• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.426-431
• /
• 1998

We propose a fuzzy rule based method for structure preserving dimensionality reduction. This method selects a small representative sample and applies Sammon's method to project it. The input data points are then augmented by the corresponding projected(output) data points. The augmented data set thus obtained is clustered with the fuzzy c-means(FCM) clustering algorithm. Each cluster is then translated into a fuzzy rule for projection. Our rule based system is computationally very efficient compared to Sammon's method and is quite effective to project new points, i.e., it has good predictability.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.99-100
• /
• 2006

One of the fundamental problems in sensor networks is the deployment of sensor nodes. The Fuzzy C-Means(FCM) clustering algorithm is proposed to determine the optimum location and minimum number of sensor nodes for the specific application space. We performed a simulation using two dimensional L shape model. The actual length of the L shape model is about 100m each. We found the minimum number of 15 nodes are sufficient for the complete coverage of modeled area. We also found the optimum location of each nodes. The real deploy experiment using 15 sensor nodes shows the 95.7%. error free communication rate.

• Annual Conference of KIPS
• /
• 2011.04a
• /
• pp.1294-1297
• /
• 2011

최근, Flickr, YouTube 와 같은 사용자 참여형 미디어 공유 및 검색 사이트가 폭발적으로 증가하면서, 이를 멀티미디어 정보 검색 서비스에 효과적으로 활용하기 위한 다양한 연구들이 시도되고 있다. 특히, 이미지에 할당되어 있는 태그를 이용하여 이미지를 효과적으로 검색하기 위한 연구가 활발히 진행 중이다. 그러나 사용자들에 의해 제공되는 소셜 이미지들은 매우 다양한 범위와 주제를 가지고 있기 때문에, 소셜 이미지들의 분류 및 태그 할당을 위한 트레이닝 집합의 획득이 쉽지 않다는 한계점을 가지고 있다. 본 논문에서는 데이터 군집화를 위한 클러스터링 알고리즘들 중 K-Means, K-Medoids, Affinity Propagation 을 활용하여 소셜 이미지 집합으로부터 트레이닝 집합을 획득하기 위한 방법들을 살펴 본다. 또한, 각 알고리즘으로부터 획득한 트레이닝 집합을 이용하여 소셜 이미지를 분류한 결과를 비교 분석한다.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.52 no.2
• /
• pp.39-50
• /
• 2024

Color is an essential visual element that has a significant impact on the formation of a city's image and people's perceptions. Quantitative analysis of color in urban environments is a complex process that has been difficult to implement in the past. However, with recent rapid advances in Machine Learning, it has become possible to analyze city colors using photos shared by tourists. This study selected Dali City, a popular tourist destination in China, as a case study. Photos of Dali City shared by tourists were collected, and a method to measure large-scale city colors was explored by combining machine learning techniques. Specifically, the DeepLabv3+ model was first applied to perform a semantic segmentation of tourist sharing photos based on the ADE20k dataset, thereby separating artificial elements in the photos. Next, the K-means clustering algorithm was used to extract colors from the artificial elements in Dali City, and an adjacency matrix was constructed to analyze the correlations between the dominant colors. The research results indicate that the main color of the artificial elements in Dali City has the highest percentage of orange-grey. Furthermore, gray tones are often used in combination with other colors. The results indicated that local ethnic and Buddhist cultures influence the color characteristics of artificial elements in Dali City. This research provides a new method of color analysis, and the results not only help Dali City to shape an urban color image that meets the expectations of tourists but also provide reference materials for future urban color planning in Dali City.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1534-1538
• /
• 2005

In this paper, we propose a method to detect contours of a face, eyes, and a mouth of a person in the color image in order to make an avatar automatically. First, we use the HSI color model to exclude the effect of various light conditions, and find skin regions in the input image by using the skin color defined on HS-plane. And then, we use deformable templates and genetic algorithm (GA) to detect contours of a face, eyes, and a mouth. Deformable templates consist of B-spline curves and control point vectors. Those represent various shapes of a face, eyes and a mouth. GA is a very useful search algorithm based on the principals of natural selection and genetics. Second, the avatar is automatically created by using GA-detected contours and Fuzzy C-Means clustering (FCM). FCM is used to reduce the number of face colors. In result, we could create avatars which look like handmade caricatures representing user's identity. Our approach differs from those generated by existing methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.3
• /
• pp.17-30
• /
• 2000

In this paper, we propose an efficient algorithm to produce 3-D surface model from a set of range data, based on NURBS (Non-Uniform Rational B-Splines) surface fitting technique. It is assumed that the range data is initially unorganized and scattered 3-D points, while their connectivity is also unknown. The proposed algorithm consists of three steps: initial model approximation, hierarchical representation, and construction of the NURBS patch network. The mitral model is approximated by polyhedral and triangular model using K-means clustering technique Then, the initial model is represented by hierarchically decomposed tree structure. Based on this, $G^1$ continuous NURBS patch network is constructed efficiently. The computational complexity as well as the modeling error is much reduced by means of hierarchical decomposition and precise approximation of the NURBS control mesh Experimental results show that the initial model as well as the NURBS patch network are constructed automatically, while the modeling error is observed to be negligible.

• Proceedings of the Korea Database Society Conference
• /
• 1999.06a
• /
• pp.253-260
• /
• 1999

The recycling cell formation problem means that disposal products me classified into recycling part families using group technology in their end of life phase. Disposal products have the uncertainties of product status by usage influences during product use phase and recycling cells are formed design, process and usage attributes. In order to treat the uncertainties, fuzzy set theory and fuzzy logic-based neural network model are applied to recycling cell formation problem far disposal products. In this paper, a heuristic approach fuzzy ART neural network is suggested. The modified fuzzy ART neural network is shown that it has a great efficiency and give an extension for systematically generating alternative solutions in the recycling cell formation problem. We present the results of this approach applied to disposal refrigerators and the comparison of performances between other algorithms. This paper introduced a procedure which integrates economic and environmental factors into the disassembly of disposal products for recycling in recycling cells. A qualitative method of disassembly analysis is developed and its ai is to improve the efficiency of the disassembly and to generated an optimal disassembly which maximize profits and minimize environmental impact. Three criteria established to reduce the search space and facilitate recycling opportunities.

• Journal of the Korea Convergence Society
• /
• v.11 no.4
• /
• pp.11-16
• /
• 2020

As a plan for oil spill accidents, research to collect and analyze optimal equipment assignments is essential. However, studies that have diversified and analyzed the optimal equipment assignments for responding to oil spill accidents have not been preceded. In response to the need for analyzing optimal equipment assignments study, we devised a genetic algorithm for optimal equipment assignments. The designed genetic algorithm yielded 10,000 optimal equipment assignments. We clustered using the k-means algorithm. As a result, the two clusters of Yeosu, Daesan, and Ulsan, which are expected to be the largest spills, were clearly identified. We also projected 16-dimensional data in two dimensions via Sammon's mapping. The projected data were analyzed for distribution. We confirmed that results of the simulation were better than those of optimal equipment assignments included in the cluster.In the future, it will be possible to implement an approximate model with excellent performance based on this study.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.431-434
• /
• 2001

Knowledge discovery in databases(KDD) is the process for extracting valid, novel, potentially useful and understandable knowledge form real data. There are many academic and industrial activities with new technologies and application areas. Particularly, data mining is the core step in the KDD process, consisting of many algorithms to perform clustering, pattern recognition and rule induction functions. The main goal of these algorithms is prediction and description. Prediction means the assessment of unknown variables. Description is concerned with providing understandable results in a compatible format to human users. We introduce an efficient data mining algorithm considering predictive and descriptive capability. Reasonable pattern is derived from real world data by a revised neural network model and a proposed fuzzy rule extraction technique is applied to obtain understandable knowledge. The proposed neural network model is a hierarchical self-organizing system. The rule base is compatible to decision makers perception because the generated fuzzy rule set reflects the human information process. Results from real world application are analyzed to evaluate the system\`s performance.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.6
• /
• pp.1159-1166
• /
• 2010

To improve prediction quality of a nonlinear prediction system, the system's capability for uncertainty of nonlinear data should be satisfactory. This paper presents a TSK fuzzy prediction system that can consider and deal with the uncertainty of nonlinear data sufficiently. In the design procedures of the proposed system, HCBKA(Hierarchical Correlationship-Based K-means clustering Algorithm) was used to generate the accurate fuzzy rule base that can control output according to input efficiently, and the first-order difference method was applied to reflect various characteristics of the nonlinear data. Also, multiple prediction systems were designed to analyze the prediction tendencies of each difference data generated by the difference method. In addition, to enhance the prediction quality of the proposed system, an error compensation method was proposed and it compensated the prediction error of the systems suitably. Finally, the prediction performance of the proposed system was verified by simulating two typical time series examples.