• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.06a
• /
• pp.248-251
• /
• 2013

컴퓨터 비전에서 BoW를 이용한 장면 분류 기법에 대한 연구가 활발히 진행되고 있다. BoW 기법의 장면 분류는 K-means 클러스터링을 통하여 코드북을 생성하는 과정에서 트레이닝 이미지의 클래스 정보를 활용하지 않기 때문에 성능이 제한적이라는 문제점을 가지고 있다. 본 논문에서는 BoW를 이용한 장면 분류 과정에서 코드북 생성을 위하여 각각 특징 기술자들의 유클리디안 거리뿐만이 아니라 클래스 확률 밀도 함수들의 히스토그램 교차값을 최소화 하는 최적화 K-means 클러스터링 기법을 제안한다. 장면의 SIFT 특징 기술자 정보뿐만 아니라 장면이 속해있는 클래스 정보를 결합하여 클러스터링을 수행함으로써 장면 분류의 정확도를 높일 수 있다. 장면 분류 정확도 실험에서 제안하는 클러스터링을 사용한 BoW 장면 분류 기법은 기존의 K-means을 사용한 BoW 장면 분류 기법보다 높은 정확도를 보여준다.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.394-398
• /
• 2020

산업/직업분류 자동코딩시스템은 고용조사 등을 함에 있어 사업체 정보, 업무, 직급, 부서명 등 사용자의 다양한 입력을 표준 산업/직업분류에 맞춰 코드 정보를 제공해주는 시스템이다. 입력 데이터로부터 비지도학습 기반의 색인어 추출 모델을 학습하고, 부분단어 임베딩이 적용된 색인어 임베딩 모델을 통해 입력 벡터를 추출 후, 출력 분류 코드를 인코딩하여 지도학습 모델에서 학습하는 방법을 적용하였다. 기존 시스템의 분류 결과 데이터를 통해 대, 중, 소, 세분류에서 높은 정확도의 모델을 구축할 수 있으며, 기계학습 기술의 적용이 가능한 시스템임을 알 수 있다.

• Proceedings of the Safety Management and Science Conference
• /
• 2012.04a
• /
• pp.435-446
• /
• 2012

생활을 향상시키고 개선하기 위해 화학물질은 전 세계적으로 널리 이용 되고 있고, 또한 국내에는 38,000여종의 화학물질이 유통되고 있다. 그러나 화학물질은 그 이점에도 불구하고 사람이나 환경에 유해 영향을 가져올 가능성이 있어 위험물안전관리법에서는 3,000여종을 위험물로 분류하여 규제하고 있다. 위험물에 관련하여 유해화학물질관리법, 위험물안전관리법, 고압가스안전관리법, 총포 도검 화약류단속법, 원자력 진흥법, 농약관리법 등에서 개별적으로 규정하고 분류하고 있어 위험물질에 대한 표지사항이 해당 부처에 따라 상이하여 혼란을 야기하고 있고, 위험물에 대한 품목 및 품명의 고정으로 인하여 새롭게 생성된 위험물질에 대해 적용하는 데 문제점이 있다. 이에 의해 위험물질을 개별법에 따라 관리함으로써 중복된 위험물질 분류 및 관리의 문제가 있으며, 위험물질 분류에 있어서 위험물질에 따라 수송수단이 상이함에도 불구하고 수송수단별(도로, 철도, 해운, 항공) 위험물질에 대한 세분화된 자료가 부족하다. 따라서 수송관점에서 표준화된 위험물 물질정보의 분류와 코드화 방안개발이 필요하다. 본 연구는 국내 외 문헌 검토 및 위험물에 관련된 법제도 비교를 통하여 위험물 수송관리체계 정비방안과 위험물 수송사고의 문제점을 도출하고 기존의 위험물 분류체계에서 운송관점에서의 위험물 매칭테이블을 구축하고 신속한 사고대응을 위한 위험물질별 코드화 방안을 제안하도록 하겠다.

• Journal of Advanced Navigation Technology
• /
• v.10 no.3
• /
• pp.250-255
• /
• 2006

In digital multimedia society, we usually use the digital sound music ( Mp3, wav, etc.) system instead of analog music. In the middle of generating or recording and transmitting, if we embed the digital code which is useful to music information, we can easily select as well as classify the music title by using Mp3 player that embedded sound source classification system. In this paper, sound source classification system which could be classify and search a music informations by way of user friendly scheme is implemented. We performed some experiments to testify the validity of proposed scheme by using implemented system.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.37 no.5
• /
• pp.863-869
• /
• 2017

In this study, the information breakdown structure of water purification plant has been made by classifying various the water purification methods and facilities. this can be utilized as a code system of computer for integrating information and analyzing quantitative of environmental impact and calculating cost of maintenance and energy consumption which was used during life cycle of water purification plant. Since the construction information contains many heterogeneous information, it is very important to have a code system for managing the integrated information. In addition, since water purification plant facilities are mainly composed of installation of facilities including many processes, a more detailed classification code is required. Therefore, in this study, the water purification breakdown structure which is not yet attempted in Korea was constructed by using facet classification system.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.23 no.3
• /
• pp.501-514
• /
• 2013

A grouping process through the similarity comparison is required to effectively classify and respond a malicious code. When we have a use of the past similarity criteria to be used in the comparison method or properties it happens a increased problem of false negatives and false positives. Therefore, in this paper we apply to choose variety of properties to complement the problem of behavior analysis on the heuristic-based of 2nd step in malicious code auto analysis system, and we suggest a similarity comparison method applying AHP (analytic hierarchy process) for properties weights that reflect the decision-making technique. Through the similarity comparison of malicious code, configured threshold is set to the optimum point between detection rates and false positives rates. As a grouping experiment about unknown malicious it distinguishes each group made by malicious code generator. We expect to apply it as the malicious group information which includes a tracing of hacking types and the origin of malicious codes in the future.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.5
• /
• pp.1119-1127
• /
• 2018

Most of the cyber attacks are caused by malicious codes. The damage caused by cyber attacks are gradually expanded to IoT and CPS, which is not limited to cyberspace but a serious threat to real life. Accordingly, various malicious code analysis techniques have been appeared. Dynamic analysis have been widely used to easily identify the resulting malicious behavior, but are struggling with an increase in Anti-VM malware that is not working in VM environment detection. On the other hand, static analysis has difficulties in analysis due to various packing techniques. In this paper, we proposed malware classification techniques regardless of known packers or unknown packers through the proposed model. To do this, we designed a model of supervised learning and unsupervised learning for the features that can be used in the PE structure, and conducted the results verification through 98,000 samples. It is expected that accurate analysis will be possible through customized analysis technology for each class.

• Review of KIISC
• /
• v.27 no.3
• /
• pp.20-26
• /
• 2017

인터넷의 발달로 인류가 많은 유익을 얻었지만 동시에 악성코드와 같은 또다른 문제를 겪고 있다. 이러한 악성코드를 막기 위해 시그니처 기반의 안티바이러스 프로그램이 많이 사용되고 있지만 악성코드의 변종이나 제로데이 악성코드를 막는데 한계를 가지고 있다. 이러한 문제를 해결하기 위하여 본 논문에서는 딥러닝을 이용하여 악성코드를 탐지하고 분류하는 연구동향에 대해 소개한다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.22 no.6
• /
• pp.1325-1336
• /
• 2012

In the past about 10 different kinds of malicious code were found in one day on the average. However, the number of malicious codes that are found has rapidly increased reachingover 55,000 during the last 10 year. A large number of malicious codes, however, are not new kinds of malicious codes but most of them are new variants of the existing malicious codes as same functions are newly added into the existing malicious codes, or the existing malicious codes are modified to evade anti-virus detection. To deal with a lot of malicious codes including new malicious codes and variants of the existing malicious codes, we need to compare the malicious codes in the past and the similarity and classify the new malicious codes and the variants of the existing malicious codes. A former calculation method of the similarity on the existing malicious codes compare external factors of IPs, URLs, API, Strings, etc or source code levels. The former calculation method of the similarity takes time due to the number of malicious codes and comparable factors on the increase, and it leads to employing fuzzy hashing to reduce the amount of calculation. The existing fuzzy hashing, however, has some limitations, and it causes come problems to the former calculation of the similarity. Therefore, this research paper has suggested a new comparison method for malicious codes to improve performance of the calculation of the similarity using fuzzy hashing and also a classification method employing the new comparison method.

• The Journal of the Korea Contents Association
• /
• v.5 no.4
• /
• pp.150-159
• /
• 2005

With the increase of interest in ubiquitous computing, image code is attracting attention in various areas. Image code is important in ubiquitous computing in that it can complement or replace RFID (radio frequency identification) in quite a few areas as well as it is more economical. However, because of the difficulty in reading precise colors due to the severe distortion of colors, its application is quite restricted by far. In this paper, we present an efficient method of image code recognition including automatically locating the image code using the hue and saturation values. In our experiments, we use an image code whose design seems most practical among currently commercialized ones. This image code uses six safe colors, i.e., R, G, B, C, M, and Y. We tested for 72 true-color field images with the size of $2464{\times}1632$ pixels. With the color calibration based on the histogram, the localization accuracy was about 96%, and the accuracy of color classification for localized codes was about 91.28%. It took approximately 5 seconds to locate and recognize the image code on a PC with 2 GHz P4 CPU.