram as word. We select key feature using topic signature and classify new inputs by the Naive Bayesian method. From the result of experiments, we can see that the proposed method is outstanding over the previous methods.