• Journal of Biomedical Engineering Research
• /
• v.18 no.4
• /
• pp.339-348
• /
• 1997

In this paper, we propose a coding method to improve compression efficiency for MR image. This can be achieved by combining coding scheme and segmentation scheme which removes noisy background region, which is meaningless for diagnosis in the MR image. In segmentation algoritm, we use full-resolution wavelet transform to extract features of regions in image and Kohonen self-organizing map to classify the features. The subsequent wavelet coder encodes only diagnostically significant foreground regions refering to segmentation map. Our proposed algorithm provides about 15% of bit rate reduction when compared with the same coder which is not combined with segmentation scheme. And the proposed scheme shows better reconstructed image quality than JPEG at the same compression ratio.

• Tuberculosis and Respiratory Diseases
• /
• v.78 no.4
• /
• pp.469-472
• /
• 2015

Cryptogenic organizing pneumonia (COP) is an inflammatory lung disease involving the distal bronchioles, respiratory bronchioles, bronchiolar ducts, and alveolae. The etiology is usually unknown; however, there are several known causes and associated systemic diseases. Corticosteroid therapy is the best treatment option and the prognosis of COP is good, with recovery in up to 80% of patients. We described a patient with in-operable hepatocellular carcinoma (HCC) undergoing chemoembolization with doxorubicin in a drug-eluting bead (DEB). COP developed in the patient after chemoembolization but resolved spontaneously in several months.

• Tuberculosis and Respiratory Diseases
• /
• v.78 no.4
• /
• pp.401-407
• /
• 2015

Cryptogenic organizing pneumonia (COP) is an idiopathic interstitial pneumonia characterized by a subacute course and favorable prognosis with corticosteroids. However, some patients show resistance to steroids. Macrolides have been used with success in those patients showing resistance to steroids. A few reports showed treatment failure with macrolides in patients with COP who were resistant to steroids. In this report, we described two cases of COP who showed different responses to clarithromycin. One recovered completely, but the other gradually showed lung fibrosis with clarithromycin.

• Korean Institute of Interior Design Journal
• /
• v.23 no.1
• /
• pp.114-121
• /
• 2014

Rikyu-Konomi and Enshu-Konomi accomplished the base of Japanese Dado as well as has set Japanese representative traditional culture. These are the products of the spiritual culture completed by the ideas of Sen Rikyu and Kobori Enshu, that are Wabi spirit and Kirei sabi spirit combined with the tea. This study is about the interpretation of Japanese traditional space designs related to Rikyu-Konomi and Enshu-Konomi as Japanese Traditional spiritual archetype. The process of this study is illustrated as follows: At first, it mentions the concept of Konomi as self-organizing system, and esthetic characteristics of Rikyu-Konomi and Enshu-Konomi. Secondly, it clarifies internal meanings and spacial characters of Konomi in the Japanese traditional space through the exploring Taian tea house as the example of Rikyu-Konomi, and Bosen tearoom and Katsurarikyu as the examples of Enshu-Konomi. Thirdly, it ascertains Rikyu-Konomi and Enshu-Konomi represented in the contemporary architectural spaces. It analyses the relation between modern traditional space designs and traditional archetypal vocabularies, and examines those spaces from an esthetic point of view for modern implication of Rikyu-Konomi and Enshu-Konomi. In conclusion, it clarifies the contemporary significance of Rikyu-Konomi and Enshu-Konomi in terms of japan traditional space design.

• Journal of Korean Institute of Industrial Engineers
• /
• v.28 no.4
• /
• pp.360-367
• /
• 2002

The machine-part group formation is to group the sets of parts having similar processing requirements into part families, and the sets of machines needed to process a particular part family into machine cells. The purpose of this study is to develop a two-phase machine-part group formation algorithm based on Self-Organizing Maps (SOM). In phase I, it forms machine cells from the machine-part incidence matrix by means of SOM whose output layer is one-dimension and the number of output nodes is the twice as many as the number of input nodes in order to spread out the input vectors. In phase II, it generates part families which are assigned to machine cells by means of machine ratio related with processing part and it gives machine-part group formation. The proposed algorithm performs remarkably well in comparison with many well-known algorithms for the machine-part group formation problems.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.7
• /
• pp.603-611
• /
• 2013

In this paper, we propose a new frame structure and the underlying dynamic resource control mechanism to support an integrated service, including a real-time (RT) service that requires to serve the end-to-end delay performance, as well as non-real-time (NRT) service, using Self-Organizing Time Division Multiple Access (SO-TDMA)-based MAC protocol in a multi-hop ad-hoc maritime communication network. The underlying frame structure is dynamically configured by resource allocation to guarantee the average target outage performance of the real-time service. Toward this end, we analyze the average outage probability and its performance is verified for the proposed frame structure by simulation.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.1144-1148
• /
• 2010

오염원이 집중되는 도시지역에서의 비점오염원에 대한 관리대책은 점오염원에 비하여 미비한 실정이다. 따라서 도시 지역의 비점오염원 부하량의 합리적인 조사, 비점오염물질 저감을 위한 관리기술 개발과 아울러 정책의 개발 등이 필요하며, 도시지역에서의 장기적인 비점오염물질 유출에 관한 모니터링을 통한 비점오염물질 원단위 조사가 절실히 요구되고 있는 실정이다. 따라서 본 연구에서는 상업 및 위락시설지역의 비점오염원 유출특성을 분석하기 위해 2008년 4월부터 2009년 10월까지 실측에 의해 측정된 강우량과 유출량 자료를 이용하여 비점오염원 유출특성을 분석하였다. 또한 본 연구에서는 자기 조직화 특성지도(Self-Organizing Feature Map: SOFM) 이론을 적용하여 측정된 유출 및 수질자료에 대해 패턴분류를 수행하여 분할구역별 자료의 특성분석을 통해 초기강우 특성이 구분되어짐을 확인 할 수 있었다. 그러나 현재 축적된 자료에 대한 양적인 한계로 인해 명확한 구분이 이루어지지 않는 항목도 있었으나, 향후 지속적인 모니터링을 통해 충분한 자료가 축적될 경우 초기강우 기준을 위한 새로운 접근방법으로 제시될 수 있을 것으로 기대된다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.4B
• /
• pp.399-404
• /
• 2011

For the underwater wireless sensor networks, we propose the packet transmission method which distinguishes more important packet than others. Because the ocean underwater transmission environments are extremely unstable, we use SON(Self Organizing Network) techniques to adapt to the constantly varying underwater acoustic communication channels and randomly deployed sensor nodes. Especially we suppose two kinds of packets which have different priorities, and through the simulations we show that high priority packets arrive at the source node faster than lower priority packets with a proposed scheme.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.8
• /
• pp.551-560
• /
• 2004

In this paper, we propose a new architecture of Self-Organizing Fuzzy Polynomial Neural Networks (SOFPNN) that is based on a genetically optimized multilayer perceptron with fuzzy polynomial neurons (FPNs) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially genetic algorithms (GAs). 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. 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, and a collection of the specific subset of input variables) and addresses specific aspects of parametric optimization. Through the consecutive process of such structural and parametric optimization, an optimized and flexible fuzzy neural network is generated in a dynamic fashion. 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), A comparative analysis reveals that the proposed SOFPNN exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literatures.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.08a
• /
• pp.142-145
• /
• 2008

This paper proposes a computationally efficient algorithm for color image segmentation using self-organizing map(SOM) and grassfire algorithm. We reduce a computation time by decreasing the number of input neuron and input data which is used for learning at SOM. First converting input image to CIE $L^*u^*v^*$ color space and run the learning stage with the SOM-input neuron size is three and output neuron structure is 4by4 or 5by5. After learning, compute output value correspondent with input pixel and merge adjacent pixels which have same output value into segment using grassfire algorithm. The experimental results with various images show that proposed method lead to a good segmentation results than others.