• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.1263-1266
• /
• 1998

In this paper, we propose an optimal feature extraction method for normally distributed multiclass data. We search the whole feature space to find a set of features that give the smallest classification error for the Gaussian ML classifier. Initially, we start with an arbitrary feature vector. Assuming that the feature vector is used for classification, we compute the classification error. Then we move the feature vector slightly and compute the classification error with this vector. Finally we update the feature vector such that the classification error decreases most rapidly. This procedure is done by taking gradient. Alternatively, the initial vector can be those found by conventional feature extraction algorithms. We propose two search methods, sequential search and global search. Experiment results show that the proposed method compares favorably with the conventional feature extraction methods.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.1
• /
• pp.113-120
• /
• 2015

In this paper, we propose a feature extraction method using the stacked autoencoders which consist of restricted Boltzmann machines. The stacked autoencoders is a sort of deep networks. Restricted Boltzmann machines (RBMs) are probabilistic graphical models that can be interpreted as stochastic neural networks. In terms of pattern classification problem, the feature extraction is a key issue. We use the stacked autoencoders networks to extract new features which have a good influence on the improvement of the classification performance. After feature extraction, fuzzy k-nearest neighbors algorithm is used for a classifier which classifies the new extracted data set. To evaluate the classification ability of the proposed pattern classifier, we make some experiments with several machine learning data sets.

• Bulletin of the Korean Chemical Society
• /
• v.30 no.7
• /
• pp.1526-1530
• /
• 2009

Solvent extraction reaction of Zn(II) by Alamine336 from strong HCl solution up to 10 M was identified by analyzing the data reported in the literature. The equilibrium constant of this reaction was estimated by considering the complex formation between zinc and chloride ion. The necessary thermodynamic parameters, such as equilibrium constant for the formation of complexes and the interaction parameters, were evaluated from the thermodynamic data reported in the literature. The following solvent extraction reaction and the equilibrium constant was obtained by considering the activity coefficients of solutes present in the aqueous phase with Bromley equation. $Zn^{2+}\;2Cl^{-}\;+\;R_3NHCl_{org}\;=\;ZnCl_3R_3NH_{org},\;K_{ex}\;=\;6.33\;{\times}\;10^2$ There was a good agreement between measured and calculated distribution coefficients of Zn(II).

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.859-861
• /
• 2003

In order to present a space in details, it is indispensable to acquire 3D shape and texture simultaneously from the same platform. 3D shape is acquired by Laser Scanner as point cloud data, and texture is acquired by CCD sensor. Positioning data is acquired by IMU (Inertial Measurement Unit). All the sensors and equipments are assembled on a hand-trolley. In this research, a method of integrating the 3D shape and texture for automated construction of Digital Surface Model is developed. This Digital Surface Model is applied for efficient feature extraction. More detailed extraction is possible , because 3D Digital Surface Model has both 3D shape and texture information.

• Natural Product Sciences
• /
• v.21 no.2
• /
• pp.141-145
• /
• 2015

Hesperidin, which is the most abundant flavonoid of Citrus unshiu (Rutaceae), has been reported to possess diverse activities and widely used as functional foods and cosmetics. For the development of functional products, extraction procedure is indispensable. Extraction conditions affect the composition of extract as well as its biological activity. Therefore, we tried to optimize extraction conditions such as extraction solvent, extraction time and extraction temperature for maximum yield of hesperidin using response surface methodology with threelevel-three-factor Box-Behnken design (BBD). Regression analysis showed a good fit of the experimental data and the optimal condition was obtained as ethanol concentration, 59.0%; temperature $71.5^{\circ}C$ and extraction time, 12.4 h. The hesperidin yield under the optimal condition was found to be $287.8{\mu}g$ per 5 mg extract, which was well matched with the predicted value of 290.5 μg. These results provides optimized extraction condition for hesperidin and might be useful for the development of hesperidin as functional products like health supplements, cosmetics and medicinal products.

• The Korean Journal of Food And Nutrition
• /
• v.32 no.5
• /
• pp.504-510
• /
• 2019

The purpose of this study was to compare the effects of soaking and ultrasonic extraction by observing the change of contents with extraction time of physicochemical properties (solid content, colorness, caffeine, chlorogenic acid, total polyphenols, DPPH, and ABTS). As a result of the analysis, solid content increased with longer extraction time and the whiteness tended to decrease with longer extraction time. Conversely, the extraction of functional materials showed a tendency to increase as the extraction time increased. Caffeine reached the maximum value after two hours soaking, but showed the same result as one hour for sonication. Chlorogenic acid did not show difference from the content of coffee extracted for one hour soaking only by sonication extraction for 30 minutes. The total polyphenols eluted with approximately two hours of soaking even after 30 minutes of sonication. DPPH and ABTS were insignificant in their concentrations, but their antioxidative effect was more than two hours of soaking with only 30 minutes of sonication. Sonication has a short time extraction from a functional aspect (caffeine content, chlorogenic acid, polyphenol content, and antioxidant capacity) and this experiment can provide basic data for the development of innovative recipes.

• Journal of Ocean Engineering and Technology
• /
• v.28 no.6
• /
• pp.552-559
• /
• 2014

In general, the number of underwater transient signals is very limited for research on automatic recognition. Data-dependent feature extraction is one of the most effective methods in this case. Therefore, we suggest WPCC (Wavelet packet ceptsral coefficient) as a feature extraction method. A wavelet packet best tree for each data set is formed using an entropy-based cost function. Then, every terminal node of the best trees is counted to build a common wavelet best tree. It corresponds to flexible and non-uniform filter bank reflecting characteristics for the data set. A GMM (Gaussian mixture model) is used to classify five classes of underwater transient data sets. The error rate of the WPCC is compared using MFCC (Mel-frequency ceptsral coefficients). The error rates of WPCC-db20, db40, and MFCC are 0.4%, 0%, and 0.4%, respectively, when the training data consist of six out of the nine pieces of data in each class. However, WPCC-db20 and db40 show rates of 2.98% and 1.20%, respectively, while MFCC shows a rate of 7.14% when the training data consists of only three pieces. This shows that WPCC is less sensitive to the number of training data pieces than MFCC. Thus, it could be a more appropriate method for underwater transient recognition. These results may be helpful to develop an automatic recognition system for an underwater transient signal.

• Journal of the Korea Society for Simulation
• /
• v.21 no.2
• /
• pp.79-90
• /
• 2012

In this paper, a feature signal extraction method is proposed in order to enhance the low performance of fault detection caused by unbalanced data which denotes the situations when severe disparity exists between the numbers of class instances. Most of the cyclic signals gathered during the process are recognized as normal, while only a few signals are regarded as fault; the majorities of cyclic signals data are unbalanced data. SOM(Self-Organizing Map)-based feature signal extraction method is considered to fix the adverse effects caused by unbalanced data. The weight neurons, mapped to the every node of SOM grid, are extracted as the feature signals of both class data which are used as a reference data set for fault detection. kNN(k-Nearest Neighbor) and SVM(Support Vector Machine) are considered to make fault detection models with comparisons to Hotelling's $T^2$ Control Chart, the most widely used method for fault detection. Experiments are conducted by using simulated process signals which resembles the frequent cyclic signals in semiconductor manufacturing.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.3
• /
• pp.372-381
• /
• 2006

The purpose of this study was to develop a process management system to manage ingot fabrication and improve ingot quality. The ingot is the first manufactured material of wafers. Trace parameters were collected on-line but measurement parameters were measured by sampling inspection. The quality parameters were applied to evaluate the quality. Therefore, preprocessing was necessary to extract useful information from the quality data. First, statistical methods were used for data generation. Then, modeling was performed, using the generated data, to improve the performance of the models. The function of the models is to predict the quality corresponding to control parameters. Secondly, rule extraction was performed to find the relation between the production quality and control conditions. The extracted rules can give important information concerning how to handle the process correctly. The dynamic polynomial neural network (DPNN) and decision tree were applied for data modeling and rule extraction, respectively, from the ingot fabrication data.

• Journal of KIBIM
• /
• v.9 no.3
• /
• pp.30-40
• /
• 2019

Extraction of fabrication documents is very important because it provides information related to tasks of fabrication and construction. Therefore, in the case of a prefabricated member such as a steel structure, it is necessary to improve the productivity of fabrication documents through 3D BIM. However, research and evidence data on direct comparison analysis of 3D BIM-based documents extraction versus 2D CAD-based documents extraction are hard to find. Thus, this study focuses on productivity analysis of 3D BIM based fabrication documents extraction. In this study, the productivity data of fabrication documents extraction for module construction of EPC project was analyzed. For the productivity analysis, a case study on the fabrication documents of Module A (1,965 sheets) and Module B (1,216 sheets) was conducted. Fabrication documents for each module include general arrangement drawing, assembly drawing, single part drawing and single plate drawing. Comparison of 2D CAD based fabrication documents extraction and 3D BIM based fabrication documents extraction, the productivity for the entire work was improved from 17 hours to 16 hours for Module A and 12 hours to 7 hours for Module B. Especially, the productivity of the assembly drawings, which occupies a large part of the fabrication documents, was improved by about 48.75% from the total time required from 281 hours to 144 hours.