• International Journal of Aeronautical and Space Sciences
• /
• v.11 no.4
• /
• pp.326-337
• /
• 2010

This work addresses problems regarding trajectory planning for unmanned aerial vehicle sensors. Such sensors are used for taking measurements of large nonlinear systems. The sensor investigations presented here entails methods for improving estimations and predictions of large nonlinear systems. Thoroughly understanding the global system state typically requires probabilistic state estimation. Thus, in order to meet this requirement, the goal is to find trajectories such that the measurements along each trajectory minimize the expected error of the predicted state of the system. The considerable nonlinearity of the dynamics governing these systems necessitates the use of computationally costly Monte-Carlo estimation techniques, which are needed to update the state distribution over time. This computational burden renders planning to be infeasible since the search process must calculate the covariance of the posterior state estimate for each candidate path. To resolve this challenge, this work proposes to replace the computationally intensive numerical prediction process with an approximate covariance dynamics model learned using a nonlinear time-series regression. The use of autoregressive time-series featuring a regularized least squares algorithm facilitates the learning of accurate and efficient parametric models. The learned covariance dynamics are demonstrated to outperform other approximation strategies, such as linearization and partial ensemble propagation, when used for trajectory optimization, in terms of accuracy and speed, with examples of simplified weather forecasting.

• 한국가시화정보학회:학술대회논문집
• /
• 2004.12a
• /
• pp.169-175
• /
• 2004

The characteristics of flow around a rotating propeller were investigated using PIV technique. For each of four different blade phases of $0^{\circ},\;18^{\circ},\;36^{\circ}\;and\;54^{\circ}$four hundred instantaneous velocity fields were ensemble averaged to investigate the spatial evolution of the flow around a propeller. The phase-averaged mean velocity fields show that the viscous wake formed by the boundary layers developed on the blade surfaces and the slipstream contraction in the near-wake region. The out-of-plane velocity component and strain rate had large values at the locations of the tip and trailing vortices. The boundary layer developed along the ship hull bottom surface of the ship stern provides a strong turbulent shear layer, affecting the vortex structure in the propeller near-wake. As the flow develops in the downstream direction, the trailing vortices formed behind the propeller hub move upward slightly due to the presence of the hull wake and free surface. The turbulence intensity has large values around the tip and trailing vortices. As the wake moves downstream, the strength of the vorticity diminishes and the turbulence intensity increases due to turbulent diffusion and active mixing between the tip vortices and adjacent wake flow.

• Advances in aircraft and spacecraft science
• /
• v.7 no.6
• /
• pp.495-516
• /
• 2020

Nonlinear state estimation is a desirable and required technique for many situations in engineering (e.g., aircraft/spacecraft tracking, space situational awareness, collision warning, radar tracking, etc.). Due to high standards on performance in these applications, in the last few decades, there was an increasing demand for methods that are able to provide more accurate results. However, because of the mathematical complexity introduced by the nonlinearities of the models, the nonlinear state estimation uses techniques that, in practice, are not so well-established which, leads to sub-optimal results. It is important to take into account that each method will have advantages and limitations when facing specific environments. The main objective of this paper is to provide a comprehensive overview and interpretation of the most well-known methods for nonlinear state estimation with Gaussian priors. In particular, the Kalman filtering methods: EKF (Extended Kalman Filter), UKF (Unscented Kalman Filter), CKF (Cubature Kalman Filter) and EnKF (Ensemble Kalman Filter) with an aerospace perspective.

• Korean Journal of Remote Sensing
• /
• v.34 no.1
• /
• pp.141-150
• /
• 2018

Crop type classification is essential for supporting agricultural decisions and resource monitoring. Remote sensing techniques, especially using hyperspectral imagery, have been effective in agricultural applications. Hyperspectral imagery acquires contiguous and narrow spectral bands in a wide range. However, large dimensionality results in unreliable estimates of classifiers and high computational burdens. Therefore, reducing the dimensionality of hyperspectral imagery is necessary. In this study, the Random Forest (RF) classifier was utilized for dimensionality reduction as well as classification purpose. RF is an ensemble-learning algorithm created based on the Classification and Regression Tree (CART), which has gained attention due to its high classification accuracy and fast processing speed. The RF performance for crop classification with airborne hyperspectral imagery was assessed. The study area was the cultivated area in Chogye-myeon, Habcheon-gun, Gyeongsangnam-do, South Korea, where the main crops are garlic, onion, and wheat. Parameter optimization was conducted to maximize the classification accuracy. Then, the dimensionality reduction was conducted based on RF variable importance. The result shows that using the selected bands presents an excellent classification accuracy without using whole datasets. Moreover, a majority of selected bands are concentrated on visible (VIS) region, especially region related to chlorophyll content. Therefore, it can be inferred that the phenological status after the mature stage influences red-edge spectral reflectance.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1910-1911
• /
• 2007

A new method for estimating and eliminating electrocardiogram (ECG) artifacts from single channel scalp electroencephalogram (EEG) is proposed. The proposed method consists of emphasis of QRS complex from EEG using least squares acceleration (LSA) filter, generation of synchronized pulse with R-peak and ECG artifacts estimation and elimination using adaptive filter. The performance of the proposed method was evaluated using simulated and real EEG recordings, we found that the ECG artifacts were successfully estimated and eliminated in comparison with the conventional multi-channel techniques, which are independent component analysis (ICA) and ensemble average (EA) method. In conclusion, we can conclude that the proposed method is useful for the detecting and eliminating the ECG artifacts from single channel EEG and simple to use for ambulatory/portable EEG monitoring system.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.4
• /
• pp.207-218
• /
• 2019

The purpose of this study is to develop a model that can systematically study the whole learning process of machine learning. Since the existing model describes the learning process with minimum coding, it can learn the progress of machine learning sequentially through the new model, and can visualize each process using the tensor flow. The new model used all of the existing model algorithms and confirmed the importance of the variables that affect the target variable, survival. The used to classification training data into training and verification, and to evaluate the performance of the model with test data. As a result of the final analysis, the ensemble techniques is the all tutorial model showed high performance, and the maximum performance of the model was improved by maximum 5.2% when compared with the existing model using. In future research, it is necessary to construct an environment in which machine learning can be learned regardless of the data preprocessing method and OS that can learn a model that is better than the existing performance.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.12 no.1
• /
• pp.428-439
• /
• 2020

The continuous development of information and communication technologies has resulted in an exponential increase in data. Consequently, technologies related to data analysis are growing in importance. The shipbuilding industry has high production uncertainty and variability, which has created an urgent need for data analysis techniques, such as machine learning. In particular, the industry cannot effectively respond to changes in the production-related standard time information systems, such as the basic cycle time and lead time. Improvement measures are necessary to enable the industry to respond swiftly to changes in the production environment. In this study, the lead times for fabrication, assembly of ship block, spool fabrication and painting were predicted using machine learning technology to propose a new management method for the process lead time using a master data system for the time element in the production data. Data preprocessing was performed in various ways using R and Python, which are open source programming languages, and process variables were selected considering their relationships with the lead time through correlation analysis and analysis of variables. Various machine learning, deep learning, and ensemble learning algorithms were applied to create the lead time prediction models. In addition, the applicability of the proposed machine learning methodology to standard work hour prediction was verified by evaluating the prediction models using the evaluation criteria, such as the Mean Absolute Percentage Error (MAPE) and Root Mean Squared Logarithmic Error (RMSLE).

• Current Applied Physics
• /
• v.18 no.11
• /
• pp.1174-1181
• /
• 2018

In nanomagnetism, one of the crucial scientific questions is whether magnetic behaviors are deterministic or stochastic on a nanoscale. Apart from the exciting physical issue, this question is also of paramount highest relevance for using magnetic materials in a wealth of technological applications such as magnetic storage and sensor devices. In the past, the research on the stochasticity of a magnetic process has been mainly done by macroscopic measurements, which only offer ensemble-averaged information. To give more accurate answer for the question and to fully understand related underlying physics, the direct observation of statistical behaviors in magnetic structures and magnetic phenomena utilizing advanced characterization techniques is highly required. One of the ideal tools for such study is a full-field soft X-ray microscope since it enables imaging of magnetic structures on the large field of view within a few seconds. Here we review the stochastic behaviors of various magnetic processes including magnetization reversal process in thin films, magnetic domain wall motions in nanowires, and magnetic vortex formations in nanodisks studied by full-field soft X-ray microscopy. The origin triggering the stochastic nature witnessed in each magnetic process and the way to control the intrinsic nature are also discussed.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.3
• /
• pp.17-24
• /
• 2023

Based on the problem of 'Tatanic - Machine Learning from Disaster', a representative competition of Kaggle that presents challenges related to data science and solves them, we want to see how data preprocessing and model construction affect prediction accuracy and score. We compare and analyze the features by selecting seven top-ranked solutions with high scores, except when using redundant models or ensemble techniques. It was confirmed that most of the pretreatment has unique and differentiated characteristics, and although the pretreatment process was almost the same, there were differences in scores depending on the type of model. The comparative analysis study in this paper is expected to help participants in the kaggle competition and data science beginners by understanding the characteristics and analysis flow of the preprocessing methods of the top score participants.

• Journal of Korea Water Resources Association
• /
• v.46 no.7
• /
• pp.755-765
• /
• 2013

This study developed a real-time dam's hydrologic variables prediction model (DHVPM) and evaluated its performance for simulating historical dam inflow and outflow in the Chungju dam basin. The DHVPM consists of the Sejong University River Forecast (SURF) model for hydrologic modeling and an autoreservoir operation method (Auto ROM) for dam operation. SURF model is continuous rainfall-runoff model with data assimilation using an ensemble Kalman filter technique. The four extreme events including the maximum inflow of each year for 2006~2009 were selected to examine the performance of DHVPM. The statistical criteria, the relative error in peak flow, root mean square error, and model efficiency, demonstrated that DHVPM with data assimilation can simulate more close to observed inflow than those with no data assimilation at both 1-hour lead time, except the relative error in peak flow in 2007. Especially, DHVPM with data assimilation until 10-hour lead time reduced the biases of inflow forecast attributed to observed precipitation error. In conclusion, DHVPM with data assimilation can be useful to improve the accuracy of inflow forecast in the basin where real-time observed inflow are available.