• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.202-204
• /
• 2018

본 논문에서는 부분 홀로그램의 중심점과 카메라의 이동에 따라 생성되는 시점 영상들의 상관성을 분석하였다. 같은 기준에서의 실험을 위하여, 물체의 실제 크기 및 시점간 거리 등의 파라미터를 조정하였으며, 카메라의 수평이동과 부분 홀로그램의 중심점이 좌, 우로 이동된 결과를 생성하는 실험을 진행하였다. 결과를 기반으로, 서로 다른 광학계와 생성방법을 통하여 생성된 임의의 시점 영상들의 상관성을 분석한다.

• The KIPS Transactions:PartD
• /
• v.16D no.3
• /
• pp.327-338
• /
• 2009

A microarray dataset is 2-dimensional dataset with a set of genes and a set of conditions. A bicluster is a subset of genes that show similar behavior within a subset of conditions. Genes that show similar behavior can be considered to have same cellular functions. Thus, biclustering algorithm is a useful tool to uncover groups of genes involved in the same cellular process and groups of conditions which take place in this process. We are proposing a polynomial time algorithm to identify functionally highly correlated biclusters. Our algorithm identifies 1) the gene set that has hidden patterns even if the level of noise is high, 2) the multiple, possibly overlapped, and diverse gene sets, 3) gene sets whose functional association is strongly high, and 4) deterministic biclustering results. We validated the level of functional association of our method, and compared with current methods using GO.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.580-582
• /
• 2002

본 논문은 위상한정상관법을 이용하여 겹쳐진 화상이 둘 중 어떤 화상에 더 유사한 지를 정량적으로 측정하는 알고리듬을 제안한다. 제안된 알고리듬은 화상을 푸리에변환하여 위상만을 가지고 합성화상을 만든 다음 역푸리에변환을 통하여 만들어지는 위상한정상관을 가지고 유사도를 측정한다. 본 알고리듬에서는 유사도를 충분히 구분할 수 있을 정도로 상수로 설정된 진폭을 충분히 크게 하고 중심부분이외에 나타나는 피크치를 무시하고 오직 중심부분 만의 피크치를 원화상의 자기상관과 비교한다. 실험결과는 진폭을 100으로 하였을 경우 위상한정상관의 피크는 그 유사도가 1에서 0까지 변함에 따라서 100에서 40까지변하는 것을 보여 준다. 이것은 제안된 알고리듬이 위상한정상관을 이용하여 화상의 유사도를 정량적으로 효과적으로 측정하는데 사용될 수 있음을 보여준다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37A no.12
• /
• pp.1145-1151
• /
• 2012

In this paper, we propose an unambiguous binary offset carrier (BOC) correlation function with narrow main-peak width for BOC code tracking. Specifically, we first separate a subcarrier pulse into two rectangular pulses, obtain the associated partial correlations, and re-combine the partial correlations to yield the unambiguous correlation function with narrow main-peak width. From numerical results, it is demonstrated that the proposed correlation function provides a significant performance improvement over the conventional correlation functions.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.7
• /
• pp.1433-1440
• /
• 2015

In this paper, we propose an unambiguous correlation function to improve tracking performance for binary offset carrier (BOC) signals. Specifically, we divide a BOC sub-carrier into multiple rectangular pulses, and analyze that the BOC autocorrelation function is made up of the sum of several partial correlation functions. Then, we obtain two sub-correlation functions by combining two partial correlation functions and propose a novel unambiguous correlation function with no side-peak which can be regulated its width based on the combination of the sub-correlation functions and partial correlation functions. From numerical results, it is confirmed that the proposed correlation function provides a tracking performance improvement over the conventional correlation functions in terms of the tracking error standard deviation.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.11a
• /
• pp.70-71
• /
• 2010

요즘 감시카메라 시장은 전 세계적으로 이슈가 되고 있다. 감시카메라는 적은 인원으로 많은 장소를 한 눈에 감시할 수 있고, 문제가 발생했을 때, 녹화 저장된 영상을 통해 그 상황을 다시 볼 수 있다. 이렇게 다양한 기능과 편리함으로 우리에게 도움을 주는 감시카메라이지만, 마스크나 선글라스, 또는 여러 가지 잡음에 의해 얼굴 영상의 부분이 훼손되는 상황에서는 신원 확인을 하기가 어렵다. 때문에 가려진 얼굴을 제대로 인식하기 위해 영상 처리 분야에서 얼굴의 가려진 영역을 찾아 그 부분을 재구성하고자 하는 연구가 활발히 진행되고 있다. 이에 본 논문은 기존 PCA 방법을 이용하여 가려진 영역을 찾아내고, PCA를 반복적으로 사용하여 재구성하는 대신 상관관계를 이용하여 얼굴의 가려진 영역을 자동적으로 검출하고 복원하는 방법을 제안한다. 본 논문에서는 두 눈의 중심이 고정되어 있는 BioID 데이터로 상관계수를 구하고 얼굴의 특정 부분을 임의로 가려 실험을 수행하였다. 제안된 방법의 결과는 PCA 방법으로 수행한 결과와 함께 비교되어 원본 영상과의 오류 값이 더 작게 나오는 것을 확인할 수 있었다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.5C
• /
• pp.437-443
• /
• 2012

In this paper, we propose a novel unambiguous correlation function for binary offset carrier (BOC) signal acquisition. Specifically, we first find out that the side-peaks arise due to the fact that the BOC autocorrelation is the sum of the irregularly shaped BOC sub-correlations, and then, propose an unambiguous correlation function with no side-peak by combining the sub-correlations. The proposed scheme is shown to remove the side-peaks completely for any type of BOC signal and to provide a better acquisition performance than the conventional correlation functions.

• Journal of IKEEE
• /
• v.8 no.1 s.14
• /
• pp.145-151
• /
• 2004

For wide-band spread spectrum communication systems such as IMT-2000, a digital matched filter is a key device for rapid spreading code synchronization. Although a digital matched filter can be implemented easily, large power consumption at the higher chip rate and large summation delay of longer chip length are the bottleneck of practical use. In this paper, we propose a optimized partial correlation digital matched filter structure which can be constructed of the so-called generalized hierarchical Golay sequence. a partial correlation structure can reduce the number of correlators, but enlarge the size of flip-flops. In this paper, The proposed approach focuses on efficient circuit size, power dissipation, maintaining the operating throughput. A proposed digital matched filter reduce the size of flip-flops by rounding method. and it reduces about 45 percentages of power dissipation and chip area as compared with digital matched filter which is not rounded. rounding. The proposed architecture was verified by using Xilinx FPGA.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.5
• /
• pp.931-940
• /
• 2011

Classification is to generate a rule of classifying objects into several categories based on the learning sample. Good classification model should classify new objects with low misclassification error. Many types of classification methods have been developed including logistic regression, discriminant analysis and tree. This paper presents a new classification method using penalized partial least squares. Penalized partial least squares can make the model more robust and remedy multicollinearity problem. This paper compares the proposed method with logistic regression and PCA based discriminant analysis by some real and artificial data. It is concluded that the new method has better power as compared with other methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.399-402
• /
• 2017

We consider an sensor partitioning problem for energy-efficient measurement scheduling in a spatially correlated sensor field where sensors are located randomly. We divide the whole sensors into subsets of k sensors in the way of letting each subset give similar amount of mutual information. Then it allows more prolonged life time of the sensor field than measuring the sensors that gives most information only. To this end, we compute the Shapley value of each sensor and compose the subsets so that each subset can have total Shapley value similar with the other subsets.