• Journal of the Korea Society of Computer and Information
• /
• v.4 no.3
• /
• pp.28-34
• /
• 1999

In this paper. we propose the method of Scene Change Detection for video sequence using the DC components and the moving vectors in the Macro Blocks in the DCT blocks. The proposed method detects the Scene Change which would not be related with the specific sequences in the compressed MPEG domain. To do this. we define new metrics for Scene Change Detection using the features of picture component and detect the exact Scene Change point of B-pictures using the characteristics of B-picture's sharp response for the moving vectors. In brief, we will detect the cut point using I-picture and the gradual scene changes such as dissolve, fade, wipe, etc. As a results, our proposed method shows good test results for the various MPEG sequences.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.27 no.5
• /
• pp.383-392
• /
• 2007

In this paper, we study the prediction of depth and width of a defect in steam generator tube in nuclear power plant using neural network. To this end, we first generate eddy current testing (ECT) signals for 4 defect patterns of SG tube: I-In type, I-Out type, V-In type, and V-Out type. In particular, we generate 400 ECT signals for various widths and depths for each defect type by the numerical analysis program based on finite element modeling. From those generated ECT signals, we extract new feature vectors for the prediction of defect size, which include the angle between the two points where the maximum impedance and half the maximum impedance are achieved. Using the extracted feature vector, multi-layer perceptron with one hidden layer is used to predict the size of defects. Through the computer simulation study, it is shown that the proposed method achieves decent prediction performance in terms of maximum error and mean absolute percentage error (MAPE).

• The Journal of the Acoustical Society of Korea
• /
• v.35 no.6
• /
• pp.501-509
• /
• 2016

We propose a method to improve the robustness of speaker verification on short test utterances. The accuracy of the state-of-the-art i-vector/probabilistic linear discriminant analysis systems can be degraded when testing utterance durations are short. The proposed method compensates for utterance variations of short test feature vectors using deep neural networks. We design three different types of DNN (Deep Neural Network) structures which are trained with different target output vectors. Each DNN is trained to minimize the discrepancy between the feed-forwarded output of a given short utterance feature and its original long utterance feature. We use short 2-10 s condition of the NIST (National Institute of Standards Technology, U.S.) 2008 SRE (Speaker Recognition Evaluation) corpus to evaluate the method. The experimental results show that the proposed method reduces the minimum detection cost relative to the baseline system.

• Journal of Korean Society of Transportation
• /
• v.23 no.7 s.85
• /
• pp.7-15
• /
• 2005

The objective of this study is to estimate highway trip demand functions in Korea. In order to estimate them, I propose various socio-economic variables that affect the highway trip demand functions. I use the unit root test for each variable and the cointegration test to and the relationships among variables. Finally, I use the vector error correction model, to get the highway trip demand functions. The implication which I derive from the estimation is that real GDP and highway tolls have positive and negative effects, respectively. on the highway trip demand.

• Aerospace Engineering and Technology
• /
• v.12 no.1
• /
• pp.189-199
• /
• 2013

This paper summarizes results of second stage attitude control of KSLV-I third flight test. The results show that three axes attitude control at coasting phases of KSLV-I was successfully accomplished by the reaction control system, and pitch and yaw attitude control at thrusting phase where second stage kick motor burns was also normally accomplished by using the thrust vector control system. It is verified that the second stage controller performed successfully for all flight phases regardless of some disturbances due to mass center offset, slag effects, and residual thrust of kick motor. These results may provide an important basis in enhancing domestic technology level of attitude control of launch vehicle.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.3
• /
• pp.471-479
• /
• 2018

Recently, the spread of smart TV based Android iOS Set Top box has become common. This paper propose a new approach to control the TV using gestures away from the era of controlling the TV using remote control. In this paper, the AdaBoost algorithm is applied to gesture recognition by using a mono camera. First, we use Camshift-based Body tracking and estimation algorithm based on Gaussian background removal for body coordinate extraction. Using global and local feature vectors, we recognized gestures with speed change. By tracking the time interval trajectories of hand and wrist, the AdaBoost algorithm with CART algorithm is used to train and classify gestures. The principal component feature vector with high classification success rate is searched using CART algorithm. As a result, 24 optimal feature vectors were found, which showed lower error rate (3.73%) and higher accuracy rate (95.17%) than the existing algorithm.

• Journal of Broadcast Engineering
• /
• v.20 no.1
• /
• pp.57-67
• /
• 2015

This paper describes and analyzes IBC (intra block copy) in HEVC (high efficiency video coding) SCC (screen content coding) to improve the coding efficiency of IBC. HEVC SCC reference software SCM 2 is employed to analyze the selection ratio of IBC which is newly adopted in HEVC SCC, and the tools for IBC such as the block vector prediction and block vector coding method are evaluated. Experimental results show the average IBC selection ratio is 31.08% and 0.33% in I-Slice and B-Slice, respectively. Based on this results, the coding efficiency of IBC could be improved by utilizing IBC selectively. In addition, analysis tests of block vector prediction and the block vector coding method show the current methods are not efficient to screen content videos, and the analysis results are presented to improve these methods.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.41 no.4
• /
• pp.277-283
• /
• 2017

In this study, we investigated how a jumping strategy changes with an increase in the vertical jump height for a resultant ground reaction force (GRF) vector. We expected that the resultant force vector between two sequential motion phases (i.e., countermovement and push-off) of the countermovement jump would significantly change with the vertical jump height to take advantage of the resulting supportive force (i.e., an initial push-off force larger than the body weight) through the countermovement phase. Nine healthy young subjects were instructed to jump straight up to five different height levels ranging from 191 cm to 221 cm, and the kinematic and kinetic data were obtained in regular trials. The results showed that a lower center of mass position and larger resultant force vector were clearly observed in a higher jump, implying that the countermovement strategy changed with the vertical jump height to prepare for sufficient joint deviation and obtain a force advantage for larger push-off work.

• Journal of the KSME
• /
• v.26 no.5
• /
• pp.389-393
• /
• 1986

고유치는 여러 공학문제에서 중요하다. 예를들어 비행기의 안전성은 어떤 행렬(matrix)의 고유 치에 의해서 결정된다. 보의 고유진동수는 실제로 행렬의 고유치이다. 좌굴(buckling) 해석도 행렬의 고유치를 구하는 문제이다. 고유치는 여러 수학적인 문제의 해석에서도 자연히 발생한다. 상수계수 일계연립상미분방정식의 해는 그 계수행렬의 고유치로 구할 수 있다. 또한 행렬의 제곱의 수렬 $A,{\;}A^{2},{\;}A^{3},{\;}{\cdots}$의 거동은 A의 고유치로서 가장 쉽게 해석할 수 있다. 이러한 수렬은 연립일차방정식(비선형)의 반복해에서 발생한다. 따라서 이 강좌에서는 행렬의 고유치를 수치적으로 구하는 문제에 대하여 고찰 하고자 한다. 실 또는 보소수 .lambda.가 행렬 B의 고유치라 함은 영이 아닌 벡터 y가 존재하여 $By={\lambda}y$ 가 성립할 때이다. 여기서 벡터 y를 고유치 ${\lambda}$에 속하는 B의 고유벡터라 한다. 윗식은 또 $(B-{\lambda}I)y=0$의 형으로도 써 줄 수 있다. 행렬의 고유치를 수치적으로 구하는 방법에는 여러 가지 방법이 있으나 그 중에서 효과있는 Danilevskii 방법을 소개 하고자 한다. 이 Danilevskii 방법에 의하여 특 성다항식(Characteristic polynomial)을 얻을 수 있고 이 다항식의 근을 얻는 방법 중에 Bairstow 방법 (또는 Hitchcock 방법)이 있는데 이에 대하여 아울러 고찰하고자 한다.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.16 no.5
• /
• pp.675-682
• /
• 2013

Reliability analysis and prediction of next failure time is critical to sustain weapon systems, concerning scheduled maintenance, spare parts replacement and maintenance interventions, etc. Since 1981, many methodology derived from various probabilistic and statistical theories has been suggested to do that activity. Nowadays, many A.I. tools have been used to support these predictions. Support Vector Regression(SVR) is a nonlinear regression technique extended from support vector machine. SVR can fit data flexibly and it has a wide variety of applications. This paper utilizes SVM and SVR with combining time series to predict the next failure time based on historical failure data. A numerical case using failure data from the military equipment is presented to demonstrate the performance of the proposed approach. Finally, the proposed approach is proved meaningful to predict next failure point and to estimate instantaneous failure rate and MTBF.