• Journal of IKEEE
• /
• v.23 no.2
• /
• pp.529-533
• /
• 2019

Combined cycle power plants are often used to produce power. These days prediction of power plant output based on operating parameters is a major concern. This paper presents an approach to using computational intelligence technique to predict the output power of combined cycle power plant. Computational intelligence techniques have been developed and applied to many real world problems. In this paper, tree architectures of fuzzy neural networks are considered to predict the output power. Tree architectures of fuzzy neural networks have an advantage of reducing the number of rules by selecting fuzzy neurons as nodes and relevant inputs as leaves optimally. For the optimization of the networks, two-step optimization method is used. Genetic algorithms optimize the binary structure of the networks by selecting the nodes and leaves as binary, and followed by random signal-based learning further refines the optimized binary connections in the unit interval. To verify the effectiveness of the proposed method, combined cycle power plant dataset obtained from the UCI Machine Learning Repository Database is considered.

• Journal of Advanced Navigation Technology
• /
• v.27 no.5
• /
• pp.502-509
• /
• 2023

This study presents a satellite constellation method that achieves optimal revisit performance by utilizing genetic algorithm techniques. The Walker method is a global coverage concept, and there are limitations to target-centered constellation considering the strategic environment of the Korean Peninsula. To overcome these limitations, targets are set in major areas of interest in North Korea, orbit elements with optimal revisit performance for each target are searched, and based on this, the number of satellites optimized for each target is derived using a genetic algorithm. The results of this study demonstrate the performance of the optimized constellation by applying phasing rules to achieve the desired revisit performance.

• Geophysics and Geophysical Exploration
• /
• v.13 no.1
• /
• pp.109-117
• /
• 2010

To enable high-performance computing (HPC) for applications with large datasets using a $Sony^{(R)}$ $PLAYSTATION^{(R)}$ 3 ($PS3^{TM}$) video game console, we configured a hybrid system consisting of a $Windows^{(R)}$ PC and a $PS3^{TM}$. To validate this system, we implemented the real-time multiplet identifier (RTMI) application, which identifies multiplets of microearthquakes in terms of the similarity of their waveforms. The cross-correlation computation, which is a core algorithm of the RTMI application, was optimised for the $PS3^{TM}$ platform, while the rest of the computation, including data input and output remained on the PC. With this configuration, the core part of the algorithm ran 69 times faster than the original program, accelerating total computation speed more than five times. As a result, the system processed up to 2100 total microseismic events, whereas the original implementation had a limit of 400 events. These results indicate that this system enables high-performance computing for large datasets using the $PS3^{TM}$, as long as data transfer time is negligible compared with computation time.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.10
• /
• pp.2466-2472
• /
• 2013

Post-dispersion compensation methods for the 3000 km long-haul transmission distance using 10 Gbps 40 wavelength division multiplexing channels were analyzed and compared. First, each channel was compensated by an individual dispersion value, next each group of eight channels by an individual value, and lastly all forty channels by a single value. Considering the lower and highest performance channels and their values, the post-dispersion compensation method by each channel group showed the possibility to simplify the transmission system without sacrifice of signal performance.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.36 no.3
• /
• pp.347-353
• /
• 2012

Recently, multi-functionalization (as in smart phones) has been in demand, and the connectors connecting the electrical signals of each board in a cellular phone have become key components. The miniaturization of these connectors is required to achieve a finer pitch design and enhance the electrical signal transfer capacity. However, the miniaturization of connectors reduces the structural safety, and a finer pitch design may cause contact problems under external impact. In this paper, a preliminary design for miniaturized, finer-pitch connectors is suggested for a product with 50 pins and a thickness of 0.2 mm. The assembly process of the FPCB (Flexible Printed Circuit Board) and connector was simulated to ensure the holding force between the two components and avoid overstressing. The design optimization process was performed with the Taguchi method. Fatigue analysis was also conducted to predict the fatigue life of the terminal, and the theoretical and experimental results were compared.

• Journal of Digital Contents Society
• /
• v.18 no.6
• /
• pp.1165-1173
• /
• 2017

Deep learning method, which is one of the most famous machine learning algorithms, has proven its applicability in various applications and is widely used in digital signal processing. However, it is difficult to apply deep learning technology to IoT devices with limited CPU performance and memory capacity, because a large number of training samples requires a lot of memory and computation time. In particular, if the Arduino with a very small memory capacity of 2K to 8K, is used, there are many limitations in implementing the algorithm. In this paper, we propose a method to optimize the ELM algorithm, which is proved to be accurate and efficient in various fields, on Arduino board. Experiments have shown that multi-class learning is possible up to 15-dimensional data on Arduino UNO with memory capacity of 2KB and possible up to 42-dimensional data on Arduino MEGA with memory capacity of 8KB. To evaluate the experiment, we proved the effectiveness of the proposed algorithm using the data sets generated using gaussian mixture modeling and the public UCI data sets.

• Journal of Korean Society of Transportation
• /
• v.20 no.1
• /
• pp.19-38
• /
• 2002

To evaluate the effects of transportation system operation, usually measures of effectiveness(MOE) such as travel time, space mean speed, stop/delay ratio have been used. But, energy consumption as well as the existing MOE in transportation receives more attention as an alternative MOE in transportation operation. The purpose of this study is a development of procedure, which could measure the relative energy consumption for each alternative and compare the results. A mesoscopic simulator called INTEGRATION is used to evaluate the operation of high occupancy vehicle lane, signal optimization, lane expansion, and the application of ITS. Among those, the application of ITS shows the greatest effectiveness in energy reduction, and then lane expansion, signal optimization, and the operation of high occupancy vehicle lane in the order named. Because we don't consider the characteristics of vehicle class, Potential demand and the simulation time is just for an hour. it is recommended that a procedure for precise economic analysis and an improvement in methodology are needed in the future for the expanded application of this study.

• Journal of the Korea Convergence Society
• /
• v.9 no.8
• /
• pp.33-39
• /
• 2018

In the Internet of Things (IoT) era, objects are connected to each other by wired and wireless networks, and information is exchanged whenever necessary. Channel and network environments change over time; thus, a carrier sensing function that identifies whether signals containing information are present in the channel is essential. The carrier sensing circuit of a wireless communication system determines the receiver sensitivity, and the receiver sensitivity is closely related to the service coverage and service quality of the system. As the receiver sensitivity decreases, the service coverage increases but it becomes sensitive to noise. However, as the receiver sensitivity increases, the service coverage decreases but it becomes insensitive to the noise. Therefore, carrier sensing design and optimization are very important from the viewpoint of the receiver sensitivity and noise sensitivity. This paper proposes an effective carrier sensing technique from the viewpoint of the receiver sensitivity for the long range IoT.

• Journal of the Korean Society of Radiology
• /
• v.12 no.4
• /
• pp.541-547
• /
• 2018

To evaluate the effect of dose and image quality for Chest Digital Tomosynthesis(CDT) using sensitivity and tube voltage(kV). CDT images of the phantom were acquired varying sensitivity 200, 320, 400 according to set tube voltage of 125 kV and 135 kV. The dose and Dose Area Product(DAP) according to change of sensitivity and kV were evaluated and Image quality was evaluated by PSNR, CNR, SNR using Image J. Dose were lowered 14~23% less than sensitivity 200, 125 kV and DAP were lowered 13~26% less than sensitivity 200, 125 kV. PSNR were over 27 dB, which were significant value and CNR, SNR were better as sensitivity value was lower. But there were different statistical significant to each item. CNR and SNR were not statistically significant at sensitivity 320, 135 kV(P>0.05). CDT can improve image quality with lower radiation dose using better than quality and correction power at digital radiography system.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.4
• /
• pp.97-105
• /
• 2016

Radiography image detector produces digital images by collecting the charges from the incident x-ray photons and converting it to the voltage signals and then the digital signals. The fixed-pattern noise from the nonuinform amplifier gains in the employed multiple readout circuits. In order to correct the nonuniform gains, a gain-correction technique which is based on the gain map is conventionally used. Since the photon noise remains in the designed gain map, the noise contaminates the gain-corrected images. In this paper, experimental observations are conducted for filtering the remained noise in the gain map, and a filter optimization algorithm is proposed to efficiently remove the noise. For acquired x-ray images from detectors, the filtered gain maps are evaluated and it is shown that optimization algorithm can improve the filtering performance even for relatively strong fixed-pattern noises, which cannot be removed by a simple filter.