• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.235-238
• /
• 2003

Fuzzy C-Means(FCM) 알고리즘은 초기 군집 중심의 개수와 위치에 따라 군집 결과의 성능차이가 많이 나타난다. 하지만 일반적인 경우에 군집 중심의 개수는 분석가의 주관에 의해 결정되고, 임의적으로 결정되기 때문에 원래 데이터의 구조와는 무관하게 수행되어 최적화된 군집화 수행을 실행하지 못하는 경우가 발생하게 된다. 따라서 본 논문에서는 원래의 데이터의 구조에 좀더 근접한 퍼지 군집화를 수행하기 위하여 격자를 바탕으로 한 데이터의 밀도를 이용한 FCM을 제안하고, 이러한 밀도 기반 FCM에 의해 결정된 군집의 합병 기법을 제안하였다. N-차원의 데이터 공간을 N-차원의 격자로 나누고, 초기 군집 중심의 개수와 위치는 각 격자의 밀도를 바탕으로 결정된다. 초기화 이후에 각 격자 내부에서 FCM을 이용하여 군집화를 수행하고, 계속해서 이웃 격자의 군집결과에 대하여 군집간의 유사도 측도를 이용하여 군집 합병을 수행함으로써 데이터의 자연적인 구조에 근접한 군집화를 수행하였다. 제안된 군집화 합병 기법의 향상된 성능은 UCI Machine Learning Repository 데이터를 이용하여 확인하였다.

• The KIPS Transactions:PartD
• /
• v.13D no.7 s.110
• /
• pp.857-866
• /
• 2006

Performance of an image retrieval system is usually very low because of the semantic gap between the low level feature and the high level concept in a query image. Semantically relevant images may exhibit very different visual characteristics, and may be scattered in several clusters. In this paper, we propose a content based image rertrieval approach which combines region based image retrieval and a new relevance feedback method using adaptive clustering together. Our main goal is finding semantically related clusters to narrow down the semantic gap. Our method consists of region based clustering processes and cluster-merging process. All segmented regions of relevant images are organized into semantically related hierarchical clusters, and clusters are merged by finding the number of the latent clusters. This method, in the cluster-merging process, applies r: using v principal components instead of classical Hotelling's $T_v^2$ [1] to find the unknown number of clusters and resolve the singularity problem in high dimensions and demonstrate that there is little difference between the performance of $T^2$ and that of $T_v^2$. Experiments have demonstrated that the proposed approach is effective in improving the performance of an image retrieval system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.722-724
• /
• 2012

문서 군집화를 통하여 문서를 효율적으로 조직, 관리, 검색 할 수 있다. 일반적으로 문서 군집화는 많은 단어와 개념들을 포함하고 있기 때문에 차원이 큰 벡터 공간 모델에서 군집화를 수행한다. 본 논문에서 문서 집합에 대응하는 온톨로지를 이용하여 문서 벡터 공간의 차원을 줄여 효율적으로 군집화하는 방법을 제안하고, 실험을 통하여 기존 방법보다 우수함을 보인다.

• The KIPS Transactions:PartB
• /
• v.16B no.1
• /
• pp.7-16
• /
• 2009

Some clustering algorithms have a problem that an image is over-segmented since both the spatial information between the segmented regions is not considered and the number of the clusters is defined in advance. Therefore, they are difficult to be applied to the applicable fields. This paper proposes the new post-processing methods, a reclassification of the inhomogeneous clusters and a region merging using Baysian algorithm, that improve the segmentation results of the clustering algorithms. The inhomogeneous cluster is firstly selected based on variance and between-class distance and it is then reclassified into the other clusters in the reclassification step. This reclassification is repeated until the optimal number determined by the minimum average within-class distance. And the similar regions are merged using Baysian algorithm based on Kullbeck-Leibler distance between the adjacent regions. So we can effectively solve the over-segmentation problem and the result can be applied to the applicable fields. Finally, we design a classification system for the segmented regions to validate the proposed method. The segmented regions are classified by SVM(Support Vector Machine) using the principal colors and the texture information of the segmented regions. In experiment, the proposed method showed the validity for various real-images and was effectively applied to the designed classification system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.5
• /
• pp.517-524
• /
• 2004

The fuzzy set theory has been wide used in clustering of machine learning with data mining since fuzzy theory has been introduced in 1960s. In particular, fuzzy C-means algorithm is a popular fuzzy clustering algorithm up to date. An element is assigned to any cluster with each membership value using fuzzy C-means algorithm. This algorithm is affected from the location of initial cluster center and the proper cluster size like a general clustering algorithm as K-means algorithm. This setting up for initial clustering is subjective. So, we get improper results according to circumstances. In this paper, we propose a cluster merging using enhanced density based fuzzy C-means clustering algorithm for solving this problem. Our algorithm determines initial cluster size and center using the properties of training data. Proposed algorithm uses grid for deciding initial cluster center and size. For experiments, objective machine learning data are used for performance comparison between our algorithm and others.

• Journal of Cadastre & Land InformatiX
• /
• v.50 no.1
• /
• pp.5-23
• /
• 2020

According to the Korean Statistical Information Service(2019), the number of public land in Korea is 10,734,439parcels and 33,395㎢, accounting for 33.2% of the land area. In the meantime, the central government and local governments have been promoting the efficiency of public land management through annexation, but if the scale of cadastral record is different or the public land is registered in different types of cadastral maps, it is impossible to annexation and it is a major obstacle to the efficiency of public land management. As a way to solve these problems, the annexation method accompanied by survey was presented and the effect was analyzed. As a result, the number of parcels to be managed decreased by 91.7% and 99.6% of the actual survey cost was reduced despite the expenditure of only 54.9% of the existing method. It was found that the annexation survey of the public land, which are clustered by connection, can ultimately contribute to the efficiency of the public land management by newly establishing the indication of the public land. In the future, we hope that follow-up research on the public land management based on cadastral surveys will be conducted in various and in-depth ways.

• Korean Journal of Remote Sensing
• /
• v.19 no.2
• /
• pp.135-147
• /
• 2003

This study used the multistage hierarchical clustering image classification to analyze the satellite images for the land-cover types of an area in the Korean peninsula. The multistage algorithm consists of two stages. The first stage performs region-growing segmentation by employing a hierarchical clustering procedure with the restriction that pixels in a cluster must be spatially contiguous, and finally the whole image space is segmented into sub-regions where adjacent regions have different physical properties. Without spatial constraints for merging, the second stage clusters the segments resulting from the previous stage. The image classification of hierarchical clustering, which merges step-by step two small groups into one large one based on the hierarchical structure of digital imagery, generates a hierarchical tree of the relation between the classified regions. The experimental results show that the hierarchical tree has the detailed information on the hierarchical structure of land-use and more detailed spectral information is required for the correct analysis of land-cover types.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.6 s.312
• /
• pp.20-27
• /
• 2006

Multi-level thresholding is a method that is widely used in image segmentation. However most of the existing methods are not suited to be directly used in applicable fields and moreover expanded until a step of image segmentation. This paper proposes region-based multi-level thresholding as an image segmentation method. At first we classify pixels of each color channel to two clusters by using EWFCM(Entropy-based Weighted Fuzzy C-Means) algorithm that is an improved FCM algorithm with spatial information between pixels. To obtain better segmentation results, a reduction of clusters is then performed by a region-based reclassification step based on a similarity between regions existing in a cluster and the other clusters. The clusters are created using the classification information of pixels according to color channel. We finally perform a region merging by Bayesian algorithm based on Kullback-Leibler distance between a region and the neighboring regions as a post-processing method as many regions still exist in image. Experiments show that region-based multi-level thresholding is superior to cluster-, pixel-based multi-level thresholding, and the existing mettled. And much better segmentation results are obtained by the post-processing method.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.10
• /
• pp.761-765
• /
• 2009

This research aims an optimal placement of Mobile Base Station (MBS) under HAP based network configurations with the restrictions of HAP capabilities. With clustering algorithm based on BIRCH, mobile ground nodes are clustered and the centroid of the clusters will be the location of MBS. The hierarchical structure of BIRCH enables mobile node management by CF tree and the restrictions of maximum nodes per MBS and maximum radio coverage are accomplished by splitting and merging clusters. Mobility models based on Jeju island are used for simulations and such restrictions are met with proper placement of MBS.

• The Journal of Bigdata
• /
• v.8 no.1
• /
• pp.131-156
• /
• 2023

The traditional retail industry significantly changed over the past decade due to the mobile and online technologies. This change has been accompanied by a shift in consumer behavior regarding purchasing patterns. Despite the rise of online shopping, there are still specific categories of products, such as "Processed food" in Mongolia, for which traditional shopping remains the preferred purchase method. To prepare for the inevitable future of retail businesses, firms need to closely analyze the performance of their offline stores to plan their further actions in a new multi-channel environment. Retailers must integrate diverse channels into their operations to stay relevant and adjust to the shifting market. In this research, we have analyzed the performance data such as sales, profit, and amount of sales of offline stores by using clustering approach. From the clustering, we have found the several distinct insights by comparing the circumstances and performance of retail stores. For the certain retail stores, we have proposed three different strategies: a fulfillment hub store between online and offline channels, an experience store to elongate customers' time on the premises, and a merge between two non-related channels that could complement each other to increase traffic based on the store characteristics. With the proposed strategies, it may enhance the user experience and profit at the same time.