• Journal of KIISE:Software and Applications
• /
• v.30 no.11
• /
• pp.1054-1061
• /
• 2003

Q-Learning, a representative algorithm of reinforcement learning, experiences repeatedly until estimation values about all state-action pairs of state space converge and achieve optimal policies. When the state space is high dimensional or continuous, complex reinforcement learning tasks involve very large state space and suffer from storing all individual state values in a single table. We introduce Q-Map that is new function approximation method to get classified policies. As an agent learns on-line, Q-Map groups states of similar situations and adapts to new experiences repeatedly. State-action pairs necessary for fine control are treated in the form of rule. As a result of experiment in maze environment and mountain car problem, we can achieve classified knowledge and extract easily rules from Q-Map

• Convergence Security Journal
• /
• v.20 no.4
• /
• pp.81-90
• /
• 2020

In the real world, new types of attacks or variants are constantly emerging, but attack traffic classification models developed through artificial neural networks and supervised learning do not properly detect new types of attacks that have not been trained. Most of the previous studies overlooked this problem and focused only on improving the structure of their artificial neural networks. As a result, a number of new attacks were frequently classified as normal traffic, and attack traffic classification performance was severly degraded. On the other hand, the softmax function, which outputs the probability that each class is correctly classified in the multi-class classification as a result, also has a significant impact on the classification performance because it fails to calculate the softmax score properly for a new type of attack traffic that has not been trained. In this paper, based on this characteristic of softmax function, we propose an efficient method to improve the classification performance against new types of attacks by classifying traffic with a probability below a certain level as attacks, and demonstrate the efficiency of our approach through experiments.

• Journal of the Korean School Mathematics Society
• /
• v.25 no.1
• /
• pp.39-60
• /
• 2022

In this study, in order to support the expression of group creativity of high school students, we developed mathematics learning contents linked with mobile and online/offline that obtain the maximum and minimum values of the function within a limited range. This learning content was developed in connection with the 'environment', a cross-curricular learning topic. We explored the concept of group creativity in school mathematics. Its manifestation process, elements of group creativity expression process, and mobile and on/offline implementation functions were also explored. Then, we developed a hybrid app, 'Making the Best Box that Thinks of the Earth', which can express group creativity through mobile and online/offline-linked cooperative learning. A learning management system (LMS) and a teaching and learning guidance plan were also developed to efficiently operate mobile and online/offline-linked math learning using the app in schools. Our study found that the hybrid app, 'Creating the Best Box that Thinks of the Earth', was suitable for promoting collective fluency and collective sophistication based on complementary-metacognitive interaction.

• Communications of Mathematical Education
• /
• v.36 no.1
• /
• pp.39-57
• /
• 2022

This study aims to design an integral instruction method that follows the Abstraction in Context (AiC) framework proposed by Hershkowitz, Schwarz, and Dreyfus to help students in acquiring in-depth understanding of the relationship between indefinite integrals and definite integrals and to analyze how the students' understanding improved as a result. To this end, we implemented lessons according to the integral instruction method designed for eight 11th grade students in a science high school. We recorded and analyzed data from graded student worksheets and transcripts of classroom recordings. Results show that students comprehend three knowledge elements regarding relationship between indefinite integral and definite integral: the instantaneous rate of change of accumulation function, the calculation of a definite integral through an indefinite integral, and The determination of indefinite integral by the accumulation function. The findings suggest that the AiC framework is useful for designing didactical activities for conceptual learning, and the accumulation function can serve as a basis for teaching the three knowledge elements regarding relationship between indefinite integral and definite integral.

• Communications of Mathematical Education
• /
• v.37 no.3
• /
• pp.419-442
• /
• 2023

This study investigated fifth graders' understanding of variables from a generalized arithmetic and a functional perspectives of early algebra. Specifically, regarding a generalized perspective, we included the property of 1, the commutative property of addition, the associative property of multiplication, and a problem context with indeterminate quantities. Regarding the functional perspective, we covered additive, multiplicative, squaring, and linear relationships. A total of 246 students from 11 schools participated in this study. The results showed that most students could find specific values for variables and understood that equations involving variables could be rewritten using different symbols. However, they struggled to generalize problem situations involving indeterminate quantities to equations with variables. They also tended to think that variables used in representing the property of 1 and the commutative property of addition could only be natural numbers, and about 25% of the students thought that variables were fixed to a single number. Based on these findings, this paper suggests implications for elementary school students' understanding and teaching of variables.

• Journal of Biomedical Engineering Research
• /
• v.19 no.5
• /
• pp.455-468
• /
• 1998

For the objective interpretation of cerebral metabolic patterns in epilepsy patients, we developed computer-aided classifier using artificial neural network. We studied interictal brain FDG PET scans of 257 epilepsy patients who were diagnosed as normal(n=64), L TLE (n=112), or R TLE (n=81) by visual interpretation. Automatically segmented volume of interest (VOI) was used to reliably extract the features representing patterns of cerebral metabolism. All images were spatially normalized to MNI standard PET template and smoothed with 16mm FWHM Gaussian kernel using SPM96. Mean count in cerebral region was normalized. The VOls for 34 cerebral regions were previously defined on the standard template and 17 different counts of mirrored regions to hemispheric midline were extracted from spatially normalized images. A three-layer feed-forward error back-propagation neural network classifier with 7 input nodes and 3 output nodes was used. The network was trained to interpret metabolic patterns and produce identical diagnoses with those of expert viewers. The performance of the neural network was optimized by testing with 5~40 nodes in hidden layer. Randomly selected 40 images from each group were used to train the network and the remainders were used to test the learned network. The optimized neural network gave a maximum agreement rate of 80.3% with expert viewers. It used 20 hidden nodes and was trained for 1508 epochs. Also, neural network gave agreement rates of 75~80% with 10 or 30 nodes in hidden layer. We conclude that artificial neural network performed as well as human experts and could be potentially useful as clinical decision support tool for the localization of epileptogenic zones.

• Journal of Wetlands Research
• /
• v.17 no.3
• /
• pp.251-263
• /
• 2015

This study suggested a novel approach of estimating the optimal probability density function (OPDF) of the annual maximum rainfall time series (AMRT) combining the L-moment ratio diagram and the geographical information system. This study also reported several interesting geographical characteristics of the AMRT in Korea. To achieve this purpose, this study determined the OPDF of the AMRT with the duration of 1-, 3-, 6-, 12-, and 24-hours using the method of L-moment ratio diagram for each of the 67 rain gages in Korea. Then, a map with the Thiessen polygons of the 67 rain gages colored differently according the different type of the OPDF, was produced to analyze the spatial trend of the OPDF. In addition, this study produced the color maps which show the fitness of a given probability density function to represent the AMRT. The study found that (1) both L-skewness and L-kurtosis of the AMRT have clear geographical trends, which means that the extreme rainfall events are highly influenced by geography; (2) the impact of the altitude on these two rainfall statistics is greater for the mountaneous region than for the non-mountaneous region. In the mountaneous region, the areas with higher altitude are more likely to experience the less-frequent and strong rainfall events than the areas with lower altitude; (3) The most representative OPDFs of Korea except for the Southern edge are Generalized Extreme Value distribution and the Generalized Logistic distribution. The AMRT of southern edge of Korea was best represented by the Generalized Pareto distribution.

• Journal of Korea Water Resources Association
• /
• v.34 no.4
• /
• pp.303-316
• /
• 2001

In this study, Radial Basis Function(RBF) Neural Networks Model, a kind of Hybrid Neural Networks was applied to hydrological forecasting in a small watershed. RBF Neural Networks Model has four kinds of parameters in it and consists of unsupervised and supervised training patterns. And Gaussian Kernel Function(GKF) was used among many kinds of Radial Basis Functions(RBFs). K-Means clustering algorithm was applied to optimize centers and widths which ate the parameters of GKF. The parameters of RBF Neural Networks Model such as centers, widths weights and biases were determined by the training procedures of RBF Neural Networks Model. And, with these parameters the validation procedures of RBF Neural Networks Model were carried out. RBF Neural Networks Model was applied to Wi-Stream basin which is one of the IHP Representative basins in South Korea. 10 rainfall events were selected for training and validation of RBF Neural Networks Model. The results of RBF Neural Networks Model were compared with those of Elman Neural Networks(ENN) Model. ENN Model is composed of One Step Secant BackPropagation(OSSBP) and Resilient BackPropagation(RBP) algorithms. RBF Neural Networks shows better results than ENN Model. RBF Neural Networks Model spent less time for the training of model and can be easily used by the hydrologists with little background knowledge of RBF Neural Networks Model.

• Korean journal of applied entomology
• /
• v.3
• /
• pp.27-30
• /
• 1964

The effects of the rice weevils(Sitophilus oryzae L.) on naked barley and wheat were studied in connection with the moisture contents and the molds in the grain under the controlled conditions; R.H. $75\%,\; 28^{\circ}C.$ 1. The moisture contents of control grain were decreased $2.07\%$ for naked barley and $1.29\%$ in wheat in four weeks. 2. The moisture contents of naked barley which had been infested with 100 weevils were decreased $0.29\%$ and were increased $0.79\% in the berley infested with 200 weevils at t beginning. In wheat, the moisture contents were decreased by$0.84\%\; and\; 0.13\%$ in respective experimental lots. 3. The moisture contents of grains have close relation with the population densities of the weevils in the grain. 4. The pattern of the change in the moisture content of grain have close relation with the population densities of the weevils in the grain. 5. The number of the mold colonies in the grain increased exponentially with the increase in the population densities of weevils in the grain. 6. The species of the mold found were A. restrictus and A. versicolor, which were the most abundant, and A. candidus was also found, but Ins common.

• Journal of Institute of Control, Robotics and Systems
• /
• v.2 no.2
• /
• pp.108-114
• /
• 1996

We present proofs of the stability and convergence of Self-organizing feature map (SOFM) neural network with time-invarient learning rate and binary reinforcement function. One of the major problems in Self-organizing feature map neural network concerns with learning rate-"Kalman Filter" gain in stochsatic control field which is monotone decreasing function and converges to 0 for satisfying minimum variance property. In this paper, we show that the stability and convergence of Self-organizing feature map neural network with time-invariant learning rate. The analysis of the proposed algorithm shows that the stability and convergence is guranteed with exponentially stable and weak convergence properties as well.s as well.