• The Journal of the Convergence on Culture Technology
• /
• v.10 no.5
• /
• pp.163-171
• /
• 2024

This study applies neural network analysis techniques to examine the factors influencing the purchasing decisions of fashion eyewear among women in their 30s and 40s, comparing these findings with traditional parametric analysis methods. In the fashion area, machine learning techniques are utilized for personalized fashion recommendation systems. However, research on such applications in Korea remains insufficient. By reanalyzing a study conducted in 2017 using traditional quantitative methods with these new techniques, this study aims to confirm the utility of neural network methods. Notably, the study finds that the classification accuracy of preferred sunglasses design is highest, at 86.2%, when the L-BFGS-B neural network is activated using the hyperbolic tangent function. The most critical factors influencing purchasing decisions were consumers' occupations and their pursuit of new styles. It is interpreted that Korean sunglasses consumers prefer "safe changes." These findings are consistent for selecting both the frames and lenses of sunglasses. Traditional quantitative analysis suggests that the type of sunglasses preferred varies according to the group to which a consumer belongs. In contrast, neural network analysis predicts the preferred sunglasses for each individual, thereby facilitating the development of personalized sunglasses recommendation systems.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.1 s.173
• /
• pp.190-195
• /
• 2000

It has been established that a crack has an important effect on the dynamic behavior of a structure. This effect depends mainly on the location and depth of the crack. To identify the location and depth of a crack in a structure. Nikolakopoulos et. al. used the intersection point of the superposed contours that correspond to the eigenfrequency caused by the crack presence. However the intersecting point of the superposed contours is not only difficult to find but also incorrect to calculate. A method is presented in this paper which uses optimization technique for the location and depth of the crack. The basic idea is to find parameters which use the structural eigenfrequencies on crack depth and location and optimization algorithm. With finite element model of the structure to calculate eigenfrequencies, it is possible to formulate the inverse problem in optimization format. Method of optimization is augmented lagrange multiplier method and search direction method is BFGS variable metric method and one dimensional search method is polynomial interpolation.

• Journal of Korean Society on Water Environment
• /
• v.24 no.2
• /
• pp.239-246
• /
• 2008

In this study, an optimized deterministic water-quality model was constructed to estimate water quality of a river and lake in the upstream basin of a dam. A stochastic water-quality analysis using reliability analysis technique was applied to the model. The model was tested in the 13.9 km reach from Maeil stage station of Kyechun to Hoengsung Dam of Sum River. After finding hydraulic characteristics from nonuniform flow analysis, Broyden-Fletcher-Goldfarb-Shanno (BFGS) optimization technique for model calibration was applied to determine optimum reaction parameters, and model verification was performed based on these. The stochastic model, using Mean First­Order Second­-Moment (MFOSM) and Monte-Carlo methods, was applied to the same reach as the deterministic study. Variations of discharge and water quality in headwater were considered, as well as variations of hydraulic coefficients and reaction coefficients. The statistical results of output variables from MFOSM were similar to those from the Monte-Carlo method. Risk analysis using MFOSM and Monte-Carlo methods presented the probabilities of some locations in the Hoengsung Lake violating existing water-quality standards in terms of DO and BOD.

• Journal of Advanced Marine Engineering and Technology
• /
• v.24 no.6
• /
• pp.7-14
• /
• 2000

Nowadays, the viscous damper using high viscosity oil was much to be used for engine shafting system to reduce the excessive additional stress by torsional vibration. In general, it was assumed that the viscous damper could be modelled having only damping coefficient, that is to say, whose stiffness be ignored. But it is found that there exists a jump phenomenon, as a kind of non-linear vibration, in the actual engine shafting system with a damper of high viscosity. Therefore the damper ring and the casing are modelled as two mass elastic system with a complex viscosity. Also, to analyze a non-linear phenomenon, it is assumed that the viscous damper has a linear stiffness coefficient in proportion to the angular amplitude and a non-linear stiffness coefficient in proportion to cube of the angular amplitude. For the analysis, Quasi-Newton method with BFGS(Broyden-Fletcher-Goldfarb-Shanno) formula is used. Both calculated and measured values are provided in this paper which confirm the possibility of applying non-linear theory to engine shafting system with viscous damper.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.14 no.3
• /
• pp.594-602
• /
• 1990

A computer-aided design system of involute cylindrical gears(spur and helical gears) for power transmission is developed, in which the volume of a gear unit is minimized with satisfying various design constraints. As the design constraints, bending strength and pitting resistance of AGMA 218.01, scoring of Dudley's flash temperature, contact ratio, and involute interference of pinion are considered and effective factors for strength calculation(life, reliability, hardness ratio, load distribution, velocity, etc.) are also included. This complicated nonlinear optimization problem is solved by using ALM(Augmented-Lagrange-Multiplier) method with self scaling BFGS(Broydon-Fletcher-Goldfarb-Shanno) method employed for unconstrained optimization programming. This design method can be easily applied to designing power transmission gear unit in the machines of various kinds. It is expected for the proposed method to be a contribution for an automated design of gear unit towards weight minimization, miniaturization and high strength of gear unit.

• Journal of Drive and Control
• /
• v.14 no.4
• /
• pp.45-50
• /
• 2017

The gas spring is a hydropneumatic adjusting element, consisting of a pressure tube, a piston rod, a piston and a connection fitting. The gas spring is filled with compressed nitrogen within the cylinder. The filling pressure acts on both sides of the piston and because of area difference it produces an extension force. Therefore, a gas spring is similar in function compare to mechanical coil spring. Conversely, optimization is a process of finding the best set of parameters to reach a goal while not violating certain constraints. The AMESim software provides NLPQL (Nonlinear Programming by Quadratic Lagrangian) and GA (genetic algorithm) for optimization. The NLPQL method builds a quadratic approximation to the Lagrange function and linear approximations to all output constraints at each iteration, starting with the identity matrix for the Hessian of the Lagrangian, and gradually updating it using the BFGS method. On each iteration, a quadratic programming problem is solved to find an improved design until the final convergence to the optimum design. In this study, we conducted optimization design of the gas spring reaction force with NLPQL.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.12
• /
• pp.5614-5633
• /
• 2018

Mobile Edge Computing (MEC) and Wireless Power Transfer (WPT) are both recognized as promising techniques, one is for solving the resource insufficient of mobile devices and the other is for powering the mobile device. Naturally, by integrating the two techniques, task will be capable of being executed by the harvested energy which makes it possible that less intrinsic energy consumption for task execution. However, this innovative integration is facing several challenges inevitably. In this paper, we aim at prolonging the battery life of mobile device for which we need to maximize the harvested energy and minimize the consumed energy simultaneously, which is formulated as residual energy maximization (REM) problem where the offloading ratio, energy harvesting time, CPU frequency and transmission power of mobile device are all considered as key factors. To this end, we jointly optimize the offloading ratio, energy harvesting time, CPU frequency and transmission power of mobile device to solve the REM problem. Furthermore, we propose an efficient convex optimization and sequential unconstrained minimization technique based combining method to solve the formulated multi-constrained nonlinear optimization problem. The result shows that our joint optimization outperforms the single optimization on REM problem. Besides, the proposed algorithm is more efficiency.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.9
• /
• pp.2764-2781
• /
• 2024

Federated learning (FL) has been proposed as an emerging distributed machine learning framework, which lowers the risk of privacy leakage by training models without uploading original data. Therefore, it has been widely utilized in the Industrial Internet of Things (IIoT). Despite this, FL still faces challenges including the non-independent identically distributed (Non-IID) data and heterogeneity of devices, which may cause difficulties in model convergence. To address these issues, a local surrogate function is initially constructed for each device to ensure a smooth decline in global loss. Subsequently, aiming to minimize the system energy consumption, an FL approach for joint CPU frequency control and bandwidth allocation, called FCBAFL is proposed. Specifically, the maximum delay of a single round is first treated as a uniform delay constraint, and a limited-memory Broyden-Fletcher-Goldfarb-Shanno bounded (L-BFGS-B) algorithm is employed to find the optimal bandwidth allocation with a fixed CPU frequency. Following that, the result is utilized to derive the optimal CPU frequency. Numerical simulation results show that the proposed FCBAFL algorithm exhibits more excellent convergence compared with baseline algorithm, and outperforms other schemes in declining the energy consumption.

• Journal of the Korean Society for Railway
• /
• v.12 no.6
• /
• pp.974-982
• /
• 2009

To improve the effectiveness and economics the bridge design methodology considering the bridge/rail longitudinal analysis and bridge/vehicle dynamic effect suggested in this study. The reliability-based Life-Cycle Costs(LCC) effective optimum design is applied to a 2-main steel girder bridge, 5$\times$(1@50m) for comparison with conventional design, initial cost optimization and equivalent LCC optimization. As a result of the optimum design based on reliability, it may be stated that the design of High-Speed railway bridges considering the bridge/rail longitudinal analysis and bridge/vehicle dynamic effect are more efficient than typical existing bridges and LCC optimization without respect to bridge/rail longitudinal analysis and bridge/vehicle dynamic effect. The result of optimization design considering the interaction, design methodology suggested in this study, is higher than result of initial cost optimization design in initial cost, but that has the advantage than result of initial cost optimization design in expected LCC.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.10 no.6
• /
• pp.27-34
• /
• 2010

Recently, high-speed railway systems have gained increased interest as a means of environmental friendly transportation, and numerous bridges for high-speed railways have been constructed accordingly. However, bridge design for high-speed railways requires more consideration than conventional railway design because fast-moving trains will lead to significant impact on bridge structures. Thus, this research proposes a revised design considering both bridge-rail longitudinal interaction and dynamic effect of trains to ensure stability of fast travelling trains. To validate the proposed design algorithm, numerical analyses are performed and compared using a constructed 250 m long bridge with 5 spans for a high-speed railway. From the numerical results, the proposed optimum design of high-speed railway bridges exhibits the most economic life-cycle-cost (LCC) when compared with several existing design approaches.