• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.10
• /
• pp.948-956
• /
• 2014

Today, Intelligent Vehicle Detection System seeks to reduce the negative factors, such as accidents over to get the traffic information of existing system. This paper proposes detection algorithm for the illegal U-turn vehicles which can cause critical accident among violations of road traffic laws. We predicted that if calculated optical flow vectors were shown on the illegal U-turn path, they would be cause of the illegal U-turn vehicles. To reduce the high computational complexity, we use the algorithm of pyramid Lucas-Kanade. This algorithm only track the key-points likely corners. Because of the high computational complexity, we detect center lane first through the color information and progressive probabilistic hough transform and apply to the around of center lane. And then we select vectors on illegal U-turn path and calculate reliability to check whether vectors is cause of the illegal U-turn vehicles or not. Finally, In order to evaluate the algorithm, we calculate process time of the type of algorithm and prove that proposed algorithm is efficiently.

• The Journal of the Acoustical Society of Korea
• /
• v.33 no.2
• /
• pp.118-125
• /
• 2014

An approximation of speed of sound in the measurement plane is essential for the inverse estimation of temperature. To this end, an inverse problem relating the measured retarded time data in between set of sensors and actuators array located on the wall is formulated. The involved transfer matrix and its coefficient vectors approximate speed of sound of the measurement plane by using the radial basis function with finite number of interpolation points deployed inside the target field. Then, the temperature field can be reconstructed by using spatial interpolation technique, which can achieve high spatial resolution with proper number of interpolation points. A large number of retarded time data of acoustic paths in between sensors and arrays are needed to obtain accurate reconstruction result. However, the shortage of interpolation points due to practical limitations can cause the decrease of spatial resolution and deterioration of the reconstruction result. In this works, a regeneration for obtaining the additional retarded time data for an arbitrary acoustic path is suggested to overcome the shortage of interpolation points. By applying the regeneration technique, many interpolation points can be deployed inside the field by increasing the number of retarded time data. As a simulation example, two rectangular duct sections having arbitrary temperature distribution are reconstructed by two different data set: measured data only, combination of measured and regenerated data. The result shows a decrease in reconstruction error by 15 % by combining the original and regenerated retarded time data.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.885-901
• /
• 2021

This paper illustratesthe impact of the temporal gap between satellite images and targetsize in mesoscale atmospheric motion vector (AMV) algorithm. A test has been performed using GEO-KOMPSAT-2A (GK2A) rapid-scan data sets with a temporal gap varying between 2 and 10 minutes and a targetsize between 8×8 and 40×40. Resultsshow the variation of the number of AMVs produced, mean AMV speed, and validation scores as a function of temporal gap and target size. As a results, it was confirmed that the change in the number of vectors and the normalized root-mean squared vector difference (NRMSVD) became more pronounced when smaller targets are used. In addition, it was advantageous to use shorter temporal gap and smaller target size for the AMV calculation in the lower layer, where the average speed is low and the spatio-temporal scale of atmospheric phenomena is small. The temporal gap and the targetsize are closely related to the spatial and temporalscale of the atmospheric circulation to be observed with AMVs. Thus, selecting the target size and temporal gap for an optimum calculation of AMVsrequires considering them. This paper recommendsthat the optimized configuration to be used operationally for the near-real time analysis of mesoscale meteorological phenomena is 4-min temporal gap and 16×16 pixel target size, respectively.

• Journal of Korea Spatial Information System Society
• /
• v.1 no.2 s.2
• /
• pp.115-125
• /
• 1999

Much efforts are being process at many ways for digitization cadastral maps that will be the base map of Parceled Based Land Information Systems. But, current digitizing systems need too much time and cost digitizing about 720,000 cadastral maps. That's way we develop new digitization system for cadastral maps by using scanning and vectorizing methods. In this paper, we treat scanner test and vectorizing program that are the most important parts of new digitization system for cadastral maps. we analyze needs of Korean Cadastral Survey Corporation, and discuss algorithms and functions of developed programs. Using newly developed scanner test program, user could test various scanners, and use inexpensive scanner if it satisfy the accuracy needed. And vectorizing program will reduce much time and cost, because it is designed and customized practically to he adequate to cadastral maps and to improve work speed, accuracy and usage.

• Journal of Korea Multimedia Society
• /
• v.4 no.3
• /
• pp.230-237
• /
• 2001

Adaptive filters are widely used for acoustic echo canceler, adaptive equalizer and adaptive noise canceler. Coefficients of adaptive filters are updated by NLMS algorithm. However, Coefficients are misaligned by ambient noises when they are adapted by NLMS algorithm. In this Paper, a method determined the adaptation constant by low-pass filtered instantaneous gradient vector of LMS algorithm using orthognality principles of optimal filter is proposed. At initial states, instantaneous gradient vector, that is the cross-correlation of input signals and estimation error signals, has large value because input signals are remained in estimation error signals. When an adaptive filter is conversed, the cross-correlation will be close to zero. It isn's affected by ambient noises because ambient noises are uncorrelated with input signals. Determining adaptation constant with the cross-correlation, adaptive filters can be robust to ambient noises and the convergence rate doesn't slower As results of computer simulations, it is shown that the performance of proposed algorithm is betted than that of conventional algorithms.

• The KIPS Transactions:PartB
• /
• v.13B no.6 s.109
• /
• pp.625-632
• /
• 2006

Collaborative filtering is a technology that aims at teaming predictive models of user preferences. Collaborative filtering systems have succeeded in Ecommerce market but they have shortcomings of high dimensionality and sparsity. In this paper we propose the nearest neighbor collaborative filtering method using non-negative matrix factorization(NNMF). We replace the missing values in the user-item matrix by using the user variance coefficient method as preprocessing for matrix decomposition and apply non-negative factorization to the matrix. The positive decomposition method using the non-negative decomposition represents users as semantic vectors and classifies the users into groups based on semantic relations. We compute the similarity between users by using vector similarity and selects the nearest neighbors based on the similarity. We predict the missing values of items that didn't rate by a new user based on the values that the nearest neighbors rated items.

• Journal of Broadcast Engineering
• /
• v.23 no.1
• /
• pp.138-145
• /
• 2018

In this paper, we propose a new motion estimation algorithm for frame rate up-conversion. The proposed algorithm uses the variance of errors in addition to SAD in motion estimation to find more accurate motion vectors. Then, it decides which motion vectors are wrong using the variance of neighbor motion vectors and the variance between current motion vector and neighbor's average motion vector. Next, incorrect motion vectors are corrected by weighted sum of eight neighbor motion vectors. Additionally, we propose adaptive search range algorithm, so we can find more accurate motion vectors and reduce computational complexity at the same time. As a result, proposed algorithm improves the average peak signal-to-noise ratio and structural similarity up to 1.44 dB and 0.129, respectively, compared with previous algorithms.

• The Journal of the Korea Contents Association
• /
• v.16 no.10
• /
• pp.687-692
• /
• 2016

Conventional way to search documents is keyword-based queries using vector space model, like tf-idf. Searching process of documents which is based on keywords can make some problems. it cannot recogize the difference of lexically different but semantically same words. This paper studies a scheme of document search based on document queries. In particular, it uses centrality vectors, instead of tf-idf vectors, to represent query documents, combined with the Word2vec method to capture the semantic similarity in contained words. This scheme improves the performance of document search and provides a way to find documents not only lexically, but semantically close to a query document.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.11
• /
• pp.6838-6844
• /
• 2014

3GPP LTE-Advanced systems adopt multiple antennas for high speed data transmission. In general, the receiver complexity of a spatially mutiplexed (SM) multiple-input multiple-output (MIMO) system grows in proportion to the number of candidate vectors. A large number of candidate vectors increases the reliability of the soft output values. The maximum likelihood (ML) signal detection with a large number of candidate vectors achieves high performance. On the other hand, low complexity receiver techniques with a small number of candidate vectors provide soft output values, such as low reliability. This paper addresses the improving reliability of the soft output obtained from a small number of candidate vectors. The improved performance of the proposed technique with the aid of computer simulations is reported.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.262-267
• /
• 2007

퍼지 ART 알고리즘에서 경계 변수는 패턴들을 클러스터링하는데 있어서 반지름 값이 되며 임의의 패턴과 저장된 패턴과의 불일치(mismatch) 허용도를 결정한다. 이 경계 변수가 크면 입력 벡터와 기대 벡터 사이에 약간의 차이가 있어도 새로운 카테고리(category)로 분류하게 된다. 반대로 경계 변수가 작으면 입력 벡터와 기대 벡터 사이에 많은 차이가 있더라도 유사성이 인정되어 입력 벡터들을 대략적으로 분류한다. 따라서 영상 인식에 적용하기 위해서는 경험적으로 경계 변수를 설정해야 단점이 있다. 그리고 연결 가중치를 조정하는 과정에서 학습률의 설정에 따라 저장된 패턴들의 정보들이 손실되는 경우가 발생하여 인식율을 저하시킨다. 본 논문에서는 퍼지 ART 알고리즘의 문제점을 개선하기 위하여 퍼지 논리 접속 연산자를 이용하여 경계 변수를 동적으로 조정하고 저장 패턴들과 학습 패턴간의 실제적인 왜곡 정도를 충분히 고려하여 승자 노드로 선택된 빈도수를 학습률로 설정하여 가중치 조정에 적용한 개선된 퍼지 ART 알고리즘을 제안하였다. 제안된 방법의 성능을 확인하기 위해서 실제 영문 명함에서 추출한 영문자들을 대상으로 실험한 결과, 기존의 ART1과 ART2 알고리즘이나 퍼지 ART 알고리즘보다 클러스터의 수가 적게 생성되었고 인식 성능도 기존의 방법들보다 우수한 성능이 있음을 확인하였다.