• Journal of the Korean earth science society
• /
• v.28 no.2
• /
• pp.214-226
• /
• 2007

Because precipitation is influenced by various atmospheric variables, it is highly nonlinear. Although precipitation predicted by a dynamic model can be corrected by using a nonlinear Artificial Neural Network, this approach has limits such as choices of the initial weight, local minima and the number of neurons, etc. In the present paper, we correct simulated precipitation by using a multiple linear regression (MLR) method, which is simple and widely used. First of all, Ensemble hindcast is conducted by the PNU/CME Coupled General Circulation Model (CGCM) (Park and Ahn, 2004) for the period from April to August in 1979-2005. MLR is applied to precipitation simulated by PNU/CME CGCM for the months of June (lead 2), July (lead 3), August (lead 4) and seasonal mean JJA (from June to August) of the Northeast Asian region including the Korean Peninsula $(110^{\circ}-145^{\circ}E,\;25-55^{\circ}N)$. We build the MLR model using a linear relationship between observed precipitation and the hindcasted results from the PNU/CME CGCM. The predictor variables selected from CGCM are precipitation, 500 hPa vertical velocity, 200 hPa divergence, surface air temperature and others. After performing a leave-oneout cross validation, the results are compared with the PNU/CME CGCM's. The results including Heidke skill scores demonstrate that the MLR corrected results have better forecasts than the direct CGCM result for rainfall.

• Journal of the Korean Chemical Society
• /
• v.59 no.2
• /
• pp.117-124
• /
• 2015

The DFT and ab initio calculations have been performed to elucidate hydrogen interaction of hydrogen polyoxide dimers, $H_2O_n-H_2O_m$ (n=1-4, m=1-4). The optimized geometries, harmonic vibrational frequencies, and binding energies are predicted at various levels of theory. The harmonic vibrational frequencies of the molecules considered in this study show all real numbers implying true minima. The higher-order correlation effect were discussed to compare MP2 result with CCSD(T) single point energy. The binding energies were corrected for the zero-point vibrational energy (ZPVE) and basis set superposition errors (BSSE). The largest binding energy predicted at the CCSD(T)/cc-pVTZ level of theory is 8.18 kcal/mol for $H_2O_4-H_2O_3$ and the binding energy of water dimer is predicted to be 3.00 kcal/mol.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.7
• /
• pp.1749-1758
• /
• 1997

This paper suggests the development of dynamic forecasting model for short-term power demand based on Radial Basis Function Network and Pal's GLVQ algorithm. Radial Basis Function methods are often compared with the backpropagation training, feed-forward network, which is the most widely used neural network paradigm. The Radial Basis Function Network is a single hidden layer feed-forward neural network. Each node of the hidden layer has a parameter vector called center. This center is determined by clustering algorithm. Theatments of classical approached to clustering methods include theories by Hartigan(K-means algorithm), Kohonen(Self Organized Feature Maps %3A SOFM and Learning Vector Quantization %3A LVQ model), Carpenter and Grossberg(ART-2 model). In this model, the first approach organizes the load pattern into two clusters by Pal's GLVQ clustering algorithm. The reason of using GLVQ algorithm in this model is that GLVQ algorithm can classify the patterns better than other algorithms. And the second approach forecasts hourly load patterns by radial basis function network which has been constructed two hidden nodes. These nodes are determined from the cluster centers of the GLVQ in first step. This model was applied to forecast the hourly loads on Mar. $4^{th},\;Jun.\;4^{th},\;Jul.\;4^{th},\;Sep.\;4^{th},\;Nov.\;4^{th},$ 1995, after having trained the data for the days from Mar. $1^{th}\;to\;3^{th},\;from\;Jun.\;1^{th}\;to\;3^{th},\;from\;Jul.\;1^{th}\;to\;3^{th},\;from\;Sep.\;1^{th}\;to\;3^{th},\;and\;from\;Nov.\;1^{th}\;to\;3^{th},$ 1995, respectively. In the experiments, the average absolute errors of one-hour ahead forecasts on utility actual data are shown to be 1.3795%.

• Journal of the Korean earth science society
• /
• v.23 no.7
• /
• pp.552-564
• /
• 2002

The data of satellite-observed Microwave Sounding Unit (MSU) channel 1 (Ch1) brightness temperature and General Circulation Model (GCM) reanalyses over the globe have been used to investigate low tropospheric hydrometeors and microwave surface emissivity during the period from January 1981 to December 1993. The average of GCM Ch1 temperature has been reconstructed from three kinds of reanalyses, based on the MSU weighting function. Since the GCM temperature mainly corresponds to the thermal state of the lower troposphere without the difference in the emissivity between ocean and land, it is higher in summer than in other seasons over the regions. The MSU temperature over the ocean shows its maximum at the ITCZ and the SPCZ due to hydrometeors. Over high latitude ocean, the temperature is enhanced because of sea ice emissivity, while it is reduced over the land. The seasonal displacement of the ITCZ and the SPCZ systematically appeared in the difference of Ch1 temperature between the GCM and the MSU. The difference values decrease in the regions of the ITCZ, the SPCZ, and the sea ice because of the increase of the MSU temperature. According to the local minima of the values, the ITCZ moves norhward to 9 N in fall, and the SPCZ moves southward to 12 S in boreal fall and winter. The sea ice in the northern hemisphere is extended southward to 53 N in winter, while the ice in the southern hemisphere, northward to 58 S in boreal summer. We also have discussed the separated contribution from hydrometeors and surface emissivity to the MSU Ch1 temperature, utilizing radiative transfer theory. The increase of 4-6K in the temperature over the ITCZ is inferred to result from hydrometeors of 1-1.5mm/day, and furthermore the increase of 10-30K over the high latitude ocean, ice emissivity of 0.6-0.9.

• Journal of the Korean earth science society
• /
• v.21 no.3
• /
• pp.287-301
• /
• 2000

In order to investigate the factors and processes affecting the vertical distributions of ozone, we analyzed the ozone profile data measured using ozonesonde from 1995 to 1997 at Pohang city, Korea. In the course of our study, we analyzed temporal and spatial distribution characteristics of ozone at four different heights: surface (100m), troposphere (10km), lower stratosphere (20km), and middle stratosphere (30km). Despite its proximity to a local, but major, industrial complex known as Pohang Iron and Steel Co. (POSCO), the concentrations of surface ozone in the study area were comparable to those typically observed from rural and/or unpolluted area. In addition, the findings of relative enhancement of ozone at this height, especially between spring and summer may be accounted for by the prevalence of photochemical reactions during that period of year. The temporal distribution patterns for both 10 and 20km heights were quite compatible despite large differences in their altitudes with such consistency as spring maxima and summer minima. Explanations for these phenomena may be sought by the mixed effects of various processes including: ozone transport across two heights, photochemical reaction, the formation of inversion layer, and so on. However, the temporal distribution pattern for the middle stratosphere (30km) was rather comparable to that of the surface. We also evaluated total ozone concentration of the study area using Brewer spectrophotometer. The total ozone concentration data were compared with those derived by combining the data representing stratospheric layers via Umkehr method. The results of correlation analysis showed that total ozone is negatively correlated with cloud cover but not with such parameter as UV-B. Based on our study, we conclude that areal characteristics of Pohang which represents a typical coastal area may be quite important in explaining the distribution patterns of ozone not only from surface but also from upper atmosphere.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.53-65
• /
• 2019

Object tracking is one of important steps to achieve video-based surveillance systems. Object tracking is considered as an essential task similar to object detection and recognition. In order to perform object tracking, various machine learning methods (e.g., least-squares, perceptron and support vector machine) can be applied for different designs of tracking systems. In general, generative methods (e.g., principal component analysis) were utilized due to its simplicity and effectiveness. However, the generative methods were only focused on modeling the target object. Due to this limitation, discriminative methods (e.g., binary classification) were adopted to distinguish the target object and the background. Among the machine learning methods for binary classification, total error rate minimization can be used as one of successful machine learning methods for binary classification. The total error rate minimization can achieve a global minimum due to a quadratic approximation to a step function while other methods (e.g., support vector machine) seek local minima using nonlinear functions (e.g., hinge loss function). Due to this quadratic approximation, the total error rate minimization could obtain appropriate properties in solving optimization problems for binary classification. However, this total error rate minimization was based on a batch mode setting. The batch mode setting can be limited to several applications under offline learning. Due to limited computing resources, offline learning could not handle large scale data sets. Compared to offline learning, online learning can update its solution without storing all training samples in learning process. Due to increment of large scale data sets, online learning becomes one of essential properties for various applications. Since object tracking needs to handle data samples in real time, online learning based total error rate minimization methods are necessary to efficiently address object tracking problems. Due to the need of the online learning, an online learning based total error rate minimization method was developed. However, an approximately reweighted technique was developed. Although the approximation technique is utilized, this online version of the total error rate minimization could achieve good performances in biometric applications. However, this method is assumed that the total error rate minimization can be asymptotically achieved when only the number of training samples is infinite. Although there is the assumption to achieve the total error rate minimization, the approximation issue can continuously accumulate learning errors according to increment of training samples. Due to this reason, the approximated online learning solution can then lead a wrong solution. The wrong solution can make significant errors when it is applied to surveillance systems. In this paper, we propose an exactly reweighted technique to recursively update the solution of the total error rate minimization in online learning manner. Compared to the approximately reweighted online total error rate minimization, an exactly reweighted online total error rate minimization is achieved. The proposed exact online learning method based on the total error rate minimization is then applied to object tracking problems. In our object tracking system, particle filtering is adopted. In particle filtering, our observation model is consisted of both generative and discriminative methods to leverage the advantages between generative and discriminative properties. In our experiments, our proposed object tracking system achieves promising performances on 8 public video sequences over competing object tracking systems. The paired t-test is also reported to evaluate its quality of the results. Our proposed online learning method can be extended under the deep learning architecture which can cover the shallow and deep networks. Moreover, online learning methods, that need the exact reweighting process, can use our proposed reweighting technique. In addition to object tracking, the proposed online learning method can be easily applied to object detection and recognition. Therefore, our proposed methods can contribute to online learning community and object tracking, detection and recognition communities.