• The Journal of the Korea Contents Association
• /
• v.9 no.7
• /
• pp.379-389
• /
• 2009

In this paper, we analyzed the effect of u-learning model school which have been in forced by the Ministry of Education. We suggested a plan which we generalized the effects of u-learning. To analyzed the effects of u-learning, first of all, we set up indexes of u-learning effect - satisfaction measurement, efficacy measurement, the scholastic achievements, possibility of generalization. After we reanalyzed reports of model school and papers of u-learning, we looked for suggestions of the effects u-learning. We draw up a plan which we generalized the effects of u-learning according to suggestions. We devide a plan by 3 steps - introduction step, diffusion step, fixation step and every step by 4 field - policy of u-learning, teaching & learning, quality control, technology. Because we suggested a concrete plan which we generalized the effects of u-learning, we expect to use usefully our plan at school in the future.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.1
• /
• pp.11-17
• /
• 2023

This paper proposes a lightweight deep learning network for detecting an image splicing forgery. The research on image forgery detection using CNN, a deep learning network, and research on detecting and localizing forgery in pixel units are in progress. Among them, CAT-Net, which learns the discrete cosine transform coefficients of images together with images, was released in 2022. The DCT coefficients presented by CAT-Net are combined with the JPEG artifact learning module and the backbone model as pre-learning, and the weights are fixed. The dataset used for pre-training is not included in the public dataset, and the backbone model has a relatively large number of network parameters, which causes overfitting in a small dataset, hindering generalization performance. In this paper, this learning module is designed to learn the characterization depending on the DCT domain in real-time during network training without pre-training. The DCT RRU-Net proposed in this paper is a network that combines RRU-Net which detects forgery by learning only images and JPEG artifact learning module. It is confirmed that the network parameters are less than those of CAT-Net, the detection performance of forgery is better than that of RRU-Net, and the generalization performance for various datasets improves through the network architecture and training method of DCT RRU-Net.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.435-441
• /
• 2024

In order for the large amount of collected data sets to be used as deep learning training data, sensitive personal information such as resident registration number and disease information must be changed or encrypted to prevent it from being exposed to hackers, and the data must be reconstructed to match the structure of the built deep learning model. Currently, these tasks are performed manually by experts, which takes a lot of time and money. To solve these problems, this paper proposes a technique that can automatically perform data processing tasks to protect personal information during the deep learning process. In the proposed technique, privacy protection tasks are performed based on data generalization and data reconstruction tasks are performed using circular queues. To verify the validity of the proposed technique, it was directly implemented using C language. As a result of the verification, it was confirmed that data generalization was performed normally and data reconstruction suitable for the deep learning model was performed properly.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.18 no.6A
• /
• pp.139-149
• /
• 2008

The amount of personal information collected by organizations and government agencies is continuously increasing. When a data collector publishes personal information for research and other purposes, individuals' sensitive information should not be revealed. On the other hand, published data is also required to provide accurate statistical information for analysis. k-Anonymity and ${\iota}$-diversity models are popular approaches for privacy preserving data publication. However, they are limited to static data release. After a dataset is updated with insertions and deletions, a data collector cannot safely release up-to-date information. Recently, the m-invariance model has been proposed to support re-publication of dynamic datasets. However, the m-invariant generalization can cause high information loss. In addition, if the adversary already obtained sensitive values of some individuals before accessing released information, the m-invariance leads to severe privacy disclosure. In this paper, we propose a novel technique for safely releasing dynamic datasets. The proposed technique offers a simple and effective method for handling inserted and deleted records without generalization. It also gives equivalent degree of privacy preservation to the m-invariance model.

• The Korean Journal of Applied Statistics
• /
• v.14 no.1
• /
• pp.25-37
• /
• 2001

The marginal model is proposed for the analysis of data which have c(2: 3) categories in the 3 x 3 cross-over trials with three periods and three treatments. This model could be used for the counterpart of the Kenward-Jones' joint probability one and should be the generalization of Balagtas et ai's univariate marginal logits one, which analyze the treatment effects in the 3 x 3 cross-over trials with binary response variables[Kenward and Jones(1991), Balagtas et al(1995)]. The model equations for the marginal probability are constructed by the three types of link functions. The methods would be given for making of the link function matrices and model ones, and the estimation of parameters shall be discussed. The proposed model is applied to the analysis of Kenward and Jones' data.

• Korean journal of applied entomology
• /
• v.36 no.3
• /
• pp.215-223
• /
• 1997

A matrix model of rice weevil population based on degree day (DD) was constructed. The basic matrix model predicted on exponential jncrcase of the adult weevil density and the finite rate of increase(h) of the population was estimated to be 2.155/100DD. Adult density simulated by the matrix model including intraspecific competition showed a damped oscillation over time and reached at the stationary level of 530 at 69, 300DD. The experimental population showed similar features to that of the model. But there were some differences in the highest density and period of adult oscillation. The differences could largely be caused by the assumption of the model; resource constancy.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.47-50
• /
• 2000

In this paper, an optimal identification method using Multi-FNN(Fuzzy-Neural Network) is proposed for model ins of nonlinear complex system. In order to control of nonlinear process with complexity and uncertainty of data, proposed model use a HCM clustering algorithm which carry out the input-output data preprocessing function and Genetic Algorithm which carry out optimization of model. The proposed Multi-FNN is based on Yamakawa's FNN and it uses simplified inference as fuzzy inference method and Error Back Propagation Algorithm as learning rules. HCM clustering method which carry out the data preprocessing function for system modeling, is utilized to determine the structure of Multi-FNN by means of the divisions of input-output space. Also, the parameters of Multi-FNN model such as apexes of membership function, learning rates and momentum coefficients are adjusted using genetic algorithms. Also, a performance index with a weighting factor is presented to achieve a sound balance between approximation and generalization abilities of the model, To evaluate the performance of the proposed model, we use the time series data for gas furnace and the numerical data of nonlinear function.

• Journal of Korea Multimedia Society
• /
• v.24 no.5
• /
• pp.659-666
• /
• 2021

With the continuous development of deep learning, human behavior recognition algorithms have achieved good results. However, in a multi-person recognition environment, the complex behavior environment poses a great challenge to the efficiency of recognition. To this end, this paper proposes a multi-person pose estimation model. First of all, the human detectors in the top-down framework mostly use the two-stage target detection model, which runs slow down. The single-stage YOLOv3 target detection model is used to effectively improve the running speed and the generalization of the model. Depth separable convolution, which further improves the speed of target detection and improves the model's ability to extract target proposed regions; Secondly, based on the feature pyramid network combined with context semantic information in the pose estimation model, the OHEM algorithm is used to solve difficult key point detection problems, and the accuracy of multi-person pose estimation is improved; Finally, the Euclidean distance is used to calculate the spatial distance between key points, to determine the similarity of postures in the frame, and to eliminate redundant postures.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.632-657
• /
• 2022

Detecting web attacks is a major challenge, and it is observed that the use of simple models leads to low sensitivity or high false positive problems. In this study, we aim to develop a robust two-stage deep learning based stacked ensemble web application firewall. Normal and abnormal classification is carried out in the first stage of the proposed WAF model. The classification process of the types of abnormal traffics is postponed to the second stage and carried out using an integrated stacked ensemble model. By this way, clients' requests can be served without time delay, and attack types can be detected with high sensitivity. In addition to the high accuracy of the proposed model, by using the statistical similarity and diversity analyses in the study, high generalization for the ensemble model is achieved. Within the study, a comprehensive, up-to-date, and robust multi-class web anomaly dataset named GAZI-HTTP is created in accordance with the real-world situations. The performance of the proposed WAF model is compared to state-of-the-art deep learning models and previous studies using the benchmark dataset. The proposed two-stage model achieved multi-class detection rates of 97.43% and 94.77% for GAZI-HTTP and ECML-PKDD, respectively.

• Proceedings of the KIEE Conference
• /
• 1989.07a
• /
• pp.101-105
• /
• 1989

The iterative learning controller makes the system output follow the desired output over a finite time interval through iterating trials. In this paper, first we discuss that the design problem of learning controller is originally the design problem of the inverse model. Then we show that the tracking error which is the difference between the desired output and the system output is reduced monotonically by properly modeled inverse system if the magnitude of the learning operator being introduced is bounded within the unit circle in complex domain. Also it would be shown that the conventional learning control method is a kind of extremely simplified inverse model learning control method of the objective controlled system. Hence this control method can be considered as a generalization of the conventional learning control method. The more a designer model the objective controlled system precisely, the better the performance of the approximated inverse model learning controller would be. Finally we compare the performance of the conventional learning control method with that of the approximated inverse model learning control method by computer simulation.