• Journal of information and communication convergence engineering
• /
• v.21 no.1
• /
• pp.82-89
• /
• 2023

Various machine-learning models may yield high predictive power for massive time series for time series prediction. However, these models are prone to instability in terms of computational cost because of the high dimensionality of the feature space and nonoptimized hyperparameter settings. Considering the potential risk that model training with a high-dimensional feature set can be time-consuming, we evaluate a feature-importance-based feature selection method to derive a tradeoff between predictive power and computational cost for time series prediction. We used two machine learning techniques for performance evaluation to generate prediction models from a retail sales dataset. First, we ranked the features using impurity- and Local Interpretable Model-agnostic Explanations (LIME) -based feature importance measures in the prediction models. Then, the recursive feature elimination method was applied to eliminate unimportant features sequentially. Consequently, we obtained a subset of features that could lead to reduced model training time while preserving acceptable model performance.

• ETRI Journal
• /
• v.30 no.2
• /
• pp.227-237
• /
• 2008

In this paper, an algorithm that provides absolute and proportional differentiation of packet delays is proposed with the objective of enhancing quality of service in future packet networks. It features an adaptive scheme that adjusts the target delay for every time slot to compensate the deviation from the target delay, which is caused by prediction error on the traffic to arrive at the next time slot. It predicts the traffic to arrive at the beginning of a time slot and measures the actual arrived traffic at the end of the time slot. The difference between them is utilized by the delay control operation for the next time slot to offset it. Because the proposed algorithm compensates the prediction error continuously, it shows superior adaptability to bursty traffic and exponential traffic. Through simulations we demonstrate that the algorithm meets the quantitative delay bounds and is robust to traffic fluctuation in comparison with the conventional non-adaptive mechanism. The algorithm is implemented with VHDL on a Xilinx Spartan XC3S1500 FPGA, and the performance is verified under the test board based on the XPC860P CPU.

• Journal of the Korea Convergence Society
• /
• v.11 no.10
• /
• pp.387-392
• /
• 2020

This study was to investigate the relationship of BMI, sleep time and experience of oral diseases in adolescents. We want to help develop basic data for improving oral health of adolescents. According to the sample design of the Youth Health Behavior online survey, a total of 57,303 adolescents were analyzed for frequency of composite samples, x2-test of composite samples, and logistic regression of composite samples, and the IBM SPSS Statistics 20.0 program was used and the significance level was 0.05. Results, BMI was associated with bad breath, and sleep time was associated with tooth break, pain, bleeding, and bad breath. Therefore, BMI and sleep time should be considered for the management and prevention of oral diseases in adolescents.

• ETRI Journal
• /
• v.33 no.4
• /
• pp.528-536
• /
• 2011

In this paper, we analyze the location accuracy of real-time locating systems (RTLSs) in multipath environments in which the RTLSs comply with the ISO/IEC 24730-2 international standard. To analyze the location error of RTLS in multipath environments, we consider a direct path and indirect path, in which time and phase are delayed, and also white Gaussian noise is added. The location error depends strongly on both the noise level and phase difference under a low signal-to-noise ratio (SNR) regime, but only on the noise level under a high SNR regime. The phase difference effect can be minimized by matching it to the time delay difference at a ratio of 180 degrees per 1 chip time delay (Tc). At a relatively high SNR of 10 dB, a location error of less than 3 m is expected at any phase and time delay value of an indirect signal. At a low SNR regime, the location error range increases to 8.1 m at a 0.5 Tc, and to 7.3 m at a 1.5 Tc. However, if the correlation energy is accumulated for an 8-bit period, the location error can be reduced to 3.9 m and 2.5 m, respectively.

• Journal of the Korean Society of Industry Convergence
• /
• v.22 no.5
• /
• pp.491-497
• /
• 2019

Dissimilar friction welding were produced using 15 mm diameter solid bar in superalloy(Alloy718) to chrome molybdenum steel(SCM440) to investigate their mechanical properties. Consequently, optimal welding conditions were n=2000 rpm, HP=60 MPa, UP=120 MPa, HT=10 sec and UT=10 sec when the metal loss(Mo) is 3.5 mm. Acoustic Emission(AE) technique was applied to analyze the dissimilar friction welding of Alloy718 and SCM440. The relationship between the AE parameters and dissimilar friction welding of both material was discussed. In the case of heating time of 6 sec, 10 sec, 14 sec and 20 sec, 5 AE events per 0.5 seconds and energy about $2.7{\times}10^{10}$ were exhibited in heating time. In upsetting time, resulting in various numbers of events per second and very low energy. The frequency range of the signal generated during the heating time was about 200 kHz. However, the upsetting time resulted in a wide range of signals from very low frequency to high frequency of 500 kHz due to rapid plasticity of the material.

• Current Photovoltaic Research
• /
• v.4 no.1
• /
• pp.16-20
• /
• 2016

$Cu_2ZnSnS_4$ (CZTS) thin films were fabricated by successive electrodeposition of layers of precursor elements followed by sulfurization of an electrodeposited Cu-Zn-Sn precursor. In order to improve quality of the CZTS films, we tried to optimize the deposition condition of absorber layers. In particular, I have conducted optimization experiments by changing the Cu-layer deposition time. The CZTS absorber layers were synthesized by different Cu-layer conditions ranging from 10 to 16 minutes. The sulfurization of Cu/Sn/Zn stacked metallic precursor thin films has been conducted in a graphite box using rapid thermal annealing (RTA). The structural, morphological, compositional, and optical properties of CZTS thin films were investigated using X-ray diffraction (XRD), Field emission scanning electron microscopy (FE-SEM), Raman spectroscopy, and X-ray Flourescenece Spectrometry (XRF). Especially, the CZTS TFSCs exhibits the best power conversion efficiency of 4.62% with $V_{oc}$ of 570 mV, $J_{sc}$ of $18.15mA/cm^2$ and FF of 45%. As the time of deposition of the Cu-layer to increasing, the properties were confirmed to be systematically changed. And we have been discussed in detail below.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.2
• /
• pp.90-97
• /
• 2020

Recently, with the growth of mixed reality industrial infrastructure, relevant convergence research has been proposed. For real-time mixed reality services such as remote video conferencing, the research on real-time acquisition-process-transfer methods is required. This paper aims to implement an AR remote rendering method of volumetric 3D video data. We have proposed and implemented two modules; one, the parsing module of the volumetric 3D video to a game engine, and two, the server rendering module. The result of the experiment showed that the volumetric 3D video sequence data of about 15 MB was compressed by 6-7%. The remote module was streamed at 27 fps at a 1200 by 1200 resolution. The results of this paper are expected to be applied to an AR cloud service.

• Journal of the Korea Convergence Society
• /
• v.6 no.5
• /
• pp.287-294
• /
• 2015

The purpose of this study, was Let's examine the exposure dose at the time of cerebral blood flow CT scan of acute ischemic stroke patients. In particular, long-term high doses of radiation sensitive organs and we Measured using phantom and a glass dosimeter. Apply the existing protocol suggested by the manufacturer (fixed time delay technique) and the proposed new convergence protocol (bolus tracking technique), reporting to measure the dose, dose reduction was to prepare the way. Results up to 39.8% as compared to the existing protocols in a new suggested convergence protocol, a minimum of 5.8% was long-term dose is reduced. Test dose of $CDTI_{vol}$ and DLP values decreased 25%, respectively, were measured at less than recommended dose. Try checking the protocol set out in the existing based on the analysis result of the above, by applying the proposed new convergence protocol by reducing the dose would have to contribute to improved public health. It is believed to be research continues to find the optimum protocol in the other tests.

• Composites Research
• /
• v.33 no.6
• /
• pp.365-370
• /
• 2020

The icing formation at aircraft occur problems such as increasing weight of the body, fuel efficiency reduction, drag reduction, the error of sensor, and etc. The viscosity of polyurethane (PU) topcoat was measured at 60℃ in real time to set the pre-curing time. SiO2 nanoparticles were dispersed in ethanol using ultra-sonication method. The SiO2/ethanol solution was sprayed on PU topcoat that was not cured fully with different pre-curing conditions. Surface roughness of SiO2/PU nanocomposites were measured using surface roughness tester and the surface roughness data was visualized using 3D mapping. The adhesion property between SiO2 and PU topcoat was evaluated using adhesion pull-off test. The static contact angle was measured using distilled water to evaluate the hydrophobicity. Finally, the pre-curing time of PU topcoat was optimized to exhibit the hydrophobicity of SiO2/PU topcoat.

• Journal of the Korea Convergence Society
• /
• v.9 no.11
• /
• pp.153-159
• /
• 2018

The purpose of this study is to grasp the internet use time that young people use for purposes other than learning purpose, to grasp the perceived status of the youth according to internet use time and to grasp the interrelationships of them. Using the 2016 youth health behavior online survey, the odds ratios and 95% confidence intervals of perceived status according to internet use time were calculated by binary logistic regression analysis. The main results are as follows. In perceived health and perceived oral health the odds ratios of perceived who feel that they are perceived and unhealthy as the time spent using the Internet increased significantly compared to those who did not use the Internet for learning purposes. In the perceived body type, the odds ratio of being overweight increased significantly with longer internet use time. The odds ratios of perceived happiness were 1.19 times (CI = 1.10-1.30) higher than the perceived expectation of unhappiness when using the Internet for over 300 minutes. The use of the internet for a long time other than the purpose of learning may have a negative effect on the health and happiness of the youth, so we think that the recommended time for using the internet is necessary.