• International Journal of Computer Science & Network Security
• /
• 제22권2호
• /
• pp.214-222
• /
• 2022

Convolutional Neural networks (CNNs) are a category of deep learning networks that have proven very effective in computer vision tasks such as image classification. Notwithstanding, not much has been seen in its use for remote sensing image classification in developing countries. This is majorly due to the scarcity of training data. Recently, transfer learning technique has successfully been used to develop state-of-the art models for remote sensing (RS) image classification tasks using training and testing data from well-known RS data repositories. However, the ability of such model to classify RS test data from a different dataset has not been sufficiently investigated. In this paper, we propose a deep CNN model that can classify RS test data from a dataset different from the training dataset. To achieve our objective, we first, re-trained a ResNet-50 model using EuroSAT, a large-scale RS dataset to develop a base model then we integrated Augmentation and Ensemble learning to improve its generalization ability. We further experimented on the ability of this model to classify a novel dataset (Nig_Images). The final classification results shows that our model achieves a 96% and 80% accuracy on EuroSAT and Nig_Images test data respectively. Adequate knowledge and usage of this framework is expected to encourage research and the usage of deep CNNs for land cover mapping in cases of lack of training data as obtainable in developing countries.

• 대기
• /
• 제31권5호
• /
• pp.637-656
• /
• 2021

The United States has been known as the world's major producer of crops such as wheat, corn, and soybeans. Therefore, using meteorological long-term forecast data to project reliable crop yields in the United States is important for planning domestic food policies. The current study is part of an effort to improve the seasonal predictability of regional-scale precipitation across the United States for estimating crop production in the country. For the purpose, a dynamic downscaling method using Weather Research and Forecasting (WRF) model is utilized. The WRF simulation covers the crop-growing period (March to October) during 2000-2020. The initial and lateral boundary conditions of WRF are derived from the Pusan National University Coupled General Circulation Model (PNU CGCM), a participant model of Asia-Pacific Economic Cooperation Climate Center (APCC) Long-Term Multi-Model Ensemble Prediction System. For bias correction of downscaled daily precipitation, empirical quantile mapping (EQM) is applied. The downscaled data set without and with correction are called WRF_UC and WRF_C, respectively. In terms of mean precipitation, the EQM effectively reduces the wet biases over most of the United States and improves the spatial correlation coefficient with observation. The daily precipitation of WRF_C shows the better performance in terms of frequency and extreme precipitation intensity compared to WRF_UC. In addition, WRF_C shows a more reasonable performance in predicting drought frequency according to intensity than WRF_UC.

• Journal of Magnetics
• /
• 제7권3호
• /
• pp.80-93
• /
• 2002

The role of magnetic anisotropy of the antiferromagnetic layer on the magnetization process of exchange coupled polycrystalline ferromagnetidantiferromagnetic bilayers is discussed. In order to elucidate the magnetic torque response of Ni-Fe/Mn-Ir bilayers, the single spin ensemble model is newly introduced, taking into account the two-dimensionally random distribution of the magnetic anisotropy axes of the antiferromagnetic grains. The mechanism of the reversible inducement of the exchange anisotropy along desirable directions by field cooling procedure is successfully explained with the new model. Unidirectional anisotropy constant, J$k$, of polycrystalline Ni-Fe/Mn-Ir and Co-Fe/Mn-Ir bilayers is investigated as functions of the chemical composition of both the ferromagnetic layer and the antiferromagnetic layer. The effects of microstructure and surface modification of the antiferromagnetic layer on JK are also discussed. As a notable result, an extra large value of J$k$, which exceeds 0.5 erg/cm$^2$, is obtained for $Co_{70}Fe_{30}Mn_{75}Ir_{25}$ bilayer with the ultra-thin (50${\AA}$∼100${\AA}$) Mn-Ir layer. The exchange anisotropy of $Co_{70}Fe_{30}$ 40 ${\AA}/Mn_{75}Ir_{25}$ 100 ${\AA}$ bilayer is stable for thermal annealing up to $400{^{\circ}C}$, which is sufficiently high for the application of spin valve magnetoresistive devices.

• 대기
• /
• 제27권4호
• /
• pp.411-422
• /
• 2017

The aim of this research is to review recent trends in weather and climate research in North Korea. We selected North Korean journal 'Weather and Hydrology' for the last 10 years (2007-2016), and identified trends in research subject, researchers, and affiliations. Furthermore, we analyzed the major achievements and trends by research sector. Our main results are same as follows. The largest number of researches on 'modernization and informatization on prediction' have been carried out in North Korea's recent meteorological and climatological research. This could be implicated that the scope of national science policy directly affected the promotion of specific research field. Especially, North Korea was evaluated to be concentrating its efforts on numerical model research and development. The numerical model which enables very short-term (6 hours) rainfall forecast which using ensemble Kalman filter data assimilation method (4D EnKF) was developed. In addition, development of automatic weather system and improvement of the data transfer system were promoted. However, the result reveals that the automated real-time data transfer system was not fully equipped yet. These results could be used as a basic data for meteorological cooperation between South and North Korea.

• Journal of the Korean Data and Information Science Society
• /
• 제26권1호
• /
• pp.77-87
• /
• 2015

파론도 역설은 두 개의 지는 게임이 결합하여 이기게 되거나, 두 개의 이기는 게임이 결합하여 지게 되는 현상을 말한다. 본 논문에서는 여러 명으로 구성된 집단에서 임의로 한 명을 선택하여 본인의 과거 실적에 의해 승패 확률이 정해지는 과거의존 파론도 게임을 실시하거나 또는 단순히 상금을 임의로 선택한 또 다른 사람에게 전달만 하는 게임을 진행하는 경우를 살펴본다. 각 게임은 지거나 공정한 게임인 반면에 두 게임을 임의로 결합한 혼합게임은 이기게 되는 파론도 효과가 존재함을 확인한다. 또한 각 게임은 이기거나 공정한 게임인데 임의로 결합한 혼합게임은 지게 되는 역 파론도 효과가 존재하는 확률 모수의 범위도 완성한다.

• 대기
• /
• 제22권3호
• /
• pp.331-344
• /
• 2012

The changes in the Hadley circulation during the second half of the 20th century were examined using observations and the 20C3M (Twentieth Century Climate in Coupled Models) simulations by the 21 IPCC AR4 models. Multi-model ensemble (MME) mean shows that the mean features of the Hadley circulation, such as the intensity, magnitude, and the seasonal variations, are very realistically reproduced, compared to the ERA40 reanalysis. But the long-term trends of the Hadley circulation in 20C3M MME are quite different to those of observations. The observed intensity of the Hadley cell is persistently enhanced, particularly during boreal winter. In comparison, the meridional overturning circulations reproduced in the MME mean remains invariant in time, and even weakened in boreal summer. This discrepancy between the ERA40 and 20C3M MME is consistently shown in the overall structure of the Hadley circulations, such as mass streamfunction, the velocity potential, the vertical shear of meridional wind, and the vertical velocity in the tropical region. This results indicate that the current climate models are skill-less to capture the long-term trend of Hadley circulation yet, and should be improved in simulation of the large-scale features to enhance the confidence level of future climate change projection.

• Tribology and Lubricants
• /
• 제36권5호
• /
• pp.290-296
• /
• 2020

When two layers of carbon nanotube (CNT) arrays are loaded to mate, the free ends of individual CNTs come into contact at the interface of the two layers. This leads to a higher contact resistance due to a smaller contact region. However, when the free CNT ends of one array penetrate into the mating array, the contact region increases, effectively lowering the contact resistance. To explore the penetration of mating CNTs, we perform molecular dynamic simulations of a simple unit cell model, incorporating four CNTs in the lower array layer coupled with a single moving CNT on the upper layer. The interaction with neighboring CNTs is modelled by long-range carbon bond order potential (LCBOP I). The model structure is optimized by energy minimization through the conjugate gradient method. A NVT ensemble is used for maintain a room temperature during simulation. The time integration is performed through the velocity-Verlet algorithm. A significant vibrational motion of CNTs is captured when penetration is not available, resulting in a specific vibration mode with a high frequency. Due to this vibrational behavior, the random behaviors of CNT motion for predicting the penetration are confirmed under the specific gap distances between CNTs. Thus, the probability of penetration is examined according to the gap distance between CNTs in the lower array and the aspect ratio of CNTs. The penetration is significantly affected by the vibration mode due to the van der Waals forces between CNTs.

• 대기
• /
• 제22권4호
• /
• pp.449-454
• /
• 2012

This study presents the long-term variability of spring precipitation over the Korean peninsula. It is found that the significant interdecadal change in the spring precipitation has occurred around year 1991. Over the Korean peninsula the precipitation for the post-1991 period increased by about 30 mm per year in CMAP and station-measured data compared to the precipitation prior to year 1991. Due to an increased baroclinicity during the later period, the low-level negative pressure anomaly has developed with its center over northern Japan. Korea is situated at the western end of the negative pressure anomaly, receiving moisture from westerly winds and producing more precipitation. Also, we estimate the change in the near future (years 2020~2040) spring precipitation using six best performing Coupled Model Intercomparison Project 3 (CMIP3) models. These best model ensemble mean shows that spring precipitation is anticipated to increase by about 4% due to the strengthened westerlies accompanied by the northwestern enhancement of the North Pacific subtropical high.

• Advances in Energy Research
• /
• 제6권2호
• /
• pp.91-101
• /
• 2019

This paper proposes an efficient data-driven approach to build models for predicting energy consumption in buildings. Data used in this research is collected by installing humidity and temperature sensors at different locations in a building. In addition to this, weather data from nearby weather station is also included in the dataset to study the impact of weather conditions on energy consumption. One of the main emphasize of this research is to make feature selection independent of domain knowledge. Therefore, to extract useful features from data, two different approaches are tested: one is feature selection through principal component analysis and second is relative importance-based feature selection in original domain. The regression model used in this research is gradient boosting regression and its optimal parameters are chosen through a two staged coarse-fine search approach. In order to evaluate the performance of model, different performance evaluation metrics like r2-score and root mean squared error are used. Results have shown that best performance is achieved, when relative importance-based feature selection is used with gradient boosting regressor. Results of proposed technique has also outperformed the results of support vector machines and neural network-based approaches tested on the same dataset.

• Bulletin of the Korean Chemical Society
• /
• 제24권11호
• /
• pp.1590-1598
• /
• 2003

In this paper we have presented the results for viscosity and self-diffusion constants of model systems for four liquid n-alkanes ($C_{12}, C_{20}, C_{32}, and C_{44}$) in a canonical ensemble at several temperatures using molecular dynamics (MD) simulations. The small chains of these n-alkanes are clearly $<{R_{ee}}^2>/6<{R_g}^2>>1$, which leads to the conclusion that the liquid n-alkanes over the whole temperatures considered are far away from the Rouse regime. Calculated viscosity ${\eta}$ and self-diffusion constants D are comparable with experimental results and the temperature dependence of both ${\eta}$ and D is suitably described by the Arrhenius plot. The behavior of both activation energies, $E_{\eta}$ and $E_D$, with increasing chain length indicates that the activation energies approach asymptotic values as n increases to the higher value, which is experimentally observed. Two calculated monomeric friction constants ${\zeta}$ and ${\zeta}_D$ give a correct qualitative trend: decrease with increasing temperature and increase with increasing chain length n. Comparison of the time auto-correlation functions of the end-to-end vector calculated from the Rouse model for n-dodecane ($C_{12}$) at 273 K and for n-tetratetracontane ($C_{44}$) at 473 K with those extracted directly from our MD simulations confirms that the short chain n-alkanes considered in this study are far away from the Rouse regime.