• Journal of Advanced Navigation Technology
• /
• v.28 no.1
• /
• pp.149-154
• /
• 2024

Research on particulate matter is advancing in real-time, and various methods are being studied to improve the accuracy of prediction models. Furthermore, studies that take into account various factors to understand the precise causes and impacts of particulate matter are actively being pursued. This paper trains an LSTM model using seasonal data and another LSTM model using concentration-based data. It compares and analyzes the PM_2.5 prediction performance of the two models. To train the model, weather data and air pollutant data were collected. The collected data was then used to confirm the correlation with PM_2.5. Based on the results of the correlation analysis, the data was structured for training and evaluation. The seasonal prediction model and the concentration-specific prediction model were designed using the LSTM algorithm. The performance of the prediction model was evaluated using accuracy, RMSE, and MAPE. As a result of the performance evaluation, the prediction model learned by concentration had an accuracy of 91.02% in the "bad" range of AQI. And overall, it performed better than the prediction model trained by season.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.12
• /
• pp.823-828
• /
• 2013

In this paper, it will improve in quality to adapt a right test process which is formalized from certification of TMMi Level. To do this, we suggest correlative relation through analyzing associations between TMMi and TPI next based on the previous research[10], which provides the guideline for enhancing test process level with measuring Test maturity model. Also schematize test maturity measurement through refining and improving the previous test maturity correlation metrics[6,8,9]. As one example with limited level, it shows the guideline to improve test process of one testing organization through improved correlation metrics with TMMi and TPI next.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.13 no.8
• /
• pp.583-590
• /
• 2003

For the preestimate of the vibration level of the ground next to a dwelling, a multivariate statistical analysis on the experiment data acquired from a variety of construction sites was performed, and then a new estimate model for the value of K and n that can be applied in the diagnosis of the damage was offered. The results maybe summarized as follows : First, the $K_{95}$ and n showed high correlation at P$\leq$0.05. Specially the correlation coefficient about $W_{max}$, S were higher in $K_{95}$ than in n. indicating that $K_{95}$ is generally associated with source conditions. Second, the factor analysis permitted to identify two major sources in each fraction. These sources accounted for at least 73 % of valiance of $K_{95}$. Third, the multiple regression model for the estimate of $K_{95}$ was developed from Fac1 which depend upon the source conditions and Fac2 which depend upon the transmission conditions. The n value is able to determine from the correlation relationship associated with $K_{95}$./.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.4
• /
• pp.1752-1758
• /
• 2015

This paper presents partial discharge localization in stator winding of generators using multi-conductor transmission line (MTL) and RLC ladder network models. The high-voltage (HV) winding of a 6kV/250kW generator has been modeled by MATLAB software. The simulation results of the MTL and the RLC ladder network models have been evaluated with the measurements results in the frequency domain by applying of the Pearson’s correlation coefficients. Two PD generated calibrator signals in kHz and MHz frequency range were injected into different points of generator winding and the signals simulated/measured at the both ends of the winding. For partial discharge localization in stator winding of generators is necessary to calculate the frequency spectrum of the PD current signals and then estimate the poles of the system from the calculated frequency spectrum. Finally, the location of PD can be estimated. This theory applied for the above generator and the simulation/measured results show the good correlation for PD Location for RLC ladder network and MTL models in the frequency range of kHz (10kHz<f<1MHz) and MHz (1MHz<f<5MHz) respectively.

• Bulletin of the Korean Space Science Society
• /
• 2008.10a
• /
• pp.24.2-24.2
• /
• 2008

We have examined the relative contributions of representative space weather proxies (geomagnetic aa index) to global warming (Global temperature anomaly) and compared them with that of green house effect characterized CO2 content from 1868 to 2005. For this we used Hadcrut3 temperature anomaly (Ta) data, aa index taken at two anti-podal subauroral stations (Canberra Australia and hartland England), and the CO2 data come from historical ice core records. From the comparison between Ta and aa index, we found several interesting results: (1) the linear correlation coefficient between two parameters increases until 1990 and then decreases rapidly, and (2) the scattered plots between two parameters shows different patterns before and after 1990. A partial correlation of Ta and two quantities (aa, CO2) also shows that the geomagnetic effect (aa index) is dominant until about 1990 and the CO2 effect becomes much more important after then. These results imply that the green house effect become very important since at least 1990. For a further analysis, we simply assume that Ta (total) = Ta (aa) + Ta (CO2) and made a linear regression between Ta and aa index from 1868 to 1990. A linear model is then made from the linear regression between energy consumption (a proxy of CO2 effect) and Ta (total) - Ta (aa) since 1990. This linear model makes it possible to predict the temperature anomaly in 2030, about 1 degree higher than the present temperature, which is much larger than in the previous century.

• Journal of the Korea Concrete Institute
• /
• v.12 no.6
• /
• pp.119-126
• /
• 2000

Reinforced concrete structural walls are widely known to provide an efficient lateral load resistance and drift control. However, many reported researches on them are mostly limited to the RC structural walls reinforced according to seismic details. When the pushover analysis technique is used for the prediction of inelastic behavior of frame-wall structures for the seismic evaluation of existing buildings having non-seismic details, the reliability of this analysis method should be checked by the test results. The objective of this study is to verify the correlation between the experimental and analytical responses of a high-rise reinforced concrete frame-wall structure having non-seismic details by using DRAIN-2DX program[11] and the test results performed previously[1]. It is concluded that the behavior of the frame-wall model is mainly affected by the fixed-end rotation(uplift at base) and bending deformation of the wall and that the analysis with the LINKS model[10] in DRAIN-2DX describes them with good reliability.

• Journal of Navigation and Port Research
• /
• v.37 no.5
• /
• pp.535-541
• /
• 2013

Expressways are built to provide for high levels of safety and efficiency in the movement of large traffic volumes at high speeds. However, Gyeongbu and Namhae expressways in the country which are often suffering from the transportation problems with increased import and exoprt cargo trucks including the container vehicles are the major expressways having the Busan Port as the origin and destination regions, and are required to study the expressway traffic characteristics for reducing the transportation problems. We therefore attempted to suggest the expressway density predictive model through the correlation analysis between lane occupancy and mean density at the 8-lane basic segments of the above major expressways in the country.

• ETRI Journal
• /
• v.33 no.4
• /
• pp.537-546
• /
• 2011

This paper introduces an automated method for building height recovery through the integration of high-resolution satellite images and digital vector maps. A cross-correlation matching method along the vertical line locus on the Ikonos images was deployed to recover building heights. The rational function models composed of rational polynomial coefficients were utilized to create a stereopair of the epipolar resampled Ikonos images. Building footprints from the digital maps were used for locating the vertical guideline along the building edges. The digital terrain model (DTM) was generated from the contour layer in the digital maps. The terrain height derived from the DTM at each foot of the buildings was used as the starting location for image matching. At a preset incremental value of height along the vertical guidelines derived from vertical line loci, an evaluation process that is based on the cross-correlation matching of the images was carried out to test if the top of the building has reached where maximum correlation occurs. The accuracy of the reconstructed buildings was evaluated by the comparison with manually digitized 3D building data derived from aerial photographs.

• Smart Structures and Systems
• /
• v.17 no.6
• /
• pp.1031-1053
• /
• 2016

The health conditions of in-service civil infrastructures can be evaluated by employing structural health monitoring technology. A reliable health evaluation result depends heavily on the quality of the data collected from the structural monitoring sensor network. Hence, the problem of sensor fault diagnosis has gained considerable attention in recent years. In this paper, an innovative sensor fault diagnosis method that focuses on fault detection and isolation stages has been proposed. The dynamic or auto-regressive characteristic is firstly utilized to build a multivariable statistical model that measures the correlations of the currently collected structural responses and the future possible ones in combination with the canonical correlation analysis. Two different fault detection statistics are then defined based on the above multivariable statistical model for deciding whether a fault or failure occurred in the sensor network. After that, two corresponding fault isolation indices are deduced through the contribution analysis methodology to identify the faulty sensor. Case studies, using a benchmark structure developed for bridge health monitoring, are considered in the research and demonstrate the superiority of the new proposed sensor fault diagnosis method over the traditional principal component analysis-based and the dynamic principal component analysis-based methods.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.23 no.8
• /
• pp.535-542
• /
• 2011

The performance of a plate heat exchanger for using liquid solution in the absorption chiller-heater was analyzed. The model was developed by using the various performance prediction correlations. The performance characteristics of the plate heat exchanger with the mass flow rate ratio was verified by using experimental data. To investigate performance of plate heat exchanger with geometry variables, the chevron angle, corrugated wave length, and corrugation depth were changed. As a result, the capacity of Kim and Martin correlation models was similar with the experimental data, and the capacity difference was less than 2%. Besides, the pressure drop of Marin correlation model showed a similar variation with experimental data, and the difference of pressure drop was less than 1.5 kPa.