• The Journal of the Korea Contents Association
• /
• v.20 no.2
• /
• pp.240-247
• /
• 2020

There have been many efforts to understand the trends of IT environments that have been rapidly changed. In a view point of management, it needs to prepare the social systems in advance by using Big-data these days. This research is for the implementation of Issue Analysis System for the Big-data based on Artificial Intelligence. This paper aims to confirm the possibility of new technology for Big-data processing through the proposed Issue Analysis System using. We propose a technique for semantic reasoning and pattern analysis based on the AI and show the proposed method is feasible to handle the Big-data. We want to verify that the proposed method can be useful in dealing with Big-data by applying latest security issues into the system. The experiments show the potentials for the proposed method to use it as a base technology for dealing with Big-data for various purposes.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.1
• /
• pp.70-75
• /
• 2016

Nowadays, there are many research for recognizing face of people using the machine vision. the machine vision is classification and analysis technology using machine that has sight such as human eyes. In this paper, we propose algorithm for classifying human face using this machine vision system. This algorithm consist of Convolutional Neural Network and cascade face detector. And using this algorithm, we classified the face of subjects. For training the face classification algorithm, 2,000, 3,000, and 4,000 images of each subject are used. Training iteration of Convolutional Neural Network had 10 and 20. Then we classified the images. In this paper, about 6,000 images was classified for effectiveness. And we implement the system that can classify the face of subjects in realtime using USB camera.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.22 no.1
• /
• pp.107-114
• /
• 2018

In this study, the damage detection method is proposed for the rotational stiffness of connections in steel moment frames by using artificial neural network(ANN). The flexural moment of columns, natural frequencies, modeshapes are used for the input layer in ANN while the damage index, that signify the damage level, is used for the output layer in ANN. The 5-story steel moment frame as an example structure is used to generate the train and test data. Total number of damage scenarios considered is 829. From the results of application, it is shown that the proposed method can accurately estimate the location and level of damages.

• The KIPS Transactions:PartA
• /
• v.16A no.4
• /
• pp.299-306
• /
• 2009

Hierarchical Folded HyperStar Network has lower network cost than HCN(n,n) and HFN(n,n) which are hierarchical networks with the same number of nodes. In this paper, we analyze embedding between Hierarchical Folded HyperStar HFH($C_n,C_n$) and Hypercube, HCN(n,n), HFN(n,n). The results of embedding are that HCN(n,n), HFN(n,n) and Hypercube $Q_{2n}$ can be embedded into HFH($C_n,C_n$) with expansion $\frac{C^n}{2^{2n}}$ and dilation 2, 3, and 4, respectively. Also, HFH($C_n,C_n$) can be embedded into HFN(2n,2n) with dilation 1. These results mean so many developed algorithms in Hypercube, HCN(n,n), HFN(n,n) can be used efficiently in HFH($C_n,C_n$).

• Journal of the Korean Geographical Society
• /
• v.45 no.4
• /
• pp.461-477
• /
• 2010

Recent environmental issues such as genetically modified organisms, the loss of biodiversity, climate change, and nuclear waste cannot be reduced to a matter of science or society and explained through nature-society dualist approaches because of their complexity and heterogeneity. This paper examines how nature-society dualism has been embedded in science studies and geography and how this dualism can be overcome. Actor-Network Theory as an attempt to overcome this nature-society dualism is appropriate in analysing "strange imbriglio" of biology, politics, technoscience, market, value, ethics and facts that constitute our society by focusing on heterogeneous association, and can contribute to providing a useful framework to solve environmental problems.

• Smart Media Journal
• /
• v.7 no.4
• /
• pp.17-23
• /
• 2018

We proposed a LSTM-based RNN model that can effectively perform the automatic spacing characteristics. For those long or noisy sentences which are known to be difficult to handle within Neural Network Learning, we defined a proper input data format and decoding data format, and added dropout, bidirectional multi-layer LSTM, layer normalization, and attention mechanism to improve the performance. Despite of the fact that Sejong corpus contains some spacing errors, a noise-robust learning model developed in this study with no overfitting through a dropout method helped training and returned meaningful results of Korean word spacing and its patterns. The experimental results showed that the performance of LSTM sequence-to-sequence model is 0.94 in F1-measure, which is better than the rule-based deep-learning method of GRU-CRF.

• Journal of Digital Convergence
• /
• v.16 no.12
• /
• pp.217-229
• /
• 2018

This paper aims at applying the data mining such as decision tree, neural network, and logistic regression to an unsold apartment complex in Wirye new town and developing the model forecasting the result of initial sale contract by house unit. Raw data are divided into training data and test data. The order of predictability in training data is neural network, decision tree, and logistic regression. On the contrary, the results of test data show that logistic regression is the best model. This means that logistic regression has more data adaptability than neural network which is developed as the model optimized for training data. Determinants of initial sale are the location of floor, direction, the location of unit, the proximity of electricity and generator room, subscriber's residential region and the type of subscription. This suggests that using two models together is more effective in exploring determinants of initial sales. This paper contributes to the development of convergence field by expanding the scope of data mining.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.109-117
• /
• 2020

In this paper, we analyze LADN(Local Area Data Network) that provides high throughput, low latency and service localization for 5G wireless networks and propose an enhanced control protocol design for LADN in 5G wireless networks. The concept of LADN is newly introduced in 3GPP 5G communication system and the LADN is a data network to which the UE(User Equipment) can connect with a specific LADN session only when the UE is located in a certain service area. If the LADN information between the UE and core network is not identical, the LADN session cannot be properly established. The proposed approach promplty synchronizes the LADN information between the UE and core network by using the specific registration procedure and appropriately establishes the LADN session, when the establishment of the LADN session is failed. Consequently, the proposed enhanced control protocol design(ECP) can prevent unnecessary signalling overhead and communication delay for LADN in 5G wireless networks.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.5
• /
• pp.229-234
• /
• 2022

This study conducted a preliminary survey to study humanities healing methods for college students. Based on the student survey, we would like to present the research direction of humanities healing and find an appropriate humanities healing method. For quantitative analysis, 10 questions were constructed, focusing on BPS-Modell, Bio, Psycho, and Sozio of life. In the question of the Bio, 50% of the students said they understood their body, mind, and will and acted accordingly, but 20% of the students showed that their actions according to their body, mind, and will did not fit. In the question of Psycho, more than 50% of students said they communicated well with their inner selves, but less than 20% of students did not. In the question of Sozio of life, more than 60% of students form a social network well, but about 10% of students have very low attitudes or meanings toward life. The ultimate purpose of humanities is 'happiness', and the purpose of human life is also 'happiness'. We hope that the power of positivity to realize a stable future society and improve the quality of life will be expanded through humanities healing.

• Journal of KIISE:Software and Applications
• /
• v.33 no.12
• /
• pp.999-1007
• /
• 2006

The Backpropagation learning algorithm is known to have slow and false convergence aroused from plateau and local minima. Many substitutes for backpropagation announced so far appear to pay some trade-off for convergence speed and stability of convergence according to parameters. Here, a new algorithm is proposed, which avoids some of those problems associated with the conventional backpropagation problems, especially with local minima, and gives relatively stable and fast convergence with low storage requirement. This is the separate learning algorithm in which the upper connections, hidden-to-output, and the lower connections, input-to-hidden, separately trained. This algorithm requires less computational work than the conventional backpropagation and other improved algorithms. It is shown in various classification problems to be relatively reliable on the overall performance.