• The Korean Journal of Applied Statistics
• /
• v.34 no.5
• /
• pp.761-772
• /
• 2021

Simulation results for the comparison of estimators of interest are usually reported in tables or plots. However, if the simulations are conducted under various conditions for many estimators, the comparison can be difficult to be made with tables or plots. Furthermore, for algorithms that take a long time to run, the number of iterations of the simulation is costly to to be increased. The analysis of simulation results using regression models allows us to compare the estimators more systematically and effectively. Since variances in performance measures may vary depending on the simulation conditions and estimators, the heteroscedasticity of the error term should be allowed in the regression model. And multiple comparisons should be made because multiple estimators should be compared simultaneously. We introduce background theories of heteroscedasticity and multiple comparisons in the context of analyzing simulation results. We also present a concrete example.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.1957-1980
• /
• 2021

The significant aim of this research has always been to evaluate the mechanism for efficient and inherently aware usage of vitality in-home devices, thus improving the information of smart metering systems with regard to the usage of selected homes and the time of use. Advances in information processing are commonly used to quantify gigantic building activity data steps to boost the activity efficiency of the building energy systems. Here, some smart data mining models are offered to measure, and predict the time series for energy in order to expose different ephemeral principles for using energy. Such considerations illustrate the use of machines in relation to time, such as day hour, time of day, week, month and year relationships within a family unit, which are key components in gathering and separating the effect of consumers behaviors in the use of energy and their pattern of energy prediction. It is necessary to determine the multiple relations through the usage of different appliances from simultaneous information flows. In comparison, specific relations among interval-based instances where multiple appliances use continue for certain duration are difficult to determine. In order to resolve these difficulties, an unsupervised energy time-series data clustering and a frequent pattern mining study as well as a deep learning technique for estimating energy use were presented. A broad test using true data sets that are rich in smart meter data were conducted. The exact results of the appliance designs that were recognized by the proposed model were filled out by Deep Convolutional Neural Networks (CNN) and Recurrent Neural Networks (LSTM and GRU) at each stage, with consolidated accuracy of 94.79%, 97.99%, 99.61%, for 25%, 50%, and 75%, respectively.

• Smart Structures and Systems
• /
• v.26 no.6
• /
• pp.693-701
• /
• 2020

The conventional Kalman Filter (KF) provides a promising way for structural state estimation. However, the physical parameters of structural systems or models should be available for the estimation. Moreover, it is not applicable when the loadings applied to the structures are unknown. To circumvent the aforementioned limitations, a two-stage KF with unknown input approach is proposed for the simultaneous identification of structural parameters and unknown loadings. In stage 1, a modified observation equation is employed. The structural state vector is estimated by KF on the basis of structural parameters identified at the previous time-step. Then, the unknown input is identified by Least Squares Estimation (LSE). In stage 2, based on the concept of sensitivity matrix, the structural parameters are updated at the current time-step by using the estimated structural states obtained from stage 1. The effectiveness of the proposed approach is numerically validated via a five-story shearing model under random and earthquake excitations. Shaking table tests on a five-story structure are also employed to demonstrate the performance of the proposed approach. It is demonstrated from numerical and experimental results that the proposed approach can be used for the identification of parameters of structure and the external force applied to it with acceptable accuracy.

• Imaging Science in Dentistry
• /
• v.51 no.2
• /
• pp.167-174
• /
• 2021

Purpose: Sex determination can be done by morphological analysis of different parts of the body. The mastoid region, with its anatomical location at the skull base, is ideal for sex identification. Statistical shape analysis provides a simultaneous comparison of geometric information on different shapes in terms of size and shape features. This study aimed to investigate the geometric morphometry of the inter-mastoid triangle as a tool for sex determination in the Iranian population. Materials and Methods: The coordinates of 5 landmarks on the mastoid process on the 80 cone-beam computed tomographic images(from individuals aged 17-70 years, 52.5% female) were registered and digitalized. The Cartesian x-y coordinates were acquired for all landmarks, and the shape information was extracted from the principal component scores of generalized Procrustes fit. The t-test was used to compare centroid size. Cross-validated discriminant analysis was used for sex determination. The significance level for all tests was set at 0.05. Results: There was a significant difference in the mastoid size and shape between males and females(P<0.05). The first 2 components of the Procrustes shape coordinates explained 91.3% of the shape variation between the sexes. The accuracy of the discriminant model for sex determination was 88.8%. Conclusion: The application of morphometric geometric techniques will significantly impact forensic studies by providing a comprehensive analysis of differences in biological forms. The results demonstrated that statistical shape analysis can be used as a powerful tool for sex determination based on a morphometric analysis of the inter-mastoid triangle.

• Journal of Korea Trade
• /
• v.24 no.7
• /
• pp.38-53
• /
• 2020

Purpose - A financial crash triggers asset fire sales by foreign investors and, as a consequence, the price of domestic assets severely decreases. Domestic investors take advantage of these low prices by replacing foreign assets with domestic assets, which helps to alleviate the liquidity shock caused by foreigners. However, is the amount of capital retrenchment by domestic investors sufficient to protect the Korean economy from capital stop by foreign investors during financial crisis? This paper answers this question and suggests the implications of this phenomenon for the Korean economy. Design/methodology - We estimate the associations between capital stop and retrenchment and various financial crises such as banking, currency, debt, and inflation crises using the complementary log-log model. Specifically, we use data of gross capital flows to differentiate between the role of foreign and domestic investors in financial markets. Capital stop and retrenchment designate a sharp decrease in gross capital inflows and outflows, respectively. Findings - Capital stop is significantly associated with financial crises, especially currency and debt crises. This implies that increased risk aversion during times of financial turmoil encourages foreign investors to retrench their investments, worsening liquidity shocks. Conversely, capital retrenchment is not significantly associated with such crises. The results show that, although financial crises reduce gross capital outflows, the reduction is not as large as that with capital inflows. Originality/value - The contribution of this paper is threefold. First, this study investigates how domestic investors behave during times of financial distress by studying gross capital flows-not net capital flows. Second, we concentrate on sharp changes in capital flows during crises. Third, we examine the associations between capital stop and retrenchment and financial crises in general, not specific events.

• Asia-Pacific Journal of Business
• /
• v.13 no.1
• /
• pp.103-123
• /
• 2022

Purpose - This study investigates the effects of earnings management, related party transactions between chaebol affiliates on earnings management and ESG score on their profitability using return on assets (ROA). Design/Methodology/Approach - We use data including ESG (Environmental, Social, and Corporate Governance) score of the Korea Corporate Governance Service(KCGS), and financial data of 10,145 firm-year observations from the Total Solution 2000 (TS 2000) and Korea Companies-Information Service (KOKOInfo), and apply the finite lagged models to investigate the long-term effects of related party transactions between chaebol affiliates of earnings management on ESG scores and corporate performance. Furthermore, to take into consideration the simultaneous mutual effects on each other of main variables, we introduce finite distributed lags of five years. Findings - First, ESG-rated firms have a higher total asset return than non-ESG-rated firms. Second, chaebol firms have a higher profitability than non-chaebol firms. Third, profit management of related party transactions between affiliates within a chaebol has a positive effect on the short-term profitability and a negative effect on the long-term profitability. Fourth, chaebol ESG firms have a lower impact on profitability due to rating up (down) than non-chaebol ESG firms. Research Implications or Originality - Based on the above results, it can be concluded that firms used related party transactions for earnings management, the effects of related party transactions change over time, and chaebol firms manipulate earnings through related party transactions and ESG scores.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.3
• /
• pp.527-534
• /
• 2023

Triple modular redundancy (TMR) systems can continue their mission by virtue of their structural redundancy even if one processor is attacked by faults. In this paper, we propose a new fault tolerance strategy by introducing checkpoints into the TMR system in which data saving and fault detection processes are separated while they corporate together in the conventional checkpoints. Faults in one processor are tolerated by synchronizing the state of three processors upon detecting faults. Simultaneous faults occurring to more than one processor are tolerated by re-executing the task from the latest checkpoint. We propose the checkpoint placement and fault detection strategy to maximize the probability of successful execution of a task within the given deadline. We develop the Markov chain model for the TMR system having the proposed checkpoint strategy, and derive the optimal fault detection and checkpoint interval.

• Journal of the Korean Geotechnical Society
• /
• v.22 no.7
• /
• pp.45-54
• /
• 2006

Resistivity cone penetrometer test (RCPT) can be employed at a relatively low cost for in-situ delineation of subsurface contamination. While the resistivity measurement has a potential to investigate the subsurface contamination, resistivity measurements alone will lead to some degree of ambiguity in the results. In this study, capacitance measurement was incorporated into the RCPT to overcome the ambiguity inherent in electrical resistivity measurements. This study is focused on verifying the applicability of resistivity and capacitance measurements of CPT module to provide information on subsurface contaminated by heavy metal and petroleum hydrocarbon. Laboratory model tests were performed to evaluate the sensitivity of the measured resistivity and relative capacitance on the water content and different types of contaminants. Test results show that simultaneous measurement of electrical resistivity and capacitance can give more reliable information on subsurface contamination. Electrical measurements of the CPT module showed high applicability to be used in detecting saturated soils contaminated by heavy metal and diesel plume floating above the groundwater table.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.1
• /
• pp.34.4-35
• /
• 2021

We present the TESS photometry and our high-resolution spectra of the semi-detached Algol EW Boo. For an orbital period study, we collected all available times of minima including ours for the last 30 years. It is found that the eclipse timing variation of the system can be represented by a periodic oscillation of 18.5±1.0 yr plus a secular period increase with a rate of [dP/dt]_orb=-6(±3)×10^-8 d yr^-1. From our observed spectra, the effective temperature of the primary star was determined to be T_eff,1=8560±118 K. From a simultaneous analysis of the TESS light and our double-lined radial velocity curves, the absolute masses, radii, and luminosities are M₁=2.30±0.07M_⊙, M₂=0.38±0.01M_⊙, R₁=1.92±0.02 R_⊙, R₂=1.27±0.01 R_⊙, L₁=1.92±0.02 L_⊙, and L₂=0.752±0.007 L_⊙, respectively. Multiple frequency analyses were carried out for the light residuals after subtracting the binary star model. We detected a total of 75 frequencies in the region of 16.50-104.8 day-1. Our results demonstrate that the more hotter primary star of EW Boo is a δ Sct pulsator by considering its position in the δ Scuti region of the Cepheid instability strip and pulsational characteristics.

• Journal of Biomedical Engineering Research
• /
• v.44 no.6
• /
• pp.392-403
• /
• 2023

This study presents a new hybrid fNIRS-EEG system to meet the demand for a lightweight and low-cost sleep pattern monitoring device. For multiple-channel configuration, a six-channel electroencephalogram (EEG) and a functional near-infrared spectroscopy (fNIRS) system with eight photodiodes (PD) and four dual-wavelength LEDs are designed. To enhance the convenience of signal measurement, the device is miniaturized into a patch-like form, enabling simultaneous measurement on the forehead. Due to its fully integrated functionality, the developed system is advantageous for performing sleep stage classification with high-temporal and spatial resolution data. This can be realized by utilizing a two-dimensional (2D) brain activation map based on the concentration changes in oxyhemoglobin and deoxyhemoglobin during sleep stage transitions. For the system verification, the phantom model with known optical properties was tested at first, and then the sleep experiment for a human subject was conducted. The experimental results show that the developed system qualifies as a portable hybrid fNIRS-EEG sleep pattern monitoring device.