• Journal of Korea Multimedia Society
• /
• v.3 no.2
• /
• pp.201-208
• /
• 2000

In this paper We describe an algorithm which is devised for 4he partition o# the input space and the generation of fuzzy rules by the fuzzy entropy and tested with the time series prediction problem using Mackey-Glass chaotic time series. This method divides the input space into several fuzzy regions and assigns a degree of each of the generated rules for the partitioned subspaces from the given data using the Shannon function and fuzzy entropy function generating the optimal knowledge base without the irrelevant rules. In this scheme the basic idea of the fuzzy neural network is to realize the fuzzy rules base and the process of reasoning by neural network and to make the corresponding parameters of the fuzzy control rules be adapted by the steepest descent algorithm. The Proposed algorithm has been naturally derived by means of the synergistic combination of the approximative approach and the descriptive approach. Each output of the rule's consequences has expressed with its connection weights in order to minimize the system parameters and reduce its complexities.

• Proceedings of the Korean Institute of Industrial Safety Conference
• /
• 1997.11a
• /
• pp.69-75
• /
• 1997

우리나라는 그동안 가스산업에서 고속성장을 이룩해 왔으나, 근래에는 중대가스산업사고가 빈번하게 일어나고 있다. 그건 이유로 1996년도에는 중대산업사고 예방제도가 전면적으로 실시되고 공정안전보고서를 작성하여 제출하도록 함으로서 위험성 평가의 중요성이 점차 높아가고 있으며, 위험성 평가 기법들에 대하여 여러 연구 단체에서 연구ㆍ시도되고 있다. 또한 이러한 연구ㆍ보고된 위험성 평가 기법들을 프로그램화하고 적용하려는 시도가 많이 있어 왔다. 본 연구에서는 기존에 연구ㆍ개발된 위험성 평가 기법들에 최근 컴퓨터 산업의 발달에 힘입어 각광을 받고 있는 지리정보시스템을 적용하고자 한다. 이러한 가스산업시설의 위험성 평가 시스템은 위험성을 평가하기 위해서 필요한 여러 가지 정보들을 지리정보시스템이 속성 데이터로서 저장하고 있으나, 가스산업시설에 관련된 주변의 도면들을 공간 데이터로서 저장하고 있다. 그리고 위험성 평가 시스템의 세부적인 기능을 모듈화하였다. 우선 위에 언급한 속성 데이터와 공간 데이터를 관리하는 모듈과 이러한 데이터를 가지고 사고영향 범위를 산출해내기 위한 모듈, 그리고 산출된 사고 영향 범위를 도면에 나타내는 모듈로 나뉘어져 있다. 이렇게 지리정보시스템에 구축되어 있는 도면에 위험성을 평가한 결과치를 나타냄으로서 위험성 평가 숙련자가 아니더라도 위험성 평가를 할 수 있고 결과를 분석하도록 도와 줄 수 있도록 할 수 있다. 또한 향후 재난관리시스템에서는 도면상의 도로에 교통량 가중치와 인근 소방서와 경찰서등의 위치를 관리하도록 지리정보시스템을 적용할 수 있으면, 가스시설물 관리시스템에서는 최근 대형가스사고의 대부분이 타공사에 의한 것임을 고려하여 가스배관망을 포함하여 기타 다른 지하배관망을 관리하도록 지리정보시스템을 적용할 수 있다. (중략)램프에서 좋은 광학적 특성을 얻기 위해 가장 중요한 것은 수축이 없이 방전을 확산시키는 것이다. 이를 위해서 램프구조와 구동법을 최적화하는 것이 필요하다. 또한 기체압력을 높임으로서 Xe의 여기복사를 얻을 수 있었다. 동시에 새로운 적용영역의 가능성을 탐구하는데 있다 하겠다.[C/N]의 값을 나타내었다.다.다.화 기술, 구동방법등에 대한 기술개요와 국내외 기술동향에 대하여 소개하고자 한다.었다.다._{2}$가 0.25[wt%] 첨가된 시편의 20[.deg.C]에서의 유전상수는 16,700으로 최대값을 유전손실을 1.28[%]로 최소값을 나타내었다. 또한 모든 시편은 온도 및 주파수에 따라 유전상수가 완만하게 변화하는 유전이완 특성을 나타내었다.다.수적인 물의 양에 따른 DIAION WA30의 라세미화 효율에 관하여 실험한 결과, 물의 양이 증가할수록 그 효율은 감소하였다. DIAION WA30을 라세미화 촉매로 사용하여 아이소옥탄 내에서 라세믹 나프록센 2,2,2-트리플로로에틸 씨오에스터의 효소적 DKR 반응을 수행해 보았다. 그 결과 DIAION WA30을 사용하지 않은 경우에 비해 반응 전환율과 생성물의 광학 순도는 급격히 향상되었다. 전통적 광학분할 반응의 최대 50%라는 전환율의 제한이 본 연구에서 찾은 DIAION WA30을 첨가함으로써 성공적으로 극복되었다. 또한 고체 염기촉매인 DIAION WA30의 사용은 라세미화 촉매의 회수 및 재사용이 가능하게 해준다.해준다.다. TN5 세포주를 0.2 L 규모 (1 L spinner flask)oJl에서 세포간의 응집현상 없이 부유배양에 적응,배양시킨 후 세포성장 시기에 따른 발현을 조사한 결과 1 MOI의 감염조건 하에서는 $0.6\times10^6$cell/m

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.5
• /
• pp.430-437
• /
• 2002

Having a variety of good characteristics against other pattern recognition techniques, the multilayer perceptron (MLP) has been widely used in speech recognition and speaker recognition. But, it is known that the error backpropagation (EBP) algorithm that MLP uses in learning has the defect that requires restricts long learning time, and it restricts severely the applications like speaker recognition and speaker adaptation requiring real time processing. Because the learning data for pattern recognition contain high redundancy, in order to increase the learning speed it is very effective to use the online-based learning methods, which update the weight vector of the MLP by the pattern. A typical online EBP algorithm applies the fixed learning rate for each update of the weight vector. Though a large amount of speedup with the online EBP can be obtained by choosing the appropriate fixed rate, firing the rate leads to the problem that the algorithm cannot respond effectively to different learning phases as the phases change and the number of patterns contributing to learning decreases. To solve this problem, this paper proposes a Changing rate and Omitting patterns in Instant Learning (COIL) method to apply the variable rate and the only patterns necessary to the learning phase when the phases come to change. In this paper, experimentations are conducted for speaker verification and speech recognition, and results are presented to verify the performance of the COIL.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.49 no.4
• /
• pp.45-54
• /
• 2012

Location-based services with GPS positioning technology as a key technology, but recognizing the current location through satellite communication is not possible in an indoor location-aware technology, low-power short-range communication is primarily made of the study. Especially, as Chirp Spread Spectrum(CSS) based location-aware approach for low-power physical layer IEEE802.15.4a is selected as a standard, Ranging distance estimation techniques and data transfer speed enhancements have been more developed. It is known that the distance measured by CSS ranging has quite a lot of noise as well as its bias. However, the noise problem can be adjusted by modeling the non-zero mean noise value by a scaling factor which corresponds to the change of magnitude of a measured distance vector. In this paper, we propose a localization system using the CSS signal to measure distance for a mobile node taken a measurement of the exact coordinates. By applying the extended kalman filter and least mean squares method, the localization system is faster, more stable. Finally, we evaluate the reliability and accuracy of the proposed algorithm's performance by the experiment for the realization of localization system.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.7
• /
• pp.157-168
• /
• 2014

We propose an novel artificial visual attention model that is capable of automatic detection and segmentation of saliency region on natural images in this paper. The proposed model is based on human visual perceptions in biological vision and contains there are main contributions. Firstly, we propose a novel framework of artificial visual attention model based on the opponent process theory using intensity and color features, and an entropy filter is designed to perceive salient regions considering the amount of information from intensity and color feature channels. The entropy filter is able to detect and segment salient regions in high segmentation accuracy and precision. Lastly, we also propose an adaptive combination method to generate a final saliency map. This method estimates scores about intensity and color conspicuous maps from each perception model and combines the conspicuous maps with weight derived from scores. In evaluation of saliency map by ROC analysis, the AUC of proposed model as 0.9256 approximately improved 15% whereas the AUC of previous state-of-the-art models as 0.7824. And in evaluation of salient region segmentation, the F-beta of proposed model as 0.7325 approximately improved 22% whereas the F-beta of previous state-of-the-art models.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.326-334
• /
• 2022

In this paper, we propose speech enhancement algorithm as a pre-processing for robust speech recognition in noisy environments. Auxiliary-function-based Independent Vector Analysis (AuxIVA) is performed with weighted covariance matrix using time-varying variances with scaling factor from target masks representing time-frequency contributions of target speech. The mask estimates can be obtained using Neural Network (NN) pre-trained for speech extraction or diffuseness using Coherence-to-Diffuse power Ratio (CDR) to find the direct sounds component of a target speech. In addition, outputs for omni-directional noise are closely chained by sharing the time-varying variances similarly to independent subspace analysis or IVA. The speech extraction method based on AuxIVA is also performed in Independent Low-Rank Matrix Analysis (ILRMA) framework by extending the Non-negative Matrix Factorization (NMF) for noise outputs to Non-negative Tensor Factorization (NTF) to maintain the inter-channel dependency in noise output channels. Experimental results on the CHiME-4 datasets demonstrate the effectiveness of the presented algorithms.

• Progress in Medical Physics
• /
• v.21 no.4
• /
• pp.332-339
• /
• 2010

We aimed to setup an adaptive radiation therapy platform using cone-beam CT (CBCT) and multileaf collimator (MLC) log data and also intended to analyze a trend of dose calculation errors during the procedure based on a phantom study. We took CT and CBCT images of Catphan-600 (The Phantom Laboratory, USA) phantom, and made a simple step-and-shoot intensity-modulated radiation therapy (IMRT) plan based on the CT. Original plan doses were recalculated based on the CT ($CT_{plan}$) and the CBCT ($CBCT_{plan}$). Delivered monitor unit weights and leaves-positions during beam delivery for each MLC segment were extracted from the MLC log data then we reconstructed delivered doses based on the CT ($CT_{recon}$) and CBCT ($CBCT_{recon}$) respectively using the extracted information. Dose calculation errors were evaluated by two-dimensional dose discrepancies ($CT_{plan}$ was the benchmark), gamma index and dose-volume histograms (DVHs). From the dose differences and DVHs, it was estimated that the delivered dose was slightly greater than the planned dose; however, it was insignificant. Gamma index result showed that dose calculation error on CBCT using planned or reconstructed data were relatively greater than CT based calculation. In addition, there were significant discrepancies on the edge of each beam while those were less than errors due to inconsistency of CT and CBCT. $CBCT_{recon}$ showed coupled effects of above two kinds of errors; however, total error was decreased even though overall uncertainty for the evaluation of delivered dose on the CBCT was increased. Therefore, it is necessary to evaluate dose calculation errors separately as a setup error, dose calculation error due to CBCT image quality and reconstructed dose error which is actually what we want to know.

• Journal of Environmental Policy
• /
• v.12 no.3
• /
• pp.21-47
• /
• 2013

The aim is to analysis landslide vulnerability in Inje, Korea, using GCI(Geospatial Correlative Integration) and probability rainfalls based on geographic information system (GIS). In order to achieve this goal, identified indicators influencing landslides based on literature review. We include indicators of exposure to climate(rainfall probability), sensitivity(slope, aspect, curvature, geology, topography, soil drainage, soil material, soil thickness and soil texture) and adaptive capacity(timber diameter, timber type, timber density and timber age). All data were collected, processed, and compiled in a spatial database using GIS. Karisan-ri that had experienced 470 landslides by Typhoon Ewinia in 2006 was selected for analysis and verification. The 50% of landslide data were randomly selected to use as training data, while the other 50% being used for verification. The probability of landslides for target years (1 year, 3 years, 10 years, 50 years, and 100 years) was calculated assuming that landslides are triggered by 3-day cumulative rainfalls of 449 mm. Results show that number of slope has comparatively strong influence on landslide damage. And inclination of $25{\sim}30^{\circ}C$, the highest correlation landslide. Improved previous landslide vulnerability methodology by adopting GCI. Also, vulnerability map provides meaningful information for decision makers regarding priority areas for implementing landslide mitigation policies.

• Journal of Biomedical Engineering Research
• /
• v.19 no.5
• /
• pp.455-468
• /
• 1998

For the objective interpretation of cerebral metabolic patterns in epilepsy patients, we developed computer-aided classifier using artificial neural network. We studied interictal brain FDG PET scans of 257 epilepsy patients who were diagnosed as normal(n=64), L TLE (n=112), or R TLE (n=81) by visual interpretation. Automatically segmented volume of interest (VOI) was used to reliably extract the features representing patterns of cerebral metabolism. All images were spatially normalized to MNI standard PET template and smoothed with 16mm FWHM Gaussian kernel using SPM96. Mean count in cerebral region was normalized. The VOls for 34 cerebral regions were previously defined on the standard template and 17 different counts of mirrored regions to hemispheric midline were extracted from spatially normalized images. A three-layer feed-forward error back-propagation neural network classifier with 7 input nodes and 3 output nodes was used. The network was trained to interpret metabolic patterns and produce identical diagnoses with those of expert viewers. The performance of the neural network was optimized by testing with 5~40 nodes in hidden layer. Randomly selected 40 images from each group were used to train the network and the remainders were used to test the learned network. The optimized neural network gave a maximum agreement rate of 80.3% with expert viewers. It used 20 hidden nodes and was trained for 1508 epochs. Also, neural network gave agreement rates of 75~80% with 10 or 30 nodes in hidden layer. We conclude that artificial neural network performed as well as human experts and could be potentially useful as clinical decision support tool for the localization of epileptogenic zones.