• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 하계학술대회 논문집 D
• /
• pp.2233-2235
• /
• 2003

본 논문에서는 mGA를 이용해 축구로봇의 속도를 제어하는 새로운 방법을 제안하였다. 축구 로봇의 목표를 최소 시간내에 도착하기 위해 속도제어에 크게 영향을 미치는 거리 오차와 각도 오차 등의 비율를 나타내는 각종 파라미터가 포함되어 있는 제어 함수를 제시하고, 이들 파라미터들을 mGA을 이용하여 최적의 값들을 탐색함으로써 변화되는 환경 속에서도 로봇의 목적지에 최소 시간내에 이동하도록 속도제어 전략을 제안한다.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• 제25권3호
• /
• pp.128-135
• /
• 2014

Objectives : The purpose of this study was to evaluate the effect of social skills training (SST) for children in two different community settings, an elementary school and a child community center. Methods : Two separate groups of 15 children (10 boys and 5 girls) and 13 children (4 boys and 9 girls) participated in a SST program twice per week at an elementary school and a child community center, respectively. Age range of participants was from 8 to 10 years. Sixty-minute-long sessions of SST were continued twice per week for 4 weeks. Korean-Child Behavior Checklist (K-CBCL), Conner's Rating Scales, Korean-Attention-Deficit Hyperactivity Disorder Rating Scale (K-ARS), Social Skills Rating System (SSRS), and Matson's Evaluation of Social Skills with Youngsters (MESSY) were evaluated by their parents before and after the SST program. Results : Pre-and-post analysis of SST indicated no significant statistical differences in the elementary school group. However, the child community center group showed significantly increased scores for total social ability (p<.05) and decreased scores for attention problem (p<.05) on the K-CBCL. In addition, scores of MESSY were significantly increased (p<.05). These differences between the two groups were still significant after controlling pre-SST scores ; and difference of SST scores between the two groups disappeared after SST. Conclusion : Results suggest that SST in the community setting is an effective tool for prevention of social deficits and problems in attention by promoting social function and attention.

• 대한가정학회지
• /
• 제37권10호
• /
• pp.43-54
• /
• 1999

The purpose of this study is to clarify the transition and terminology of sanitary spaces in Korean houses, based on the analysis of novels. The resets are as follows. The sanitary space huts been developed in all aspects including locations and facility levels. Duikan, Pyunso, Tongsi, Whajangsil, and Yoksil were the terminology of sanitary space that appeared often in the novels. Before 1930, the word most frequently mentioned was Duikan. Whajangsil and Yoksil appeared shortly between 1930-1750. Duikan, Pyunso, and Tongsi were presented again between 1950-1970. Whajangsil and Yoksil were substituted for most other words after 1980. Other than the usual function of sanitary space, these areas also used as hiding spaces and places where one could observe others secretly. The sanitary spaces in most novels were located behind kitchens, nearby fences or stables and were typically unpleasant places with a messy dung tub, no lighting system, and a shed-like construction.

• Journal of information and communication convergence engineering
• /
• 제15권3호
• /
• pp.151-159
• /
• 2017

Steganography, which is popular as an image processing technology, is the art of using digital images to hide a secret message in such a way that its existence can only be discovered by the sender and the intended receiver. This technique has the advantage of concealing secret information in a cover medium without drawing attention to it, unlike cryptography, which tries to convert data into something messy or meaningless. In this paper, we propose two efficient least significant bit (LSB)-based steganography techniques for designing an image-based steganography system on chip using hardware description language (HDL). The proposed techniques manipulate the LSB plane of the cover image to embed text inside it. The output of these algorithms is a stego-image which has the same quality as that of the original image. We also implement the proposed techniques using the Altera field programmable gate array (FPGA) and Quartus II design software.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 B
• /
• pp.507-509
• /
• 1999

In this paper, we propose a new fuzzy model identification method that can yield a successful fuzzy rule base for fundamental approximations. The method in this paper uses a set of input-output data and is based on a hybrid messy genetic algorithm (mGA) with a fine-tuning scheme. The mGA processes variable-length strings, while standard GAs work with a fixed-length coding scheme. For successfully identifying a complex nonlinear system, we first use the mGA, which coarsely optimizes the structure and the parameters of the fuzzy inference system, and then the gradient descent method which tine tunes the identified fuzzy model. In order to demonstrate the superiority and efficiency of the proposed scheme, we finally show its application to a nonlinear approximation.

• 한국지능시스템학회논문지
• /
• 제11권2호
• /
• pp.95-100
• /
• 2001

비선형 시스템의 성공적인 퍼지 모델을 구성하기 위한 최적의 퍼지 추론 시스템의 동정은 중요하고도 어려운 문제이다. 전통적으로 유전 알고리즘은 어느 정도의 전역 최적해를 찾을 수 있기 때문에 퍼지 모델의 구조와 파라미터를 동정하는데 사용되어 왔다. 그러나, 유전 알고리즘은 개체군 진화 시 우수한 개체의 출현은 지역수렴의 원인이 된다. 따라서, 본 논문에서는 바이러스 메시 유전알고리즘을 이용한 효과적인 퍼지 모델링 방법을 제안한다. 제안된 방법은 지역 정보가 개체군 내에서 교환됨으로써 지역 수렴의 대인아 될 수 있을 뿐 아니라, 가변길이 스트링을 사용함으로써 좀더 효과적이고 적응적인 구조를 가질 수 있다. 또한 본 논문에서 제안한 방법의 우수성과 일반성을 증명하기 위해 복잡한 비선형 시스템과 가스로의 퍼지모델링에 적용하였다.

• 스마트미디어저널
• /
• 제1권4호
• /
• pp.27-34
• /
• 2012

In this paper, a novel text binarization is presented that can deal with some complex conditions, such as shadows, non-uniform illumination due to highlight or object projection, and messy backgrounds. To locate the target text region, a focus line is assumed to pass through a text region. Next, connected component analysis and stroke width estimation based on location information of the focus line is used to locate the bounding box of the text region, and each box of connected components. A series of classifications are applied to identify whether each CC(Connected component) is text or non-text. Also, a modified K-means clustering method based on an HCL color space is applied to reduce the color dimension. A text binarization procedure based on location of text component and seed color pixel is then used to generate the final result.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2002년도 추계학술대회 및 정기총회
• /
• pp.187-190
• /
• 2002

주어진 시스템의 정확한 제어를 위해 뉴로-퍼지 제어시스템의 성공적인 제어는 그 네트웍의 구성에 크게 의존한다. 현재 유전알고리즘을 사용한 제어기 구조의 최적화 방법에 대한 많은 연구가 이루어지고 있으나, 기존의 유전 알고리즘은 고정된 길이의 스트링 구조로 인하여 적합한 연계(linkage)를 얻기 어렵다는 단점이 있다 본 논문에서는 뉴로-퍼지 제어기의 구조적 최적화 설계의 새로운 방법을 제안한다. 여기서, 우리는 구조적으로 최적화 된 뉴로-퍼지 제어기를 설계하기 위해 가변길이 스트링을 사용하는 메시 유전 알고리즘(messy Genetic Algorithm mGA)을 사용한다. 그리고 제안된 방법의 우수성을 증명하기 위해 대표적인 비선형 시스템인 cart-pole 시스템에 제안된 방법을 적용한다.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2008년도 춘계 종합학술대회 논문집
• /
• pp.521-524
• /
• 2008

기존 모바일 학습 서비스는 실시간으로 방대한 량의 학습 정보를 데이터 패킷으로 제공받음으로써 사용자는 전송속도와 과다한 데이터 패킷 요금의 문제점을 가진다. 본 논문에서는 실시간 무선 패킷으로 정보를 제공하는 학습 방법에서 하드웨어 형태로 정보제공이 가능한 보조저장장치를 활용한 새로운 형식의 모바일 학습 시스템을 구축하는 방안을 제안한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 하계학술대회 논문집 D
• /
• pp.1952-1954
• /
• 2001

In this paper, we propose the neuro-fuzzy modeling method using VmGA (Virus messy Genetic Algorithm) for the complex nonlinear system. VmGA has more effective and adaptive structure than sGA. in this paper, we suggest a new coding method for applying the model's input and output data to the optimal number of rules in fuzzy models and the structure and parameter identification of membership functions simultaneously. The proposed method realizes the optimal fuzzy inference system using the learning ability of neural network. For fine-tune of parameters identified by VmGA, back- propagation algorithm is used for optimizing the parameter of fuzzy set. The proposed fuzzy modeling method is applied to a nonlinear system to prove the superiority of the proposed approach through comparing with ANFIS.