• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.5
• /
• pp.552-559
• /
• 2005

Recurrent neural networks(RNNs) trained with gradient based such as real time recurrent learning(RTRL) has a drawback of slor convergence rate. This algorithm also needs the derivative calculation which is not trivialized in error back propagation process. In this paper a derivative free Kalman filter, so called the unscented Kalman filter(UKF), for training a fully connected RNN is presented in a state space formulation of the system. A derivative free Kalman filler learning algorithm makes the RNN have fast convergence speed and good tracking performance without the derivative computation. Through experiments of nonlinear channel equalization, performance of the RNNs with a derivative free Kalman filter teaming algorithm is evaluated.

• Nuclear Engineering and Technology
• /
• v.53 no.9
• /
• pp.2803-2815
• /
• 2021

This paper addresses the uncertainty quantification and sensitivity analysis of a depleted light-water fuel assembly of the Turkey Point-3 benchmark. The uncertainty of the fuel assembly decay heat and isotopic densities is quantified with respect to three different groups of diverse parameters: nuclear data, assembly design, and reactor core operation. The uncertainty propagation is conducted using a two-step analysis code system comprising the lattice code STREAM, nodal code RAST-K, and spent nuclear fuel module SNF through the random sampling of microscopic cross-sections, fuel rod sizes, number densities, reactor core total power, and temperature distributions. Overall, the statistical analysis of the calculated samples demonstrates that the decay heat uncertainty decreases with the cooling time. The nuclear data and assembly design parameters are proven to be the largest contributors to the decay heat uncertainty, whereas the reactor core power and inlet coolant temperature have a minor effect. The majority of the decay heat uncertainties are delivered by a small number of isotopes such as ²⁴¹Am, ¹³⁷Ba, ²⁴⁴Cm, ²³⁸Pu, and ⁹⁰Y.

• Journal of Information Processing Systems
• /
• v.15 no.2
• /
• pp.305-319
• /
• 2019

The prediction of the sum of container is very important in the field of container transport. Many influencing factors can affect the prediction results. These factors are usually composed of many variables, whose composition is often very complex. In this paper, we use gray relational analysis to set up a proper forecast index system for the prediction of the sum of containers in foreign trade. To address the issue of the low accuracy of the traditional prediction models and the problem of the difficulty of fully considering all the factors and other issues, this paper puts forward a prediction model which is combined with a back-propagation (BP) neural networks and the support vector machine (SVM). First, it gives the prediction with the data normalized by the BP neural network and generates a preliminary forecast data. Second, it employs SVM for the residual correction calculation for the results based on the preliminary data. The results of practical examples show that the overall relative error of the combined prediction model is no more than 1.5%, which is less than the relative error of the single prediction models. It is hoped that the research can provide a useful reference for the prediction of the sum of container and related studies.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.10 no.4
• /
• pp.29-35
• /
• 2014

The formula contains up between the text and the structural information, as well as their mathematical symbols. Research on-line or off-line recognition formula is underway actively used in various fields, and various forms of the equation are implemented recognition system. Although many documents are included in the various formulas, it is not easy to enter a formula into the computer. Recognition of the expression is divided into two processes of symbol recognition and structural analysis. After analyzing the location information of each character is specified to recognize the effective area after each symbol, and to the structure analysis based on the proximity between the characters is recognized as an independent single formula. Furthermore, analyzing the relationship between the front and back each time a combination of the position relationship between each symbol, and then to add the symbol which was able to easily update the structure of the entire formula. In this paper, by using a scanner to scan the book formula was used to interpret the meaning of the recognized symbol has a relative size and location information of the expression symbol. An algorithm to remove the formulas for calculation of the number of formula is present at the same time is proposed. Using the proposed algorithms to scan the books in the formula in order to evaluate the performance verification as 100% separation and showed the recognition rate equation.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.1
• /
• pp.41-46
• /
• 2023

Iterative reconstruction of CT takes a long time because projection and back-projection are alternatively repeated until taking a good image. To reduce the reconstruction time, we need a fast algorithm for calculating the projection which is a time-consuming step. In this paper, we proposed a new algorithm to calculate the line integral and the algorithm is approximately 10% faster than the well-known Siddon method (Jacobs version) and has a good image quality. Although the algorithm has been investigated for the case of parallel beams, it can be extended to the case of fan and cone beam geometries in the future.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2021.05a
• /
• pp.14-15
• /
• 2021

Recently, the size of tiles used for bathroom walls in apartment houses is gradually increasing in size. The problem is that when these large-sized tiles are attached by the sticking method, due to the nature of the method, there is a concern about the stability of the attachment to the part (pupil) where the tile and the adhesive are not attached. The problem is serious as it leads to lawsuits in the outbreak court. In addition, it is urgent to verify the adhesion stability of the sticking method because secondary damage occurs due to a safety accident caused by the falling of the tile. Ministry of Land, Infrastructure and Transport [Investigation of defects in apartment houses, calculation of repair cost and defect determination criteria] ① The tile adhesion strength is 0.39N/mm² or more and ② It is specified to fill 80% or more of the base area of the tile backside, but this is currently trendy. It is considered that large-sized tiles need to be verified from multiple angles, and as part of that, we intend to verify the adhesion stability according to the area to be attached to large-sized tiles.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.114-114
• /
• 2020

Water contamination in a water distribution network (WDN) is harmful since it directly induces the consumer's health problem and suspends water service in a wide area. Actions need to be taken rapidly to countermeasure a contamination event. A contaminant source ident ification (CSI) is an important initial step to mitigate the harmful event. Here, a CSI approach focused on determining the contaminant intrusion possible location and time (PLoT) is introduced. One of the methods to discover the PLoT is an inverse calculation to connect all the paths leading to the report specification of a sensor. A filtering procedure is then applied to narrow down the PLoT using the results from individual sensors. First, we spatially reduce the suspect intrusion points by locating the highly suspicious nodes that have similar intrusion time. Then, we narrow the possible intrusion time by matching the suspicious intrusion time to the reported information. Finally, a likelihood-score is estimated for each suspect. Another important aspect that needs to be considered in CSI is that there are inherent uncertainties, such as the variations in user demand and inaccuracy of sensor data. The uncertainties can lead to overlooking the real intrusion point and time. To reflect the uncertainties in the CSI process, the Monte-Carlo Simulation (MCS) is conducted to explore the ranges of PLoT. By analyzing all the accumulated scores through the random sets, a spread of contaminant intrusion PLoT can then be identified in the network.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1935-1950
• /
• 2023

The arrival of the Internet of Things and 5G technology enables users to rely on edge computing platforms to process massive data. Data sharing based on edge computing refines the efficiency of data collection and analysis, saves the communication cost of data transmission back and forth, but also causes the privacy leakage of a lot of user data. Based on attribute-based encryption and blockchain technology, we design a fine-grained access control scheme for data in edge computing, which has the characteristics of verifiability, support for outsourcing decryption and user attribute revocation. User attributes are authorized by multi-attribute authorization, and the calculation of outsourcing decryption in attribute encryption is completed by edge server, which reduces the computing cost of end users. Meanwhile, We implemented the user's attribute revocation process through the dual encryption process of attribute authority and blockchain. Compared with other schemes, our scheme can manage users' attributes more flexibly. Blockchain technology also ensures the verifiability in the process of outsourcing decryption, which reduces the space occupied by ciphertext compared with other schemes. Meanwhile, the user attribute revocation scheme realizes the dynamic management of user attribute and protects the privacy of user attribute.

• Nuclear Engineering and Technology
• /
• v.3 no.3
• /
• pp.148-154
• /
• 1971

Some formulae have been derived for the handy calculation of the formation of radioisotope when a reactor is operated regularly on a usual on-off pattern. In particular, the case of isotope production with the present operation condition of tile Korean reactor, which is in operation for 8.2 hours from Monday to Thursday and is not operated on friday and Sunday but is back in operation on Saturday only for 3.2 hours, is discussed herein with special emphasis. Should there be no secondary nuclear reaction resulting in the transformation of produced nuclide, the formula for the calculation of its activity could be derived as follows: (equation omitted) where A: activity (dps), $\Phi$： neutron flux (n cm$^{-2}$ sec$^{-1}$ ), No : number of atoms before the irradiation, $\sigma$ : activation cross section ($\textrm{cm}^2$), λ : disintegration constant of the radioactiveisotope formed (hr$^{-1}$ ), t : elapsed time of target in the reactor (hr), n : number of elasped days of target in the reactor, m : number of days from the first day of sample irradiation to Friday, s, r, q: number of weekday of Friday, Saturday and Sunday, respectively. Since the above formula consists of many invariables on the whole, the activity of each radioisotope to be produced can he easily and conveniently made available from the chart in advance which is made of the invariable terms calculated.

• The KIPS Transactions:PartB
• /
• v.9B no.6
• /
• pp.853-862
• /
• 2002

Face Detection can be defined as follows : Given a digitalized arbitrary or image sequence, the goal of face detection is to determine whether or not there is any human face in the image, and if present, return its location, direction, size, and so on. This technique is based on many applications such face recognition facial expression, head gesture and so on, and is one of important qualify factors. But face in an given image is considerably difficult because facial expression, pose, facial size, light conditions and so on change the overall appearance of faces, thereby making it difficult to detect them rapidly and exactly. Therefore, this paper proposes fast and exact face detection which overcomes some restrictions by using neural network. The proposed system can be face detection irrelevant to facial expression, background and pose rapidily. For this. face detection is performed by neural network and detection response time is shortened by reducing search region and decreasing calculation time of neural network. Reduced search region is accomplished by using skin color segment and frame difference. And neural network calculation time is decreased by reducing input vector sire of neural network. Principle Component Analysis (PCA) can reduce the dimension of data. Also, pose estimates in extracted facial image and eye region is located. This result enables to us more informations about face. The experiment measured success rate and process time using the Squared Mahalanobis distance. Both of still images and sequence images was experimented and in case of skin color segment, the result shows different success rate whether or not camera setting. Pose estimation experiments was carried out under same conditions and existence or nonexistence glasses shows different result in eye region detection. The experiment results show satisfactory detection rate and process time for real time system.