• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.11a
• /
• pp.17-20
• /
• 2003

본 논문에서는 공유 모델링의 대표적인 방법인 결정트리 기반 상태공유 모델을 기반으로 하여 그 출력 확률 분포의 혼합 가우시안 수를 줄임으로써 모델을 최적화하고자 하였다. 결정트리 기반의 상태공유 모델링은 일반적인 방법을 따랐으며 혼합 가우시안 수를 늘려 인식률이 최대가 되는 지점에서 혼합 가우시안을 클러스터링하여 그 수를 줄였다. 클러스터링 시에 필요한 거리 측정 방법이나 가까운 두 가우시안의 합성 방법을 여러 기법을 실험하였다. 이때 인식률은 클러스터링 이전인 97.2%를 유지하였으며 총 혼합 가우시안의 감소율은 1.0%를 보임으로써 모델을 최적화할 수 있었다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.435-438
• /
• 2007

움직이는 객체를 검출하기 위해서 정확한 배경을 사용하기 위해 널리 사용되는 방법으로는 가우시안 혼합 모델이다. 가우시안 혼합 모텔은 확률적 학습 방법을 사용하는데, 이 방법은 움직이는 배경일 경우와 이동하던 물체가 정지하는 경우 배경을 정확히 모델링하지 못한다. 본 논문에서는 확률적 모델링을 통해 혼잡한 배경을 모델링하고 객체의 계층적 처리를 통해 보다 정확한 배경으로 갱신할 수 있는 학습 방법을 제안한다.

• Smart Media Journal
• /
• v.4 no.3
• /
• pp.50-55
• /
• 2015

In this paper, we present background modeling method based on Gaussian mixture model to subtract background for night-time video surveillance. In night-time video, it is hard work to distinguish the object from the background because a background pixel is similar to a object pixel. To solve this problem, we change the pixel of input frame to more advantageous value to make the Gaussian mixture model using scaled histogram stretching in preprocessing step. Using scaled pixel value of input frame, we then exploit GMM to find the ideal background pixelwisely. In case that the pixel of next frame is not included in any Gaussian, the matching test in old GMM method ignores the information of stored background by eliminating the Gaussian distribution with low weight. Therefore we consider the stacked data by applying the difference between the old mean and new pixel intensity to new mean instead of removing the Gaussian with low weight. Some experiments demonstrate that the proposed background modeling method shows the superiority of our algorithm effectively.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.3
• /
• pp.387-391
• /
• 2008

For the detection of moving objects, background subtraction methods are widely used. In case the background has variation, we need to update the background in real-time for the reliable detection of foreground objects. Gaussian mixture model (GMM) combined with probabilistic learning is one of the most popular methods for the real-time update of the background. However, it does not work well in the complex and dynamic backgrounds with high traffic regions. In this paper, we propose a new method for modelling and updating more reliably the complex and dynamic backgrounds based on the probabilistic learning and the layered processing.

• KIPS Transactions on Computer and Communication Systems
• /
• v.13 no.1
• /
• pp.1-9
• /
• 2024

In the development and mass production of polymers, there are many uncontrollable variables. Even small changes in chemical composition, structure, and processing conditions can lead to large variations in properties. Therefore, Traditional linear modeling techniques that assume a general environment often produce significant errors when applied to field data. In this study, we propose a new modeling method (GPR-SEM) that combines Structural Equation Modeling (SEM) and Gaussian Process Regression (GPR) to study the Friction-Coefficient and Flexural-Strength properties of Polyacetal resin, an engineering plastic, in order to meet the recent trend of using plastics in industrial drive components. And we also consider the possibility of using it for materials modeling with nonlinearity.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.1
• /
• pp.177-183
• /
• 2010

In continuous vocabulary recognition system by statistical method vocabulary recognition to be performed using probability distribution it also modeling using phoneme clustering for based sample probability parameter presume. When vocabulary search that low recognition rate problem happened in express vocabulary result from presumed probability parameter by not defined phoneme and insert phoneme and it has it's bad points of gaussian model the accuracy unsecure for one clustering modeling. To improve suggested probability distribution mixed gaussian model to optimized for based resemble Euclidean and Bhattacharyya distance measurement method mixed clustering modeling that system modeling for be searching phoneme probability model in clustered model. System performance as a result of represent vocabulary dependence recognition rate of 98.63%, vocabulary independence recognition rate of 97.91%.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2522-2524
• /
• 2003

본 논문은 다수의 가우시안(Gaussian) 함수를 가중치 함수로 이용하여 퍼지 소속 함수의 효율적인 동정기법을 제안한다. 먼저 데이터를 가장 잘 구분하는 특징 변수를 선정하고, 이에 대한 기본 소속 함수를 가우시안 함수로 설정한 후, 다수의 가우시안 함수를 곱하여 소속 함수를 동정한다. 해당 특징 변수에 대한 소속 함수의 동정 후, 다음 우선 순위의 특징 변수를 퍼지 규칙에 첨가하여 가장 높은 정확도를 획득할 때까지 반복적으로 소속 함수를 동정한다. 이러한 방법은 데이터의 분포 성향을 소속 함수에 반영시킬 수 있을 뿐만아니라, 알고리듬의 고속 연산도 가능하다. 제안한 방법의 성능을 검증하기 위해 iris 데이터에 적용하여 모의실험의 예를 보인다.

• Journal of Advanced Navigation Technology
• /
• v.9 no.1
• /
• pp.56-60
• /
• 2005

To calculate the probability of bit error of UWB communication systems, the exact expression of multiple access interference is essential. So far, in many researches, MAI has been modeled by the Gaussian Approximation, which leads to the huge errors. And there are some tries to obtain the exact model fot the MAI but they have some problems such as long calculation time. We introduce the simple expression to calculate the probability of error of an UWB-TH system with BPSK. The multiple access interference is explained by the characteristic function method combined with the Gaussian approximation. It allows us to easily and fast calculate the bit error rate of an UWB-TH system.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.6
• /
• pp.110-114
• /
• 1997

When applying the nonuniform sampling to noisy speech signal, the required data rate increases to be comparable to or more than that by uniform sampling such as PCM. To solve this problem, we have proposed the waveform coding method, multiband nonuniform waveform coding(MNWC), applying the nonuniform sampling to band-separated speech signal[7]. However, the speech quality is deteriorated when it is compared to the uniform sampling method, since the high band is simply modeled as a Gaussian noise with average level. In this paper, as a good method to overcome this drawback, the high band is modeled as one of 16 codewords having different center frequencies. By doing this, with maintaining high speech quality as MOS score of average 3.16, the proposed method achieves 1.5 times higher compression ratio than that of the conventional nonuniform sampling method(CNSM).

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.6
• /
• pp.167-176
• /
• 2005

This paper describes how the state tying model based on the decision tree which is one of Acoustic models used for speech recognition optimizes the model by reducing the number of mixture Gaussians of the output probability distribution. The state tying modeling uses a finite set of questions which is possible to include the phonological knowledge and the likelihood based decision criteria. And the recognition rate can be improved by increasing the number of mixture Gaussians of the output probability distribution. In this paper, we'll reduce the number of mixture Gaussians at the highest point of recognition rate by clustering the Gaussians. Bhattacharyya and Euclidean method will be used for the distance measure needed when clustering. And after calculating the mean and variance between the pair of lowest distance, the new Gaussians are created. The parameters for the new Gaussians are derived from the parameters of the Gaussians from which it is born. Experiments have been performed using the STOCKNAME (1,680) databases. And the test results show that the proposed method using Bhattacharyya distance measure maintains their recognition rate at $97.2\%$ and reduces the ratio of the number of mixture Gaussians by $1.0\%$. And the method using Euclidean distance measure shows that it maintains the recognition rate at $96.9\%$ and reduces the ratio of the number of mixture Gaussians by $1.0\%$. Then the methods can optimize the state tying model.