• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.6
• /
• pp.163-171
• /
• 2021

In this paper, the energy transaction system was optimized by applying a resource allocation algorithm and deep reinforcement learning in the distributed power system. The power demand and supply environment were predicted by deep reinforcement learning. We propose a system that pursues common interests in power trading and increases the efficiency of long-term power transactions in the paradigm shift from conventional centralized to distributed power systems in the power trading system. For a realistic energy simulation model and environment, we construct the energy market by learning weather and monthly patterns adding Gaussian noise. In simulation results, we confirm that the proposed power trading systems are cooperative with each other, seek common interests, and increase profits in the prolonged energy transaction.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.30 no.3
• /
• pp.243-251
• /
• 2019

Recently, several studies were conducted on the micro-Doppler(MD) phenomenon to identify a warhead from decoys. Both, the warhead and decoy, can be modeled as various shapes and maneuver with their own micro-motion. Their MD phenomenon can be demonstrated by amplitude modulation and phase modulation. Most studies have utilized approximate solutions to express the amplitude modulation regardless of various warhead and decoy shapes. However, the exact solution of the amplitude modulation is required for more effective warhead identification. In this study, we proposed a new modeling method of receiving radar signals from warheads and decoys based on physical optics. The proposed solution was evaluated using an electromagnetic prediction technique and computer-aided design models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1814-1828
• /
• 2021

Low-light image enhancement is a key technique to overcome the quality degradation of photos taken under scotopic vision illumination conditions. The degradation includes low brightness, low contrast, and outstanding noise, which would seriously affect the vision of the human eye recognition ability and subsequent image processing. In this paper, we propose an approach based on deep learning and Retinex theory to enhance the low-light image, which includes image decomposition, illumination prediction, image reconstruction, and image optimization. The first three parts can reconstruct the enhanced image that suffers from low-resolution. To reduce the noise of the enhanced image and improve the image quality, a super-resolution algorithm based on the Laplacian pyramid network is introduced to optimize the image. The Laplacian pyramid network can improve the resolution of the enhanced image through multiple feature extraction and deconvolution operations. Furthermore, a combination loss function is explored in the network training stage to improve the efficiency of the algorithm. Extensive experiments and comprehensive evaluations demonstrate the strength of the proposed method, the result is closer to the real-world scene in lightness, color, and details. Besides, experiments also demonstrate that the proposed method with the single low-light image can achieve the same effect as multi-exposure image fusion algorithm and no ghost is introduced.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.1
• /
• pp.14-21
• /
• 2021

Green networking has become a issue to reduce energy wastes and CO2 emission by adding energy managing mechanism to wired data networks. Energy consumption of the overall wired data networks is driven by access networks, expect for end devices. However, on a global scale, it is more difficult to manage centrally energy, measure and model the real energy use and energy savings potential of the access networks. This paper presented the multiple linear regression model to predict energy consumption of wired access networks using supervised learning of machine learning with data collected by existing investigated materials, actual measured values and results of many models. In addition, this work optimized the performance of it by various experiments and predict energy consumption of wired access networks. The performance evaluation of the regression model was achieved by well-knowned evaluation metrics.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.4
• /
• pp.328-337
• /
• 2021

Air pollution, which is a class 1 carcinogen, such as asbestos and benzene, is the cause of various diseases. The spread of ultra-air pollution is one of the important causes of the spread of the corona virus. This paper analyzes and predicts fine dust and ultra-air pollution from 2015 to 2019 based on weather data such as average temperature, precipitation, and average wind speed in Seoul and atmospheric environment data such as SO2, NO2, and O3. Linear regression, SVM, and ensemble models among machine learning models were compared and analyzed to predict fine dust by grasping and analyzing the status of air pollution and ultra-air pollution by season and month. In addition, important features(attributes) that affect the generation of fine dust and ultra-air pollution are identified. The highest ultra-air pollution was found in March, and the lowest ultra-air pollution was observed from August to September. In the case of meteorological data, the data that has the most influence on ultra-air pollution is average temperature, and in the case of meteorological data and atmospheric environment data, NO2 has the greatest effect on ultra-air pollution generation.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.4
• /
• pp.81-85
• /
• 2022

Mist-CVD is known to have advantages of low cost and high productivity method since the precursor solution is misting with an ultrasonic generator and reacted on the substrate under vacuum-free conditions of atmospheric pressure. However, since the deposition distribution is not uniform, various efforts have been made to derive optimal conditions by changing the angle of the substrate and the position of the outlet to improve the result of the preceding study. Therefore, in this study, a deposition distribution uniformity model was derived through the shape and position of the substrate support and the conditions of inlet flow rate using the particle tracking method of computational fluid dynamics (CFD). The results of analysis were compared with the previous studies through experiment. It was confirmed that the rate of deposition area was improved from 38.7% to 100%, and the rate of deposition uniformity was 79.07% which was higher than the predicted result of simulation. Particle tracking method can reduce trial and error in experiments and can be considered as a reliable prediction method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.11
• /
• pp.1619-1626
• /
• 2021

Unlike traditional delta-sigma analog-to-digital converters, incremental analog-to-digital converters enable 1:1 mapping of input and output through a reset operation, which can be used very easily for multiplexing. Incremental analog-to-digital converters also allow for simpler digital filter designs compared to traditional delta-sigma converters. Therefore, starting with analysis in the time domain of the delayed integrator and non-delayed integrator, which are the basic blocks of analog-to-digital converter design, the design equations of a second-order input feed-forward, extended counting, 2+1 MASH (Multi-stAge-noise-SHaping), 2+2 MASH incremental analog-to-digital converter are derived in this paper. This allows not only prediction of the performance of the incremental analog-to-digital converter before design, but also the design of a digital filter suitable for each analog-to-digital converter. In addition, extended counting and MASH design techniques were proposed to improve the accuracy of analog-to-digital converters.

• Progress in Medical Physics
• /
• v.32 no.4
• /
• pp.116-121
• /
• 2021

Purpose: To investigate the effects of dose rate on intensity-modulated radiation therapy (IMRT) quality assurance (QA). Methods: We performed gamma tests using portal dose image prediction and log files of a multileaf collimator. Thirty treatment plans were randomly selected for the IMRT QA plan, and three verification plans for each treatment plan were generated with different dose rates (200, 400, and 600 monitor units [MU]/min). These verification plans were delivered to an electronic portal imager attached to a Varian medical linear accelerator, which recorded and compared with the planned dose. Root-mean-square (RMS) error values of the log files were also compared. Results: With an increase in dose rate, the 2%/2-mm gamma passing rate decreased from 90.9% to 85.5%, indicating that a higher dose rate was associated with lower radiation delivery accuracy. Accordingly, the average RMS error value increased from 0.0170 to 0.0381 cm as dose rate increased. In contrast, the radiation delivery time reduced from 3.83 to 1.49 minutes as the dose rate increased from 200 to 600 MU/min. Conclusions: Our results indicated that radiation delivery accuracy was lower at higher dose rates; however, the accuracy was still clinically acceptable at dose rates of up to 600 MU/min.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.1
• /
• pp.33-40
• /
• 2023

With the development of supercomputing technology and hardware technology, numerical computation methods are also being advanced. Accordingly, improved weather prediction becomes possible. In this paper, we propose to apply the LAPACK(Linear Algebra PACKage) BLAS(Basic Linear Algebra Subprograms) library to the linear algebraic numerical computation part within the source code to improve the performance of the cumulative parametric code, Unicon(A Unified Convection Scheme), which is included in SCAM(Single-Columns Atmospheric Model, simplified version of CESM(Community Earth System Model)) and performs standby operations. In order to analyze this, an overall execution structure diagram of SCAM was presented and a test was conducted in the relevant execution environment. Compared to the existing source code, the SCOPY function achieved 0.4053% performance improvement, the DSCAL function 0.7812%, and the DDOT function 0.0469%, and all of them showed a 0.8537% performance improvement. This means that the LAPACK BLAS application method, a library for high-density linear algebra operations proposed in this paper, can improve performance without additional hardware intervention in the same CPU environment.

• Computers and Concrete
• /
• v.32 no.3
• /
• pp.327-337
• /
• 2023

Concrete is the most widely used building material, with various types including high- and ultra-high-strength, reinforced, normal, and lightweight concretes. However, accurately predicting concrete properties is challenging due to the geotechnical design code's requirement for specific characteristics. To overcome this issue, researchers have turned to new technologies like machine learning to develop proper methodologies for concrete specification. In this study, we propose a highly accurate deep learning-based predictive model to investigate the compressive strength (UCS) of lightweight concrete with natural aggregates (pumice). Our model was implemented on a database containing 249 experimental records and revealed that water, cement, water-cement ratio, fine-coarse aggregate, aggregate substitution rate, fine aggregate replacement, and superplasticizer are the most influential covariates on UCS. To validate our model, we trained and tested it on random subsets of the database, and its performance was evaluated using a confusion matrix and receiver operating characteristic (ROC) overall accuracy. The proposed model was compared with widely known machine learning methods such as MLP, SVM, and DT classifiers to assess its capability. In addition, the model was tested on 25 laboratory UCS tests to evaluate its predictability. Our findings showed that the proposed model achieved the highest accuracy (accuracy=0.97, precision=0.97) and the lowest error rate with a high learning rate (R2=0.914), as confirmed by ROC (AUC=0.971), which is higher than other classifiers. Therefore, the proposed method demonstrates a high level of performance and capability for UCS predictions.