• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1993.10a
• /
• pp.353-362
• /
• 1993

The purpose of this study is to develop a crop-row detector which can be applied to an automatic row following control for cultivators or thinning machines. In this report, a possibility of new crop-row detecting method was discussed. This detecting method consists of two principal means. One is the hardware means to convert the two dimensional crop-row vision to the compacted one dimensional information. The conversion is achieved by a color line sensor and a rotating mirror. In order to extract crop-row , R and G signals of RGB color system are used. The locations of two different points on the target row are detected by this means. Another is the software means to estimate the offset value and the heading angle between the detector and the target row which can be assumed as a straight line. As a result of discussion, it was concluded that this detecting method would be accurate enough for practical use.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.27 no.2
• /
• pp.146-159
• /
• 2023

This paper proposes a hybrid algorithm combining K-means clustering and watershed algorithms for flower segmentation and counting. We use the K-means clustering algorithm to obtain the main colors in a complex background according to the cluster centers and then take a color space transformation to extract pixel values for the hue, saturation, and value of flower color. Next, we apply the threshold segmentation technique to segment flowers precisely and obtain the binary image of flowers. Based on this, we take the Euclidean distance transformation to obtain the distance map and apply it to find the local maxima of the connected components. Afterward, the proposed algorithm adaptively determines a minimum distance between each peak and apply it to label connected components using the watershed segmentation with eight-connectivity. On a dataset of 30 images, the test results reveal that the proposed method is more efficient and precise for the counting of overlapped flowers ignoring the degree of overlap, number of overlap, and relatively irregular shape.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.107-110
• /
• 2021

글로벌 퍼블릭 클라우드 산업 규모는 매년 폭발적으로 성장하고 있으며 최근 COVID-19 등 비대면 문화 확산에 따라 지속 확장되고 있다. 클라우드 사업자는 유한한 인프라 자원으로 다수의 사용자에게 양질의 IT 서비스 제공을 위해 잉여 자원 할당을 최소화하는 것이 중요하다. 그러나 일반적인 퍼블릭 클라우드 환경에서는 정적 자원 할당 기법을 채택하고 있기 때문에 사용자의 주관적인 판단에 따라 잉여 자원의 발생은 필연적이다. 본 논문에서는 머신 러닝 기법 중 K-Means Clustering 알고리즘을 적용하여 클라우드 동적 자원 관리 기법을 제안한다. K-Means Clustering 기반으로 클라우드에 탑재된 각 Instance 의 자원 사용률 데이터를 분석하고, 분석 결과를 토대로 각 Instance 가 속한 Cluster 에 대하여 자원 최적화 작업을 수행한다. 이를 통해 전체 데이터센터 관점에서 잉여 자원의 발생을 최소화하면서도 SLA 수준 및 서비스 연속성을 보장한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.539-540
• /
• 2023

최근 물체 인식 모델의 성능을 개선하기 위한 다양한 연구가 진행 중이다. 본 논문에서는 K-means 기반 앵커박스 선정 기법을 적용한 새로운 물체 인식 모델 성능 개선 방법을 제안한다. 제안된 방법은 항만 내 설치된 컨테이너 사고를 예방하기 위한 컨테이너 사고위험도 분류 모델에 적용하여 성능 평가를 하였다. 특히, 컨테이너 사고위험도 분류 모델은 작은 물체를 인식해야 하며 이런 환경에서는 기존 물체 인식 모델 성능이 낮게 나타난다. 본 논문에서는 제안한 K-means 기반 앵커박스 선정 기법을 적용하여 물체 인식 모델 성능이 개선됨을 확인하였디.

• Journal of applied mathematics & informatics
• /
• v.41 no.5
• /
• pp.1057-1069
• /
• 2023

In this paper, we have determined the degree of approximation of function belonging of Lipschitz class by using Deferred-Generalized Nörlund (D^𝛾_𝛽.N_pq) means of Fourier series and conjugate series of Fourier series, where {p_n} and {q_n} is a non-increasing sequence. So that results of DEGER and BAYINDIR [23] become special cases of our results.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2010.04a
• /
• pp.91-93
• /
• 2010

• Journal of Power System Engineering
• /
• v.20 no.4
• /
• pp.32-37
• /
• 2016

This paper proposes two measurement methods for injured rate of fish surface using color image segmentation method based on K-means clustering algorithm and Otsu's threshold algorithm. To do this task, the following steps are done. Firstly, an RGB color image of the fish is obtained by the CCD color camera and then converted from RGB to HSI. Secondly, the S channel is extracted from HSI color space. Thirdly, by applying the K-means clustering algorithm to the HSI color space and applying the Otsu's threshold algorithm to the S channel of HSI color space, the binary images are obtained. Fourthly, morphological processes such as dilation and erosion, etc. are applied to the binary image. Fifthly, to count the number of pixels, the connected-component labeling is adopted and the defined injured rate is gotten by calculating the pixels on the labeled images. Finally, to compare the performances of the proposed two measurement methods based on the K-means clustering algorithm and the Otsu's threshold algorithm, the edge detection of the final binary image after morphological processing is done and matched with the gray image of the original RGB image obtained by CCD camera. The results show that the detected edge of injured part by the K-means clustering algorithm is more close to real injured edge than that by the Otsu' threshold algorithm.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.6
• /
• pp.1163-1168
• /
• 2011

Most transformers use insulating and cooling fluids derived from petroleum crude oil, but mineral oil has some possibility of environmental pollution and fire with explosion. vegetable oil fluids extracted from seed has superior biodegradation and fire-resistant properties including an exceptionally high fire point enhancing fire safety. In this study, it is aimed at the practicality of substituting natural ester dielectric fluid for mineral oil in liquid insulation system of transformers. As a rise in coil winding temperature has a direct influence on transformer life time, it is important to evaluate the temperature rise of coil winding in vegetable oil in comparison with mineral oil. Four transformers for the test are designed with 10KVA, 13.2KV, one phase unit. The temperature are directly measured in insulating oil of these transformers with the two sorts of natural ester and mineral oil dielectric fluid respectively. Experiment for aging carry out two means. First means remained $120^{\circ}C$ that transformer of mineral oil were operated at 185% load. Second means is that insulating oils of two natural ester and mineral oil were aged by thermal cycles repeating from $30^{\circ}C$ to $120^{\circ}C$. For the heating, Transformers were operated at 185% load. For the cooling, cooling system was operated in the chamber. Samples were analyzed at 42, 63, 93, 143, 190, 240 300cycles. Analysis contents are dielectric strength, total acid value. Mineral oils compared results of first means with results of second means. And compared two sort natural esters respectively with mineral oil in second means.

• Journal of KIISE:Computer Systems and Theory
• /
• v.31 no.10
• /
• pp.575-587
• /
• 2004

In this paper. a new Fast Expectation-Maximization algorithm(FEM) is proposed. Firstly the K-means algorithm is modified to reduce the number of iterations for finding the initial values that are used as the initial values in EM process. Conventionally the Initial values in K-means clustering are chosen randomly. which sometimes forces the process of clustering converge to some undesired center points. Uniform partitioning method is added to the conventional K-means to extract the proper initial points for each clusters. Secondly the effect of posterior probability is emphasized such that the application of Maximum Likelihood Posterior(MLP) yields fast convergence. The proposed FEM strengthens the characteristics of conventional EM by reinforcing the speed of convergence. The superiority of FEM is demonstrated in experimental results by presenting the improvement results of EM and accelerating the speed of convergence in parameter estimation procedures.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.9
• /
• pp.1557-1563
• /
• 2016

According to recent studies, poor sitting posture of the spine has been shown to lead to a variety of spinal disorders. For this reason, it is important to measure the sitting posture. We proposed a strategy for classification of sitting posture using machine learning. We retrieved acceleration data from single tri-axial accelerometer attached on the back of the subject's neck in 5-types of sitting posture. 6 subjects without any spinal disorder were participated in this experiment. Acceleration data were transformed to the feature vectors of principle component analysis. Support vector machine (SVM) and K-means clustering were used to classify sitting posture with the transformed feature vectors. To evaluate performance, we calculated the correct rate for each classification strategy. Although the correct rate of SVM in sitting back arch was lower than that of K-means clustering by 2.0%, SVM's correct rate was higher by 1.3%, 5.2%, 16.6%, 7.1% in a normal posture, sitting front arch, sitting cross-legged, sitting leaning right, respectively. In conclusion, the overall correction rates were 94.5% and 88.84% in SVM and K-means clustering respectively, which means that SVM have more advantage than K-means method for classification of sitting posture.