• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.2
• /
• pp.305-312
• /
• 2020

The Privacy Act stipulates that the privacy policy document, which is a privacy statement, should be disclosed in order to guarantee the rights of the information subjects, and the Fair Trade Commission considers the privacy policy as a condition and conducts an unfair review of the terms and conditions under the Terms and Conditions Control Act. However, the information subjects tend not to read personal information because it is complicated and difficult to understand. Simple and legible information processing policies will increase the probability of participating in online transactions, contributing to the increase in corporate sales and resolving the problem of information asymmetry between operators and information entities. In this study, complex personal information processing policies are analyzed using deep learning, and models are presented for acquiring simplified personal information processing policies that are highly readable by the information subjects. To present the model, the personal information processing policies of 258 domestic companies were established as data sets and analyzed using deep learning technology.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.1
• /
• pp.144-150
• /
• 2017

Recently, deep learning is used for intelligent processing and accuracy improvement of data. It is formed calculation model composed of multi data processing layer that train the data representation through an abstraction of the various levels. A category of deep learning, convolution neural network is utilized in various research fields, which are human pose estimation, face recognition, image classification, speech recognition. When using the deep layer and lots of class, CNN that show a good performance on image classification obtain higher classification rate but occur the overfitting problem, when using a few data. So, we design the training network based on convolution neural network and trained our image data set for object classification in few class problem. The experiment show the higher classification rate of 7.06% in average than the previous networks designed to classify the object in 1000 class problem.

• Journal of Convergence for Information Technology
• /
• v.10 no.5
• /
• pp.1-7
• /
• 2020

This paper proposes a link adaptation method for Underwater Internet of Things (IoT), which reduces power consumption of sensor nodes and improves the throughput of network in underwater IoT network. Adaptive Modulation and Coding (AMC) technique is one of link adaptation methods. AMC uses the strong correlation between Signal Noise Rate (SNR) and Bit Error Rate (BER), but it is difficult to apply in underwater IoT as it is. Therefore, we propose the machine learning based AMC technique for underwater environments. The proposed Modulation Coding and Scheme (MCS) prediction model predicts transmission method to achieve target BER value in underwater channel environment. It is realistically difficult to apply the predicted transmission method in real underwater communication in reality. Thus, this paper uses the high accuracy BER prediction model to measure the performance of MCS prediction model. Consequently, the proposed AMC technique confirmed the applicability of machine learning by increase the probability of communication success.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.5
• /
• pp.425-430
• /
• 2015

This paper is a study to improve the classification efficiency of rotating objects by using deep neural networks to which a deep learning algorithm was applied. For the classification experiment of rotating objects, COIL-20 is used as data and total 3 types of classifiers are compared and analyzed. 3 types of classifiers used in the study include PCA classifier to derive a feature value while reducing the dimension of data by using Principal Component Analysis and classify by using euclidean distance, MLP classifier of the way of reducing the error energy by using error back-propagation algorithm and finally, deep learning applied DBN classifier of the way of increasing the probability of observing learning data through pre-training and reducing the error energy through fine-tuning. In order to identify the structure-specific error rate of the deep neural networks, the experiment is carried out while changing the number of hidden layers and number of hidden neurons. The classifier using DBN showed the lowest error rate. Its structure of deep neural networks with 2 hidden layers showed a high recognition rate by moving parameters to a location helpful for recognition.

• Journal of the Korea Convergence Society
• /
• v.10 no.2
• /
• pp.1-6
• /
• 2019

The proposed model is developed to minimize the loss of information in incomplete data including missing data. The first step is to transform the learning data to compensate for the loss information using the data extension technique. In this conversion process, the attribute values of the data are filled with binary or probability values in one-hot encoding. Next, this conversion data is input to the deep learning model, where the number of entries is not constant depending on the cardinality of each attribute. Then, the entry values of each attribute are assigned to the respective input nodes, and learning proceeds. This is different from existing learning models, and has an unusual structure in which arbitrary attribute values are distributedly input to multiple nodes in the input layer. In order to evaluate the learning performance of the proposed model, various experiments are performed on the missing data and it shows that it is superior in terms of performance. The proposed model will be useful as an algorithm to minimize the loss in the ubiquitous environment.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.2
• /
• pp.11-24
• /
• 2022

For the questions asked for LMS-based online evaluation the professor directly set exam questions, or use the automatic question-taking method according to the level of difficulty using the question bank divided by category. Among them, it is important to manage the difficulty of questions in an objective and efficient way, above all, in the automatic question-taking method according to difficulty. Because the questions presented to the evaluators may be different. In this paper, we propose an difficulty re-adjustment algorithm that considers not only the correct rate of a problem but also the time taken to solve the problem. For this, a logistic regression classification algorithm was used of machine learning, and a reference threshold was set based on the predicted probability value of the learning model and used to readjust the difficulty of each item. As a result, it was confirmed that there were many changes in the difficulty of each item that depended only on the existing correct rate. Also, as a result of performing group evaluation using the adjustment difficulty problem, it was confirmed that the average score improved in most groups compared to the difficulty problem based on the percentage of correct answers.

• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.322-330
• /
• 2021

In modern aquaculture, mass mortality is a very important issue that determines the success of aquaculture business. If a fish disease is not detected at an early stage in the farm, the disease spreads quickly because the farm is a closed environment. Therefore, early detection of diseases is crucial to prevent mass mortality of fish raised in farms. Recently deep learning-based automatic identification of fish diseases has been widely used, but there are many difficulties in identifying objects due to insufficient images of fish diseases. Therefore, this paper suggests a method to generate a large number of fish disease images by synthesizing normal images and disease images using SinGAN deep learning model in order to to solve the lack of fish disease images. We generate images from the three most frequently occurring Paralichthys Olivaceus diseases such as Scuticociliatida, Vibriosis, and Lymphocytosis and compare them with the original image. In this study, a total of 330 sheets of scutica disease, 110 sheets of vibrioemia, and 110 sheets of limphosis were made by synthesizing 10 disease patterns with 11 normal halibut images, and 1,320 images were produced by quadrupling the images.

• Journal of the Korea Convergence Society
• /
• v.13 no.2
• /
• pp.249-255
• /
• 2022

This study proposed an analysis framework for real-time prediction of CNC processing defects using machine learning-based models that are recently attracting attention as processing defect prediction methods, and applied it to CNC machines. Analysis shows that the XGBoost, CatBoost, and LightGBM models have the same best accuracy, precision, recall, F1 score, and AUC, of which the LightGBM model took the shortest execution time. This short run time has practical advantages such as reducing actual system deployment costs, reducing the probability of CNC machine damage due to rapid prediction of defects, and increasing overall CNC machine utilization, confirming that the LightGBM model is the most effective machine learning model for CNC machines with only basic sensors installed. In addition, it was confirmed that classification performance was maximized when an ensemble model consisting of LightGBM, ExtraTrees, k-Nearest Neighbors, and logistic regression models was applied in situations where there are no restrictions on execution time and computing power.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.2
• /
• pp.175-182
• /
• 2023

Differential cryptanalysis is one of the analysis techniques for block ciphers, and uses the property that the output difference with respect to the input difference exists with a high probability. If random data and differential data can be distinguished, data complexity for differential cryptanalysis can be reduced. For this, many studies on deep learning-based neural distinguisher have been conducted. In this paper, a deep learning-based neural distinguisher for PIPO 64/128 is proposed. As a result of experiments with various input differences, the 3-round neural distinguisher for the differential characteristics for 0, 1, 3, and 5-rounds achieved accuracies of 0.71, 0.64, 0.62, and 0.64, respectively. This work allows distinguishing attacks for up to 8 rounds when used with the classical distinguisher. Therefore, scalability was achieved by finding a distinguisher that could handle the differential of each round. To improve performance, we plan to apply various neural network structures to construct an optimal neural network, and implement a neural distinguisher that can use related key differential or process multiple input differences simultaneously.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.143-149
• /
• 2022

Since patent documents contain detailed results of research and development technologies, many studies on various patent analysis methods for effective technology analysis have been conducted. In particular, research on quantitative patent analysis by statistics and machine learning algorithms has been actively conducted recently. The most used patent data in quantitative patent analysis is technology keywords. Most of the existing methods for analyzing the keyword data were models based on the Gaussian probability distribution with random variable on real space from negative infinity to positive infinity. In this paper, we propose a model using gamma probability distribution to analyze the frequency data of patent keywords that can theoretically have values from zero to positive infinity. In addition, in order to determine the regression equation of the gamma-based regression model, two-mode network is constructed to visualize the technological association between keywords. Practical patent data is collected and analyzed for performance evaluation between the proposed method and the existing Gaussian-based analysis models.