• Journal of Digital Convergence
• /
• v.20 no.4
• /
• pp.389-396
• /
• 2022

Deep Learning is based on a perceptron, and is currently being used in various fields such as image recognition, voice recognition, object detection, and drug development. Accordingly, a variety of learning algorithms have been proposed, and the number of neurons constituting a neural network varies greatly among researchers. This study analyzed the learning characteristics according to the number of neurons of the currently used SGD, momentum methods, AdaGrad, RMSProp, and Adam methods. To this end, a neural network was constructed with one input layer, three hidden layers, and one output layer. ReLU was applied to the activation function, cross entropy error (CEE) was applied to the loss function, and MNIST was used for the experimental dataset. As a result, it was concluded that the number of neurons 100-300, the algorithm Adam, and the number of learning (iteraction) 200 would be the most efficient in deep learning learning. This study will provide implications for the algorithm to be developed and the reference value of the number of neurons given new learning data in the future.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.9
• /
• pp.1564-1570
• /
• 2016

This study proposes a newly modified form of existing ground electrodes in order to secure trust of grounding system for large current caused by a stroke of lightning. Proposed planar earth structure has a several needle electrodes around a circular rod and 4 plane electrodes in all directions. The plane electrodes are fused with the insulator on the linear rod, so that they're electrically isolated. The concept is to increase the discharge amount of earth structure using multiple discharge paths like needle and plane electrodes. To check the discharge efficiency of the suggested scheme, the discharge currents are compared with typically used two kinds of ground rods. To ensure accuracy in the measurement of the discharge current, the same material was used for the comparison model. Also, the ground resistance are simulated by CDEGS commercial software and the results are compared with measured data. Based on this kind of experimental study, the suggested ground rod can be used when designing a ground system or when constructing a ground system at the site.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.11
• /
• pp.115-124
• /
• 2013

In this paper, we suggest a secure data dissemination by Lightweight Individual Encryption Multicast scheme over wireless sensor networks using the individual encryption method with Forward Error Correction instead of the group key encryption method. In wireless sensor networks, a sink node disseminates multicast data to the number of sensor nodes to update the up to date software such as network re-programming and here the group key encryption method is the general approach to provide a secure transmission. This group key encryption approach involves re-key management to provide a strong secure content distribution, however it is complicated to provide group key management services in wireless sensor networks due to limited resources of computing, storage, and communication. Although it is possible to control an individual node, the cost problem about individual encryption comes up and the individual encryption method is difficult to apply in multicast data transmission on wireless sensor networks. Therefore we only use 0.16% of individually encrypted packets to securely transmit data with the unicast to every node and the rest 99.84% non-encrypted encoded packets is transmitted with the multicast for network performance.

• Journal of Aerospace System Engineering
• /
• v.16 no.1
• /
• pp.17-27
• /
• 2022

A certain level of stability margin airworthiness criteria should be met to secure robustness against uncertainties between the real plant and the model in a flight control system design. The U.S. Department of Defense (DoD) specification of MIL-F-9490D and airworthiness certification standard of MIL-HDBK-516B uses gain and phase margin criteria of flight control system. However, the same stability margin criteria is applied at all development phases without considering the design maturity of each development phase of the aircraft. Ultimately, a problem arises when the aircraft operation envelope is excessively restricted. This paper proposes the relation of handling qualities and stability margin, and presents re-established stability margin criteria as a development phases and verification methods. The results of the research study are considered to contribute to the verification of the stability margin criteria more flexibly and effectively by applying the method to not only the currently manned developing aircrafts but also the unmanned vehicle to be developed in the future.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.12
• /
• pp.27-36
• /
• 2019

The demand for a low dispersion lens with a small refractive index and a high refractive index is increasing, and accordingly, there is an increasing need for a releasable protective film with high heat resistance and abrasion resistance. On the other hand, the optical industry has not yet established a clear standard for the manufacturing process and quality standards for mold-releasing protective films used in aspheric glass lens molding. Optical lens manufacturers treat this technology as proprietary information. In this study, an experiment was conducted regarding the optimization of ion etching, magnetron, and arc current at each source and filter part, and bias voltage in FCVA (filtered cathode vacuum arc)-based Ta-C thin film coatings. This study found that compared to iridium-rhenium alloy thin film sputtering products, the coating conditions were improved by approximately 50%, 20%, and 40% in terms of thickness, hardness, and adhesive strength of the film, respectively. The thin-film coating process proposed in this study is expected to contribute significantly to the development and utilization of glass lenses, which will help enhance the minimum mechanical properties and quality of the mold-release thin film layer required for glass mold surface forming technology.

• Progress in Medical Physics
• /
• v.31 no.2
• /
• pp.20-28
• /
• 2020

Purpose: The objective of this study is to perform Postal dosimetry audits for medical linear accelerators in radiation therapy institutions using glass dosimeters and Gafchromic film reading systems and postal dosimetry audit procedures, and to evaluate radiation therapy doses and mechanical accuracy in medical institutions. Methods: Photon output measured and analyzed using a standard phantom for measuring photon output dose using a glass dosimeter for medical linear accelerators. Mechanical accuracy was measured and analyzed using software for film measurement. Results: Measurement and analysis of photon beam output dose using a standard phantom glass dosimeter for photon beam output dose measurement was completed. All tolerance doses were within 5%. Mechanical accuracy measurement and analysis using a standard phantom for verifying the mechanical accuracy of linear accelerator (LINAC) using a Gafchromic film were completed, and all results were shown within tolerances (2 mm or less). Conclusions: In this study, Postal dosimetry audits were performed on the output dose and mechanical accuracy of photon beams (207 beams) for 106 LINACs from 48 institutions. As a result of corrective action and re-execution, it was confirmed that all engines met the acceptable standard within 2 mm in the linear accelerator.

• The Journal of Korea Robotics Society
• /
• v.12 no.2
• /
• pp.239-247
• /
• 2017

The purpose of this study is to develop a motion generation technique based on a double inverted pendulum model (DIPM) that learns and reproduces humanoid robot (or virtual human) motions while keeping its balance in a pattern similar to a human. DIPM consists of a cart and two inverted pendulums, connected in a serial. Although the structure resembles human upper- and lower-body, the balancing motion in DIPM is different from the motion that human does. To do this, we use the motion capture data to obtain the reference motion to keep the balance in the existence of external force. By an optimization technique minimizing the difference between the motion of DIPM and the reference motion, control parameters of the proposed method were learned in advance. The learned control parameters are re-used for the control signal of DIPM as input of linear quadratic regulator that generates a similar motion pattern as the reference. In order to verify this, we use virtual human experiments were conducted to generate the motion that naturally balanced.

• Journal of Construction Engineering and Project Management
• /
• v.6 no.3
• /
• pp.1-7
• /
• 2016

The purpose of this paper is to develop a model for selecting the best contractor in the Gaza Strip using the Artificial Neural Network (ANN). The contractor's selection methods and criteria were identified using a field survey. Fifty four engineers were asked to fill a questionnaire that covers factors related to the selection criteria of contractors practiced in Gaza Strip. The results shows that the dominant part of respondents (91%) confirmed that the current awarding method "the lowest bid price" is considered one of the major problems of the construction sector, "award the bid to the highest weight after combination of the technical and financial scores" represented 50% of the respondents. The criteria weights were determined based on Relative Importance Index (RII. Ninety-one tenders(13 projects) were used to train and test the ANN model after re-evaluating the contractors depend on the weights of factors to select the best contractor who achieves the highest score. Neurosolution software was used to train the models. The results of the trained models indicated that neural network reasonably succeeded in selection the best contractor with 95.96% accuracy. The performed sensitivity analysis showed that the profitability and capital of company are the most influential parameters in selection contractors. This model gives chance to the owner to be more accurate in selecting the most appropriate contractor.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.16 no.3
• /
• pp.54-62
• /
• 2017

When gears mesh, shock and noise are produced as results of tooth error and tooth deformation under load. Transmission error (TE) is the most important cause of gear noise and vibration because TEs affect the changes of the force and the speed of gears. Gear tooth modification research plays a positive role in reducing TE and improving the design level and transmission performance of transmission systems. In high-precision manufacturing gear, gear tooth modification is also commonly used to reduce noise in practical applications. In order to study the accuracy of gear transmission, some empirical gear profile micro-modifications are introduced, and a helical gear pair is modeled and analyzed in RomaxDesigner software to investigate the utility of these modification methods. Some of these will be selected as experimental proposals for gear pairs, and these manufactured gears will be tested and compared in a semi-anechoic room later. The final purpose of this study is to find reasonable and convenient empirical formulae to facilitate improved gear production.

• Journal of Advanced Marine Engineering and Technology
• /
• v.30 no.2
• /
• pp.275-283
• /
• 2006

Experiment and three dimensional numerical investigations of incompressible turbulent flow through square channels with one- and two-sided ribbed walls are performed to determine pressure drop and heat transfer. The CFX(version 5.7) software package is used for the computation. The ribbed walls have a $45^{\circ}$ inclined square rib. Uniform heat flux is maintained on whole inner heat transfer channel area. The numerical results coincide with experimental data that obtained for $7,600{\le}Re{\le}24.900$, the pitch-to-rib height ratio (p/e) of 8.0. and the rib height-to-channel hydraulic diameter ratio ($e/D_h$) of 0.0667. The results show that values of local heat transfer coefficient and friction factor in the channel with two-sided ribbed wall are higher than those in the channel with one-sided ribbed walls.