• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.3
• /
• pp.483-490
• /
• 2022

Malaria is a disease caused by a parasite and it is prevalent in all over the world. The usual method used to recognize malaria cells is a thick and thin blood smears examination methods, but this method requires a lot of manual calculation, so the efficiency and accuracy are very low as well as the lack of pathologists in impoverished country has led to high malaria mortality rates. In this paper, a malaria cell image recognition model using transfer learning is proposed, which consists in the feature extractor, the residual structure and the fully connected layers. When the pre-training parameters of the VGG-19 model are imported to the proposed model, the parameters of some convolutional layers model are frozen and the fine-tuning method is used to fit the data for the model. Also we implement another malaria cell recognition model without residual structure to compare with the proposed model. The simulation results shows that the model using the residual structure gets better performance than the other model without residual structure and the proposed model has the best accuracy of 97.33% compared to other recent papers.

• The KIPS Transactions:PartC
• /
• v.13C no.3 s.106
• /
• pp.369-374
• /
• 2006

This paper related with the performance improvement of adaptive equalizer that is a based on the tricepstrum eqalization algorithm by using the received signal. Adaptive equalizer used for the improvement of communication performance, like as high speed, maintain of synchronization, BER, at the receive side in the environment of communication channel of the presence of the aditive noise, phase distortion and frequency selective fading, mainly. It's characteristics are nearly same as the inverse characterstics of the communication channel. In this paper, the TEA algorithm using the HOS and the 16-QAM which is 2-dimensional signaling method for being considered signal was used. For the precoding of 16-QAM singnal in the assignment of the signal costellation, Gray code was used, and the improvement of performance was gained by computer simulation in the residual intersymbol interence and mean squared error which is representive measurement of adaptive equalizer.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.2
• /
• pp.85-90
• /
• 2019

This paper related with the M-CMA adaptive equalization algorithm which is possible to improve the residual isi and robustness performance compare to the current MMA algorithm that is reduce the intersymbol interference occurs in channel when transmitting the QAM signal. The current MMA algorithm depend on the cost function and error function using fixed signal dispersion constant, but the M-CMA algorithm depend on the new proposed cost function and error function using multiple dispersion constant. By this, it is possible to having robustness of the CMA and simultaneous compensation of amplitude and phase of MMA. The computer simulation was performed in the same channel and noise environment for compare the proposed M-CMA and current MMA algorithm. The equalizer output signal constellation, residual isi, MD, MSE learning courves and SER, represents the robustness were used for performance index. As a result of simulation, the M-CMA has more superior to the MMA in robustness and other performance index.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.5
• /
• pp.115-121
• /
• 2019

In this paper, we propose MSAG-SCS-MMA-I adaptive blind equalization with double step size with very small residual ISI and MSE at steady-state while significantly improving the convergence speed of the traditional SCS-MMA-I algorithm in 256-QAM system. And we evaluate the equalization performance for this algorithm. Different step sizes according to the absolute value of decision-directed error instead of a fixed step-size are applied to the tap update equation of MSAG-SCS-MMA-I, which is controlled by binary flags of '1' or '0' obtained from SCS-MMA-I and decision-directed algorithms. This makes for excellent equalization performance. As a result of computer simulation, we confirmed that the proposed algorithm has more better performance than the MMA, SCS-MMA-I, and MSAG-SCS-MMA-I algorithms in terms of the performance index such as residual ISI, MSE, and MD.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.5
• /
• pp.331-338
• /
• 2023

Modern bulletproof armor must be light and have excellent penetration resistance to ensure the mobility and safety of soldiers and military vehicles. The ballistic performance of heterogeneous structures of laminated flat plates as bulletproof armor depends on the arrangement of constituent materials for the same weight. In this study, we analyze bulletproof performance according to the stacking sequence of laminated bulletproof armor composed of Kevlar, ultra-high molecular weight polyethylene, and ethylene-vinyl-acetate foam. A ballistic analysis was performed by colliding a 7.62 × 51 mm NATO cartridge's M80 bullet at a speed of 856 m/s with six lamination arrangements with constituent materials thicknesses of 5 mm and 6.5 mm. To evaluate the bulletproof performance, the residual speed and residual energy of the projectile that penetrated the heterogeneous laminated flat plates were measured. Simulation results confirmed that the laminated structure with a stacking sequence of Kevlar, ultra-high molecular weight polyethylene, and ethylene-vinyl-acetate foam had the best bulletproof performance for the same weight.

• Proceedings of the Korea Society for Energy Engineering kosee Conference
• /
• 1997.10a
• /
• pp.9-16
• /
• 1997

원유 정제의 가장 heavy한 잔류물인 중잔유(heavy residual oil)의 IGCC 프랜트의 적용성능을 평가하기 위한 방안으로, 정적시스템 모사방법을 사용하여 중잔유를 발전 연료로 사용한 IGCC 플랜트를 모사하였다. 모사에 적용한 중잔유는 Visbreaker Residue와Butane Asphalt이며, 시스템 모사방법의 검증을 위해서, 중잔유의 가스화 반응 모사결과를 Shell사에서 발표한 실증자료와 비교하여 사용된 모사방법이 적절함을 입증한 후 이 결과를 이용하여 IGCC 플랜트에 대한 모사에 적용하였다.

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.1028-1029
• /
• 2015

본 연구에서는 대전류 구간에서의 아크해석 결과를 이용하여 SLF 차단성능을 예측하기 위하여 과도회복전압 상승률에 따라 전류영점 후 수~수백 마이크로초 동안 $SF_6$ 아크현상 이력과 영점후전류를 계산하여 대전류 구간 마지막 시점에서의 10,000K 이하의 가느다란 잔류아크가 완전히 소호될지 아니면 아크가 다시 재발호될지 판단하였다.

• Applied Chemistry for Engineering
• /
• v.35 no.1
• /
• pp.16-22
• /
• 2024

Polymer electrolyte membrane fuel cells have the advantage of low operating temperatures and fast startup and response characteristics compared to others. Simulation studies are actively researched because their cost and time benefits. In this study, the resistance of water residual in the gas diffusion layer (GDL) of the unit cell was added to the existing equation to compare the actual data with the model data. The experiments were conducted with a 25 cm² unit cell, and the samples were separated into stopping times of 0, 10, and 60 minutes following primary impedance measurement, activation, and polarization curve data acquisition. This gives 0, 10, and 60 minutes for the residual water in the GDL to evaporate. Without the rest period, the magnitude of the performance improvement was not significantly different at the same potential and flow rate, but the rest period did improve the performance of the membrane electrode assembly when measuring impedance. By changing the magnitude of the resistance reduction to an overvoltage, the voltage difference between the fuel cell model with and without residual water was compared, and the error rate in the high current density region, which is dominated by concentration losses, was reduced.

• Proceedings of the KSME Conference
• /
• 2005.11a
• /
• pp.141.2-141.2
• /
• 2005

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.25 no.6
• /
• pp.169-176
• /
• 2021

In this study, pull-out tests were conducted at room temperature, 150 ℃ and 250 ℃ to evaluate the residual bond strength of carbon fiber reinforcement polymer, CFRP after elevated temperature and deformed steel rebar of D10 and D13 were also evaluated after the high temperature heating for comparison. As a result of the experiment, the bond strength of the CFRP after 150 ℃ and 250 ℃ decreased by 9.94 % and 41 %, respectively. On the other hand, after thermal heating, both the steel rebar of D10 and D13 had a lower rate of reduction in bond strength than that of the CFRP. Also slip at the maximum bond strength also decreased after the heating for both the CFRP and the rebars. Through it, the correlation between the bond strength and the slip reduction due to thermal heating was confirmed and bond slip models were presented. Finally the experimental result was evaluated as relative bond strength to identify the residual bond performance of the CFRP and the rebar after the heating was confirmed by comparing with the existing test result of the bond strength after elevated temperature.