• The KIPS Transactions:PartB
• /
• v.13B no.7 s.110
• /
• pp.643-652
• /
• 2006

Decision trees are mainly used for the classification and prediction in data mining. The distribution of spatial data and relationships with their neighborhoods are very important when conducting classification for spatial data mining in the real world. Spatial decision trees in previous works have been designed for reflecting spatial data characteristic by rating Euclidean distance. But it only explains the distance of objects in spatial dimension so that it is hard to represent the distribution of spatial data and their relationships. This paper proposes a decision tree based on spatial entropy that represents the distribution of spatial data with the dispersion and dissimilarity. The dispersion presents the distribution of spatial objects within the belonged class. And dissimilarity indicates the distribution and its relationship with other classes. The rate of dispersion by dissimilarity presents that how related spatial distribution and classified data with non-spatial attributes we. Our experiment evaluates accuracy and building time of a decision tree as compared to previous methods. We achieve an improvement in performance by about 18%, 11%, respectively.

• Trans-
• /
• v.3
• /
• pp.1-28
• /
• 2017

As the field of film aesthetics expands, the concept of classical the mise-en-scene expands too its scope. This paper examines the concept of mise-en-scene through spatial connections. The primary goals of this study are understanding the relation between the frame and the shot, the continuity between the scene and the sequence, and the aesthetic dimension to the plan-sequence. In modern cinema theory, the elements of mise-en-scene are more emphasized in terms of efficiency, but this study is concerned that the classical aesthetic system is still important. To this end, we examine the concept of plan-sequence, which was called the best technique of past visual realism aesthetics, is utilized in digital cinema. Finding significance for the modern use of plan-sequences is a secondary goal of this paper and we expect it to be a stepping stone to search for the aesthetics of digital cinema. The plan-sequence is one of the important factors that can be evaluated in the preparation and application of the event for the movie director. In the real world where the film itself is used commercially, digital film will have a conceptual tool that can utilize allegorics of 'geopolitical unconsciousness' through plan-sequences.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.749-754
• /
• 2011

In this study, we propose the design of optimized pRBFNNs-based face recognition system using two-dimensional Image and ASM algorithm. usually the existing 2 dimensional face recognition methods have the effects of the scale change of the image, position variation or the backgrounds of an image. In this paper, the face region information obtained from the detected face region is used for the compensation of these defects. In this paper, we use a CCD camera to obtain a picture frame directly. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. AdaBoost algorithm is used for the detection of face image between face and non-face image area. We can butt up personal profile by extracting the both face contour and shape using ASM(Active Shape Model) and then reduce dimension of image data using PCA. The proposed pRBFNNs consists of three functional modules such as the condition part, the conclusion part, and the inference part. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of RBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of Differential Evolution. The proposed pRBFNNs are applied to real-time face image database and then demonstrated from viewpoint of the output performance and recognition rate.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.25 no.6
• /
• pp.664-670
• /
• 2014

Generally, the properties of metamaterials are analyzed based on the infinite array of the unit cells. In real application of the metamaterial, however, the array has to be finite. Hence, it is important that a method can analyze the effect of the finite array of the metamaterial. In this paper, a model is proposed which can calculate the scattering by a large-size finite array of an I-shaped metamaterial without a full-wave simulation. The proposed model is based on the surface current estimation of each unit cells. The ratio of the current distribution on a finite array of the metamaterial to that of the infinite array of the same metamaterial for a TM polarized incident wave is approximated as a quartic polynomial. The coefficients of the polynomial are a function of the physical dimension of the metallic patch. Hence, the current distribution of the finite metamaterial can be estimated based on the proposed polynomial and the current of the infinite array. The scattered field is calculated by using the surface current model. The proposed model is numerically and experimentally verified by comparing calculated and measured RCS(Radar Cross Section) data.

• Archives of design research
• /
• v.12 no.4
• /
• pp.294-303
• /
• 1999

With the breakthrough development of computing environment, the design phases have been changed a lot nowadays. In the case of prior phases of transportation design such as cars and forklift-trucks design, designers have depended on surveys and 2D line drawings for fixing a product layout and extracting ergonomic data. In this method, designers don't meet only the problem of reliability of measuring data but also, the problems of unknown situation of operators' fatigue and comfort in work situation. In these methods, it has much less creditability to have a 2D human model to check the real world motion due to the limitation of the 3 Dimension. Even though with a 2D human model, perfect layout is determined, it is still difficult to measure about comfort and fatigue for a user because it measuring an analysing method is static. The development of computer hardware and software have not only changed the flow in the social-wide range but also immerged design into Virtual Environment. In conventional design method, visualization and data transferring have been the main issues but, in virtual environment, determining of design layout and analysing ergonomic data with sophisticated feeling about comfort and fatigue are possible by using 3D virtual human. In this study, the general characteristics of virtual environment was discussed and the possibility of digital process of design was treated. For these studies, layout design for forklift-trucks was tested. Eventually, the merits of each design phase applied virtual environment are discussed.