• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.157-159
• /
• 2001

신경 트리는 신경망과 결정 트리의 구조를 결합한 형태의 분류기로서 비선형적 결정 경계 형성이 가능하며 기존 신경망에 비해 학습, 출력시 계산량이 적다는 장점을 갖는다. 본 논문에서는 신경 트리의 노드를 구성하는 신경망을 학습하기 위하여 기존의 방법들과는 달리 교사 학습 방법인 LVQ3 알고리즘을 사용하는 신경 트리 분류기를 제안한다. 학습 과정을 통해 생성된 트리는 오인식율 추정을 이용한 가지치기를 통하여 효율적인 트리로 재구성된다. 제안하는 방법은 실제 데이터 집합들을 이용한 실험을 통하여 그 성능을 검증하였다.

• Journal of Internet Computing and Services
• /
• v.2 no.1
• /
• pp.31-38
• /
• 2001

Speech database built of phonemes is significant in the studies of speech recognition, speech synthesis and analysis, Phoneme, consist of voiced sounds and unvoiced ones, Though there are many feature differences in voiced and unvoiced sounds, the traditional algorithms for detecting the boundary between phonemes do not reflect on them and determine the boundary between phonemes by comparing parameters of current frame with those of previous frame in time domain, In this paper, we propose the assort algorithm, which is based on a block and reflecting upon the feature differences between voiced and unvoiced sounds for phoneme segmentation, The assort algorithm uses the distance measure based upon MFCC(Mel-Frequency Cepstrum Coefficient) as a comparing spectrum measure, and uses the energy, zero crossing rate, spectral energy ratio, the formant frequency to separate voiced sounds from unvoiced sounds, N, the result of out experiment, the proposed system showed about 79 percents precision subject to the 3 or 4 syllables isolated words, and improved about 8 percents in the precision over the existing phonemes segmentation system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.5C
• /
• pp.486-492
• /
• 2003

The vigilance threshold of conventional fuzzy ART algorithm decide whether to permit the mismatch between any input pattern and stored pattern. If the vigilance threshold was large, despite of little difference among input and stored patterns, the input pattern may be classified to new category. On the other hand, if the vigilance threshold was small, the similarity between two patterns may be accepted in spite of lots of difference and the input pattern are classified to category of the stored pattern. Therefore, the vigilance threshold for the image recognition must be experientially set for the good result. Moreover, it may occur in the fuzzy ART algorithm that the information of stored patterns is lost in the weight-adjusting process and the rate of pattern recognition is dropped. In this paper, I proposed the enhanced fuzzy ART algorithm that supports the dynamical setting of the vigilance threshold using the generalized intersection operator of fuzzy logic and the weight value being adaptively set in proportional to the current weight change and the previous weight by reflecting the frequency of the selection of winner node. For the performance evaluation of the proposed method, we applied to the recognition of container identifiers from shipping container images. The experiment showed that the proposed method produced fewer clusters than conventional ART2 and fuzzy ART algorithm. and had tile higher recognition rate.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.2
• /
• pp.53-60
• /
• 2012

Nearest-neighbor classification predicts the class of an input data with the most frequent class among the near training data of the input data. Even though nearest-neighbor classification doesn't have a training stage, all of the training data are necessary in a predictive stage and the generalization performance depends on the quality of training data. Therefore, as the training data size increase, a nearest-neighbor classification requires the large amount of memory and the large computation time in prediction. In this paper, we propose a prototype selection algorithm that predicts the class of test data with the new set of prototypes which are near-boundary training data. Based on Tomek links and distance metric, the proposed algorithm selects boundary data and decides whether the selected data is added to the set of prototypes by considering classes and distance relationships. In the experiments, the number of prototypes is much smaller than the size of original training data and we takes advantages of storage reduction and fast prediction in a nearest-neighbor classification.

• Journal of Korea Water Resources Association
• /
• v.53 no.8
• /
• pp.617-626
• /
• 2020

This study investigates changes of bifurcation discharge ratio, flow velocity distributions and characteristics of separation zone due to variation of bifurcation angle by using TELEMAC-2D model. When the bifurcation angle is reduced from 90° to 45° without changing the boundary conditions, the bifurcation discharge ratio increased by 1.5 times from 0.523 to 0.785 because of increasing the radius of curvatures, the inertia force of the downstream flow, and the pressure gradient by the downstream boundary conditions. The bifurcation discharge ratio increases non-linearly whenever the bifurcation angle decreases by 15° intervals from 90° to 45° in flow with the upstream Froude number of 0.45 to 0.74. In flow with a maximum Froude number of 0.74, the rate of increase for bifurcation discharge ratio is 31.1% and the minimum value. When the Froude number is 0.58, the bifurcation discharge ratio is 0.7 or less, and the maximum rate of increase for that ratio is 53.5%. As the upstream Froude number decreases less than 0.58, the bifurcation discharge ratio exceeds 0.7, and the rate of increase decreases. When the upstream Froude number is 0.4 higher, the dimensionless width and length changing ratio of the separation zone are about 2.56 and 5.5 times higher than in 0.4 or less.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.01a
• /
• pp.73-74
• /
• 2017

SVM(Support Vector Machine) 알고리즘은 대표적인 기계 학습 분류 알고리즘으로 감정 분석, 제스처 인식 등 다양한 분야의 문제를 해결하기 위해 사용되고 있다. SVM 알고리즘은 분리경계면(Hyper-Plane) 또는 분리경계면 집합 중 지지벡터(Support Vector)라 불리는 특정한 점들로 이루어진 두 그룹 간의 거리 차이(Margin)를 최대로 하는 분리경계면을 이용하여 데이터를 분류하는 알고리즘이다. 높은 정확도를 제공하지만 처리 속도가 느리며 학습을 위해 대량의 데이터 및 메모리가 필요하기 때문에 자원이 제한적인 IoT 환경에서 사용이 어렵다. 본 논문에서는 자원이 제한된 IoT 노드를 기반으로 효율적으로 데이터를 학습하기 위해 K-means 알고리즘을 이용하여 SVM 알고리즘의 저전력화 방안을 연구한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11b
• /
• pp.1591-1594
• /
• 2002

BE(Best-Effort)방식의 인터넷에서 제공되던 Text위주의 서비스 제공 방식이 Multimedia 위주의 서비스로 점차 바뀌어 감에 따라, 기존의 BE(Best-Effort)방식으로는 Multimedia QoS(Quality of Service)를 보장하기가 어려워졌다. 이에 IETF(Internet Engineering Task Force)에서는 변화하는 인터넷 환경에서 QoS 보장을 위해 Diffserv(Differentiated Service)방식을 제안하게 되었다. 본 논문에서는 Content를 제공하는 Linux Web Server에서 패킷을 클래스 분류기준(Classification Method)에 의해 분류하고 Scheduling Algorithm을 적용하여 DSCP(Differentiated Service CodePoint) 값을 Web Server 자체에서 결정하여 경계라우터(Edge Router)로 전송하는 방식을 취하였으며, 이를 토대로 하여 경계라우터의 Traffic 부하를 줄이고, 경계라우터의 코어라우터(Core Router)화를 통해 더욱더 향상된 Differentiated Service를 제공하는 것이 목적이다. 이를 본 논문에서는 ns2 를 통해 IETF에서 제안된 Diffserv방식과 본 논문에서 제안한 방식의 Diffserv 방식과 현재의 BE방식을 비교하여 어느 정도의 성능 향상이 있었는지 비교 분석하였다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.32 no.5
• /
• pp.443-450
• /
• 2014

To fulfill the recent increasement in the public and private demands for various spatial data, the central and local governments started to produce those data. The low-level land cover map has been produced since 2000, yet the production of high-level land covered map has started later in 2010, and recently, a few regions was completed recently. Although many studies have been carried to improve the quality of land that covered in the map, most of them have been focused on the low-level and mid-level classifications. For that reason, the study for high-level classification is still insufficient. Therefore, in this study, we suggested the automatic extraction of land readjustment for paddy land that updated in the mid-level land mapping. At the study, the RapidEye satellite images, which consider efficient to apply in the agricultural field, were used, and the high pass filtering emphasized the outline of paddy field. Also, the binary images of the paddy outlines were generated from the Otsu thresholding. The boundary information of paddy field was extracted from the image-to-map registrations and masking of paddy land cover. Lastly, the snapped edges were linked, as well as the linear features of paddy outlines were extracted by the regional Hough line extraction. The start and end points that were close to each other were linked to complete the paddy field outlines. In fact, the boundary of readjusted paddy fields was able to be extracted efficiently. We could conclude in that this study contributed to the automatic production of a high-level land cover map for paddy fields.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.171-174
• /
• 2010

본 논문에서는 렌즈의 흠집을 추출할 수 있는 퍼지 기법을 이용한 렌즈 흠집 검출 방법을 제안한다. 제안된 방법은 렌즈 영상을 그레이 영상으로 변환한 후, 캐니 마스크를 이용하여 렌즈의 경계선을 추출한다. 추출된 렌즈의 경계선에 대해 평균 이진화와 모폴로지를 이용하여 렌즈 경계선을 보정한다. 렌즈 경계선이 보정된 영상에서 Seed Fill 알고리즘을 적용하여 렌즈의 내부 영역만을 추출한다. 추출된 렌즈의 내부 영역에 해당하는 원 영상에서 소벨 마스크를 적용하여 렌즈 내부 영역의 에지를 추출한다. 렌즈 내부 영역에서 추출된 에지 객체들의 정보를 이용하여 흠집과 비흠집을 분류하는 퍼지 기법을 적용하여 흠집 영역을 추출한다. 본 논문에서 제안된 렌즈의 흠집 검출 방법의 성능을 평가하기 위해 CHEMI, MID, HL, HM 시력 보정용 렌즈를 대상으로 실험한 결과, 제안된 방법이 흠집을 효과적으로 검출하는 것을 확인하였다.

• Journal of Broadcast Engineering
• /
• v.3 no.2
• /
• pp.111-117
• /
• 1998

Due to independent processing of image block, DCT-based block coding algorithms can produce the blocking effect qhich is gray-level discontinuity along block boundaries of the reconstructed image. In this paper, we have proposed two techniques to reduce the blocking effect: two-stage transform coding with variable quantizer and the globally optimum filtering. We have also compared performances of our algorithms and other conventional algorithms by applying optimal allocation.