• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.179-182
• /
• 2010

본 논문에서는 영상으로부터 손금을 추출하기 위해서 획득된 영상을 YCbCr 컬러 공간으로 변환한다. YCbCr 컬러 공간에서 Y:65~255, Cb:25~255, Cr:130~255에 해당되는 피부색 정보를 추출하고 이 피부색 정보를 임계치로 설정하여 손 영역을 추출한다. 추출된 손 영역에서 내부 픽셀의 3:1 이상, 전체 영상의 2:1 이상인 손의 형태학적 정보와 8 방향 윤곽선 추적 기법을 이용하여 잡음을 제거한다. 잡음이 제거된 영상에서 손금을 추출하기 위해서 스트레칭 기법과 소벨 마스크를 이용하여 에지를 추출한다. 추출된 에지 영상에서도 미세한 잡음이 존재하므로 퍼지 이진화 기법을 이용하여 효과적으로 이진화 한다. 이진화된 영상에서 손금의 형태학적 정보를 이용하여 손의 윤곽선을 제외한 손금 영역을 추출한다. 추출된 손금 영역은 동치 테이블을 이용하는 연결 영역 검색 기법과 퍼지 추론 기법을 적용하여 개별 손금의 중요선을 추출하고 분석한다. 다양한 손금 영상을 대상으로 실험한 결과, 제안된 방법이 기존의 손금 추출 방법보다 손금을 분석하는데 효율적인 것을 확인하였다.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1993.04a
• /
• pp.275-281
• /
• 1993

본 발표에서는 신경회로망을 이용하여 연속음성중에서 키워드를 인식하는 방법을 설명한다. 연속음성에서 파형소편 및 음절을 식별하는 휴리스틱 알고리즘을 개발하였고, 연속음성을 음절단위로 파형소편 스펙트럼분석(선형예측법)으로 특성치를 추출하였다. 음절의 특성치는 코호넨 신경회로망을 통하여 학습을 시켰으며, 연속음성중 키워드인식은 먼저 음절을 인식하여 단어를 찾고, 인식된 단어가 키워드와 일치하는가를 확인한다. 본 연구의 의의는 파형소편 및 음절식별 알고리즘을 통하여, 크기불변성(Scaling invariance), 시간불변성(Time warping 및 Time-shift invariance), 중복성제거의 문제점을 해결하였고, 신경회로망의 학습을 통하여 화자독립적인 연속음성인식시스템 구축의 기반을 확립한데 있다. 본 음성인식모델은 학교구내 전화번호 안내시스템으로 활용단계에 있으며 전화번호뿐만아니라 주소안내시스템으로도 활용될 예정이다. 또한 자동차 운전보조시스템 및 주행안내시스템의 음성명령에 응용될 수 있는데, 예로 음성명령은 "핸들 좌로 20도", "시청까지 주행", "시청 지도안내"등이 될 수 있다. 현재 자동차 운전보조시스템은 컴퓨터 화면상 모의동작시스템으로 운영되고 있다. 본 음성인식모델은 화자종속시 90%이상, 화자독립시 70%의 인식결과를 보였다.시 90%이상, 화자독립시 70%의 인식결과를 보였다.

• KIISE Transactions on Computing Practices
• /
• v.23 no.2
• /
• pp.128-133
• /
• 2017

In recent years, the number of systems for the analysis of large volumes of data is increasing. Hadoop, a representative big data system, stores and processes the large data in the distributed environment of multiple servers, where system-resource management is very important. The authors attempted to detect anomalies from the rapid changing of the log data that are collected from the multiple servers using simple but efficient anomaly-detection techniques. Accordingly, an Apache Hive storage architecture was designed to store the log data that were collected from the multiple servers in the Hadoop ecosystem. Also, three anomaly-detection techniques were designed based on the moving-average and 3-sigma concepts. It was finally confirmed that all three of the techniques detected the abnormal intervals correctly, while the weighted anomaly-detection technique is more precise than the basic techniques. These results show an excellent approach for the detection of log-data anomalies with the use of simple techniques in the Hadoop ecosystem.

• Journal of dental hygiene science
• /
• v.13 no.4
• /
• pp.434-439
• /
• 2013

This study was conducted to compare the dental plaque reduction using various mouthwashes with Quantitative Light induced Fluorescence-Digital (QLF-D). A survey on 20 students was carried out. The students who were at Shingu College. Experimental group was gargled 20 ml of Listerine during 30 seconds and 15 ml of Hexamedine during 60 seconds. Control group was gargled distilled water during 30 second. The data were analyzed with t-test using SPSS 20.0 program. The ratios of control group and experimental group were reduced. Degree of ${\Delta}R30$ and ${\Delta}R70$ Listerine group was a significant difference (p>0.05). Degree of Simple Plaque Score and ${\Delta}R30$ Hexamedine group was a significant difference (p>0.05). There was no significant difference in the distilled water gargle group (p<0.05). The result of this study has the effect of two mouthwashes reduced dental plaque. The evaluation data of this study will be used in clinical application and research about QLF-D.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.3
• /
• pp.321-326
• /
• 2019

Image denoising methods based on block matching are founded on the experimental observations that neighboring patches or blocks in images retain similar features with each other, and have been proved to show superior performance in denoising different kinds of noise. The methods, however, take into account only neighboring blocks in searching for similar blocks, and ignore the characteristic features of the reference block itself. Consequently, denoising performance is negatively affected when outliers of the Gaussian distribution are included in the reference block which is to be denoised. In this paper, we propose an expanded block matching method in which noisy images are first decomposed into a number of bit-planes, then the range of true signals are estimated based on the distribution of pixels on the bit-planes, and finally outliers are replaced by the neighboring pixels belonging to the estimated range. In this way, the advantages of the conventional Gaussian filter can be added to the blocking matching method. We tested the proposed method through extensive experiments with well known test-bed images, and observed that performance gain can be achieved by the proposed method.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.4
• /
• pp.91-98
• /
• 2022

Lifelog data continuously collected through a wearable device may contain many outliers, so in order to improve data quality, it is necessary to find and remove outliers. In general, since the number of outliers is less than the number of normal data, a class imbalance problem occurs. To solve this imbalance problem, we propose a method that applies Variational AutoEncoder to outliers. After preprocessing the outlier data with proposed method, it is verified through a number of machine learning models(classification). As a result of verification using body weight data, it was confirmed that the performance was improved in all classification models. Based on the experimental results, when analyzing lifelog body weight data, we propose to apply the LightGBM model with the best performance after preprocessing the data using the outlier processing method proposed in this study.

• Journal of KIISE:Software and Applications
• /
• v.33 no.2
• /
• pp.252-266
• /
• 2006

Many problems in computer vision are mainly based on mathematical models. Their optimal solutions can be found by estimating the parameters of each model. However, provided an input data set is involved outliers which are relative]V larger than normal noises, they lead to incorrect results. RANSAC is a representative robust algorithm which is used to resolve the problem. One major problem with RANSAC is that it needs priori knowledge(i.e. a percentage of outliers) of the distribution of data. To solve this problem, we propose a FRANSAC algorithm which improves the rejection rate of outliers and the accuracy of solutions. This is peformed by categorizing all data into good sample set, bad sample set and vague sample set using a fuzzy classification at each iteration and sampling in only good sample set. In the experimental results, we show that the performance of the proposed algorithm when it is applied to the linear regression and the calculation of a homography.

• The Korean Journal of Applied Statistics
• /
• v.31 no.4
• /
• pp.463-473
• /
• 2018

Variable selection algorithms for linear regression models of large data are considered. Many algorithms are proposed focusing on the speed and the robustness of algorithms. Among them variance inflation factor (VIF) regression is fast and accurate due to the use of a streamwise regression approach. But a VIF regression is susceptible to outliers because it estimates a model by a least-square method. A robust criterion using a weighted estimator has been proposed for the robustness of algorithm; in addition, a robust VIF regression has also been proposed for the same purpose. In this article a fast and robust variable selection method is suggested via a VIF regression with detecting and removing potential outliers. A simulation study and an analysis of a dataset are conducted to compare the suggested method with other methods.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.5
• /
• pp.624-630
• /
• 2012

The peer review learning is a method which improves learning outcome of students through feedback between students and the observation and analysis of other students. One of the important problems in a peer review system is to find proper evaluators to each learner considering characteristics of students for improving learning outcomes. Some of peer review systems randomly assign peer review evaluators to learners, or chose evaluators based on limited strategies. However, these systems have a problem that they do not consider various characteristics of learners and evaluators who participate in peer reviews. In this paper, we propose a novel prediction approach of learning outcomes to apply peer review systems considering various characteristics of learners and evaluators. The proposed approach extracts representative attributes from the profiles of students and predicts learning outcomes using various regression models. In order to verify how much outliers affect on the prediction of learning outcomes, we also apply several outlier removal methods to the regression models and compare the predictive performance of learning outcomes. The experiment result says that the SVR model which does not removes outliers shows an error rate of 0.47% on average and has the best predictive performance.

• Korean Journal of Remote Sensing
• /
• v.30 no.6
• /
• pp.787-795
• /
• 2014

This paper presents an image registration using Triangulation-based Local Transformation (TLT) applied to the remaining matched points after elimination of the matched points with gross error. The corners extracted using geometric mean-based corner detector are matched using Pearson's correlation coefficient and then accepted as initial matched points only when they satisfy the Left-Right Consistency (LRC) check. We finally accept the remaining matched points whose RANdom SAmple Consensus (RANSAC)-based global transformation (RGT) errors are smaller than a predefined outlier threshold. After Delaunay triangulated irregular networks (TINs) are created using the final matched points on reference and sensed images, respectively, affine transformation is applied to every corresponding triangle and then all the inner pixels of the triangles on the sensed image are transformed to the reference image coordinate. The proposed algorithm was tested using KOMPSAT-2 images and the results showed higher image registration accuracy than the RANSAC-based global transformation.