• Journal of The Korean Society of Agricultural Engineers
• /
• v.64 no.1
• /
• pp.15-26
• /
• 2022

3D open-field farm model developed from UAV (Unmanned Aerial Vehicle) data could make crop monitoring easier, also could be an important dataset for various fields like remote sensing or precision agriculture. It is essential to separate crops from the non-crop area because labeling in a manual way is extremely laborious and not appropriate for continuous monitoring. We, therefore, made a 3D open-field farm model based on UAV images and developed a crop segmentation model using a supervised machine learning algorithm. We compared performances from various models using different data features like color or geographic coordinates, and two supervised learning algorithms which are SVM (Support Vector Machine) and KNN (K-Nearest Neighbors). The best approach was trained with 2-dimensional data, ExGR (Excess of Green minus Excess of Red) and z coordinate value, using KNN algorithm, whose accuracy, precision, recall, F1 score was 97.85, 96.51, 88.54, 92.35% respectively. Also, we compared our model performance with similar previous work. Our approach showed slightly better accuracy, and it detected the actual crop better than the previous approach, while it also classified actual non-crop points (e.g. weeds) as crops.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.12
• /
• pp.2265-2267
• /
• 2007

The purpose of this work is to compare the local fitting and global fitting approaches while applying regression model to the PTT-BP data for the prediction of exercise blood pressures. We used linear and nonlinear regression models to represent the PTT-BP relationship during exercise. PTT-BP data were acquired both under resting state and also after cycling exercise with several load conditions. PTT was calculated as the time between R-peak of ECG and the peak of differential photo-plethysmogram. For the identification of the regression models, we used local fitting which used only the resting state data and global fitting which used the whole region of data including exercise BP. The results showed that the global fitting was superior to the local fitting in terms of the coefficient of determination and the RMS (root mean square) error between the experimental and estimated BP. The nonlinear regression model which used global fitting showed slightly better performance than the linear one (no significant difference). We confirmed that the wide-range of data is required for the regression model to appropriately predict the exercise BP.

• Journal of Astronomy and Space Sciences
• /
• v.27 no.4
• /
• pp.359-366
• /
• 2010

In this study, we developed a global ionosphere model based on measurements from a worldwide network of global positioning system (GPS). The total number of the international GPS reference stations for development of ionospheric model is about 100 and the spherical harmonic expansion approach as a mathematical method was used. In order to produce the ionospheric total electron content (TEC) based on grid form, we defined spatial resolution of 2.0 degree and 5.0 degree in latitude and longitude, respectively. Two-dimensional TEC maps were constructed within the interval of one hour, and have a high temporal resolution compared to global ionosphere maps which are produced by several analysis centers. As a result, we could detect the sudden increase of TEC by processing GPS observables on 29 October, 2003 when the massive solar flare took place.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2011.08a
• /
• pp.312-312
• /
• 2011

In SiH4/H2 discharge for growth process of hydrogenated amorphous silicon (a-Si:H), silane polymers, produced by SiH2 + Sin-1H2n ${\rightarrow}$ SinH2n+2, have no reactivity on the film-growing surface. However, under the SiH2 rich condition, high silane reactive species (HSRS) can be produced by electron collision to silane polymers. HSRS, having relatively strong reactivity on the surface, can react with dangling bond and form Si-H2 networks which have a close correlation with photo-induced degradation of a-Si:H thin film solar cell [1]. To find contributions of suggested several external plasma conditions (pressure, frequency and ratio of mixture gas) [2,3] to suppressing productions of HSRS, some plasma characteristics are studied by numerical methods. For this study, a zero-dimensional global model for SiH4/H2 discharge and a one-dimensional particle-in-cell Monte-Carlo-collision model (PIC-MCC) for pure SiH4 discharge have been developed. Densities of important reactive species of SiH4/H2 discharge are observed by means of the global model, dealing 30 species and 136 reactions, and electron energy probability functions (EEPFs) of pure SiH4 discharge are obtained from the PIC-MCC model, containing 5 charged species and 15 reactions. Using global model, SiH2/SiH3 values were calculated when pressure and driving frequency vary from 0.1 Torr to 10 Torr, from 13.56 MHz to 60 MHz respectively and when the portion of hydrogen changes. Due to the limitation of global model, frequency effects can be explained by PIC-MCC model. Through PIC-MCC model for pure SiH4, EEPFs are obtained in the specific range responsible for forming SiH2 and SiH3: from 8.75 eV to 9.47 eV [4]. Through densities of reactive species and EEPFs, polymerization reactions and production of HSRS are discussed.

• The Journal of Society for e-Business Studies
• /
• v.7 no.3
• /
• pp.121-137
• /
• 2002

SCM(Supply Chain Management) have been introduced in many companies for integrated management and improvement of business process. Recently, as internet and e-business concept are spread globally, the SCM concept is expanded from one internal company process to inter-company process, it makes a Global SCM concept. In this paper, we discuss the implementation of the Global SCM concept using e-business infrastructure, and propose SCM portal models. Four types of the SCM portal model are discussed, which are forecasting information sharing model, e-Marketplace-typed model, collaboration model and logistics information sharing model. The major concept of the SCM portal is to share information of supply chain process, it provide merits of scale to company. The result of this paper can be summarized as follows : First, the information sharing is very useful in the Global SCM. Second, the e-business infrastructure, especially e-Marketplace can be usefully used for implementation of SCM portal. Third, the M2M(Market to Market) function of e-Marketplace is a major function for implementing SCM portal.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.6 no.1
• /
• pp.39-46
• /
• 2006

We propose an global color model based method for tracking motions of multiple human using a networked multiple-camera system in intelligent space as a human-robot coexistent system. An intelligent space is a space where many intelligent devices, such as computers and sensors(color CCD cameras for example), are distributed. Human beings can be a part of intelligent space as well. One of the main goals of intelligent space is to assist humans and to do different services for them. In order to be capable of doing that, intelligent space must be able to do different human related tasks. One of them is to identify and track multiple objects seamlessly. In the environment where many camera modules are distributed on network, it is important to identify object in order to track it, because different cameras may be needed as object moves throughout the space and intelligent space should determine the appropriate one. This paper describes appearance based unknown object tracking with the distributed vision system in intelligent space. First, we discuss how object color information is obtained and how the color appearance based model is constructed from this data. Then, we discuss the global color model based on the local color information. The process of learning within global model and the experimental results are also presented.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.8 no.2
• /
• pp.161-173
• /
• 1996

Two-dimensional numerical models with 1$^{\circ}$ and 1/3$^{\circ}$ resolution have been established to investigate the Ma distribution of global ocean tides. Especially, a 1/3$^{\circ}$ numerical model in this study has the most fine resolution among the existing global tidal model and it has been applied to the computation of detailed tidal distributions in the marginal seas and the shelf seas. Tidal characteristics in shallow areas could be hardly interpreted with the existing global chart due to the low resolution. The Ma tidal charts obtaind by 1$^{\circ}$ and 1/3$^{\circ}$ numerical model have been compared with the existing global maps and the altimetry-derived tidal charts. Also, the computed harmonic constants have been compared with the pelagic observations. The results obtained by 1/3$^{\circ}$ numerical model show better agreement with the existing global charts and the observed data than those obtained by 1$^{\circ}$ model. The possibility has been presented that the results obtained by 1/3$^{\circ}$ model can provide the open boundary conditions of the regional tidal numerical model.

• Journal of Korean Society of societal Security
• /
• v.3 no.1
• /
• pp.33-42
• /
• 2010

This study predicts the stress history for truss bridge with local damages by using global-local model combination method. For this end, the global structure is modeled by 3D frame elements and the selected local details are modeled by shell elements. Then superposition principle enable the global-local model to be combined interactively. Because the frame model cannot consider the rigidity of gusset plate and the interation of structural members due to the complexity of stress distribution in truss connection. The section modification factors are proposed to calibrate the stiffness of global frame element. The global-local model combination is verified by comparing the numerical results with experimental data obtained from the proof loading test to the operating truss bridge. Furthermore, stress histrories of the truss bridge are generated in the consideration of the rigidity of truss connection with local damage by using the combination method.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.24 no.2
• /
• pp.11-18
• /
• 2016

Global Positioning System (GPS) is currently widely used for aviation applications. Single-frequency GPS receivers are highly affected by the ionospheric delay error, and the ionospheric delay should be corrected for accurate positioning. Single-frequency GPS receivers use the Klobuchar model, whose model parameters are transmitted from GPS satellites. In this paper, the long-term accuracy of the Klobuchar model from 2002 to 2014 is analyzed. The IGS global ionosphere map is considered as true ionospheric delay, and hourly, seasonal, and geographical error variations are analyzed. Histogram of the ionospheric delay error is also analyzed. The influence of solar and geomagnetic activity on the Klobuchar model error is analyzed, and the Klobuchar model error is highly correlated with solar activity. The results show that the Klobuchar model estimates 8 total electron content unit (TECU) over the true ionosphere delay in average. The Klobuchar model error is greater than 12 TECU within $20^{\circ}$ latitude, and the error is less than 6 TECU at high latitude.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.29 no.9 s.240
• /
• pp.1243-1252
• /
• 2005

A current trend of design methodologies is to make engineers objectify or automate the decision-making process. Numerical optimization is an example of such technologies. However, in numerical optimization, the uncertainties are uncontrollable to efficiently objectify or automate the process. To better manage these uncertainties, the Taguchi method, reliability-based optimization and robust optimization are being used. To obtain the target performance with the maximum robustness is the main functional requirement of a mechanical system. In this research, a design procedure for global robust optimization is developed based on the kriging and global optimization approaches. The DACE modeling, known as the one of Kriging interpolation, is introduced to obtain the surrogate approximation model of the function. Robustness is determined by the DACE model to reduce real function calculations. The simulated annealing algorithm of global optimization methods is adopted to determine the global robust design of a surrogated model. As the postprocess, the first order second-moment approximation method is applied to refine the robust optimum. The mathematical problems and the MEMS design problem are investigated to show the validity of the proposed method.