• 한국통신학회논문지
• /
• 제42권2호
• /
• pp.536-544
• /
• 2017

무선 RSSI fingerprinting 방식은 기존 무선 인프라를 이용하면서 적정수준의 정확도를 얻을 수 있는 실내위치인식 방법 중의 하나이다. 하지만 라디오 맵 구성( fingerprint calibration) 과정에서 목표 환경의 다양한 위치에서 정확한 물리적 좌표와 무선 신호를 측정해야 하므로 시간과 노력이 많이 소요된다. 이 논문은 이러한 방식으로 위치 정보를 수집하지 않고 반지도식 자기조직화지도 학습 알고리즘을 사용하여 labeled RSSI를 얻고 RSSI 조합으로부터 맵을 구성하는 방법을 제안한다. 모의 데이터에 대한 실험을 통해 제안 방법이 fingerprint 데이터베이스로 부터 1%의 RSSI 샘플을 가지고 효과적인 전체 맵을 얻을 수 있다는 결론을 얻었다.

• 한국물환경학회지
• /
• 제24권5호
• /
• pp.611-617
• /
• 2008

It is necessary to analysis the data characteristics of discharge and water quality for efficient water resources management, aggressive alternatives to inundation by flood and various water pollution accidents, the basic information to manage water quality in lakes and to make environmental policy. Therefore, the present study applied Self-Organizing Map (SOM) showing excellent performance in classifying patterns with weights estimated by self-organization. The result revealed five patterns and TOC versus rainfall-storage data according to the respective patterns were depicted in two-dimensional plots. The visualization presented better understanding of data distribution pattern. The result in the present study might be expected to contribute to the modeling procedure for data prediction in the future.

• 대기
• /
• 제21권3호
• /
• pp.221-228
• /
• 2011

The nonlinear characteristics of summer monsoon intraseasonal oscillation (ISO) in precipitation, which is manifested as fluctuations in convection and circulation, is one of the major difficulty on the prediction of East Asian summer monsoon (EASM). The present study aims to identify the spatial distribution and time evolution of nonlinear phases of monsoon ISO. In order to classify the different phases of monsoon ISO, Self-Organizing Map(SOM) known as a nonlinear pattern recognition technique is used. SOM has a great attractiveness detecting self-similarity among data elements by grouping and clustering such self-similar components. The four important patterns are demonstrated as Meiyu-Baiu, Changma, post-Changma, and dry-spell modes. It is found that SOM well captured the formation of East Asian monsoon trough during early summer and its northward migration together with enhanced convection over subtropical western Pacific and regionally intensive precipitation including Meiyu, Changma and Baiu. The classification of fundamental large scale spatial pattern and evolutionary history of nonlinear phases of monsoon ISO provides the source of predictability for extended-range forecast of summer precipitation.

• 한국경영과학회지
• /
• 제23권1호
• /
• pp.143-159
• /
• 1998

This paper proposes a new type of fuzzy approximate reasoning method that combines a self organizing feature map and a fuzzy logic. Previous methods considered only input part to determine the number of fuzzy rules, while this paper considers both input and output parts simultaneously. Our approach proved to improve the inference performance. We also developed a new index for avoiding overlearning which guarantees more accurate results. Experimental results showed that our approach surpasses the performance of Takagi & Hayashi (1991) approach.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1993년도 한국자동제어학술회의논문집(국내학술편); Seoul National University, Seoul; 20-22 Oct. 1993
• /
• pp.408-411
• /
• 1993

In this paper, we propose the Fuzzy Neural Controller with a Self-Organizing Map based on the fuzzy relation neuron. The fuzzy ndes expressing the input-output relation of the system are obtained by using the fuzzy relation neuron and updated automatically by means of the generalized delta rule. Also, the proposed method has a capability to express the knowledge acquired from the input-output data in form of fuzzy inferences rules. The learning algorithm of this fuzzy relation neuron is described. The effectiveness of the proposed fuzzy neural controller is illustrated by applying it to a number of test data sets.

• 전자공학회논문지B
• /
• 제32B권1호
• /
• pp.180-188
• /
• 1995

A modified Kohonen's self-organizing feature map (SOFM) algorithm which has binary reinforcement function and a constant learning rate is proposed. In contrast to the time-varing adaptaion gain of the original Kohonen's SOFM algorithm, the proposed algorithm uses a constant adaptation gain, and adds a binary reinforcement function in order to compensate for the lowered learning ability of SOFM due to the constant learning rate. Since the proposed algorithm does not have the complicated multiplication, it's digital hardware implementation is much easier than that of the original SOFM.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.115.4-115
• /
• 2001

This paper deals with recognizing ten korean voiced vowels using Self Organizing Map. SOM is a good classifier. The output layer is composed of two dimensions. The input vector is the frequency values having the characteristic of voiced vowels. The short time frequency transform is used getting input vector. The final neural networks is attached SOM output layer.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제9권1호
• /
• pp.36-41
• /
• 2009

Self organizing map(SOM) is one of the unsupervised methods based on the competitive learning. Many clustering works have been performed using SOM. It has offered the data visualization according to its result. The visualized result has been used for decision process of descriptive data mining as exploratory data analysis. In this paper we propose improvement of SOM using stratified sampling of statistics. The stratification leads to improve the performance of SOM. To verify improvement of our study, we make comparative experiments using the data sets form UCI machine learning repository and simulation data.

• 방송공학회논문지
• /
• 제26권3호
• /
• pp.283-295
• /
• 2021

본 논문은 자기 조직화 지도 기법을 기반으로 라이다 기반으로 생성된 깊이 맵과 컬러 이미지의 정보를 기반으로 고밀도 깊이 맵을 생성하는 방법을 제안한다. 제안하는 깊이 맵 업샘플링 방법은 라이다에서 취득되지 않은 공간에 대한 초기 깊이 예측 단계와 초기 깊이 필터링 단계로 구성된다. 초기 깊이 예측 단계에서는 두 장의 컬러 이미지에 대해 스테레오 매칭을 수행하여 초기 깊이 값을 예측한다. 깊이 맵 필터링 단계에서는 예측된 초기 깊이 값의 오차를 감소시키고자 예측 깊이 픽셀에 대하여 주변의 실측 깊이 값을 이용하여 자기 조직화 지도 기법을 수행한다. 자기 조직화 기법 수행 시 예측 깊이 픽셀과 실측 깊이 픽셀의 거리와, 각 픽셀에 대응되는 컬러 값의 차이에 따라 가중치를 결정한다. 본 논문에서는 성능 비교를 위하여 깊이 맵 업샘플링 방법으로 널리 사용되고 있는 양방향 필터 및 k-최근접 이웃 알고리즘과 비교를 진행하였다. 제안하는 방법은 양방향 필터 방법 및 k-최근접 이웃 알고리즘 대비 MAE 관점에서 각각 약 6.4%, 8.6%이 감소하였고 RMSE 관점에서 각각 약 10.8%, 14.3%이 감소하였다.

• 산업경영시스템학회지
• /
• 제42권2호
• /
• pp.94-103
• /
• 2019

Self Organizing Map (SOM) is a neural network that is effective in classifying patterns that form the feature map by extracting characteristics of the input data. In this study, we propose an algorithm to determine the cell formation and the machine layout within the cell for the cell formation problem with operation sequence using the SOM. In the proposed algorithm, the output layer of the SOM is a one-dimensional structure, and the SOM is applied to the parts and the machine in two steps. The initial cell is formed when the formed clusters is grouped largely by the utilization of the machine within the cell. At this stage, machine cell are formed. The next step is to create a flow matrix of the all machine that calculates the frequency of consecutive forward movement for the machine. The machine layout order in each machine cell is determined based on this flow matrix so that the machine operation sequence is most reflected. The final step is to optimize the overall machine and parts to increase machine layout efficiency. As a result, the final cell is formed and the machine layout within the cell is determined. The proposed algorithm was tested on well-known cell formation problems with operation sequence shown in previous papers. The proposed algorithm has better performance than the other algorithms.