• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.7
• /
• pp.307-314
• /
• 2022

Recently, researches using deep learning-based models are being actively conducted to replace statistical-based time series forecast techniques to predict electric power demand. The result of analyzing the researches shows that the performance of the LSTM-based prediction model is acceptable, but it is not sufficient for long-term regional-wide power demand prediction. In this paper, we propose a WaveNet deep learning model to predict electric power demand 24-hour-ahead with temperature data in order to achieve the prediction accuracy better than MAPE value of 2% which statistical-based time series forecast techniques can present. First of all, we illustrate a delated causal one-dimensional convolutional neural network architecture of WaveNet and the preprocessing mechanism of the input data of electric power demand and temperature. Second, we present the training process and walk forward validation with the modified WaveNet. The performance comparison results show that the prediction model with temperature data achieves MAPE value of 1.33%, which is better than MAPE Value (2.33%) of the same model without temperature data.

• Journal of information and communication convergence engineering
• /
• v.5 no.2
• /
• pp.98-103
• /
• 2007

Long term Electrocardiogram (ECG) [1] analysis plays a key role in heart disease analysis. A combined detection of QRS-complex and P-wave in ECG signal for ubiquitous healthcare system was designed and implemented which can be used as an advanced warning device. The ECG features are used to detect life-threating arrhythmias, with an emphasis on the software for analyzing QRS complex and P-wave in wireless ECG signals at server after receiving data from base station. Based on abnormal ECG activity, the server will transfer alarm conditions to a doctor's Personal Digital Assistant (PDA). Doctor can diagnose the patients who have survived from cardiac arrhythmia diseases.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.7 no.3
• /
• pp.152-157
• /
• 2004

Wave energy distribution along the Korean coastal sea area was analysed based on the calculated wave data at KORDI. The wave data for the analysis is for the last 24 years (1979∼2002) and the model is HYPA and WAM using known wind field. The wave energy or wave power was evaluated based on the linear wave theory with a simple wave period assumption. The results shed some idea on the amount of usable wave energy and the sites of higher efficiency. It is fair to say that 3kw/m wave energy is easily observable and 10kw/m is frequently available depending on the season and location. The south west region of Jeju island is believed to have the highest overall wave energy density.

• Journal of the Korea Convergence Society
• /
• v.10 no.9
• /
• pp.229-236
• /
• 2019

This is an exploratory study examining factors associated with awareness of the National Long Term Care Insurance in Korea. The researchers also examined the differences in factors based on their age, between the middle-aged group(45-64 years of age) and the elderly group(65 years and older). The 6th wave of Korean Longitudinal Study of Ageing(KLoSA) was used for secondary data analysis. Results indicated that for the middle-aged, gender, volunteer participation, ADL, IADL, and depression were related to their awareness of the long term care insurance. However, for the elderly, social capital factors were significantly related to their awareness of the insurance. Age and depression were also significant factors associated with the awareness level of the long term care insurance among the elderly. Based on the findings, implications for social welfare policy are discussed.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.29 no.3
• /
• pp.129-138
• /
• 2017

The coastal wave environment is a very important factor that directly affects the change of coastal topography, the habitat of marine life, and the design of offshore structures. In recent years, changes in the wave environment due to climate change are expected, and a trend analysis of the wave environment using available data sets is required. In this paper, significant wave heights which are measured at six ocean buoys (Deokjeokdo, Oeyeondo, Chibaldo, Marado, Pohang, Ullengdo) have been used to analyze long-term trend of normal waves. In advance, the outlier of measured data by Korea Meteorological Administration have been removed using Rosner test. And Pearson correlation analysis between the measured data and ECMWF reanalysis data has been conducted. As a results, correlation coefficient between two data were 0.849~0.938. Meanwhile, Mann-Kendall test has been used to analyze the long-term trend of normal waves. As a results, it was found that there were no trend at Deokjeokdo, Oeyeondo and Chibaldo. However, Marado, Pohang and Ullengdo showed an increasing tendency.

• Steel and Composite Structures
• /
• v.43 no.6
• /
• pp.809-819
• /
• 2022

This paper proposes a method to predict the deflection of prestressed concrete (PC) beams with corrugated steel web (CSW) under constant load concerning time-dependent variation in concrete material. Over time, the top and bottom concrete slabs subjected to asymmetric compression experience shrinkage and creep deformations. Here, the classical Euler-Bernoulli beam theory assumption that the plane sections remain plane is not valid due to shear deformation of CSW. Therefore, this study presents a method based on the first-order shear deformation to find the long-term deflection of the composite beams under bending by considering time effects. Two experimental prestressed beams of this type were monitored under their self-weight over time, and the theoretical results were compared with those data. Additionally, 3D analytical models of the experimental beams were used according to material properties, and the results were compared with two previous cases. There was good consistency between the analytical and numerical results with low error, which increased by wave radius. It is concluded that the proposed method could reliably be used for design purposes.

• The Bulletin of The Korean Astronomical Society
• /
• v.37 no.2
• /
• pp.125.1-125.1
• /
• 2012

The wave number 4 (wave-4) and wave number 3 (wave-3) longitudinal structures in the thermospheric neutral mass density are understood as tidal structures driven by diurnal eastward-propagating zonal wave number 3 (DE3) and wave number 2 (DE2) tides, respectively. However, those structures have been identified using data from limited time periods, and the consistency and recurrence of those structures have not yet been examined using long-term observation data. We examine the persistence of those structures by analyzing the neutral mass density data for the years 2001-2008 taken by the CHAllenging Minisatellite Payload (CHAMP) satellite. During years of low solar activity, the amplitude of the wave-4 structure is pronounced during August and September, and the wave-4 phase shows a consistent eastward phase progression of $90^{\circ}$ within 24 h local time in different months and years. During years of high solar activity, the wave-4 amplitude is small and does not show a distinctive annual pattern, but the tendency of the eastward phase shift at a rate of $90^{\circ}$/24 h exists. Thus the DE3 signature in the wave-4 structure is considered as a persistent feature. The wave-3 structure is a weak feature in most months and years. The amplitude and phase of the wave-3 structure do not show a notable solar cycle dependence. Among the contributing tidal modes to the wave-3 structure, the DE2 amplitude is most pronounced. This result may suggest that the DE2 signature, although it is a weak signature, is a perceivable persistent feature in the thermosphere.

• Journal of the Korean earth science society
• /
• v.36 no.1
• /
• pp.16-26
• /
• 2015

To investigate the applicability of physical prospecting technique in soft ground assessment, the resistivity monitoring data of 6 months are acquired. The Multichannel Analysis Surface Wave (MASW) has been additionally performed to identify the shear wave velocity and strength distribution of soft ground. Moreover, by using the Cone Penetration Test (CPT) and laboratory tests of drilling samples, a relationship with the physical prospect data is checked and the reliability of the physical prospect data is increased. Through these activities, the behavior patterns of soft soil are identified by long term monitoring, and the significant relationship between the shear wave velocity and laboratory tests has been confirmed, both of which can be useful in the surface wave exploration to evaluate the strength of soft ground. Finally, using the geostatistical method, 3-dimensional soil base distribution images are obtained about the combined physical prospecting data with heterogeneous data. Through the studies, the nature of entire area can be determined by long term resistivity monitoring for the soft ground assessment in wider area. It would be more economic and reliable if additional exploring and drilling samples can be analyzed, which can reinforce the assessment.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.15 no.4
• /
• pp.357-362
• /
• 2012

Despite the Wave observations data is very important information to human life at sea, the technology development and research for wave equipments are lacking. In this study, the wave observation system using GPS was evaluated the quality of wave observation data by comparing of long-term observations. The result of the comparison of the acceleration sensor (Hippy-40) and GPS sensor (Mose-1000), the correlation coefficient of the significant wave height and significant wave periods is 0.997 and 0.990 respectively. Also in case of BIAS, the significant wave height is 0.014 m, the significant wave period is -0.212 sec. It makes no significant differences whether the acceleration sensor (Hippy-40) and GPS sensor (Mose-1000). These results of the wave observation data using GPS quality will be evaluated as very good.

• Journal of the Korea Society for Simulation
• /
• v.30 no.4
• /
• pp.1-8
• /
• 2021

Deep learning is one of the most widely accepted methods for the forecasting of time series data which have the complexity and non-linear behavior. In this paper, we investigate the modification of a state-of-art WaveNet deep learning architecture and walk forward validation (WFV) in order to forecast electric power consumption data 24-hour-ahead. WaveNet originally designed for raw audio uses 1D dilated causal convolution for long-term information. First of all, we propose a modified version of WaveNet which activates real numbers instead of coded integers. Second, this paper provides with the training process with tuning of major hyper-parameters (i.e., input length, batch size, number of WaveNet blocks, dilation rates, and learning rate scheduler). Finally, performance evaluation results show that the prediction methodology based on WFV performs better than on the traditional holdout validation.