• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.4
• /
• pp.691-698
• /
• 2003

We extend the sue of the method of least square to develop a recursive algorithm for the design of adaptive transversal filters such that, given the least-square estimate of this vector of the filter at iteration n-l, we may compute the updated estimate of this vector at iteration n upon the arrival of new data. We begin the development of the RLS algorithm by reviewing some basic relations that pertain to the method of least squares. Then, by exploiting a relation in matrix algebra known as the matrix inversion lemma, we develop the RLS algorithm. An important feature of the RLS algorithm is that it utilizes information contained in the input data, extending back to the instant of time when the algorithm is initiated. In this paper, we propose new tap weight updated RLS algorithm in adaptive transversal filter with data-recycling buffer structure. We prove that convergence speed of learning curve of RLS algorithm with data-recycling buffer is faster than it of exiting RLS algorithm to mean square error versus iteration number. Also the resulting rate of convergence is typically an order of magnitude faster than the simple LMS algorithm. We show that the number of desired sample is portion to increase to converge the specified value from the three dimension simulation result of mean square error according to the degree of channel amplitude distortion and data-recycle buffer number. This improvement of convergence character in performance, is achieved at the B times of convergence speed of mean square error increase in data recycle buffer number with new proposed RLS algorithm.

• Biomolecules & Therapeutics
• /
• v.17 no.1
• /
• pp.47-56
• /
• 2009

Schizandra chinensis (S. chinensis) exhibits a harmless, 'adaptogen-type' effect leading to improvements in mental performance and learning efficacy in brain. Activated microglia contributes to neuronal injury by releasing neurotoxic products, which make it important to regulate microglial activation to prevent further cytological as well as functional brain damage. However, the effect of S. chinensis on microglial activation has not been examined yet. We have investigated the effects of four compounds (Gomisin A, Gomisin N, Schizandrin and Schizandrol A) from S. chinensis on lipopolysaccharide (LPS)-induced microglial activation. In this study, BV2 microglial cells were activated with LPS and the microglial activation was assessed by up-regulation of activation markers such as nitric oxide (NO), reactive oxygen species (ROS), and matrix metalloproteinase-9 (MMP-9). The results showed that all four compounds significantly reduced the intracellular level of ROS, the release of NO and MMP-9 as well as LPS-induced phosphorylation of ERK1/2. These results strongly suggested that S. chinensis may be useful to modulate inflammation-mediated brain damage by regulating microglial activation.

• Communications of Mathematical Education
• /
• v.31 no.3
• /
• pp.241-255
• /
• 2017

The 4th industrial revolution is coming. In order to prepare for the new learning environment with it, we may need digital mathematics textbooks that fully utilize all possible technologies. So various attempts have been made in elementary and middle school mathematics education. However, despite the importance of higher mathematics, we haven't seen a best possible math digital textbooks yet in Korea. In this paper, we introduce our new model of interactive math digital textbook about Linear Algebra/ Calculus/ Differential Equations/ Statistics/ Engineering Math. Especially, this manuscript focuses on our experience of using digital contents and interactive labs for developing a new model for linear algebra digital textbook. We introduce our works on linear algebra digital textbooks which include pdf e-book, web contents, video clips of lectures, interactive lab. Using this linear algebra digital textbook, students can freely use any mobile devices to access diverse learning materials, lessons, and hands-on exercises without any limitations. Also, times saved in the computation, coding, and typing process can be used to have more discussions for deeper understanding of mathematical concepts. This type of linear algebra digital textbook, which contains all interactive free cyber-lab with codes and all lectures for each sections, can be considered as a new model for the next generation of math digital textbook.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.48 no.10
• /
• pp.773-782
• /
• 2020

The development of joint FE models for deep learning neural network (DLNN)-based hybrid FEA is presented. Material models of bolts and bearings in the front axle of tractor, showing complex behavior induced by various tightening conditions, were replaced with DLNN models. Bolts are modeled as one-dimensional Timoshenko beam elements with six degrees of freedom, and bearings as three-dimensional solid elements. Stress-strain data were extracted from all elements after finite element analysis subjected to various load conditions, and DLNN for bolts and bearing were trained with Tensorflow. The DLNN-based joint models were implemented in the ABAQUS user subroutines where stresses from the next increment are updated and the algorithmic tangent stiffness matrix is calculated. Generalization of the trained DLNN in the FE model was verified by subjecting it to a new loading condition. Finally, the DLNN-based FEA for the front axle of the tractor was conducted and the feasibility was verified by comparing with results of a static structural experiment of the actual tractor.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.28 no.5
• /
• pp.277-283
• /
• 2016

Tetrapod is one of the most widely used concrete armor units for rubble mound breakwaters. The calculation of the stability number of Tetrapods is necessary to determine the optimal weight of Tetrapods. Many empirical formulas have been developed to calculate the stability number of Tetrapods, from the Hudson formula in 1950s to the recent one developed by Suh and Kang. They were developed by using the regression analysis to determine the coefficients of an assumed formula using the experimental data. Recently, software engineering (or machine learning) methods are introduced as a large amount of experimental data becomes available, e.g. artificial neural network (ANN) models for rock armors. However, these methods are seldom used probably because they did not significantly improve the accuracy compared with the empirical formula and/or the engineers are not familiar with them. In this study, we propose an explicit method to calculate the stability number of Tetrapods using the weights and biases of an ANN model. This method can be used by an engineer who has basic knowledge of matrix operation without requiring knowledge of ANN, and it is more accurate than previous empirical formulas.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.2
• /
• pp.164-171
• /
• 2006

Recently Digital multimedia broadcasting (DMB) has been available as a commercial service. The users sometimes have difficulty in finding their preferred multimedia contents and need to spend a lot of searching time finding them. They are even very likely to miss their preferred contents while searching for them. In order to solve the problem, we need a method for recommendation users preferred only minimum information. We propose an algorithm and a system for recommending users' preferred contents using preference transition probability from user's usage history. The system includes four agents: a client manager agent, a monitoring agent, a learning agent, and a recommendation agent. The client manager agent interacts and coordinates with the other modules, the monitoring agent gathers usage data for analyzing the user's preference of the contents, the learning agent cleans the gathered usage data and modeling with state transition matrix over time, and the recommendation agent recommends the user's preferred contents by analyzing the cleaned usage data. In the recommendation agent, we developed the recommendation algorithm using a user's preference transition probability for the contents. The prototype of the proposed system is designed and implemented on the WIPI(Wireless Internet Platform for Interoperability). The experimental results show that the recommendation algorithm using a user's preference transition probability can provide better performances than a conventional method.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.28 no.8
• /
• pp.628-635
• /
• 2017

It is important to prescribe and take medicines that are appropriate for symptoms, since medicines are closely related to human health and life. Moreover, it becomes more important to accurately classify genuine medicines with counterfeit, since the number of counterfeit increases worldwide. However, the number of high-quality experts who have enough experience to properly classify them is limited and there exists a need for the automatic technique to classify medicine tablets. In this paper, we propose a method to classify the tablets by using a handheld spectrometer which provides both Near Infra-Red (NIR) and visible light spectrums. We adopted Support Vector Machine(SVM) as a machine learning algorithm for tablet classification. As a result of the simulation, we could obtain the classification accuracy of 99.9 % on average by using both NIR and visible light spectrums. Also, we proposed a two-step SVM approach to discriminate the counterfeit tablets from the genuine ones. This method could improve both the accuracy and the processing time.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.4
• /
• pp.772-780
• /
• 2008

K-means is one of the simplest unsupervised learning algorithms that solve the clustering problem. However K-means suffers the basic shortcoming: the number of clusters k has to be known in advance. In this paper, we propose extensions of X-means, which can estimate the number of clusters using Bayesian information criterion(BIC). We introduce two different versions of algorithm: modified X-means(MX-means) and generalized X-means(GX-means), which employ one full covariance matrix for one cluster and so can estimate the number of clusters efficiently without severe over-fitting which X-means suffers due to its spherical cluster assumption. The algorithms start with one cluster and try to split a cluster iteratively to maximize the BIC score. The former uses K-means algorithm to find a set of optimal clusters with current k, which makes it simple and fast. However it generates wrongly estimated centers when the clusters are overlapped. The latter uses EM algorithm to estimate the parameters and generates more stable clusters even when the clusters are overlapped. Experiments with synthetic data show that the purposed methods can provide a robust estimate of the number of clusters and cluster parameters compared to other existing top-down algorithms.

• Journal of Digital Convergence
• /
• v.19 no.2
• /
• pp.245-251
• /
• 2021

As the trend of steadily increasing the number of single or double household, there is a growing demand to see who is the outsider visiting the home during the free time. Various models of face recognition technology have been proposed through many studies, and Harr Cascade of OpenCV and Hog of Dlib are representative open source models. Among the two modes, Dlib's Hog has strengths in front of the indoor and at a limited distance, which is the focus of this study. In this paper, a face recognition visitor access system based on Dlib was designed and implemented. The whole system consists of a front module, a server module, and a mobile module, and in detail, it includes face registration, face recognition, real-time visitor verification and remote control, and video storage functions. The Precision, Specificity, and Accuracy according to the change of the distance threshold value were calculated using the error matrix with the photos published on the Internet, and compared with the results of previous studies. As a result of the experiment, it was confirmed that the implemented system was operating normally, and the result was confirmed to be similar to that reported by Dlib.

• Journal of the Korean Society of Radiology
• /
• v.16 no.4
• /
• pp.411-417
• /
• 2022

This study aimed to learn and evaluate the effectiveness of VGGNet in the detection of pulmonary emphysema using low-dose chest computed tomography images. In total, 8000 images with normal findings and 3189 images showing pulmonary emphysema were used. Furthermore, 60%, 24%, and 16% of the normal and emphysema data were randomly assigned to training, validation, and test datasets, respectively, in model learning. VGG16 and VGG19 were used for learning, and the accuracy, loss, confusion matrix, precision, recall, specificity, and F1-score were evaluated. The accuracy and loss for pulmonary emphysema detection of the low-dose chest CT test dataset were 92.35% and 0.21% for VGG16 and 95.88% and 0.09% for VGG19, respectively. The precision, recall, and specificity were 91.60%, 98.36%, and 77.08% for VGG16 and 96.55%, 97.39%, and 92.72% for VGG19, respectively. The F1-scores were 94.86% and 96.97% for VGG16 and VGG19, respectively. Through the above evaluation index, VGG19 is judged to be more useful in detecting pulmonary emphysema. The findings of this study would be useful as basic data for the research on pulmonary emphysema detection models using VGGNet and artificial neural networks.