• 산업공학
• /
• 제22권3호
• /
• pp.252-262
• /
• 2009

It is crucial to prevent low yields in the semiconductor industry. Since many factors affect variation in yield and they are deeply related, preventing low yield is difficult. There have been substantial researches in the field of yield prediction. Many researchers had used the statistical methods. Many studies have shown that artificial neural network (ANN) achieved better performance than traditional statistical methods. However, despite ANN's superior performance some problems such as over-fitting and poor explanatory power arise. In order to overcome these limitations, a relatively new machine learning technique, support vector machine (SVM), is introduced to classify the yield. SVM is simple enough to be analyzed mathematically, and it leads to high performances in practical applications. This study presents a new efficient classification methodology, Stepwise-SVM (SSVM), for detecting high and low yields. SSVM is step-by-step adjustment of parameters to be precisely the classification for actual high and low yield lot. The objective of this paper is to examine the feasibility of SVM and SSVM in the yield classification. The experimental results show that SVM and SSVM provides a promising alternative to yield classification for the field data.

• 한국의류산업학회지
• /
• 제13권4호
• /
• pp.624-634
• /
• 2011

The purpose of this study is to develop the pattern of safety clothes used at flat or mountainous areas and to identify the pattern of safety clothes by conducting experimental evaluation of virtual wear. Three subjects were selected, based on fire fighters' physical constitution. A prototype design for safety clothing was determined after in-depth interviewing of professionals and surveying of Forest service staff and related agency. Wearing test should be carried out in the order of pattern making, virtual and real wearing evaluation. For data analysis, technical statistical values should be obtained by using body measurements of subject, frequency analysis and T-test. The jacket is designed to have a front extension and the entire length of clothing enough for wearer to put on it over ordinary shirts or sweater. The collar of jacket is of round type. Cyber reality enables to identify the movement and activity of virtual fitting model and to find out errors or problems in safety clothing prior to on-the-spot wear test, thus raising the precision level of pattern. There was significant difference between real and virtual fit preference. The results show that the virtual try-on system need the development of a specific style.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2008년도 추계학술대회A
• /
• pp.1588-1593
• /
• 2008

This paper describes a real-time isometric pinch force prediction algorithm from surface electromyogram (sEMG) using multilayer perceptron (MLP) for human robot interactive applications. The activities of seven muscles which are observable from surface electrodes and also related to the movements of the thumb and index finger joints were recorded during pinch force experiments. For the successful implementation of the real-time prediction algorithm, an off-line analysis was performed using the recorded activities. Four muscles were selected for the force prediction by using the Fisher linear discriminant analysis among seven muscles, and the four muscle activities provided effective information for mapping sEMG to the pinch force. The MLP structure was designed to make training efficient and to avoid both under- and over-fitting problems. The pinch force prediction algorithm was tested on five volunteers and the results were evaluated using two criteria: normalized root mean squared error (NRMSE) and correlation (CORR). The training time for the subjects was only 2 min 29 sec, but the prediction results were successful with NRMSE = 0.112 ${\pm}$ 0.082 and CORR = 0.932 ${\pm}$ 0.058. These results imply that the proposed algorithm is useful to measure the produced pinch force without force sensors in real-time. The possible applications include controlling bionic finger robot systems to overcome finger paralysis or amputation.

• Journal of Information Processing Systems
• /
• 제16권2호
• /
• pp.435-446
• /
• 2020

With the ability to learn rules from training data, the machine learning model can classify unknown objects. At the same time, the dimension of hyperspectral data is usually large, which may cause an over-fitting problem. In this research, an identification methodology of tea diseases was proposed based on spectral reflectance and machine learning, including the feature selector based on the decision tree and the tea disease recognizer based on random forest. The proposed identification methodology was evaluated through experiments. The experimental results showed that the recall rate and the F1 score were significantly improved by the proposed methodology in the identification accuracy of tea disease, with average values of 15%, 7%, and 11%, respectively. Therefore, the proposed identification methodology could make relatively better feature selection and learn from high dimensional data so as to achieve the non-destructive and efficient identification of different tea diseases. This research provides a new idea for the feature selection of high dimensional data and the non-destructive identification of crop diseases.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권3호
• /
• pp.163-172
• /
• 2016

Electric load forecasting is essential for effective power system planning and operation. Complex and nonlinear relationships exist between the electric loads and their exogenous factors. In addition, time-series load data has non-stationary characteristics, such as trend, seasonality and anomalous day effects, making it difficult to predict the future loads. This paper proposes a locally-weighted polynomial neural network (LWPNN), which is a combination of a polynomial neural network (PNN) and locally-weighted regression (LWR) for daily shortterm peak load forecasting. Model over-fitting problems can be prevented effectively because PNN has an automatic structure identification mechanism for nonlinear system modeling. LWR applied to optimize the regression coefficients of LWPNN only uses the locally-weighted learning data points located in the neighborhood of the current query point instead of using all data points. LWPNN is very effective and suitable for predicting an electric load series with nonlinear and non-stationary characteristics. To confirm the effectiveness, the proposed LWPNN, standard PNN, support vector regression and artificial neural network are applied to a real world daily peak load dataset in Korea. The proposed LWPNN shows significantly good prediction accuracy compared to the other methods.

• 한국신재생에너지학회:학술대회논문집
• /
• 한국신재생에너지학회 2011년도 추계학술대회 초록집
• /
• pp.63.1-63.1
• /
• 2011

To analyze the phenomenon of corrosion in the PV module, we experimented damp heat test at $85^{\circ}C$/85% relative humidity(RH) and $65^{\circ}C$/85% RH for 2,000 hours, respectively. We used 30 mini-modules designed of 6inch one cell. Despite of 2,000 hours test, measured $P_{max}$ is not reached failure which is defined less than 80% compared to initial $P_{max}$. Therefore, we calculate proper curve fitting over 2,000 hours. Data less than 80% $P_{max}$ is found and B10 lifetime is calculated by the number of failure specimens and weibull distribution. Using B10 lifetime that the point of failure rate 10% and Peck's model, the predictable equation of lifetime was derived under temperature and humidity condition.

• 한국의류학회지
• /
• 제9권3호
• /
• pp.17-26
• /
• 1985

The purpose of this study is to develop a bodice pattern drafting method for Korean elderly women over sixty years old on the basis of their physical characteristics which differ from those of adult women. The study is composed as follows; 1. One hundred and five elderly women were measured on 20 items. Twenty-five items including 20 measured items and 5 calculated items were analyzed statistically. 2. A new method was developed based on the results of data analysis. Basic shells constructed from the patterns were examined through three fitting tests for completion. 3. The sensory evaluation was applied to evaluate the new pattern for elderly women by comparing it with the conventional pattern for adult women. A five-point rating scale was developed for the evaluation. According to a statistical analysis of the result of the 20 items on the questionnaire, all the items showed significant differences (a$\leqq$0.01) between the two, with the new pattern having higher scores.

• 대한조선학회논문집
• /
• 제52권1호
• /
• pp.1-7
• /
• 2015

The weight estimation of floating offshore structures such as FPSO, TLP, semi-Submersibles, Floating Offshore Wind Turbines etc. in the preliminary design, is one of direct measures of both construction cost and basic performance. Through both literature investigation and internet search, the weight data of floating offshore structures such as FPSO and TLP was collected. In this study, the weight estimation model with the genetic programming was suggested for FPSO. The weight estimation model using genetic programming was established by fixing the independent variables based on this data. In addition, the correlation analysis was performed to make up for the weak points of genetic programming; it is apt to induce over-fitting when the number of data is relatively smaller than that of independent variables. That is, by reducing the number of variables through the analysis of the correlation between the independent variables, the increasing effect in the number of weight data can be expected. The reliability of the developed weight estimation model was within 2% of error rate.

• 반도체디스플레이기술학회지
• /
• 제15권2호
• /
• pp.61-65
• /
• 2016

Facial feature detection is a fundamental function in the field of computer vision such as security, bio-metrics, 3D modeling, and face recognition. There are many algorithms for the function, active shape model is one of the most popular local texture models. This paper addresses issues related to face detection, and implements an efficient extraction algorithm for extracting the facial feature points to use on iOS platform. In this paper, we extend the original ASM algorithm to improve its performance by four modifications. First, to detect a face and to initialize the shape model, we apply a face detection API provided from iOS CoreImage framework. Second, we construct a weighted local structure model for landmarks to utilize the edge points of the face contour. Third, we build a modified model definition and fitting more landmarks than the classical ASM. And last, we extend and build two-dimensional profile model for detecting faces within input images. The proposed algorithm is evaluated on experimental test set containing over 500 face images, and found to successfully extract facial feature points, clearly outperforming the original ASM.

• Journal of Pharmaceutical Investigation
• /
• 제30권3호
• /
• pp.207-211
• /
• 2000

The objective of this work is to investigate the effect of molecular weight of poly(ethylene oxide) (PEO) and release medium on the release of nifedipine (NP) from PEO tablets containing NP and to get some mechanistic insights into the release of NP. The tablets containing NP were prepared by direct compression, using a flat-faced punch and die. The molecular weights of PEOs used were 200K, 900K, 2000K and 7,000K. The release kinetics were studied for 24 hours in aqueous ethanol solution, using a dissolution tester at $36.5^{\circ}C$ and 100 rpm. Drug release rate increased, as the concentration of ethanol in the dissolution medium increased, due to the increased solubility of NP. As the molecular weight of PEO increased, release rate decreased, due to the slower swelling and dissolution of PEO. The power values obtained by fitting data to the power law expression $(M_t/M_{\infty}=kt^n)$ indicated that, at low ethanol concentration, the release of NP is governed by anomalous diffusion. However, as the ethanol concentration increases, diffusional release becomes to prevail over anomalous or zero-order release. Overall, these results provided some insights into the release of NP from PEO tablet.