• Journal of Korea Water Resources Association
• /
• v.31 no.6
• /
• pp.727-739
• /
• 1998

The main objectives o reservoir optimal operation can be described as follows : maximization of the benefits through optimal allocation of the limited water resources for various purpose; minimization of t도 costs by the flood damage in potential damaging regions and risk of dam failure, etc. through safe drainage of a bulky volume of excessive water by a proper reservoir operation. Reviewing the past research works related to reservoir operation, we can find that the study on the matter of the former has been extensively carried out in last decades rather than the matter of the latter. This study is focused on developing a methodology of optimal reservoir operation for flood control, and a case study is performed on the Chungju multipurpose reservoir in Korea. The final goal of the study is to establish a reservoir optimal operation system which can search optimal policy to compromise two conflicting objectives: downstream flood damage and dam safety-upstream flood damage. In order to reach the final goal of the study, the following items were studied : (1)validation of hydrological data using HYMOS: (2)establishment of a downstream flood routing model coupling a rainfall-runoff model and SOBEK system for 1-D hydrodynamic flood routing; (3)replication of a flood damage estimation model by a neural network; (4)development of an integrated reservoir optimization module for an optimal operation policy.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.5 s.305
• /
• pp.123-136
• /
• 2005

We propose a recognition system for superimposed patterns based on selective attention model and SVM which produces better performance than artificial neural network. The proposed selective attention model includes attention layer prior to SVM which affects SVM's input parameters. It also behaves as selective filter. The philosophy behind selective attention model is to find the stopping criteria to stop training and also defines the confidence measure of the selective attention's outcome. Support vector represents the other surrounding sample vectors. The support vector closest to the initial input vector in consideration is chosen. Minimal euclidean distance between the modified input vector based on selective attention and the chosen support vector defines the stopping criteria. It is difficult to define the confidence measure of selective attention if we apply common selective attention model, A new way of doffing the confidence measure can be set under the constraint that each modified input pixel does not cross over the boundary of original input pixel, thus the range of applicable information get increased. This method uses the following information; the Euclidean distance between an input pattern and modified pattern, the output of SVM, the support vector output of hidden neuron that is the closest to the initial input pattern. For the recognition experiment, 45 different combinations of USPS digit data are used. Better recognition performance is seen when selective attention is applied along with SVM than SVM only. Also, the proposed selective attention shows better performance than common selective attention.

• The Journal of Bigdata
• /
• v.5 no.1
• /
• pp.109-124
• /
• 2020

In Korea, despite much interest in real estate, it is not easy to predict prices. Because apartments are both residential spaces and investment materials. Key figures affecting the price of apartments vary widely, and there are also regional characteristics. This study was conducted to derive the factors and characteristics that affect the sale price of apartments in S City, Gyeonggi-do. In general, people diagnose that better subway accessibility leads to higher apartment sales price. Nevertheless, in the case of S City, the price was slightly lower as it was closer to Line 1, but the higher the subway accessibility at Shinbundang Line, the higher the price. The five-year average of government bonds and the price were inversely related, and it was found to be proportional to the M2 balance and the price. The floor area ratio and the total number of parking lots had a great influence on the price, and the presence of department stores and discount marts within 1.5 km were the most important factors in the area of cultural aspect.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.1
• /
• pp.169-177
• /
• 2020

In South Korea, the results of R&D in science and technology are submitted to the National Science and Technology Information Service (NTIS) in reports that have Korea national science and technology standard classification codes (K-NSCC). However, considering there are more than 2000 sub-categories, it is non-trivial to choose correct classification codes without a clear understanding of the K-NSCC. In addition, there are few cases of automatic document classification research based on the K-NSCC, and there are no training data in the public domain. To the best of our knowledge, this study is the first attempt to build a highly performing K-NSCC classification system based on NTIS report meta-information from the last five years (2013-2017). To this end, about 210 mid-level categories were selected, and we conducted preprocessing considering the characteristics of research report metadata. More specifically, we propose a convolutional neural network (CNN) technique using only task names and keywords, which are the most influential fields. The proposed model is compared with several machine learning methods (e.g., the linear support vector classifier, CNN, gated recurrent unit, etc.) that show good performance in text classification, and that have a performance advantage of 1% to 7% based on a top-three F1 score.

• Journal of Korea Water Resources Association
• /
• v.40 no.1 s.174
• /
• pp.89-99
• /
• 2007

Uncertainty analysis is used to eliminate the climatic variables of input nodes and construct the model of an optimal type from COMBINE-GRNNM-GA(Type-1), which have been developed in this issue(2007). The input variable which has the lowest smoothing factor during the training performance, is eliminated from the original COMBINE-GRNNM-GA (Type-1). And, the modified COMBINE-GRNNM-GA(Type-1) is retrained to find the new and lowest smoothing factor of the each climatic variable. The input variable which has the lowest smoothing factor, implies the least useful climatic variable for the model output. Furthermore, The sensitive and insensitive climatic variables are chosen from the uncertainty analysis of the input nodes. The optimal COMBINE-GRNNM-GA(Type-1) is developed to estimate and calculate the PE which is missed or ungaged and the $ET_r$ which is not measured with the least cost and endeavor Finally, the PE and $ET_r$. maps can be constructed to give the reference data for drought and irrigation and drainage networks system analysis using the optimal COMBINE-GRNNM-GA(Type-1) in South Korea.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.6
• /
• pp.477-484
• /
• 2016

Small industrial appliances such as fan, audio, electric rice cooker mostly consist of ABS, PP, PS materials. In colored plastics, it is possible to classify by near infrared(NIR) spectroscopy, while in black plastics, it is very difficult to classify black plastic because of the characteristic of black material that absorbs the light. So the RBFNNs pattern classifier is introduced for sorting electrical and electronic waste plastics through LIBS(Laser Induced Breakdown Spectroscopy) spectrometer. At the preprocessing part, PCA(Principle Component Analysis), as a kind of dimension reduction algorithms, is used to improve processing speed as well as to extract the effective data characteristics. In the condition part, FCM(Fuzzy C-Means) clustering is exploited. In the conclusion part, the coefficients of linear function of being polynomial type are used as connection weights. PSO and 5-fold cross validation are used to improve the reliability of performance as well as to enhance classification rate. The performance of the proposed classifier is described based on both optimization and no optimization.

• Journal of Korean Society of Transportation
• /
• v.23 no.2
• /
• pp.25-36
• /
• 2005

In this study, we suggested a new approach method forecasting distribution demand of urban rail transit usign fuzzy control, with intend to reflect irregularity and various functional relationship between trip length and distribution demand. To establish fuzzy control model and test this model, the actual trip volume(production, attraction and distribution volume) and trip length (space distance between a departure and arrival station) of Daegu subway line 1 were used. Firstly, usign these data we established a fuzzy control model, nd the estimation accuracy of the model was examined and compared with that of generalized gravity model. The results showed that the fuzzy control model was superior to gravity model in accuracy of estimation. Therefore, wwe found that fuzzy control was able to be applied as a effective method to predict the distribution demand of urban rail transit. Finally, to increase the estimation precision of the model, we expect studies that define membership functions and set up fuzzy rules organized with neural networks.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.4
• /
• pp.580-586
• /
• 2021

The CAT methodology is a numerical analysis technique using CAE. Recently, a methodology of applying artificial intelligence techniques to a simulation has been studied. A previous study compared the deformation results according to the injection molding process using a machine learning technique. Although MLP has excellent prediction performance, it lacks an explanation of the decision process and is like a black box. In this study, data was generated using Autodesk Moldflow 2018, an injection molding analysis software. Several Machine Learning Algorithms models were developed using RapidMiner version 9.5, a machine learning platform software, and the root mean square error was compared. The decision-tree showed better prediction performance than other machine learning techniques with the RMSE values. The classification criterion can be increased according to the Maximal Depth that determines the size of the Decision-tree, but the complexity also increases. The simulation showed that by selecting an intermediate value that satisfies the constraint based on the changed position, there was 7.7% improvement compared to the previous simulation.

• Journal of the Korea Convergence Society
• /
• v.10 no.1
• /
• pp.103-113
• /
• 2019

License plate recognition camera is dedicated device designed for acquiring images of the target vehicle for recognizing letters and numbers in a license plate. Mostly, it is used as a part of the system combined with server and image analysis module rather than as a single use. However, building a system for vehicle license plate recognition is costly because it is required to construct a facility with a server providing the management and analysis of the captured images and an image analysis module providing the extraction of numbers and characters and recognition of the vehicle's plate. In this study, we would like to develop an embedded type convergent camera (Edge Base) which can expand the function of the camera to not only the license plate recognition but also the security CCTV function together and to perform two functions within the camera. This embedded type convergence camera equipped with a high resolution 4K IP camera for clear image acquisition and fast data transmission extracted license plate area by applying YOLO, a deep learning software for multi object recognition based on open source neural network algorithm and detected number and characters of the plate and verified the detection accuracy and recognition accuracy and confirmed that this camera can perform CCTV security function and vehicle number plate recognition function successfully.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.6
• /
• pp.859-865
• /
• 2018

A construction of infrastructures and base station on the moon could be undertaken by linking with the regions where construction materials and energy could be supplied on site. It is necessary to detect craters on the lunar surface and gather their topological information in advance, which forms permanent shaded regions (PSR) in which rich ice deposits might be available. In this study, an effective method for automatic detection of lunar craters on the moon surface is taken into consideration by employing a latest version of deep-learning algorithm. A training of a deep-learning algorithm is performed by involving the still images of 90000 taken from the LRO orbiter on operation by NASA and the label data involving position and size of partly craters shown in each image. the Faster RCNN algorithm, which is a latest version of deep-learning algorithms, is applied for a deep-learning training. The trained deep-learning code was used for automatic detection of craters which had not been trained. As results, it is shown that a lot of erroneous information for crater's positions and sizes labelled by NASA has been automatically revised and many other craters not labelled has been detected. Therefore, it could be possible to automatically produce regional maps of crater density and topological information on the moon which could be changed through time and should be highly valuable in engineering consideration for lunar construction.