• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.5
• /
• pp.1957-1975
• /
• 2016

The outage probability (OP) performance of multiple-relay-based incremental hybrid decode-amplify-forward (IHDAF) relaying mobile-to-mobile (M2M) networks with transmit antenna selection (TAS) over N-Nakagami fading channels is investigated in this paper. The closed-form expressions for approximate OP of the optimal and suboptimal TAS schemes are derived. The power allocation problem is formulated for performance optimization. Then the OP performance under different conditions is evaluated through numerical simulations to verify the analysis. The simulation results showed that optimal TAS scheme has a better OP performance than suboptimal TAS scheme; the power-allocation parameter has an important influence on the OP performance.

• Korean Journal of Materials Research
• /
• v.34 no.7
• /
• pp.363-369
• /
• 2024

In this study, the magnetocaloric effect and transition temperature of bulk metallic glass, an amorphous material, were predicted through machine learning based on the composition features. From the Python module 'Matminer', 174 compositional features were obtained, and prediction performance was compared while reducing the composition features to prevent overfitting. After optimization using RandomForest, an ensemble model, changes in prediction performance were analyzed according to the number of compositional features. The R2 score was used as a performance metric in the regression prediction, and the best prediction performance was found using only 90 features predicting transition temperature, and 20 features predicting magnetocaloric effects. The most important feature when predicting magnetocaloric effects was the 'Fe' compositional ratio. The feature importance method provided by 'scikit-learn' was applied to sort compositional features. The feature importance method was found to be appropriate by comparing the prediction performance of the Fe-contained dataset with the full dataset.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.12
• /
• pp.9-16
• /
• 2017

In this paper, the aerodynamic design process of wind turbine blades is established. The optimization design strategy is presented and the constraints that must be reviewed during the aerodynamic design process are summarized. Based on this, this study developed a BEMT-based aerodynamic optimal design program that can be applied easily to actual work, not only for research purposes, but also can be integrated from the initial concept design stage to the final 3D shape detail design stage. The developed program AeroDA consisted of a concept design module, basic design module, optimal TSR module, local shape optimization module, performance analysis module, design verification module, and 3D shape generation module. Using the developed program, an improved design of the 5MW blade by NREL was made, and it was confirmed that this program could be used for design optimization. In addition, a 10kW blade aerodynamic design and turbine detailed performance analysis were carried out, and it was verified by a comparison with the commercial program DNVGL Bladed.

• Smart Structures and Systems
• /
• v.4 no.5
• /
• pp.641-653
• /
• 2008

This paper proposes a practical and realistic method to establish an optimal lifetime maintenance strategy for deteriorating bridges by considering the life-cycle performance as well as the life-cycle cost. The proposed method offers a set of optimal tradeoff maintenance scenarios among other conflicting objectives, such as minimizing cost and maximizing performance. A genetic algorithm is used to generate a set of maintenance scenarios that is a multi-objective combinatorial optimization problem related to the lifetime performance and the life-cycle cost as separate objective functions. A computer program, which generates optimal maintenance scenarios, was developed based on the proposed method using the life-cycle costs and the performance of bridges. The subordinate relation between bridge members has been considered to decide optimal maintenance sequence and a corresponding algorithm has been implemented into the program. The developed program has been used to present a procedure for finding an optimal maintenance scenario for steel-girder bridges on the Korean National Road. Through this bridge maintenance scenario analysis, it is expected that the developed method and program can be effectively used to allow bridge managers an optimal maintenance strategy satisfying various constraints and requirements.

• Korean Journal of Radiology
• /
• v.24 no.7
• /
• pp.698-714
• /
• 2023

In recent years, artificial intelligence, especially object detection-based deep learning in computer vision, has made significant advancements, driven by the development of computing power and the widespread use of graphic processor units. Object detection-based deep learning techniques have been applied in various fields, including the medical imaging domain, where remarkable achievements have been reported in disease detection. However, the application of deep learning does not always guarantee satisfactory performance, and researchers have been employing trial-and-error to identify the factors contributing to performance degradation and enhance their models. Moreover, due to the black-box problem, the intermediate processes of a deep learning network cannot be comprehended by humans; as a result, identifying problems in a deep learning model that exhibits poor performance can be challenging. This article highlights potential issues that may cause performance degradation at each deep learning step in the medical imaging domain and discusses factors that must be considered to improve the performance of deep learning models. Researchers who wish to begin deep learning research can reduce the required amount of trial-and-error by understanding the issues discussed in this study.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.4
• /
• pp.678-691
• /
• 2015

Internet and mobile traffic continues to surge exponentially in recent years due to popularization of smart devices, the appearance of various internet services carrying large amount of traffic from richer content and applications. This phenomenon leaded to various network problems such as the congestion delay, the non-balanced traffic ratio between ISPs, the continuous network investment cost and the Internet access problems. In light of changed data-driven communication ecosystem, There are growing concerns by both academia and industry that settlement-free peering and full transit regime have the limitations such as not only difficulties in maintaining mutual benefits but also difficulties in securing investment incentives for upgrading network performance and quality. Thus, it becomes more necessary for introducing the evolved internet interconnection regime which can fulfill the All-IP network environment. This study derives core issues regarding internet interconnection regime in Korea and suggest new evolved alternatives based on three point of view(traffic optimization, cost optimization, network investment optimization) through the empirical analysis.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.37 no.8
• /
• pp.737-743
• /
• 2009

Design optimization process and results of Loop Heat Pipe(LHP) using Tabu Search have been presented in this study. An objective of optimization is to reduce a mass of the LHP with satisfying operating temperature of a Lithium Ion battery onboard an aircraft. The battery is assumed to be used as power supply of air borne high energy laser system because of its high specific energy. The analytical models are based on a steady state mathematical model and the design optimization is performed using a Meta Model and Tabu Search. As an optimization results, the Tabu search algorithm guarantees global optimum with small computation time. Due to searching by random numbers, initial value is dominant factor to search global optimum. The optimization process could reduce the mass of the LHP which express the same performance as an published LHP.

• Structural Engineering and Mechanics
• /
• v.86 no.5
• /
• pp.647-661
• /
• 2023

It is recognized that the installation of energy dissipation devices, such as the tuned mass damper (TMD), decreases the dynamic response of structures, however, the best parameters of each device persist hard to determine. Unlike many works that perform only a deterministic optimization, this work proposes a complete methodology to minimize the dynamic response of footbridges by optimizing the parameters of multiple tuned mass dampers (MTMD) taking into account uncertainties present in the parameters of the structure and also of the human excitation. For application purposes, a steel footbridge, based on a real structure, is studied. Three different scenarios for the MTMD are simulated. The proposed robust optimization problem is solved via the Circle-Inspired Optimization Algorithm (CIOA), a novel and efficient metaheuristic algorithm recently developed by the authors. The objective function is to minimize the mean maximum vertical displacement of the footbridge, whereas the design variables are the stiffness and damping constants of the MTMD. The results showed the excellent capacity of the proposed methodology, reducing the mean maximum vertical displacement by more than 36% and in a computational time about 9% less than using a classical genetic algorithm. The results obtained by the proposed methodology are also compared with results obtained through traditional TMD design methods, showing again the best performance of the proposed optimization method. Finally, an analysis of the maximum vertical acceleration showed a reduction of more than 91% for the three scenarios, leading the footbridge to acceleration values below the recommended comfort limits. Hence, the proposed methodology could be employed to optimize MTMD, improving the design of footbridges.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.9
• /
• pp.39-45
• /
• 2009

When Mobile IPv6 is deployed in commercial network, a mobile node needs AAA services for an authentication, authorization and accounting. AAA and Mobile IPv6 are protocols which are operated independently. Then schemes which merge these protocols have been emerged. These schemes can enable a mobile node to establish a security association between the mobile node and a home agent and to perform a binding update for the home agent using AAA authentication request. But these schemes introduce many signal messages and long handover latency during the handover, since Route Optimization mode for Mobile Ipv6 is performed using Return Routability procedure. To solve this problem, we propose a scheme for Route Optimization mode that the home agent performs the binding update for a correspondent node via the AAA infrastructure between the home agent and the correspondent node instead of Return Routability procedure. For performance evaluation, we analyze signal message transmission costs and handover latencies during handover. We show performance improvement of the proposed scheme which reduces handover latency as 61% compared with the existing scheme.

• Journal of the Korean Society of Radiology
• /
• v.18 no.1
• /
• pp.21-26
• /
• 2024

The one of the famous deep learning models for object detection task is you only look once version 5 (YOLOv5) framework based on the one stage architecture. In addition, YOLOv5 model indicated high performance for accurate lesion detection using the bottleneck CSP layer and skip connection function. The purpose of this study was to evaluate the performance of YOLOv5 framework according to various hyperparameters in position emission tomogrpahy (PET) phantom images. The dataset was obtained from QIN PET segmentation challenge in 500 slices. We set the bounding box to generate ground truth dataset using labelImg software. The hyperparameters for network train were applied by changing optimization function (SDG, Adam, and AdamW), activation function (SiLU, LeakyRelu, Mish, and Hardwish), and YOLOv5 model size (nano, small, large, and xlarge). The intersection over union (IOU) method was used for performance evaluation. As a results, the condition of outstanding performance is to apply AdamW, Hardwish, and nano size for optimization function, activation function and model version, respectively. In conclusion, we confirmed the usefulness of YOLOv5 network for object detection performance in nuclear medicine images.