• 대한안전경영과학회지
• /
• 제3권1호
• /
• pp.117-125
• /
• 2001

Polyacetal resin is usually used to make molds, but it is difficult to achieve dimension accuracy during molding. Therefore it is usually necessary to cut the polyacetal resin after a molding process. Polyacetal resin is easily machining by standard machine tool. Acetal is also a thermal stable material which can be totted without coolant Another concern about the use of polyacetal resin is that it absorbs water easily, which also results in problems with dimension accuracy Therefore, in this study, the cutting resistance of water-absorbed polyacetal resin and its surface roughness after cutting in order to achieve the highest degree of accuracy in the cutting of polyacetal resin were investigated. Also, The Robust Design method uses a mathematical tool called orthogonal arrays to study a large number of decision variables with a small number of experiments. It also uses a new measure of quality, called signal-to-noise (S/N) ratio, to predict the quality from the customer's perspective. Thus, we have taken Taguchi's parameter design approach, specifically orthogonal array, and determined the optimal levels of the selected variables through analysis of the experimental results using S/N ratio.

• 대한원격탐사학회지
• /
• 제25권3호
• /
• pp.205-214
• /
• 2009

This paper investigates stereo 3D viewing for linear pushbroom satellite images using the Orbit-Attitude Model proposed by Kim (2006) and using OpenGL graphic library in Digital Photogrammetry Workstation. 3D viewing is tested with KOMPSAT-2 satellite stereo images, a large number of GCPs (Ground control points) collected by GPS surveying and orbit-attitude sensor model as a rigorous sensor model. Comparison is carried out by two accuracy measurements: the accuracy of orbit-attitude modeling with bundle adjustment and accuracy analysis of errors in x and y parallaxes. This research result will help to understand the nature of 3D objects for high resolution satellite images, and we will be able to measure accurate 3D object space coordinates in virtual or real 3D environment.

• Journal of Multimedia Information System
• /
• 제6권2호
• /
• pp.75-80
• /
• 2019

In machine learning, the performance of the system depends upon the nature of input data. The efficiency of the system improves when the behavior of the input data changes from un-normalized to normalized form. This paper experimentally demonstrated the performance of KNN, SVM, LDA and NB on Alzheimer's dataset. The dataset undertaken for the study consisted of 3 classes, i.e. Demented, Converted and Non-Demented. Analysis shows that LDA and NB gave an accuracy of 89.83% and 88.19% respectively in both the cases whereas the accuracy of KNN and SVM improved from 46.87% to 82.80% and 53.40% to 88.75% respectively when input data changed from un-normalized to normalized state. From the above results it was observed that KNN and SVM show significant improvement in classification accuracy on normalized data as compared to un-normalized data, whereas LDA and NB reflect no such change in their performance.

• ETRI Journal
• /
• 제41권5호
• /
• pp.684-695
• /
• 2019

In a cloud environment, performance degradation, or even downtime, of virtual machines (VMs) usually appears gradually along with anomalous states of VMs. To better characterize the state of a VM, all possible performance metrics are collected. For such high-dimensional datasets, this article proposes a feature extraction algorithm based on unsupervised fuzzy linear discriminant analysis with kernel (UFKLDA). By introducing the kernel method, UFKLDA can not only effectively deal with non-Gaussian datasets but also implement nonlinear feature extraction. Two sets of experiments were undertaken. In discriminability experiments, this article introduces quantitative criteria to measure discriminability among all classes of samples. The results show that UFKLDA improves discriminability compared with other popular feature extraction algorithms. In detection accuracy experiments, this article computes accuracy measures of an anomaly detection algorithm (i.e., C-SVM) on the original performance metrics and extracted features. The results show that anomaly detection with features extracted by UFKLDA improves the accuracy of detection in terms of sensitivity and specificity.

• Communications for Statistical Applications and Methods
• /
• 제28권2호
• /
• pp.161-169
• /
• 2021

The two-dimensional confusion matrix used in credit assessment, biostatistics, and many other fields consists of true positive, true negative, false positive, and false negative. Their rates, such as the true positive rate (TPR), true negative rate (TNR), false positive rate, and false negative rate, can be applied to measure its accuracy. In this study, we propose the TPR-TNR plot, a graphical method that can geometrically describe and explain these rates based on the confusion matrix. The proposed TPR-TNR plot consists of two right-angled triangles. We obtain that the TPR and TNR describe the acute angles of right-angled triangles in the plot. These acute angles can be used to determine optimal thresholds corresponding to lots of accuracy measures.

• 천문학회보
• /
• 제40권1호
• /
• pp.46.4-47
• /
• 2015

Carnegie Hubble Program II (hereafter CHP II) is a large Hubble Space Telescope (HST) observing campaign in the cycle 22 composed of a total of 184 orbits (132 primes + 52 parallels), which aims to measure H0 directly with an unprecedented accuracy. Unlike our previous efforts in CHP I which used Cepheids as a yardstick, CHP II takes the Population II (Pop II) distance indicators such as RR Lyraes and tip of the red giant branch stars (TRGBs) to set up a new calibration to Type Ia supernovae (SN Ia) distance. The Pop II distance scales have two immediate advantages over the classical Cepheid method: 1) The period-luminosity relation of the RR Lyrae has a scatter that is a factor of 2 smaller; 2) The RR Lyrae/TRGB distance scale can be applied to both elliptical and spiral galaxies. This will provide a great systematic benefit by ultimately allowing us to double the number of SN Ia distances based on geometry. By taking advantage of this Pop II route, we expect to measure H0 value to 3 % of error which will be the highest accuracy H0 measurement to date using the "Distance Ladder" method. In this talk I will present a brief background/overview on the CHP II, observations/data acquisition status, and ongoing research progress/preliminary results.

• 센서학회지
• /
• 제27권3호
• /
• pp.199-203
• /
• 2018

In this study, we develop a methane sensor module that can detect low concentrations below 5,000 ppm and measure up to the detection limit of 50 ppm with the NDIR method, with a long lifetime and high accuracy. Methane ($CH_4$) is one of a representative greenhouse gas, which is very explosive. Thus, it is important to quickly and accurately measure methane concentration in the air. To adjust the methane sensor for industrial field applications, a NDIR-based small sensor was implemented and characterized, where its volume was $4cm{\times}4cm{\times}2cm$ and its response time ($T_{90}$) was less than 30 sec. These results demonstrate that the proposed sensor is commercially available for low-concentration measurement, low volume, and fast response application, such as IoT sensor nodes and portable devices.

• 한국생산제조학회지
• /
• 제8권6호
• /
• pp.55-63
• /
• 1999

The acceleration of the performance of machine tools influences the development of the semi-conductor and optical technology as the development of NC and measurement technology. Because the measurement has been done to unload condition without considering of mechanical stiffness in the case of machining center as we measure the quasi-static error of machine tools on general study people who works on the spot has many problems on the data value. Also there are no satisfiable results until now in spite of many studys about this because the deflections of the table and the shaft supporting a workpiece influence, influence the accuracy of the table and shaft supporting a workpiece influence the accuracy of the workpiece. And there is doubt about the inspection method of measured error. In this paper Therefor we will help working more accurately on the spot by measuring analyzing displaying the defoec-tion of the table and support shaft when we load on the table and the support shaft of machining center using laser interfer-ometer. Also we try to settle new conception of the measurement method and more accurate grasp of the deflection tenden-cy by verifing the tendency of the error measured through the comparison of the simulated error measured through the comparison of the simulated error using ANSYS a common finite element analysis program which is able to measure heat deformation material deformation and error resulted from this study.

• 한국통신학회논문지
• /
• 제41권12호
• /
• pp.1752-1755
• /
• 2016

본 논문에서는 "축구 동영상"의 배경 분리 정확도 향상을 위한 "최적의" 수학적 모폴로지 연산자를 결정하기 위하여 정량적인 비교 평가 연구를 수행하였다. 이를 위해 본 논문에서는 여섯 가지 서로 다른 수학적 모폴로지 연산자를 동일한 실험 환경에서 비교 평가하였다. F-measure를 이용하여 평가한 결과 복구에 의한 닫기-복구에 의한 열기 연산자가 최적의 연산자임을 확인하였다. 본 논문에서 제시된 정량적 비교 평가 결과는 지능형 축구 동영상 분석 시스템 개발을 위해 배경 분리 기술을 이용하거나 축구 동영상에 특화된 배경 분리 기술을 연구하고자 하는 연구자 및 개발자들에게 실질적인 도움이 될 것으로 판단된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권7호
• /
• pp.3301-3318
• /
• 2016

Online social networks (OSNs) have changed the way people communicate with each other. An OSN usually encourages the participants to provide personal information such as real names, birthdays and educational background to look for and establish friendships among them. Some users are unwilling to reveal personal information on their personal pages due to potential privacy concerns, but their friends may inadvertently reveal that. In this work, we investigate the possibility of leaking personal information on Facebook in an unintentional and involuntary manner. The revealed information may be useful to malicious users for social engineering and spear phishing. We design the inference methods to find birthdays and educational background of Facebook users based on the interactions among friends on Facebook pages and groups, and also leverage J-measure to find the inference rules. The inference improves the finding rate of birthdays from 71.2% to 87.0% with the accuracy of 92.0%, and that of educational background from 75.2% to 91.7% with the accuracy of 86.3%. We also suggest the sanitization strategies to avoid the private information leakage.