• Journal of Korea Multimedia Society
• /
• v.16 no.11
• /
• pp.1272-1280
• /
• 2013

In this paper, we propose an audio surveillance system which can detect and localize dangerous sounds in real-time. The location information about dangerous sounds can render a PTZ camera to be directed so as to catch a snapshot image about the dangerous sound source area and send it to clients instantly. The proposed audio surveillance system firstly detects foreground sounds based on adaptive Gaussian mixture background sound model, and classifies it into one of pre-trained classes of foreground dangerous sounds. For detected dangerous sounds, a sound source localization algorithm based on Dual delay-line algorithm is applied to localize the sound sources. Finally, the proposed system renders a PTZ camera to be oriented towards the dangerous sound source region, and take a snapshot against over the sound source region. Experiment results show that the proposed system can detect foreground dangerous sounds stably and classifies the detected foreground dangerous sounds into correct classes with a precision of 79% while the sound source localization can estimate orientation of the sound source with acceptably small error.

• The Korean Journal of Applied Statistics
• /
• v.19 no.1
• /
• pp.171-181
• /
• 2006

The Wald confidence interval has been considered as a standard method for the difference of proportions. However, the erratic behavior of the coverage probability of the Wald confidence interval is recognized in various literatures. Various alternatives have been proposed. Among them, Agresti-Caffo confidence interval has gained the reputation because of its simplicity and fairly good performance in terms of coverage probability. It is known however, that the Agresti-Caffo confidence interval is conservative. In this note, a confidence interval is developed using the weighted Polya posterior which was employed to obtain a confidence interval for the binomial proportion in Lee(2005). The resulting confidence interval is simple and effective in various respects such as the closeness of the average coverage probability to the nominal confidence level, the average expected length and the mean absolute error of the coverage probability. Practically it can be used for the interval estimation of the difference of proportions for any sample sizes and parameter values.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.6 no.2
• /
• pp.186-192
• /
• 2011

In this paper, we propose a new procedure for improvement of the linear predictive coding. To reduce the error power incurred by the coding, we interchanged the order of the two procedures of windowing on the signal and linear prediction. This scheme corresponds to LPC extraction with windowed autocorrelation. The proposed method requires more calculational time because it necessitates matrix inversion on more parameters than the conventional technique where an efficient Levinson-Durbin recursive procedure is applicable with smaller parameters. Experimental test over various speech phonemes showed, however, that our procedure yields about 5 % less power distortion compared to the conventional technique. Consequently, the proposed method in this paper is thought to be preferable to the conventional technique as far as the fidelity is concerned. In a separate study of speaker-dependent speech recognition test for 50 isolated words pronounced by 40 people, our approach yielded better performance too.

• Journal of the Korea Convergence Society
• /
• v.8 no.11
• /
• pp.77-83
• /
• 2017

For efficient predictive analysis, self-healing research is needed that enables the system to recover autonomously by self-cognition and diagnosing system problems. However, software development does not provide formal contextual information analysis and appropriate presentation structure according to external situation. In this paper, we propose a prediction analysis method based on the change contents by applying the extraction rule to the functions that can act, data, and transaction based on the new Goal-scenario. We also evaluated how well the predictive analysis met through the performance indicators for achieving the requirements goal. Compared with the existing methods, the proposed method has a maximum 32.8% higher matching result through performance measurement, resulting in a 28.9% error rate and a 45.8% reduction in the change code. This shows that it can be processed into a serviceable form through rules, and it shows that performance can be expanded through predictive analysis of changes.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.5
• /
• pp.1044-1051
• /
• 2003

This paper surveys the EBP(Error Back Propagation) learning, the Cross Entropy function and the LBL(Layer By Layer) learning, which are used for learning the MLP(Multi Layer Perceptrons). We compare the merits and demerits of each learning method in the handwritten digit recognition. Although the speed of EBP learning is slower than other learning methods in the initial learning process, its generalization capability is better. Also, the speed of Cross Entropy function that makes up for the weak points of EBP learning is faster than that of EBP learning. But its generalization capability is worse because the error signal of the output layer trains the target vector linearly. The speed of LBL learning is the fastest speed among the other learning methods in the initial learning process. However, it can't train for more after a certain time, it has the lowest generalization capability. Therefore, this paper proposes the standard of selecting the learning method when we apply the MLP.

• Journal of Navigation and Port Research
• /
• v.29 no.8 s.104
• /
• pp.685-692
• /
• 2005

In this study, it is surveyed and analyzed under the condition of developing GPS receiver that the present status of use and the precision of GPS receiver installed in naval vessels. Throughout interview and questionnaire with the workers in naval vessels, reliability and utilization of GPS receiver are verified. In conclusion, it is suggested that the development of GPS receiver system as well as navigation methods in naval vessels. The result of this study is as follows. Though the workers in naval vessels regard the accuracy of GPS receiver position as the fix by geographical navigation method. However, it is confirmed that its practical usage is when it is difficult to obtain the fix by geographical navigation method or R/D position or for verification. The suggested plans to develop the navigation methods from naval vessels standpoint are designing a parallel systems and introducing the GPS receiver system that functions well and is linked to the electronic navigation chart.

• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.894-896
• /
• 1999

PID 제어는 50년의 역사를 갖기 때문에 현장의 사용자는 이 제어방식에 익숙해져 있으며, 제어장치의 구성이 간단하며 제어기의 최적동조가 가능하므로 많은 분야에서 사용되고 있다[1]. 그러나 PID 제어기에 의해서 얻은 결과에 대하여 만족하기 위해서는 많은 시행착오를 겪어야 한다. 또한 만족하는 결과를 얻었다고 할지라도 외란, 플랜트의 동특성이 바뀌는 경우 시스템을 추종하지 못하기 때문에 파라미터를 재조정하여야 한다. 유전 알고리즘은 자연세계의 진화 현상에 기초한 계산모델로서 John Holland에 의해서 1975년에 개발된 전역적인 최적화 알고리즘이며[1][2], 비선형 고차원, 불연속, 다중모드, 노이즈 함수 등에 대하여 강건함을 보여주고, 복잡한 탐색 공간에서 최적 값을 스스로 발견하는 학습 능력을 갖는다. 이 방법은 재생산, 교배, 돌연변이를 통하여 최적해를 찾은 방법으로 1989년에 D. E. Goldgerg에 의해서 체계적으로 정리된 후 여러 분야에서 응용되고 있다[3][4]. 그러나 유전 알고리즘은 목적함수만을 이용하여 해집단을 탐색하기 때문에 숙련운전자가 원하는 제어 특성 명세인 상승시간, 정착시간, 초과량(oveshoot) 둥을 구체적으로 명시하여 제어에 반영할 수 없다. 또한, 유전 알고리즘은 입력 값이 크게 바뀔 경우 다른 시스템으로 인식하여 새로운 탐색을 수행하는 단점을 가지고 있다. 본 논문은 첫째, 기준모델을 도입하여 플랜트의 성능을 기준모델로 표현하여 플랜트가 요구하는 성능지표를 정량적으로 규정하는 것이 가능하였다. 또한, 이것은 미지 플랜트 동특성을 식별하기 위한 신호로 사용되어, 플랜트의 정보를 얻는데 이용되었다. 즉, 기준모델과 플랜트 출력사이의 추종 오차 정보가 적응기구인 PID 유전제어기의 입력으로 사용되며, 구형파 입력의 경우에도 기준모델과 플랜트의 출력차는 크게 변하지 않는다. 따라서, 유전 알고리즘의 목적함수에 기준 모델을 제안 적용하여 안정적이고, 세밀한 제어를 수행하였다. 둘째, PID의 간단하면서 확실한 제어가 가능하다는 점과 전역적인 최적값을 찾을 수 있는 유전 알고리즘을 적용하여 고속제어를 요하는 직류 서보 모터(DC Servo Motor) 운전 시 실시간 파라미터 동조에 적용하였다.

• Proceedings of KOSOMES biannual meeting
• /
• 2007.11a
• /
• pp.43-49
• /
• 2007

The metals we are familiar with(Al, Ag, Au, Cu, Cd, Co, Fe, Ni, Pb, Zn, etc) are common elements and conservative pollutants. Although metals are often vital constituents of the metabolism of living organisms(trace elements}, a number of them are toxic if their concentration exceeds a certain threshold. It has long been recognized that measurements of trace metals in natural waters are often subject to large errors in terms of precision and accuracy. Since 1975 in US and European countries, seawater concentration of many trace metals have been shown to be factors of 10-1,000 lower than those previously accepted. Vertical profiles have been found to be consistent with known biological, physical and/or geochemical processes. These are resulted from major advances in analytical instrumentation and methodology for trace elements, and greater attention has been given to assuring the elimination of contamination during sampling, storage, and analysis.

• Journal of Korea Multimedia Society
• /
• v.9 no.2
• /
• pp.234-243
• /
• 2006

The recent rapid development of HCI and surveillance technologies has brought great interests in application systems to process faces. Much of research efforts in these systems has been primarily focused on such areas as face recognition, facial expression analysis and facial feature extraction. However, not many approaches have been reported toward face direction detection. This paper proposes a method to detect the direction of a face using a facial feature called facial triangle, which is formed by two eyebrows and the lower lip. Specifically, based on the single monocular view of the face, the proposed method introduces very simple formulas to estimate the horizontal or vertical rotation angle of the face. The horizontal rotation angle can be calculated by using a ratio between the areas of left and right facial triangles, while the vertical angle can be obtained from a ratio between the base and height of facial triangle. Experimental results showed that our method makes it possible to obtain the horizontal angle within an error tolerance of ${\pm}1.68^{\circ}$, and that it performs better as the magnitude of the vertical rotation angle increases.

• Journal of Korea Multimedia Society
• /
• v.12 no.3
• /
• pp.383-396
• /
• 2009

Bone age assessment has been widely used in pediatrics to identify endocrine problems of children. Since the number of trained doctors is far less than the demands, there has been numerous requests for automatic estimation of bone age. Therefore, in this paper, we propose an automatic bone age assessment method that utilizes pattern classification techniques. The proposed method consists of three modules; a finger segmentation module, a normalized shape model generation module and a bone age estimation module. The finger segmentation module segments fingers and epiphyseal regions by means of various image processing algorithms. The shape model abstraction module employ ASM to improves the accuracy of feature extraction for bone age estimation. In addition, SVM is used for estimation of bone age. Features for the estimation include the length of bone and the ratios of bone length. We evaluated the performance of the proposed method through statistical analysis by comparing the bone age assessment results by clinical experts and the proposed automatic method. Through the experimental results, the mean error of the assessment was 0.679 year, which was better than the average error acceptable in clinical practice.