• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1597-1599
• /
• 2015

본 논문에서는 곡물이나 광석 등의 원료들 중에서 양품 및 불량품을 검출하기 위해, Color CCD 카메라로 촬영한 원료영상에서 Mean-Shift 클러스터링 알고리즘과 단계별 병합 방법을 제안하고 있다. 먼저 원료 학습 영상에서 배경을 제거하고 영상 색 분포정도를 기준으로 모폴로지를 이용하여 영상의 전경맵을 얻는다. 전경맵 영상에 대해서 Mean-Shift 군집화 알고리즘을 적용하여 영상을 N개의 군집으로 나누고, 단계별로 위치 근접성, 색상대푯값 유사성을 비교하여 비슷한 군집끼리 통합한다. 이렇게 통합된 원료 객체는 영상채널마다의 연관관계를 반영할 수 있도록 RG/GB/BR의 2차원 컬러분포도로 표현한다. 원료 객체별로 변환된 2차원 컬러 분포도에서 분포의 주성분의 기울기와 타원들을 생성한다. 객체별 분포 타원은 테스트 원료 영상데이터에서 양품과 불량품을 검출하는 임계값이 된다. 본 논문에서 제안한 방법으로 다양한 원료영상에 실험한 결과, 기존 선별방식에 비해 사용자의 인위적 조작이 적고 정확한 원료 선별 결과를 얻을 수 있었다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.8 no.1
• /
• pp.45-50
• /
• 2015

In this paper, we confirm the effective adaptive algorithm for tha active noise contorl (ANC) though the performance comparison between adaptive algorithms. Generally, the normalized least mean square (NLMS) algorithm has been widely used for an adaptive algorithm thanks to its simplicity and having a fast convergence speed. However, the convergence performance of the NLMS algorithms is often deteriorated by colored input signals. To overcome this problem, the affine pojection (AP) algorithm that updates the weight vector based on a number of recent input vectors can be used for allowing a higher convergence speed than the NLMS algorithm, but it is computationally complex. Thus, the proper algorithm were determined by the comparison between NLMS and AP algorithms regarding as the convergence performance and complexity. Simulation results confirmed that the noise reduction performance of NLMS algorithm was comparable to AP algorithm with low complexity. Therefore the NLMS algorithm is more effective for ANC system.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.6
• /
• pp.95-101
• /
• 2009

Among the adaptive noise cancellers (ANC), the least mean square (LMS) algorithm has probably become the most popular algorithm because of its robustness, good tracking properties, and simplicity of implementation. However, it has non-uniform convergence and a trade-off between the rate of convergence and excess mean square error (EMSE). To overcome these shortcomings, a number of variable step size least mean square (VSSLMS) algorithms have been researched for years. These LMS algorithms use a complex variable step method approach for rapid convergence but need high computational complexity. A variable step approach can impair the simplicity and robustness of the LMS algorithm. The proposed instantaneous gain control (IGC) algorithm uses the instantaneous gain value of the original signal and the noise signal. As a result, the IGC algorithm can reduce computational complexity and maintain better performance.

• The Journal of the Acoustical Society of Korea
• /
• v.12 no.1E
• /
• pp.20-31
• /
• 1993

Berman과 Feuer의 SLMS(smoothed least mean square)알고리즘의 근사적 분석을 행하여 보다 유용한 분석결과를 얻었다. 수렴범위와 misadjustment에 대한 분석에서는 기존의 알고리즘의 분석결과들과 비교할 수 있는 형태로 얻었을뿐만아니라 여러 변수들이 이 알고리즘의 성능에 미치는 영향을 명확히 알 수 있는 형태로 얻었다. 둘째로 몇몇 서로 유사한 알고리즘들을 비교검토함으로써 서로간의 관계를 밝히고 이 결과들을 해석하였다. 이어서 위의 분석결과들이 유효함을 실험을 통하여 밝혔다. 수렴한계 근처에서 LMS알고리즘보다 안정됨을 보였다. 이들 아고리즘의 비정상특성(nonstationary characteristics)에 대하여서도 살펴보았는데, SLMS알고리즘의 경우 추적능력의 별다른 희생 없이도 가중계수(weight)의 잡음을 줄일 수 있음을 보였다.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.7
• /
• pp.81-89
• /
• 1999

Image obtained by incomplete communication always include noise, blur and distortion, etc. In this paper, we propose and apply the new spatial filter algorithm, called an optimal adaptive generalized stack filter(AGSF), which optimizes adaptive generalized stack filter(AGSF) using neural network weight learning algorithm of back-propagation learning algorithm for improving noise removal and edge preservation rate. AGSF divides into two parts: generalized stack filter(GSF) and adaptive multistage median filter(AMMF), GSF improves the ability of stack filter algorithm and AMMF proposes the improved algorithm for reserving the sharp edge. Applied to neural network theory, the proposed algorithm improves the performance of the AGSF using two weight learning algorithms, such as the least mean absolute(LAM) and least mean square (LMS) algorithms. Simulation results of the proposed filter algorithm are presented and discussed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.10
• /
• pp.2417-2422
• /
• 2015

Mean-Shift tracking using hue has a problem that it fail in the object tracking when background has similar hue to the object. This paper proposes an improved Mean-Shift tracking algorithm using new data instead of a hue. The new data is generated by adaptive mixture of hue and saturation which have low interrelationship . That is, the proposed algorithm selects a main attribute of color that is able to distinguish the object and background well and a secondary one which don't, and places their upper 4 bits on upper 4 bits and lower 4 bits on the mixture data, respectively. The proposed algorithm properly tracks the object, keeping tracking error maximum 2.0~4.2 pixel and average 0.49~1.82 pixel, by selecting the saturation as the main attribute of color under tracking environment that background has similar hue to the object.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.7 no.2
• /
• pp.69-74
• /
• 2013

In this paper, we propose the pattern classification algorithm of recognizing wrist movements based on electromyogram(EMG) to raise the recognition rate. We consider 30 characteristics of EMG signals wirh the root mean square(RMS) and the difference absolute standard deviation value(DASDV) for the extraction of precise features from EMG signals. To get the groups of each wrist movement, we estimated 2-dimension features. On this basis, we divide each group into two parts with mean to compare and promote the recognition rate of pattern classification effectively. For the motion classification based on EMG, the k-nearest neighbor(k-NN) is used. In this paper, the recognition rate is 92.59% and 0.84% higher than the study before.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.4
• /
• pp.772-780
• /
• 2008

K-means is one of the simplest unsupervised learning algorithms that solve the clustering problem. However K-means suffers the basic shortcoming: the number of clusters k has to be known in advance. In this paper, we propose extensions of X-means, which can estimate the number of clusters using Bayesian information criterion(BIC). We introduce two different versions of algorithm: modified X-means(MX-means) and generalized X-means(GX-means), which employ one full covariance matrix for one cluster and so can estimate the number of clusters efficiently without severe over-fitting which X-means suffers due to its spherical cluster assumption. The algorithms start with one cluster and try to split a cluster iteratively to maximize the BIC score. The former uses K-means algorithm to find a set of optimal clusters with current k, which makes it simple and fast. However it generates wrongly estimated centers when the clusters are overlapped. The latter uses EM algorithm to estimate the parameters and generates more stable clusters even when the clusters are overlapped. Experiments with synthetic data show that the purposed methods can provide a robust estimate of the number of clusters and cluster parameters compared to other existing top-down algorithms.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.22 no.1
• /
• pp.55-66
• /
• 2018

Purpose In PET/CT exam, washed-out artifact could occur due to severe motion of the patient and high specific activity, it results in lowering not only qualitative reading but also quantitative analysis. Scatter limitation correction by GE is an algorism to correct washed-out artifact and recover the images in PET scan. The purpose of this study is to measure the threshold of specific activity which can recovers to original uptake values on the image shown with washed-out artifact from phantom experiment and to compare the quantitative analysis of the clinical patient's data before and after correction. Materials and Methods PET and CT images were acquired in having no misalignment(D0) and in 1, 2, 3, 4 cm distance of misalignment(D1, D2, D3, D4) respectively, with 20 steps of each specific activity from 20 to 20,000 kBq/ml on $^{68}Ge$ cylinder phantom. Also, we measured the distance of misalignment of foley catheter line between CT and PET images, the specific activity which makes washed-out artifact, $SUV_{mean}$ of muscle in artifact slice and $SUV_{max}$ of lesion in artifact slice and $SUV_{max}$ of the other lesion out of artifact slice before and after correction respectively from 34 patients who underwent $^{18}F-FDG$ Fusion Whole Body PET/CT exam. SPSS 21 was used to analyze the difference in the SUV between before and after scatter limitation correction by paired t-test. Results In phantom experiment, $SUV_{mean}$ of $^{68}Ge$ cylinder decreased as specific activity of $^{18}F$ increased. $SUV_{mean}$ more and more decreased as the distance of misalignment between CT and PET more increased. On the other hand, the effect of correction increased as the distance more increased. From phantom experiments, there was no washed-out artifact below 50 kBq/ml and $SUV_{mean}$ was same from origin. On D0 and D1, $SUV_{mean}$ recovered to origin(0.95) below 120 kBq/ml when applying scatter limitation correction. On D2 and D3, $SUV_{mean}$ recovered to origin below 100 kBq/ml. On D4, $SUV_{mean}$ recovered to origin below 80 kBq/ml. From 34 clinical patient's data, the average distance of misalignment was 2.02 cm and the average specific activity which makes washed-out artifact was 490.15 kBq/ml. The average $SUV_{mean}$ of muscles and the average $SUV_{max}$ of lesions in artifact slice before and after the correction show a significant difference according to a paired t-test respectively(t=-13.805, p=0.000)(t=-2.851, p=0.012), but the average $SUV_{max}$ of lesions out of artifact slice show a no significant difference (t=-1.173, p=0.250). Conclusion Scatter limitation correction algorism by GE PET/CT scanner helps to correct washed-out artifact from motion of a patient or high specific activity and to recover the PET images. When we read the image occurred with washed-out artifact by measuring the distance of misalignment between CT and PET image, specific activity after applying scatter limitation algorism, we can analyze the images more accurately without repeating scan.

• Journal of IKEEE
• /
• v.19 no.4
• /
• pp.603-609
• /
• 2015

Thermal comfort is one of the fundamental aspects of indoor environmental quality and it is strongly related to occupant satisfaction and energy used in building. In this paper, we proposes smart comfort algorithm that save energy and provide a pleasant and comfortable environment for workers by the indoor comfort conditions(Predictive Mean Vote) detection and controlling the temperature and humidity, air flow. Simulation results, heating and cooling control of the thermal comfort control can be compared with the existing general air conditioners reduces the power of 0.5kW and indoor comfort can be maintained. Also, It showed a 49.2% improvement in the light by lighting control algorithm.