• Geomechanics and Engineering
• /
• v.30 no.3
• /
• pp.247-258
• /
• 2022

A field velocity resistivity probe (FVRP) can measure compressional waves, shear waves and electrical resistivity in boreholes. The objective of this study is to perform the soil classification through a machine learning technique through elastic wave velocity and electrical resistivity measured by FVRP. Field and laboratory tests are performed, and the measured values are used as input variables to classify silt sand, sand, silty clay, and clay-sand mixture layers. The accuracy of k-nearest neighbors (KNN), naive Bayes (NB), random forest (RF), and support vector machine (SVM), selected to perform classification and optimize the hyperparameters, is evaluated. The accuracies are calculated as 0.76, 0.91, 0.94, and 0.88 for KNN, NB, RF, and SVM algorithms, respectively. To increase the amount of data at each soil layer, the synthetic minority oversampling technique (SMOTE) and conditional tabular generative adversarial network (CTGAN) are applied to overcome imbalance in the dataset. The CTGAN provides improved accuracy in the KNN, NB, RF and SVM algorithms. The results demonstrate that the measured values by FVRP can classify soil layers through three kinds of data with machine learning algorithms.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 1997.04a
• /
• pp.8-11
• /
• 1997

This study makes SrTiO$_{3}$ with nonpolarity among ferroelectrics by RF sputtering as dielectric layer, produces thin film of Si/SrTiO$_{3}$ and Si/Ti/SrTiO$_{3}$ of MOS structure using Ti as buffer layer, measures and examines the electrical features with optical refractive index, absorption rate, permittivity, photon energy and as a result, ferroelectrics oscillation occurrs by the interaction within a film by light temperature and the absorption of thin film with Ti as buffer layer is increased. It is found that the pea\ulcorner of permittivity value of Ti/SrTiO$_{3}$ thin film has low values and is appeared late and as dipole which is found in dielectric is shown, the experiment satisfies the theory In the nature of permittivity by photon energy, imaginary value is higher and current variation slope of thin film of thickness SrTiO$_{3}$ has lower values in reverse bias.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.2
• /
• pp.25-31
• /
• 2011

Principal component analysis (PCA) is a well-known method for dimensionality reduction and feature extraction. Although PCA has been applied in many areas successfully, it is sensitive to outliers due to the use of sum-square-error. Several variants of PCA have been proposed to resolve the noise sensitivity and, among the variants, improved robust fuzzy PCA (RF-PCA2) demonstrated promising results. RF-PCA2, however, still can fall into a local optimum due to equal initial membership values for all data points. Another reason comes from the fact that RF-PCA2 is based on sum-square-error although fuzzy memberships are incorporated. In this paper, a variant of RF-PCA2 called RF-PCA3 is proposed. The proposed algorithm is based on the objective function of RF-PCA2. RF-PCA3 augments RF-PCA2 with the objective function of PCA and initial membership calculation using data distribution, which make RF-PCA3 to have more chance to converge on a better solution than that of RF-PCA2. RF-PCA3 outperforms RF-PCA2, which is demonstrated by experimental results.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.37 no.1
• /
• pp.8-18
• /
• 2000

We presented a BGA(Ball Grid Array) package for RF circuit modules and extracted its electrical parameters. As the frequency of RF system devices increases, the effect of its electrical parasitics in the wireless communication system requires new structure of RF circuit modules because of its needs to be considered of electrical performance for minimization and module mobility. RF circuit modules with BGA packages can provide some advantages such as minimization, shorter circuit routing, and noise improvement by reducing electrical noise affected to analog and digital mixed circuits, etc. We constructed a BGA package of ITS(Intelligent Transportation System) RF module and measured electrical parameters with a TDR(Time Domain Reflectometry) equipment and compared its electrical parasitic parameters with PCB RF circuits. With a BGA substrate of 3${\times}$3 input and output terminals, we have found that self capacitance of BGA solder ball is 68.6fF, and self inductance 146pH, whose values were reduced to 34% and 47% of the value of QFP package structure. S11 parameter measurement with a HP4396B Network Analyzer showed the resonance frequency of 1.55GHz and the loss of 0.26dB. Routing length of the substrate was reduced to 39.8mm. Thus, we may improve electrical performance when we use BGA package structures in the design of RF circuit modules.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.38 no.10
• /
• pp.687-698
• /
• 2001

This paper presents a three dimensional stacked pad area away (PAA) package configuration as an implementation method of radio frequency (RF) circuits. 224MHz RF circuits of intelligence traffic system(ITS) were constructed with the stacked PAA RF pakage configuration. In the process of manufacturing the stacked PAA RF pakage, RF circuits were partitioned to subareas following their function and operating frequency. Each area of circuits separated to each subunits. The operating characteristics of RF PAA package module and the electrical properties of each subunits were examined. The measurement of electrical parameters for solder balls which were interconnects for stacked PAA RF packages showed that the parasitic capacitance and inductance were 30fF and 120pH, respectively, which might be negligible in PAA RF packaging system. HP 4396B network/spectrum analyzer revealed that the amplification gain of a receiver and transmitter at 224 MHz was 22dB and 27dB, respectively. The gain was 3dB lower than designed values. The difference was probably generated from fabrication process of the circuits by employing commercial standard

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.28 no.3
• /
• pp.572-578
• /
• 1999

This study was conducted to investigate processing condition and characteristics of chestnut paste. The kinds of chestnut powder processed with blanching and drying of raw material were four named RH(not blanched, hot air dried), RF(not blanched, freeze dried), BH(blanched, hot air dried) and BF(blanched, freeze dried). Blanching affected the reduction of drying time in chestnut. Water absorption index of the blanched samples were higher than the nonblanched. Blanching affected the viscosity of pastes when water was added to process paste also, but drying methods did not affected to it. The proper ratio of water to the powder to process paste was 1.3 to 1.5 times in RH and RF, whereas 2.7 times in BH and BF by sensory evaluation. Soluble tannin content of paste was higher in RF and RH paste than BF and BH. Vitamin C content was the highest(88.49mg/100g) in RF paste and reducing sugar content was the highest in RF paste. Hunter's L and a values were the highest in BF and RH pastes, respectively, among the all paste samples. Volatile compounds detected from chestnutpastes were hydrocarbons, alcohols, phenols, ketones. The major volatile compound in all the pastes was 2,6 bis(1,1 dimethylethyl) 4 methyl phenol.

• Journal of The Korean Society of Emergency Medicine
• /
• v.29 no.5
• /
• pp.455-464
• /
• 2018

Objective: Machine learning is not yet widely used in the medical field. Therefore, this study was conducted to compare the performance of preexisting severity prediction models and machine learning based models (random forest [RF], gradient boosting [GB]) for mortality prediction in pneumonia patients. Methods: We retrospectively collected data from patients who visited the emergency department of a tertiary training hospital in Seoul, Korea from January to March of 2015. The Pneumonia Severity Index (PSI) and Sequential Organ Failure Assessment (SOFA) scores were calculated for both groups and the area under the curve (AUC) for mortality prediction was computed. For the RF and GB models, data were divided into a test set and a validation set by the random split method. The training set was learned in RF and GB models and the AUC was obtained from the validation set. The mean AUC was compared with the other two AUCs. Results: Of the 536 investigated patients, 395 were enrolled and 41 of them died. The AUC values of PSI and SOFA scores were 0.799 (0.737-0.862) and 0.865 (0.811-0.918), respectively. The mean AUC values obtained by the RF and GB models were 0.928 (0.899-0.957) and 0.919 (0.886-0.952), respectively. There were significant differences between preexisting severity prediction models and machine learning based models (P<0.001). Conclusion: Classification through machine learning may help predict the mortality of pneumonia patients visiting the emergency department.

• Korean Journal of Materials Research
• /
• v.22 no.2
• /
• pp.86-90
• /
• 2012

Insoluble catalytic electrodes were fabricated by RF magnetron sputtering of Pt on Ti substrates and the performance of seawater electrolysis was compared in these electrodes to that is DSA electrodes. The Pt-sputtered insoluble catalytic electrodes were nearly 150 nm-thick with a roughness of $0.18{\mu}m$, which is 1/660 and 1/12 of these values for the DSA (dimensionally stable anodes) electrodes. The seawater electrolysis performance levels were determined through measurements of the NaOCl concentration, which was the main reaction product after electrolysis using artificial seawater. The NaOCl concentration after 2 h of electrolysis with artificial seawater, which has 3.5% NaCl normally, at current densities of 50, 80 and 140 mA/$cm^2$ were 0.76%, 1.06%, and 2.03%, respectively. A higher current density applied through the electrodes led to higher electrolysis efficiency. The efficiency reached nearly 58% in the Pt-sputtered samples after 2 h of electrolysis. The reaction efficiency of DSA showed higher values than that of the Pt-sputtered insoluble catalytic electrodes. One plausible reason for this is the higher specific surface area of the DSA electrodes; the surface cracks of the DSAs resulted in a higher specific surface area and higher reaction sites. Upon the electrolysis process, some Mg- and Ca-hydroxides, which were minor components in the artificial seawater, were deposited onto the surface of the electrodes, resulting in an increase in the electrical resistances of the electrodes. However, the extent of the increase ranged from 4% to 7% within an electrolysis time of 720 h.

• Journal of Biomedical Engineering Research
• /
• v.19 no.2
• /
• pp.143-152
• /
• 1998

In this paper, we present the performances of a Doppler system using single channel RF(Radio Frequency) sampling. This technique consists of undersampling the ultrasonic blood backscattered RF signal on a single channel. Conventional undersampling method in Doppler imaging system have to use a minimum of two identical parallel demodulation channels to reconstruct the multigate analytic Doppler signal. However, this system suffers from hardware complexity and problem of unbalance(gain and phase) between the channels. In order to reduce these problems, we have realized a multigate pulsed Doppler system using undersampling on a single channel, It requires sampling frequency at $4f_o$(where $f_o$ is the center frequency of the transducer) and 12bits A/D converter. The proposed " single-Channel RF Sampling" method aims to decrease the required sampling frequency proportionally to $4f_o$/(2k+1). To show the influence of the factor k on the measurements, we have compared the velocity profiles obtained in vitro and in vivo for different intersequence delays time (k=0 to 10). We have used a 4MHz center frequency transducer and a Phantom Doppler system with a laminar stationary flow. The axial and volumetric velocity profiles in the vessel have been computed according to factor k and have been compared. The influence of the angle between the ultrasonic beam and the flow axis direction, and the fluid viscosity on the velocity profiles obtained for different values of k factor is presented. For experiment in vivo on the carotid, we have used a data acquisition system with a sampling frequency of 20MHz and a dynamic range of 12bits. We have compared the axial velocity profiles in systole and diastole phase obtained for single channel RF sampling factor.ng factor.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.35 no.12
• /
• pp.560-566
• /
• 1986

In the design of an RF discharge system, the electrical equivalence of the gas discharge must be known. With this knowledge, one can design a suitable matching network for a maximum power transfer from the RF generator into the discharge. For this purpose, an experiment has been conducted in which the electrical impedance (conductance and capacitance) was determined as a function of power. In parallel with this, a detailed theoretical analysis has been done and the results are in accord with those of our experiment. Design equations are also given for a simple matching network, and a design example is presented to demonstrate its application. During the actual operation of an RF discharge system, however, it has been often observed that the reflected power tends to vary in small values due to the changes in the impedance of the system. This problem can be relieved by adding an automatic impedance matching circuit to the system and this paper presents such an automatic impedance matching network.