• Communications for Statistical Applications and Methods
• /
• v.29 no.2
• /
• pp.193-202
• /
• 2022

Semi-supervised learning has gained significant attention in recent applications. In this article, we provide a selective overview of popular semi-supervised methods and then propose a simple but effective algorithm for semi-supervised classification using support vector machines (SVM), one of the most popular binary classifiers in a machine learning community. The idea is simple as follows. First, we apply the dimension reduction to the unlabeled observations and cluster them to assign labels on the reduced space. SVM is then employed to the combined set of labeled and unlabeled observations to construct a classification rule. The use of SVM enables us to extend it to the nonlinear counterpart via kernel trick. Our numerical experiments under various scenarios demonstrate that the proposed method is promising in semi-supervised classification.

• Nonlinear Functional Analysis and Applications
• /
• v.27 no.2
• /
• pp.381-403
• /
• 2022

The main goal of this research is to solve variational inequalities involving quasimonotone operators in infinite-dimensional real Hilbert spaces numerically. The main advantage of these iterative schemes is the ease with which step size rules can be designed based on an operator explanation rather than the Lipschitz constant or another line search method. The proposed iterative schemes use a monotone and non-monotone step size strategy based on mapping (operator) knowledge as a replacement for the Lipschitz constant or another line search method. The strong convergences have been demonstrated to correspond well to the proposed methods and to settle certain control specification conditions. Finally, we propose some numerical experiments to assess the effectiveness and influence of iterative methods.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.5
• /
• pp.100-107
• /
• 1997

A pneumatic artificial muscle type of actuator, which acts similar to human muscle, is developed recently. In this paper, an adaptive controller is presented for the trajectory tracking problem of a two-degree- of-freedom manipulator using two pairs of pneumatic artificial muscle actuators. Due to the nonlinearity and the uncertainty on the dynamics of the actuator, it is difficult to make the effective control schemes of this system. By the adaptive control law which inclueds a nonlinear "feedforward" term compensating paramet- ric uncertainties in addition to P.I.D. scheme, both golbal stability of the system and convergence of the tracking error are guaranted. The effectiveness of the proposed control method for the manipulator using this actuator is illustrated through experiments.periments.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.27 no.4
• /
• pp.272-280
• /
• 2023

We study the numerical analysis for the Cahn-Hilliard (CH) equation using the decoupled projection (DP) method. The CH equation is a fourth order nonlinear partial differential equation that is hard to solve. Therefore, various of numerical schemes have been proposed to solve the CH equation. To verify the relation of each existing scheme for the CH equation, we consider the DP method for linear convex splitting schemes. We present the numerical experiments to demonstrate our analysis. Throughout this study, it is expected to construct a novel numerical scheme using the relation with existing numerical schemes.

• Bulletin of the Korean Mathematical Society
• /
• v.61 no.1
• /
• pp.93-115
• /
• 2024

In this paper, the Gauge-Uzawa methods for the Darcy-Brinkman equations driven by temperature and salt concentration (DBTC) are proposed. The first order backward difference formula is adopted to approximate the time derivative term, and the linear term is treated implicitly, the nonlinear terms are treated semi-implicit. In each time step, the coupling elliptic problems of velocity, temperature and salt concentration are solved, and then the pressure is solved. The unconditional stability and error estimations of the first order semi-discrete scheme are derived, at the same time, the unconditional stability of the first order fully discrete scheme is obtained. Some numerical experiments verify the theoretical prediction and show the effectiveness of the proposed methods.

• Journal of Sensor Science and Technology
• /
• v.33 no.3
• /
• pp.119-124
• /
• 2024

Effective fire sensing is important to protect lives and property from the disaster. In this paper, we present an intelligent visual sensing method for detecting fires based on machine learning techniques. The proposed method involves a two-step process. In the first step, fire and non-fire images are used to train a convolutional neural network (CNN), and in the next step, feature vectors consisting of 256 values obtained from the CNN are used for the learning of a support vector machine (SVM). Linear and nonlinear SVMs with different parameters are intensively tested. We found that the proposed hybrid method using an SVM with a linear kernel effectively increased the recall rate of fire image detection without compromising detection accuracy when an imbalanced dataset was used for learning. This is a major contribution of this study because recall is important, particularly in the sensing of disaster situations such as fires. In our experiments, the proposed system exhibited an accuracy of 96.9% and a recall rate of 92.9% for test image data.

• Nonlinear Functional Analysis and Applications
• /
• v.29 no.3
• /
• pp.781-802
• /
• 2024

In this paper, we propose an inertial method for solving a common solution to fixed point and Variational Inequality Problem in Hilbert spaces. Under some standard and suitable assumptions on the control parameters, we prove that the sequence generated by the proposed algorithm converges strongly to an element in the solution set of Variational Inequality Problem associated with a quasimonotone operator which is also solution to a fixed point problem for a demimetric mapping. Finally, we give some numerical experiments for supporting our main results and also compare with some earlier announced methods in the literature.

• Advances in concrete construction
• /
• v.9 no.3
• /
• pp.235-248
• /
• 2020

Progressive collapse in a structure occurs when load bearing members are failed and the adjoining structural elements cannot resist the redistributed forces and fails subsequently, that leads to complete collapse of structure. Recently, construction using precast concrete technology is adopted increasingly because it offers many advantages like faster construction, less requirement of skilled labours at site, reduced formwork and scaffolding, massive production with reduced amount of construction waste, better quality and better surface finishing as compared to conventional reinforced concrete construction. Connections are the critical elements for any precast structure, because in past, major collapse of precast structure took place because of connection failure. In this study, behavior of four different precast wet connections with U shaped reinforcement bars provided at different locations is evaluated. Reduced 1/3^rd scale precast beam column assemblies having two span beam and three columns with removed middle column are constructed and examined by performing experiments. The response of precast connections is compared with monolithic connection, under column removal scenario. The connection region of test specimens are filled by cast-in-place micro concrete with and without polypropylene fibers. Performance of specimen is evaluated on the basis of ultimate load carrying capacity, maximum deflection at the location of removed middle column, crack formation and failure propagation. Further, Finite element (FE) analysis is carried out for validation of experimental studies and understanding the performance of structural components. Monolithic and precast beam column assemblies are modeled using non-linear Finite Element (FE) analysis based software ABAQUS. Actual experimental conditions are simulated using appropriate boundary and loading conditions. Finite Element simulation results in terms of load versus deflection are compared with that of experimental study. The nonlinear FE analysis results shows good agreement with experimental results.

• Journal of the Korea Concrete Institute
• /
• v.18 no.2 s.92
• /
• pp.177-188
• /
• 2006

Conventional nonlinear finite element analysis requires complicated modeling and analytical technique. Furthermore, it is difficult to interpret the analytical results presented as the stress-strain relationship. In the present study, a design-oriented analytical method using the truss model was developed. A reinforced concrete member to be analyzed was idealized by longitudinal, transverse, and diagonal line elements. Basically, each element was modeled as a composite element of concrete and re-bars. Simplified cyclic models for the concrete and re-bar elements were developed. RC beams and walls with various reinforcement details were analyzed by the proposed method. The inelastic strength, energy dissipation capacity, deformability, and failure mode predicted by the proposed method were compared with those of existing experiments. The results showed that the proposed model accurately predicted the strength and energy dissipation capacities, and to predict deformability of the members, the compression-softening model used for the concrete strut element must be improved.

• Bulletin of the Society of Naval Architects of Korea
• /
• v.26 no.4
• /
• pp.3-13
• /
• 1989

In recent towing tank experiments, it has been observed that a ship moving near the critical speed $\sqrt{gh}$(g=gravitational acceleration, h=water depth) radiates solitons upstream in an almost periodic manner. As a ,consequence, the ship experiences considerable changes in resistance, trim and sinkage, or better known as squat. Mei and Choi(1987) developed a nonlinear theory for a slender ship by using the method of matched asymptotic expansions. For a certain class of channel width and ship slenderness, they found that the waves generated can be described by an inhomogeneous Korteweg-de Vries(KdV) equation. The leading-order solution properly predicts solitons propagating upstream, but it fails to render three-dimensional waves in the wake. In this paper a new approach has been made by choosing a different class of channel width and ship slenderness. The wave equation in the farfield turns out to be a homogeneous Kadomtsev-Petviashvili(KP) equation, which predicts solitons upstream and three-dimensional waves in the wake. Numerical results for the wave resistance, sinkage and trim reflect the experimentally identified phenomena.