• 산업경영시스템학회지
• /
• 제45권4호
• /
• pp.233-239
• /
• 2022

The injection molding process is a process in which thermoplastic resin is heated and made into a fluid state, injected under pressure into the cavity of a mold, and then cooled in the mold to produce a product identical to the shape of the cavity of the mold. It is a process that enables mass production and complex shapes, and various factors such as resin temperature, mold temperature, injection speed, and pressure affect product quality. In the data collected at the manufacturing site, there is a lot of data related to good products, but there is little data related to defective products, resulting in serious data imbalance. In order to efficiently solve this data imbalance, undersampling, oversampling, and composite sampling are usally applied. In this study, oversampling techniques such as random oversampling (ROS), minority class oversampling (SMOTE), ADASYN(Adaptive Synthetic Sampling), etc., which amplify data of the minority class by the majority class, and complex sampling using both undersampling and oversampling, are applied. For composite sampling, SMOTE+ENN and SMOTE+Tomek were used. Artificial neural network techniques is used to predict product quality. Especially, MLP and RNN are applied as artificial neural network techniques, and optimization of various parameters for MLP and RNN is required. In this study, we proposed an SA technique that optimizes the choice of the sampling method, the ratio of minority classes for sampling method, the batch size and the number of hidden layer units for parameters of MLP and RNN. The existing sampling methods and the proposed SA method were compared using accuracy, precision, recall, and F1 Score to prove the superiority of the proposed method.

• 대한의용생체공학회:의공학회지
• /
• 제10권3호
• /
• pp.323-330
• /
• 1989

Large bias errors which occur during a numerical evaluation of the Rayleigh's integral is not due to the replicated source problem but due to the coincidence of singularities of the Green's function and the sampling points in Fourier domain. We found that there is no replicated source problem in evaluating the Rayleigh's integral numerically by the reason of the periodic assumption of the input sequence in Dn or by the periodic sampling of the Green's function in the Fourier domain. The wrap around error is not due to an overlap of the individual adjacent sources but berallse of the undersampling of the Green's function in the frequency domain. The replicated and overlApped one is inverse Fourier transformed Green's function rather than the source function.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2004년도 추계학술발표논문집(상)
• /
• pp.241-244
• /
• 2004

일반적으로 메쉬(mesh)는 비정규 연결 형태(irregular connectivity)로 되어 있다. 리메싱(remeshing)은 비정규 연결 형태의 메쉬를 정규 연결 형태(regular connectivity)로 바꾸어 주는 작업이다. 메쉬의 기하 정보가 2D 그리드에 저장이 되어 있는 기하이미지(geometry Images)는 비정규 연결 형태의 메쉬를 완전 정규 형태(completely regular connectivity)로 리메싱하는 데 사용된다. 원본 메쉬를 기하 이미지로 생성하는 방법은 변형되는 크기를 최소화 하는 스트레치 메트릭(stretch metric)을 기반으로 이루어 졌다. 이 방법은 리메싱된 메쉬의 언더샘플링(undersampling)을 줄여 주게 된다. 하지만 리메싱 과정에서 생기는 오버샘플링(oversampling)은 줄여 주지 못한다. 본 논문에서는 정점(vertex)의 법선 벡터(normal vector)를 이용하여 기하이미지의 오버샘플링을 줄이는 방법을 제시한다.

• 전기학회논문지
• /
• 제65권8호
• /
• pp.1418-1423
• /
• 2016

The purpose of this research is to investigate the effect of sampling frequency on the photoplethysmography (PPG) and to evaluate the performance of interpolation methods for under-sampled PPG. We generated down-sampled PPG using 10 kHz-sampled PPG then evaluated waveshape changes with correlation coefficient. Correlation coefficient was significantly decreased at 50 Hz or below sampling frequency. We interpolated the down-sampled PPG using four interpolation method-linear, nearest, cubic spline and piecewise cubic Hermitt interpolation polynomial - then evaluated interpolation performance. As a result, it was shown that PPG waveform that was sampled over 20 Hz could be reconstructed by interpolation. Among interpolation methods, cubic spline interpolation showed the highest performance. However, every interpolation method has no or less effect on 5 Hz sampled PPG.

• 대한상한금궤의학회지
• /
• 제14권1호
• /
• pp.41-50
• /
• 2022

Objective : The purpose of this study is to explore the most suitable machine learning model algorithm for Shanghanlun diagnostic system classification using natural language processing (NLP). Methods : A total of 201 data items were collected from 『Shanghanlun』 and 『Clinical Shanghanlun』, 'Taeyangbyeong-gyeolhyung' and 'Eumyangyeokchahunobokbyeong' were excluded to prevent oversampling or undersampling. Data were pretreated using a twitter Korean tokenizer and trained by logistic regression, ridge regression, lasso regression, naive bayes classifier, decision tree, and random forest algorithms. The accuracy of the models were compared. Results : As a result of machine learning, ridge regression and naive Bayes classifier showed an accuracy of 0.843, logistic regression and random forest showed an accuracy of 0.804, and decision tree showed an accuracy of 0.745, while lasso regression showed an accuracy of 0.608. Conclusions : Ridge regression and naive Bayes classifier are suitable NLP machine learning models for the Shanghanlun diagnostic system classification.

• ETRI Journal
• /
• 제45권6호
• /
• pp.1007-1021
• /
• 2023

Stroke is the leading cause of permanent disability in adults, and it can cause permanent brain damage. According to the World Health Organization, 795 000 Americans experience a new or recurrent stroke each year. Early detection of medical disorders, for example, strokes, can minimize the disabling effects. Thus, in this paper, we consider various risk factors that contribute to the occurrence of stoke and machine learning algorithms, for example, the decision tree, random forest, and naive Bayes algorithms, on patient characteristics survey data to achieve high prediction accuracy. We also consider the semisupervised self-training technique to predict the risk of stroke. We then consider the near-miss undersampling technique, which can select only instances in larger classes with the smaller class instances. Experimental results demonstrate that the proposed method obtains an accuracy of approximately 98.83% at low cost, which is significantly higher and more reliable compared with the compared techniques.

• ETRI Journal
• /
• 제40권2호
• /
• pp.237-245
• /
• 2018

The Distributed Modulated Wideband Converter (DMWC) is a networking system developed from the Modulated Wideband Converter, which converts all sampling channels into sensing nodes with number variables to implement signal undersampling. When the number of sparse subbands changes, the number of nodes can be adjusted flexibly to improve the reconstruction rate. Owing to the different attenuations of distributed nodes in different locations, it is worthwhile to find out how to select the optimal sensing node as the sampling channel. This paper proposes the spectrum sensing of DMWC based on a Markov random field (MRF) to select the ideal node, which is compared to the image edge segmentation. The attenuation of the candidate nodes is estimated based on the attenuation of the neighboring nodes that have participated in the DMWC system. Theoretical analysis and numerical simulations show that neighboring attenuation plays an important role in determining the node selection, and selecting the node using MRF can avoid serious transmission attenuation. Furthermore, DMWC can greatly improve recovery performance by using a Markov random field compared with random selection.

• 천문학회지
• /
• 제36권spc1호
• /
• pp.117-124
• /
• 2003

Pre-launch calibration data have been analyzed for evaluating the point spread function (PSF) of Yohkoh Soft X-ray Telescope (SXT). Especially, it is found crucial that the effect of undersampling should be treated properly. The best fit solution of the SXT PSF, which is modeled by an elliptical Moffat function, has been derived by the comparison with the ground experiment data. In order to examine the off-axis variation of the SXT PSF, we need to define in advance the location of the optical axis on the CCD. According to the previous studies, the off-axis variation of effective area (the vignetting function) may be approximated either by two non-concentric cones or by a cone with some flat distortions. There have been, however, no fully approved representations for the SXT vignetting effect. The effect of the shift of the optical axis from the geometrical center of the telescope is investigated by numerical simulation. It is revealed from our study that the full width at half maximum (FWHM) of the SXT PSF stays nearly constant within an error bound over the central area of the CCD where the solar disk is located.

• Journal of the Optical Society of Korea
• /
• 제20권3호
• /
• pp.381-388
• /
• 2016

The performance of a staring infrared imaging system can be characterized based on estimating the modulation transfer function (MTF). The slant edge method is a widely used MTF estimation method, which can effectively solve the aliasing problem caused by the discrete undersampling of the infrared focal plane array. However, the traditional slant edge method has some limitations such as the low precision of the edge angle extraction and using the approximate function to fit the edge spread function (ESF), which affects the accuracy of the MTF estimation. In this paper, we propose a modified slant edge method, including an edge angle extraction method that can improve the precision of the edge angle extraction and an ESF fitting algorithm which is based on the transfer function model of the imaging system, to enhance the accuracy of the MTF estimation. This modified slant edge method presents higher estimation accuracy and better immunity to noise and edge angle than other traditional methods, which is demonstrated by the simulation and application experiments operated in our study.

• 대한전자공학회논문지SD
• /
• 제37권5호
• /
• pp.16-22
• /
• 2000

본 논문은 HPO 홀로그램의 산란패턴을 전송하는데 적용 가능한 데이터 압축 알고리즘을 제시한다. 제시된 알고리즘은 홀로그램 데이터를 decimation 하기 위해서 변조함수를 이용해서 홀로그램 패턴의 대역폭을 압축시킨 것으로 수신단에서 데이터 복원을 위해서 인터폴레이션 과정이 필요하다. 압축 알고리즘 및 압축률의 유도와 함께 수신단에서 영상이 복원될 때 복원영상의 해상도 및 고조파(harmonic) 간섭영상의 주기를 분석한다. 마지막으로 시뮬레이션을 통해서 undersampling된 홀로그램 패턴에 대해 직접 복원시킨 결과와 변조함수에 의한 decimation 및 인터폴레이션 과정을 거친 후 복원시킨 결과를 비교하여 제시된 방법의 타당성을 보인다.