• Geomechanics and Engineering
• /
• v.37 no.6
• /
• pp.629-641
• /
• 2024

The presence of excavations or cavities beneath the foundations of a building can have a significant impact on their stability and cause extensive damage. Traditional methods for calculating the bearing capacity and subsidence of foundations over cavities can be complex and time-consuming, particularly when dealing with conditions that vary. In such situations, machine learning (ML) and deep learning (DL) techniques provide effective alternatives. This study concentrates on constructing a prediction model based on the performance of ML and DL algorithms that can be applied in real-world settings. The efficacy of eight algorithms, including Regression Analysis, k-Nearest Neighbor, Decision Tree, Random Forest, Multivariate Regression Spline, Artificial Neural Network, and Deep Neural Network, was evaluated. Using a Python-assisted automation technique integrated with the PLAXIS 2D platform, a dataset containing 272 cases with eight input parameters and one target variable was generated. In general, the DL model performed better than the ML models, and all models, except the regression models, attained outstanding results with an R² greater than 0.90. These models can also be used as surrogate models in reliability analysis to evaluate failure risks and probabilities.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.54 no.4
• /
• pp.211-216
• /
• 2005

In this paper a robust controller using adaptive backstepping technique is proposed to control the speed of wind power generation system. To make wind power generation truly cost effective and reliable, advanced and robust control algorithms are derived to on-line adjust the excitation winding voltage of the generator based on both mechanical and electrical dynamics. This method is shown to be able to achieve smooth and asymptotic rotor speed tracking, as justified by analysis and computer simulation.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1227-1229
• /
• 2007

In this paper a robust controller using adaptive backstepping technique is proposed to control the position of wind power generation system. To make wind power generation truly cost effective and reliable, advanced and robust control algorithms are derived to on-line adjust the excitation winding voltage of the generator based on both mechanical and electrical dynamics. This method is shown to be able to achieve smooth and asymptotic rotor speed tracking, as justified by analysis and computer simulation.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.15 no.5
• /
• pp.65-71
• /
• 2006

This paper presents the robust design of gripper part for a high-speed LCD(Liquid Crystal Display) transfer system. In this paper, the $1^{st}$ DOE(Design of Experiment) is conducted to find out main-effect factors for the design of gripper part. Thirty-six analysis are performed using $ANSYS^{(R)}$ and their results are statistically analyzed using $MINITAB^{(R)}$, which shows that the factors, i.e., First-width, Second-width, Rec-width, and thickness of gripper part, are more important than other factors. The main effect plots shows that the maximum deflection and mass of gripper part are minimized by increasing First-width, Second-width, Rec-width and thickness. The $2^{nd}$ DOE is conducted to obtain RSM(Response Surface Method) equation. The CCD(Central Composite Design) technique with four factors is used. Optimum design is conducted using the RSM equation. Genetic algorithm is used for optimal design. Six sigma robust design is conducted to find out a guideline for control range of design parameter. To obtain six sigma level quality, the standard deviations of design parameters are shown to be controlled within 5% of average design value.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.12 no.2
• /
• pp.205-214
• /
• 2004

This paper presents design concepts, specifications and performances of a newly developed Black Box, the reconstruction analysis tool with the records, and results of validation tests. The Black Box can detect crash accidents automatically, and record the vehicle's motion and driver's maneuvers during a pre-defined time period before and after the accident. The items of the Black Box included the acceleration, yaw-rate, vehicle speed, engine RPM, braking application, steering and several digital inputs for recording driver's maneuvers. To detect the accident-related-crash, it is important to understand characteristics of the crash signal, which are much different from those of normal driving. Therefore, analytical considerations should be taken in designing pre-filtering circuits and selecting appropriate parameters for identifying crash accidents. And, it is necessary to select proper combination of motion sensors and design proper pre-filtering circuits in order to describe the vehicle's motion. The analysis algorithms were developed and implemented which can perform accurate detection of crash accidents, simulating pre-crash trajectories, and calculating parameters for reconstruction analysis of crash accidents. The developed Black Box was installed on passenger cars and several types of validation tests were conducted. Through the tests, the accuracy of the recorded data and usefulness of the analysis tool for reconstruction have been validated.

• Journal of East-West Nursing Research
• /
• v.18 no.2
• /
• pp.95-103
• /
• 2012

Purpose: This methodological study was done to develop a computerized telephone triage and consultation system for patients discharged with ophthalmic disease in order to provide more efficient practice guidelines for nurses, and evaluate the usability of the system. Methods: Development of the system consisted of six phases: strategic planning, analysis, design, implementation, evaluation, modification, and maintenance. Results: In the strategic planning phase, ophthalmic problems and nursing interventions of triage algorithms and practice guidelines were cross-mapped with the Omaha system. In the analysis phase, users requirements were identified. Then infrastructure including database, nursing knowledge base, and user interface were designed in the implementation phase. Usability and satisfaction of the system presented as very positive. Telephone consultation took about 2 minutes less than time in the previous system. The system was modified based on users' comments during the evaluation phase. Conclusion: This study was the first attempt in Korea to develop computerized triage system to prompt the quality of telephone consultation. It is suggestive that the computerized triage system may improve the quality of nursing.

• Proceedings of the KIEE Conference
• /
• 2005.10a
• /
• pp.128-131
• /
• 2005

In this paper a robust controller using adaptive backstepping technique is proposed to control the speed of a wind turbine system. To make wind power generation truly cost effective and reliable, advanced and robust control algorithms are derived to on-line adjust the excitation winding voltage of the generator based on both mechanical and electrical dynamics. This method is shown to be able to achieve smooth and asymptotic rotor position tracking, as justified by analysis.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.04a
• /
• pp.481-484
• /
• 1996

When logistics system is integrated with production system and marketing system, it takes a very important role of the business management. In general, measurement of logistics cost in logistics system uses the conventional cost assignment method. However the conventional method may result in the incorrect cost because the overhead cost may be incorrectly assigned to the products. Activity-Based Costing(ABC) was proposed as an alternative method which will distribute the overhead cost to each cost obeject more accurately. ABC assigns cost to activities based on the amounts of resources used by resource driver, and assigns cost to cost objects based on the amount of activities driver. This study proposes two heuristic algorithms. The first algorithm selects the best activity driver for each cost object by using correlation analysis. The best activity driver is the one that minimizes the sum of loss cost and measurement cost of activity driver. The second algorithm selects the best number of activities by using correlation analysis. The pair of activities with the highest correlation are combined into one if the saving of measurement cost is no less than the loss due to inaccurate distribution of overhead cost. In order to demonstrate the procedure and validity of the algorithms, Real data of one year from a paper manufacturer are used.

• Korean Journal of Remote Sensing
• /
• v.9 no.2
• /
• pp.21-34
• /
• 1993

Digitalized topographic information is necessary for many areas such as landscape analysis, civil engineering planning and design, and geographic information systems. It can also be used in flight simulator and automatic navigation of unmanned plane if it is stored in computer in relevant format. Topographic information is coded with various symbols including contour lines, and is analyzed by trained personnels. The information should be stored in computer for automatic analysis, but it requires a lot of time and manpower to enter the contours using manual input devices such as digitizing tablet. This paper deals with automatic extraction and reconstruction of 3D topographic information from 2D terrain map. Several algorithms were developed in this work including contour segment finding algorithm and contour segment linking algorithm. The algorithm were tested using real 2D terrain map.

• Computers and Concrete
• /
• v.33 no.2
• /
• pp.137-145
• /
• 2024

The technique of experimentally determining concrete's compressive strength for a given mix design is time-consuming and difficult. The goal of the current work is to propose a best working predictive model based on different machine learning algorithms such as Gradient Boosting Machine (GBM), Stacked Ensemble (SE), Distributed Random Forest (DRF), Extremely Randomized Trees (XRT), Generalized Linear Model (GLM), and Deep Learning (DL) that can forecast the compressive strength of ternary geopolymer concrete mix without carrying out any experimental procedure. A geopolymer mix uses supplementary cementitious materials obtained as industrial by-products instead of cement. The input variables used for assessing the best machine learning algorithm not only include individual ingredient quantities, but molarity of the alkali activator and age of testing as well. Myriad statistical parameters used to measure the effectiveness of the models in forecasting the compressive strength of ternary geopolymer concrete mix, it has been found that GBM performs better than all other algorithms. A sensitivity analysis carried out towards the end of the study suggests that GBM model predicts results close to the experimental conditions with an accuracy between 95.6 % to 98.2 % for testing and training datasets.