• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.12-14
• /
• 2005

In this paper, we propose a new architecture of Self-Organizing Fuzzy Polynomial Neural Networks(SOFPNN) by means of genetically optimized fuzzy polynomial neuron(FPN) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially genetic algorithms(GAs). The conventional SOFPNNs hinges on an extended Group Method of Data Handling(GMDH) and exploits a fixed fuzzy inference type in each FPN of the SOFPNN as well as considers a fixed number of input nodes located in each layer. The design procedure applied in the construction of each layer of a SOFPNN deals with its structural optimization involving the selection of preferred nodes (or FPNs) with specific local characteristics (such as the number of input variables, the order of the polynomial of the consequent part of fuzzy rules, a collection of the specific subset of input variables, and the number of membership function) and addresses specific aspects of parametric optimization. Therefore, the proposed SOFPNN gives rise to a structurally optimized structure and comes with a substantial level of flexibility in comparison to the one we encounter in conventional SOFPNNs. To evaluate the performance of the genetically optimized SOFPNN, the model is experimented with using two time series data(gas furnace and chaotic time series).

• 제어로봇시스템학회논문지
• /
• 제15권4호
• /
• pp.451-455
• /
• 2009

This paper provides a comparison of global path planning method in single string by using pulled and pushed SOFM (Self-Organizing Feature Map) which is a method among a number of neural network. The self-organizing feature map uses a randomized small valued initial-weight-vectors, selects the neuron whose weight vector best matches input as the winning neuron, and trains the weight vectors such that neurons within the activity bubble are move toward the input vector. On the other hand, the modified SOFM method in this research uses a predetermined initial weight vectors of the one dimensional string, gives the systematic input vector whose position best matches obstacles, and trains the weight vectors such that neurons within the activity bubble are move toward or reverse the input vector, by rising a pulled- or a pushed-SOFM. According to simulation results one can conclude that the modified neural networks in single string are useful tool for the global path planning problem of a mobile robot. In comparison of the number of iteration for converging to the solution the pushed-SOFM is more useful than the pulled-SOFM in global path planning for mobile robot.

• 컴퓨터교육학회논문지
• /
• 제9권5호
• /
• pp.77-84
• /
• 2006

본 논문에서는 HVS(Human Visual System)와 신경회로망 중 SOM(Self-Organizing Map)을 이용하여 DWT 영역에서 영상에 적응적인 워터마킹 알고리즘을 제안한다. HVS는 brightness sensitivity와 texture sensitivity의 두가지 특성으로 설명될 수 있다. SOM은 영상의 지역적인 특징들을 얻는데 사용된다. 따라서 HVS와 SOM을 이용하여 삽입되는 워터마크의 최적의 강도와 길이를 결정한다. 실험을 통해 제안한 방법이 최적의 워터마크 강도와 길이를 제공하며 비가시성 테스트에서 우수함과 다양한 공격에 강인함을 알 수 있다.

• 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.

• 환경생물
• /
• 제26권3호
• /
• pp.203-213
• /
• 2008

Benthic macro invertebrate communities were collected at six different sampling sites in the Musucheon stream in Korea from July 2006 to July 2007, and ecological exergy values were calculated based on five different functional feeding groups (collector-gatherer, collector-filterer, predator, scrapper, and shredder) of benthic macro invertebrates. Each sampling site was categorized to three stream types (perennial, intermittent and drought) based on the water flow condition. Exergy values were low at all study sites right after a heavy rain and relatively higher in the perennial stream type than in the intermittent or the drought stream type. Self-Organizing Map (SOM), unsupervised artificial neural network, was implemented to pattern spatial and temporal dynamics of ecological exergy of the study sites. SOM classified samples into four clusters. The classification reflected the effects of floods and droughts on benthic macroinvertebrate communities, and was mainly related with the stream types of the sampling sites. Exergy values of each functional feeding group also responded differently according to the different stream types. Finally, the results showed that exergy is an effective ecological indicator, and patterning changes of exergy using SOM is an effective way to evaluate target ecosystems.

• 대한산업공학회지
• /
• 제31권3호
• /
• pp.257-264
• /
• 2005

This paper suggests a heuristic algorithm for the clustering problem. Clustering involves grouping similar objects into a cluster. Clustering is used in a wide variety of fields including data mining, marketing, and biology. Until now there are a lot of approaches using Self-Organizing Feature Maps(SOFMs). But they have problems with a small output-layer nodes and initial weight. For example, one of them is a one-dimension map of k output-layer nodes, if they want to make k clusters. This approach has problems to classify elaboratively. This paper suggests one-dimensional output-layer nodes in SOFMs. The number of output-layer nodes is more than those of clusters intended to find and the order of output-layer nodes is ascending in the sum of the output-layer node's weight. We can find input data in SOFMs output node and classify input data in output nodes using Euclidean distance. We use the well known IRIS data as an experimental data. Unsupervised clustering of IRIS data typically results in 15 - 17 clustering error. However, the proposed algorithm has only six clustering errors.

• Investigative Magnetic Resonance Imaging
• /
• 제21권1호
• /
• pp.43-50
• /
• 2017

Chronic expanding organizing hematoma (CEH) occasionally mimics a soft tissue tumor on MRI, which becomes more problematic in patients with a history of surgical resection for musculoskeletal malignancy. Herein, we present a case of CEH which we were able to differentiate from recurrent tumor through MRI follow-up, including diffusion-weighted imaging (DWI) and dynamic contrast enhanced (DCE) imaging. A 66-year-old male visited our institution under suspicion of recurrent leiomyosarcoma of the thigh, 19 months after surgery and radiation therapy. Due to inconclusive results, three US-guided biopsies and 6 MRI examinations were performed over 2 years. In the end, we could diagnose a CEH using conventional and functional MRI techniques, and it was histopathologically confirmed after surgical resection. A CEH may occur remotely after an initiating event, and it may persist and expand over several years. Functional MR sequences, in addition to conventional sequences, are helpful in differentiating CEH from malignant neoplasms.

• 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.

• Biotechnology and Bioprocess Engineering:BBE
• /
• 제11권5호
• /
• pp.432-441
• /
• 2006

2D fluorescence sensors produce a great deal of spectral data during fermentation processes, which can be analyzed using a variety of statistical techniques. Principal component analysis (PCA) and a self-organizing map (SOM) were used to analyze these 2D fluorescence spectra and to extract useful information from them. PCA resulted in scores and loadings that were visualized in the score-loading plots and used to monitor various fermentation processes with recombinant Escherichia coli and Saccharomyces cerevisiae. The SOM was found to be a useful and interpretative method of classifying the entire gamut of 2D fluorescence spectra and of selecting some significant combinations of excitation and emission wavelengths. The results, including the normalized weights and variances, indicated that the SOM network is capable of being used to interpret the fermentation processes monitored by a 2D fluorescence sensor.

• 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.