• Smart Media Journal
• /
• v.8 no.4
• /
• pp.33-37
• /
• 2019

Because the ECG signals are time-series data acquired as time elapses, it is important to obtain comparative data the same in size as the enrolled data every time. This paper suggests a network model of GAN (Generative Adversarial Networks) based on an auxiliary classifier to generate synthetic ECG signals which may address the different data size issues. The Cosine similarity and Cross-correlation are used to examine the similarity of synthetic ECG signals. The analysis shows that the Average Cosine similarity was 0.991 and the Average Euclidean distance similarity based on cross-correlation was 0.25: such results indicate that data size difference issue can be resolved while the generated synthetic ECG signals, similar to real ECG signals, can create synthetic data even when the registered data are not the same as the comparative data in size.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.190-192
• /
• 2002

데이터 마이닝(Data Mining)이란 저장된 많은 양의 자료로부터 통계적 수학적 분석방법을 이용하여 다양한 가치 있는 정보를 찾아내는 일련의 과정이다. 데이터 클러스터링은 이러한 데이터 마이닝을 위한 하나의 중요한 기법이다. 본 논문에서는 Fuzzy C-Means 알고리즘을 이용하여 웹 사용자들의 행위가 기록되어 있는 웹 로그 데이터를 데이터 클러스터링 하는 방법에 관하여 연구하고자 한다. Fuzzv C-Means 클러스터링 알고리즘은 각 데이터와 각 클러스터 중심과의 거리를 고려한 유사도 측정에 기초한 목적 함수의 최적화 방식을 사용한다. 웹 로그 데이터의 여러 필드 중에서 사용자 IP, 시간, 웹 페이지 필드를 WLDF(Web Log Data for FCM)으로 가공한 후, 다차원 Fuzzy C-Means 클러스터링을 한다. 그리고 이를 이용하여 샘플 데이터와 임의의 데이터간의 유사 패턴 분석을 하고자 한다.

• The KIPS Transactions:PartA
• /
• v.16A no.6
• /
• pp.453-462
• /
• 2009

Studies on software plagiarism detection, prevention and judgement have become widespread due to the growing of interest and importance for the protection and authentication of software intellectual property. Many previous studies focused on comparing all pairs of submitted codes by using attribute counting, token pattern, program parse tree, and similarity measuring algorithm. It is important to provide a clear-cut model for distinguishing plagiarism and collaboration. This paper proposes a source code clustering algorithm using a probability model on extreme value distribution. First, we propose an asymmetric distance measure pdist($P_a$, $P_b$) to measure the similarity of $P_a$ and $P_b$ Then, we construct the Plagiarism Direction Graph (PDG) for a given program set using pdist($P_a$, $P_b$) as edge weights. And, we transform the PDG into a Gumbel Distance Graph (GDG) model, since we found that the pdist($P_a$, $P_b$) score distribution is similar to a well-known Gumbel distribution. Second, we newly define pseudo-plagiarism which is a sort of virtual plagiarism forced by a very strong functional requirement in the specification. We conducted experiments with 18 groups of programs (more than 700 source codes) collected from the ICPC (International Collegiate Programming Contest) and KOI (Korean Olympiad for Informatics) programming contests. The experiments showed that most plagiarized codes could be detected with high sensitivity and that our algorithm successfully separated real plagiarism from pseudo plagiarism.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.162-165
• /
• 2017

The proposed paper extracts the region of interest from the x-lay input image and compares it with the reference image. The x-ray image has the same shape, but the size, direction and position of the object are photographed differently. In this way, we measure the erection difference of darkness and darkness using the similarity measurement method for the same object. Distance measurement also calculates the distance between two points with vector coordinates (x, y, z) of x-lay data. Experimental results show that the proposed method improves the accuracy of ROI extraction and the reference image matching time is more efficient than the conventional method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37C no.12
• /
• pp.1271-1280
• /
• 2012

In the recent parking assistant systems, finding out the distance to the object behind a car is often performed by the range sensors such as ultrasonic sensors, radars. However, the installation of additional sensors on the used vehicle could be difficult and require extra cost. On the other hand, the motion stereo technique that extracts distance information using only an image sensor was also proposed. However, In the stereo rectification step, the motion stereo requires good features and exacts matching result. In this paper, we propose a fast algorithm that extracts the accurate distance information for the parallel parking situation using the consecutive images that is acquired by a rear-view camera. The proposed algorithm uses the quadrangle transform of the image, the horizontal line integral projection, and the blocking-based correlation measurement. In the experiment with the magna parallel test sequence, the result shows that the line-accurate distance measurement with the image sequence from the rear-view camera is possible.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.10 no.4 s.50
• /
• pp.45-54
• /
• 2006

The characteristics of the ground motion attenuation in Korea and Japan were estimated using the earthquake ground motions recorded at the equal distance observation stations by KMA, K-NET and KiK-net of Korea and Japan. The ground motion attenuation equations proposed for Korea and Japan were evaluated by comparing the predicted value fer the Fukuoka earthquake with the observed records. The predicted value from the attenuation equations shows good agreement with the observed records and each other. It can be concluded from this study that the ground motion attenuation equations developed for Japan can be used usefully for the prediction of a ground motion from far field earthquake more than 200 km and for the evaluation of the far field ground motion attenuation equations proposed fer Korea.

• Progress in Medical Physics
• /
• v.15 no.2
• /
• pp.94-99
• /
• 2004

Radiochromic film has several advantages; high spatial resolution, relatively low spectral sensitivity, near tissue equivalence and requires no special development procedure. The object of this study was to measure the anisotropy of an Ir-192 source (microSelectron manufactured by Nucletron) in a few mm regions from the source, using the GafChromic film. The GafChromic film was calibrated in the range of 0∼105 Gy, using a 4 MV photon beam, and the anisotropy function measured in an acrylic phantom using the GafChroimic film. The data obtained gave agreement to within 4.4% of the Monte Calro calculation, by J. F. Williamson, at a radial distance of 2.5 mm with polar angles of 50 to 130$^{\circ}$, while a maximum deviation of 17.6% was observed at angles near 140$^{\circ}$and agreement within 3.7% at a radial distance of 5 mm at polar angles between 35 to 150$^{\circ}$ and a maximum deviation of 7.6% was observed at angles near 30$^{\circ}$. A GafChromic film can be used as a more efficient detector for measuring the anisotropy of an HDR $^{192}$ Ir source at close distances than any other detector.

• Journal of the Korean GEO-environmental Society
• /
• v.13 no.12
• /
• pp.43-49
• /
• 2012

Noise measurements were performed by distance for major construction equipment. especially, For construction equipment that large width of variations is depending on the type of work, noise measurements were performed by the detail type of work. For a time of quiescent and construction, "A" compensation equivalent noise level (Leq) were measured. Most of the construction equipment and the characteristics of the point source appears to be similar in analyzed noise measurement results.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.414-414
• /
• 2011

우리나라 뿐만 아니라 전 세계적으로 기후변화로 인한 집중호우, 폭설 등이 빈번하게 일어나고 있으며 수공구조물 설계에 필요한 확률강우량도 증가하고 있다. 확률강우량을 산정하는 빈도해석의 경우 지점빈도해석의 문제점을 보완한 지역빈도해석에 대한 연구가 꾸준히 진행되고 있다. 지역빈도해석을 적용하기 위해서는 수문학적 동질성을 가지는 지역 구분이 무엇보다 중요하다. 군집 분석은 개체들이 지니고 있는 다양한 속성의 유사성을 동질적인 집단으로 군집화하는 방법을 말한다. 군집분석의 기본원리는 분석하고자 하는 여러 특성등을 유사성(similaruty) 거리(distance)로 환산하고 거리가 상대적으로 가까운 개체들을 동질적으로 군집화하는 것이다. 군집분석을 적용하기 위해서는 기상학적 인자와 지형학적 인자를 이용하여 군집분석을 실시한다. 군집분석을 실시할 때 가장 중요한 것은 입력변수의 선택으로 입력 변수의 적절한 선택이 결과값에 큰 영향을 준다. 상호정보량(Mutual Information, MI) 기법은 두 무작위 변수간의 관련성을 측정하는 방법이며 (Cover and Tomas, 2006), 두 변수간의 독립성 구조에 관한 가정이 없고 데이터 변형이나 잡음(noise)에 대한 영향이 적어 다른 기법보다 신뢰도가 높다고 알려져 있다(Peng et al., 2005). 본 연구에서는 상호정보량 기법을 이용하여 군집된 지점들의 종속성과 독립성의 관계를 정량적으로 산정하여 비교하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.554-557
• /
• 2016

2015년 우리나라 스마트폰 보급률이 83%에 다다르고 인터넷 정보 검색은 PC보다 모바일이 추월한지 오래다. 범람하는 정보 안에서 편하고 빠른 것에 익숙해진 사용자들은 이제 개인화된 맞춤형 추천 정보의 제공을 원한다. 맞춤형 추천을 위해서는 사용자의 행동을 이해하고 추천하는 것이 필요하다. 현재 대중화된 개인 추천 서비스는 책과 영화가 있는데 생활에 많은 부분을 차지하고 있는 음식점 방문에 대해서도 맞춤형 추천 서비스를 제공해 줄 수 있다. 본 논문에서는 음식점 방문에 대한 비슷한 태도를 보인 사용자를 추출한 후 방문했던 장소를 비교하여 추천하는 사용자 행동 기반 다속성 태도 모델 기반의 장소 추천 모델을 연구한다. 다속성 태도점수를 산출하기 위해 피쉬바인(Fishbein) 방정식을 활용하고 피어슨 상관계수를 이용하여 사용자들간의 유사한 장소를 추출했다. 그리고 그룹렌즈의 선호도 예측 알고리즘을 활용하여 추천 대상 장소를 선정하고 유클라디안 거리법으로 사용자의 거리기반 장소를 추천하였다. 또한 본 논문에서는 실제 데이터를 이용한 실험을 통해 본 논문에서 제시한 시스템의 우수성도 입증하였다.