• Journal of the Korean Geosynthetics Society
• /
• v.17 no.4
• /
• pp.277-292
• /
• 2018

This paper presents the development and implementation of an artificial intelligence (AI)-based deep excavation induced wall and ground displacements and wall support member forces prediction program (ANN-EXCAV). The program has been developed in a C# environment by using the well-known AI technique artificial neural network (ANN). Program used ANN to predict the induced displacement, groundwater drawdown and wall and support member forces parameters for deep excavation project and run the stability check by comparing predict values to the calculated allowable values. Generalised ANNs were trained to predict the said parameters through databases generated by numerical analysis for cases that represented real field conditions. A practical example to run the ANN-EXCAV is illustrated in this paper. Results indicate that the program efficiently performed the calculations with a considerable accuracy, so it can be handy and robust tool for preliminary design of wall and support members for deep excavation project.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.7
• /
• pp.17-24
• /
• 2009

Increasing use of information system has led to larger amount of developing expenses and demands on software. Until recent days, the model using regression analysis based on statistical algorithm has been used. However, Machine learning is more investigated now. This paper estimates the software cost using SVR(Support Vector Regression). a sort of machine learning technique. Also, it finds the best set of parameters applying immune algorithm. In this paper, software cost estimation is performed by SVR based on immune algorithm while changing populations, memory cells, and number of allele. Finally, this paper analyzes and compares the result with existing other machine learning methods.

• Proceedings of the Korean Nuclear Society Conference
• /
• 1996.11a
• /
• pp.289-294
• /
• 1996

Feasibility study on conceptual design tool for liquid metal reactor has been conducted to optimize the thermohydraulic and neutronic design parameters. To accomplish this task the neutronic code PRISM, fuel performance code and scaling method have been included into the conceptual design support system. ALMR(PRISM 303MWe) has been adopted as the reference plant and principally according to the power level, conceptual design parameters are optimized so that energy balance and neutronics balance seem to be satisfied. This paper presents only the results of optimization on primary system including the IHX system.

• Proceedings of the KAIS Fall Conference
• /
• 2009.12a
• /
• pp.461-465
• /
• 2009

Normally, a distributed computing environment is flexible in controlling complex embedded systems but their software components are becoming complex as these systems are equipped with several platforms and attached to various electronic devices, sensors, and actuators. These systems requires inter-object communication mechanisms to provide fault tolerant and QoS-enabled middleware service support in a distributed system. Generally, a middleware performs analysis of the parameters to ensure the availability and reliability of data dissemination. This paper focuses in particular to designing an application middleware for the specific scenario to improve the high availability and fault tolerance of data thus improving the QoS (Quality of Service) of a distributed system. The performance of an adaptive and highly reliable middleware can be significant based on the selection of vital parameters of the system.

• Journal of applied mathematics & informatics
• /
• v.28 no.1_2
• /
• pp.351-361
• /
• 2010

The solution of large sparse linear systems is one of the most important problems in large scale scientific computing. Among the many methods developed, the preconditioned Krylov subspace methods are considered the preferred methods. Selecting a suitable preconditioner with appropriate parameters for a specific sparse linear system presents a challenging task for many application scientists and engineers who have little knowledge of preconditioned iterative methods. The prediction of ILU type preconditioners was considered in [27] where support vector machine(SVM), as a data mining technique, is used to classify large sparse linear systems and predict best preconditioners. In this paper, we apply the data mining approach to the sparse approximate inverse(SAI) type preconditioners to find some parameters with which the preconditioned Krylov subspace method on the linear systems shows best performance.

• Journal of information and communication convergence engineering
• /
• v.12 no.1
• /
• pp.14-18
• /
• 2014

A recent major development in computer technology is the advent of wearable computer systems. Wearable computer systems employ a wireless universal serial bus (WUSB), which refers to a combination of USB with the WiMedia wireless technical specifications. In this study, we focus on an integrated system of WUSB over wireless body area networks (WBANs) for wireless wearable computer systems. However, current WBAN MACs do not have well-defined quality of service (QoS) mapping and resource allocation mechanisms to support multimedia streams with the requested QoS parameters. To solve this problem, we propose a novel QoS-aware time slot allocation method. The proposed method provides fair and adaptive QoS provisioning to isochronous streams according to current traffic loads and their requested QoS parameters by executing a QoS satisfaction algorithm at the WUSB/WBAN host. The simulation results show that the proposed method improves the efficiency of time slot utilization while maximizing QoS provisioning.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.5
• /
• pp.925-931
• /
• 2009

In this paper we propose a variance function estimation method for replicated data based on averages of squared residuals obtained from estimated mean function by the least squares support vector machine. Newton-Raphson method is used to obtain associated parameter vector for the variance function estimation. Furthermore, the cross validation functions are introduced to select the hyper-parameters which affect the performance of the proposed estimation method. Experimental results are then presented which illustrate the performance of the proposed procedure.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.134.2-134
• /
• 2001

This paper treats the implementation of a statically stable control system for a biped walking robot with 10 degrees-of-freedom. Statically stable walking of a biped robot can be realized by keeping the center of mass (COM) inside the sole of the supporting foot (or feet) during single-support or double-support phases. We predetermined five static positions for walking based on the COM method. The positions can be represented by the length of the gait, the width between the feet, the height of the foot and two parameters in the hip movement. With the five parameters, we calculated the position trajectory. And we got the angular trajectories of 10 joints from the posit ion trajectory using the position tracking control and neural network. By tracking the angular trajectories, the robot can walk maintaining stability. We implemented walking of a biped robot throught the above ...

• Geomechanics and Engineering
• /
• v.15 no.1
• /
• pp.631-643
• /
• 2018

The estimation of the strength and other mechanical parameters characterizing the tensile behavior of granites can play an important role in civil engineering tasks such as design, construction, rehabilitation and repair of existing structures. The purpose of this paper is to apply data mining techniques, such as multiple regression (MR), artificial neural networks (ANN) and support vector machines (SVM) to estimate the mechanical properties of granites. In a first phase, the mechanical parameters defining the complete tensile behavior are estimated based on the tensile strength. In a second phase, the estimation of the mechanical properties is carried out from different combination of the physical properties (ultrasonic pulse velocity, porosity and density). It was observed that the estimation of the mechanical properties can be optimized by combining different physical properties. Besides, it was seen that artificial neural networks and support vector machines performed better than multiple regression model.

• 한국신재생에너지학회:학술대회논문집
• /
• 2011.11a
• /
• pp.38.1-38.1
• /
• 2011

This study investigates the effects of Pierson-Moskowitz, Jonswap spectrum that are typical irregular wave spectrums for wind turbine system with jacket support structure. Also various offshore environmental parameters based on korean local condition were used in our study. The loads acting on the system was considered by referring to the Design Load Case from IEC guide line. And improved von Karman model was used as a turbulence model. As a result, various significant wave height and peak spectral period cause noticeable difference of extreme and fatigue loads prediction.