• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.43-43
• /
• 2017

종자산업은 농작물 생산에 중요한 역할을 끼치는 좌우하는 요소 중에 하나로, 우량종자의 확보는 농작물 수급에 중요한 역할을 하는 농업부문의 원천산업이다. 오이 녹반 모자이크 바이러스(CGMMV)는 박과류에 가장 많은 피해를 끼치는 바이러스로 종자전염을 방지하고, 우량종자의 공급을 위해서는 감염종자와 비 감염종자의 판별은 필수적이다. 이에 본 연구에서는 초분광 영상 시스템을 이용하여 수박종자의 CGMMV의 감염 및 비 감염종자를 판별할 수 있는 기술을 개발하고자 하였다. 본 연구에서 사용된 바이러스 감염 종자는 CGMMV 바이러스 감염 수박종자를 사용하였으며, 생산된 종자를 초분광 영상 시스템을 통해 스크린 후, RNA를 추출하여 PCR분석법으로 바이러스의 감염유무를 확인하였으며, 이후 바이러스의 감염유무와 획득된 스펙트럼을 비교 분석하여 판별모델을 개발하고 이를 선별 시스템에 적용하였다. 모델개발에 사용된 초분광 영상 기술은 초분광 SWIR(Shortwave infraed : 1000-2500nm)영상 기술이 다. 획득된 초분광 SWIR 영상을 분석한 결과 바이러스 감염 종자가 유의미한 정확도로 판별이 되는 것으로 나타났다. 초분광 SWIR 영상기술이 바이러스 감염종자와 비감염종자를 비파괴적으로 선별하는데 효과적으로 적용이 가능할 것으로 판단된다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.3
• /
• pp.565-571
• /
• 2010

This paper proposes a parity discrimination algorithm which discriminates N bit parity using a perceptron neural network and back propagation algorithm. This algorithm decides minimum hidden unit numbers when discriminates N bit parity. Therefore, this paper implements parity discrimination experiments for N bit by changing hidden unit numbers of the proposed perceptron neural network. Experiments confirm that the proposed algorithm is possible to discriminates N bit parity.

• Research in Plant Disease
• /
• v.23 no.3
• /
• pp.249-255
• /
• 2017

The rice blast fungus is a representative model phytopathogenic fungus in which Gene-for-Gene interaction with host rice is applicable. After 1980, eight differential varieties have been constructed and classified to analyze the race of rice blast isolates in Korea. However, since there is limited information about the genetic background of rice blast resistance genes within the Korean differentials, scientific analysis on the emergence of new race or resistance break down was difficult. Recently, a differential system has been developed using monogenic resistance lines to understand the interactions of pathogen race and rice resistance genes. In this study, a total of 50 isolates were selected from four different races isolated in Korea, and they were inoculated into monogenic lines. As a result, the isolates in the same race classified by the Korean differential system reacted differently in single monogenic lines. This suggests that the isolates categorized as the same race group contains different avirulence genes and furthermore, it is presumed that the Korean differential system is difficult to provide useful information for breeding program. For this reason, introduction of differential system using monogenic resistance lines is required in addition to the current system.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.3
• /
• pp.195-198
• /
• 2013

Many libraries utilize RFID tags for checking in and out of books. However, the recognition rate of this automatic process may depend on the orientation of antennas and RFID tags. Therefore we need supplemental systems to improve the recognition rate. The proposed algorithm sets up the ROI of the book existing area from the input image and then performs Canny edge detection algorithm to extract edges of books. Finally Hough line transform algorithm allows to detect the number of books from the extracted edges. To evaluate the performance of the proposed method, we applied our method to 350 book images under various circumstances. We then analyzed the performance of proposed method from results using recognition and mismatch ratio. The experimental result gave us 97.1% accuracy in book counting.

• Journal of KIISE:Information Networking
• /
• v.36 no.3
• /
• pp.153-162
• /
• 2009

It is a challenging work for service operators to accurately classify different services, which runs on various wireless networks based upon numerous platforms. This works focuses on design and implementation of a classifier, which accurately classifies applications, which are captured horn WiBro Network. Notion of session is introduced for the classifier, instead of commonly used Flow to develop a classifier. Based on session information of given traffic, two classification algorithms are presented, Classification and Regression Tree and Support Vector Machine. Both algorithms are capable of classifying accurately and effectively with misclassification rate of 0.85%, and 0.94%, respectively. This work shows that classifier using CART provides ease of interpreting the result and implementation.

• Annual Conference on Human and Language Technology
• /
• 2010.10a
• /
• pp.194-196
• /
• 2010

휴대폰의 광범위한 보급으로 문자메시지의 사용이 급증하고 있다. 이와 동시에 사용자가 원하지 않는 광고성 스팸문자도 넘쳐나고 있다. 본 연구는 이러한 스팸문자메시지를 자동으로 판별하는 시스템을 개발하는 것이다. 우리는 기계학습방법인 지지벡터기계(Support Vector Machine)을 사용하여 시스템을 학습하였으며 자질의 선택은 카이제곱 통계량을 이용하였다. 실험결과 F1 척도로 약 95.5%의 정확률을 얻었다

• Smart Media Journal
• /
• v.4 no.4
• /
• pp.9-17
• /
• 2015

Recently the need for advanced security technologies are increasing as the occurrence of intelligent crime is growing fastly. Previous liveness detection and fake face detection methods are required for the improvement of accuracy in order to be put to practical use. In this paper, we propose a new liveness detection method using pupil reflection, and new fake image detection using Adaboost detector. The proposed system detects eyes based on multi-scale Gabor feature vector in the first stage, The template matching plays a role in determining the allowed eye area. And then, the reflected image in the pupil is used to decide whether or not the captured image is live or not. Experimental results indicate that the proposed method is superior to the previous methods in the detection accuracy of fake images.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.1
• /
• pp.163-168
• /
• 2011

Blogs are an easy way to publish information, engage in discussions, and form communities on the Internet. Recently, there are several varieties of spam blog whose purpose is to host ads or raise the PageRank of target sites. Our purpose is to develope the system which detects these spam blogs (splogs) automatically among blogs on Web environment. After removing HTML of blogs, they are tagged by part of speech(POS) tagger. Words and their POS tags information is used as a feature type. Among features, we select useful features with X2 statistics and train the SVM with the selected features. Our system acquired 90.5% of F1 measure with SPLOG data set.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.3
• /
• pp.380-387
• /
• 2010

For the fault diagnosis of three-phase induction motors, we propose a diagnosis algorithm based on mutual information and linear discriminant analysis (LDA). The experimental unit consists of machinery module for induction motor drive and data acquisition module to obtain the fault signal. As the first step for diagnosis procedure, DFT is performed to transform the acquired current signal into frequency domain. And then, frequency components are selected according to discriminate order calculated by mutual information As the next step, feature extraction is performed by LDA, and then diagnosis is evaluated by k-NN classifier. The results to verify the usability of the proposed algorithm showed better performance than various conventional methods.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.429-431
• /
• 2008

생체 인식 기술이 사회 전반에 걸쳐 다양하게 사용되어짐에 따라 인식기술 중의 하나인 Face Recognition 은 하루가 다르게 발전하고 있다. 하지만, 그와 함께 해킹방법도 다양화되어지고 있다. 그럼에도 불구하고, 위, 변조 영상 판별(Liveness Detection) 분야에 관련된 연구들은 초기 단계를 벗어나지 못하고 있다. 본 논문에서는 적외선 영상을 이용하여 동공부분의 반사 정도를 이용하여 실제 이미지와 위, 변조 이미지를 판별하는 방법을 제안한다.