• The Transactions of the Korean Institute of Electrical Engineers C
• /
• v.52 no.7
• /
• pp.424-424
• /
• 2003

Evolutionary design related to the optimal design of Polynomial Neural Networks (PNNs) structure for model identification of complex and nonlinear system is studied in this paper. The PNN structure is consisted of layers and nodes like conventional neural networks but is not fixed and can be changable according to the system environments. three types of polynomials such as linear, quadratic, and modified quadratic is used in each node that is connected with various kinds of multi-variable inputs. Inputs and order of polynomials in each node are very important element for the performance of model. In most cases these factors are decided by the background information and trial and error of designer. For the high reliability and good performance of the PNN, the factors must be decided according to a logical and systematic way. In the paper evolutionary algorithm is applied to choose the optimal input variables and order. Evolutionary (genetic) algorithm is a random search optimization technique. The evolved PNN with optimally chosen input variables and order is not fixed in advance but becomes fully optimized automatically during the identification process. Gas furnace and pH neutralization processes are used in conventional PNN version are modeled. It shows that the designed PNN architecture with evolutionary structure optimization can produce the model with higher accuracy than previous PNN and other works.

• International Journal of Advanced Culture Technology
• /
• v.9 no.3
• /
• pp.81-85
• /
• 2021

The purpose of this paper is to measure the relative efficiency of the police agencies in Korea with data collected from 2018 to 2020, using data envelopment analysis (DEA), as put forward by Charnes et al., which is used to construct a scalar measure of efficiency for all police agencies. The results of this study can be used to assist police agencies in delivering better and more efficient services to the community. The analytical results based on DEA identify potentially weak and strong police agencies on policing performance, their efficient benchmarking, and the levels of clear-ups that would make inefficient police agencies efficient. We could suggest that higher levels of the police force are associated with higher performance efficiency against crimes. But, it is a little hard to say that higher levels of the police force can keep the local police agencies efficient without explaining the contribution of other input variables to criminal arrest and prevention. On the other hand, our analysis presents that differences in operating environments and socioeconomic factors do not have a significant influence on the efficiency of local police agencies. But, it is necessary to note that we need to examine the effect of environments and socioeconomic factors on crime to create the better-policing performance.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.17 no.4
• /
• pp.161-175
• /
• 2021

This study analyzed the efficiency and influence factors according to the main research institute type of R&D Program for the local community problem-solving. This study applied data envelopment analysis (DEA) method and Tobit regression analysis by using 20 institutions that participated in R&D Program. The results are summarized as follows. First, Analysis results according to the research institute type of R&D project, Efficient DMUs showed more regional innovation institutions than social economy enterprises. But regional innovation institutions were the lowest in the CCR and BCC model. However, efficiency dose not differ between regional innovation institutions and social economy enterprises. Second, as a result of the analysis relation between efficiency and allocation characteristics of R&D input, the participation of regional innovation organizations as participating organizations has a negative effect on efficiency. It was found that the higher the proportion of government subsidies and the higher the employment rate of the vulnerable, which is a social achievement, the positive effect on efficiency. The implication of this study is that the participation of social economy enterprises as the main R&D institution and government R&D support can provide social economy enterprises with opportunities to accumulate R&D capabilities and experience successful commercialization.

• Atmosphere
• /
• v.31 no.1
• /
• pp.73-83
• /
• 2021

Numerical weather prediction (NWP) models play an essential role in predicting weather factors, but using them is challenging due to various factors. To overcome the difficulties of NWP models, deep learning models have been deployed in weather forecasting by several recent studies. This study adapts long short-term memory (LSTM), which demonstrates remarkable performance in time-series prediction. The combination of LSTM model input of meteorological features and activation functions have a significant impact on the performance therefore, the results from 5 combinations of input features and 4 activation functions are analyzed in 9 Automated Surface Observing System (ASOS) stations corresponding to cities/islands/mountains. The optimized LSTM model produces better performance within eight forecast hours than Local Data Assimilation and Prediction System (LDAPS) operated by Korean meteorological administration. Therefore, this study illustrates that this LSTM model can be usefully applied to very short-term weather forecasting, and further studies about CNN-LSTM model with 2-D spatial convolution neural network (CNN) coupled in LSTM are required for improvement.

• Progress in Superconductivity and Cryogenics
• /
• v.11 no.3
• /
• pp.65-68
• /
• 2009

The Stirling cryocoolers have been widely used for the cooling of the infrared detector(InSb, HgCdTe, and etc,) and HTS(High Temperature Superconductor) to the cryogenic temperature. The monobloc Stirling cryocoolers with the rotary compressor are applicable to the cooling device for the compact mobile thermal imaging system, because the cryocoolers have the compact structure and light weight. The typical performance factors of the Stirling cryocooler are the cool-down time, cooling capacity at the desired temperature (80 K), the electric input power and COP. The above performance factors depend on the operating conditions such as the charging pressure of the helium gas, the thermal environment and etc.. In this study, the effects of the thermal environment (temperature of 241, 293, and 333 K) on the performance of the cryocooler were investigated by experiments. The results show the effects of the temperature of the thermal environment on the cooling capacity and input power.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.8 no.1
• /
• pp.129-133
• /
• 2020

The concentration of remaining formaldehyde contained in waste liquid emitted from the process of urea-formaldehyde microcapsule synthesis was analyzed by gas chromatography-mass spectrometry (GC-MS). Three factors that can affect on the reaction of formaldehyde were selected including pH, ammonium chloride input and temperature. The effect of these factors on the concentration of remaining formaldehyde was studied. When ammonium chloride input was 0.025g, microcapsules could not be obtained or core substance leaked out because of weak shell, and therefore this reaction condition would be inadequate. It was confirmed that the concentration of remaining formaldehyde could be minimized when the microencapsulation was conducted at 70℃ and pH 2.5 by using a ammonium chloride input of 0.050g. This study can make contribution to UF microencapsulation in safer working environment.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2002.09a
• /
• pp.11-12
• /
• 2002

Accidental overexposures by radiotherapy have gathered attention recently in Japan. The widely publicized accidents have occurred at the government official benefit society hospital and at the hospital affiliated to a medical school. The accident at the government official benefit society hospital occurred when one of two existing accelerators was renewed. A radiotherapy planning system was also introduced at that time. Then treatment planning for the old and the new linear accelerator was performed using the system. There were variations in wedge factors for the 30 degrees wedge filter between the old and the new linear accelerator. That is, the difference in the structure of the wedge filter (30 degrees) resulted in variations of the wedge factors between both accelerators. In order to keep strength, a lead board was backed to the lead wedge filter for the new linear accelerator, whereas the wedge filter for the old one was made of the iron. The X-ray attenuation of the iron wedge filter is smaller than that of the lead wedge filter. The basic beam data of the old linear accelerator, however, wasn't delivered properly between the user and the maker. Then, the accident took place because the same wedge factor was used for the old and the new linear accelerator. On the other hand, the accident which occurred at the university hospital was brought about by the input mistake in initialization of the computer system when a linear accelerator was introduced. The input mistake was found when the software of the system was updated. If the dose had been measured and confirmed adequately, the accidents could have been prevented in both cases.

• International Journal of Quality Innovation
• /
• v.10 no.1
• /
• pp.1-23
• /
• 2009

Face the process yield rate improvements of motherboard, although general enterprises finish deployment goal of each functions by overall quality managements, through quality improvement methods, industry engineering methods, plan-do-check-act (PDCA) methods and other improvement solutions, but it is only can be improved partially and unable to enhance the yield rate of product to the target. It only can takes one step ahead to enhance the process yield rate of motherboard with six sigma ($6{\sigma}$) overall DMAIC process and tactics. This research aimed to use six sigma quality improvement tactics by DMAIC systematic procedure and tactics, and find the key factors that effect to the process yield rate of surface mount technology. It also identified the keys input and process and output index to satisfy customer requirements and internal process index. The results showed that the major effective factors by fishbone and process failure modes and effects analysis (PFMEA). If the index of input and output that can be quantified, the optimum parameter can be found through design of experiment to ensure that the process is stable. If the factor of input and output that cannot be quantified, we found out the effective countermeasure by Mind_Mapping, make sure whole processes can be controlled stably, to reach the high product quality and enhance the customer satisfaction.

• Journal of Korean Society for Quality Management
• /
• v.49 no.2
• /
• pp.213-231
• /
• 2021

Purpose: This study intends to provide decision-making information to improve efficiency by analyzing the management efficiency of smart greenhouse business entities and identifying factors that affect the efficiency based on input and output. Methods: The subjects of analysis were business entities for cultivating strawberries in smart greenhouses in Jeolla region (northern and southern Jeolla provinces), and the analysis focused on the management performance of the 2019-2020 crop period (year). Data Envelopment Analysis(DEA) was applied as an analysis method for efficiency analysis, Quantile Regression(QR) analysis was applied as a factor affecting the efficiency. Results: The reason for the efficiency gap between business entities was that there were many business entities that did not minimize the input cost at the current level of output, and the area where the variance among business entities was large was the fixed cost per 10a. In the results of the affecting factor analysis, it was found that the seed-seedlings cost, fertilizer cost, other material cost, and employment and labor cost had a negative (-) effect on the efficiency, and that the repair and maintenance cost had a positive (+) effect. Conclusion: Therefore, to achieve the efficiency of scale, it is necessary to reduce the input scale to an appropriate level. In the case of business entities with low efficiency by quartile, the seed-seedlings, fertilizer, and other material costs reduce expenditures, and repair maintenance costs can improve efficiency by increasing expenditures.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.246-246
• /
• 2023

Multi-purpose dams are operated accounting for both physical and socioeconomic factors. This study aims to evaluate the utility of a deep learning algorithm-based model for three multi-purpose dam operation (Seomjin River dam, Juam dam, and Juam Control dam) in Seomjin River. In this study, the Gated Recurrent Unit (GRU) algorithm is applied to predict hourly water level of the dam reservoirs over 2002-2021. The hyper-parameters are optimized by the Bayesian optimization algorithm to enhance the prediction skill of the GRU model. The GRU models are set by the following cases: single dam input - single dam output (S-S), multi-dam input - single dam output (M-S), and multi-dam input - multi-dam output (M-M). Results show that the S-S cases with the local dam information have the highest accuracy above 0.8 of NSE. Results from the M-S and M-M model cases confirm that upstream dam information can bring important information for downstream dam operation prediction. The S-S models are simulated with altered outflows (-40% to +40%) to generate the simulated water level of the dam reservoir as alternative dam operational scenarios. The alternative S-S model simulations show physically inconsistent results, indicating that our deep learning algorithm-based model is not explainable for multi-purpose dam operation patterns. To better understand this limitation, we further analyze the relationship between observed water level and outflow of each dam. Results show that complexity in outflow-water level relationship causes the limited predictability of the GRU algorithm-based model. This study highlights the importance of socioeconomic factors from hidden multi-purpose dam operation processes on not only physical processes-based modeling but also aritificial intelligence modeling.