• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.343-345
• /
• 2017

With the development of IoT technology, terminals connected with IoT are being used. However, security incidents are occurring as IoT is applied to society as a whole. IoT security incidents can be linked to personal risk and social disruption. In this study, we extract the evidence of security breach in IoT device. Analyze IoT security breach environment and extract Hashing function to secure original integrity and integrity. Then, the Forensic evidence is extracted from the IoT security device to verify the integrity of the original and Forensic reports should be written and studied to be used as legal evidence.

• Smart Media Journal
• /
• v.5 no.4
• /
• pp.75-82
• /
• 2016

Although Korea's economic and domestic automobile market through the change of road environment are growth, the traffic accident rate has also increased, and the casualties is at a serious level. For this reason, the government is establishing and promoting policies to open traffic accident data and solve problems. In this paper, describe the method of predicting traffic accidents by eliminating the class imbalance using the traffic accident data and constructing the Hybrid Model. Using the original traffic accident data and the sampled data as learning data which use FP-Growth algorithm it learn patterns associated with traffic accident injury severity. Accordingly, In this paper purpose a method for predicting the severity of a victim of a traffic accident by analyzing the association patterns of two learning data, we can extract the same related patterns, when a decision tree and multinomial logistic regression analysis are performed, a hybrid model is constructed by assigning weights to related attributes.

• Journal of the Korean Society of Costume
• /
• v.56 no.5 s.104
• /
• pp.29-43
• /
• 2006

The purpose of this study is to examine a unique characteristic of the colors of the costumes in Korean basic culture in the aim of seeking the characteristics and the conceptual meanings of colors found in the majority’s culture. The scope of the basic culture was divided into folk belief, folk game and folk play. Within these limits, the colors of the dress, accessories, instruments were extracted by comparing with the naked eye in NCS Color System. For the analysis of hue and tone, the secondary dimensional analysis using NCS color system and the three-dimensional analysis using the software, COLOR 3D Version 2.0, were done. The result of this investigation is that the colors of the costume in the Korean basic culture are white, gray and black of achromatic color and yellow, yellowish red and purplish blue. This confirms that the colors based on Five-elements color are becoming the basis too basic culture. And Arche-pattern, which is a characteristic commonly found in the Korean traditional society, was shown as a characteristic of color. The colors of the costumes in Korean basic culture are uniquely adopted by the Korean civilians according to their religious and philosophical living standard. This study is meaningful in seeking a root for the formation of their unique color culture.

• Convergence Security Journal
• /
• v.11 no.3
• /
• pp.85-90
• /
• 2011

JPMP SID Tag is the security senor tag to provides physical information protective function using sensor module, has impossible feature to copy and fake the data which is stored in the tag. So data which is stored in the JPMP SID Tag has authenticity, integrity, originality. Therefore JPMP SID Tag could be applied in the place where the security of data is demanded. This paper propose the system using the JPMP SID Tag to acquire and protect digital evidence where cause investigation of accident is necessary. Also, proposed systems is complement of software security with composition secondary control logic for JPMP SID tag access control.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.6
• /
• pp.115-122
• /
• 2019

CCTV(Closed-Circuit Television) is increasingly exposed to CCTV per person as the number of installations increases every year for accident prevention and facility safety. The intelligent video surveillance system technology is attracting attention to the privacy protection of exposed subjects. The intelligent video surveillance system performs a process for the privacy protection so as to perform the action type of the subject and the judgment of the situation in the simple identification of the photographed image data, or to prevent the information, from which the information of the photographed subject is exposed. The proposed technique is applied to the video surveillance system and converts the original image information taken from the video surveillance system into similar image information so that the original image information is not leaked to the outside. In this paper, we propose an image conversion mechanism that inserts a virtual face image that approximates a preset similarity.

• Journal of Internet Computing and Services
• /
• v.21 no.6
• /
• pp.23-31
• /
• 2020

This study was carried out to generate various images of railroad surfaces with random defects as training data to be better at the detection of defects. Defects on the surface of railroads are caused by various factors such as friction between track binding devices and adjacent tracks and can cause accidents such as broken rails, so railroad maintenance for defects is necessary. Therefore, various researches on defect detection and inspection using image processing or machine learning on railway surface images have been conducted to automate railroad inspection and to reduce railroad maintenance costs. In general, the performance of the image processing analysis method and machine learning technology is affected by the quantity and quality of data. For this reason, some researches require specific devices or vehicles to acquire images of the track surface at regular intervals to obtain a database of various railway surface images. On the contrary, in this study, in order to reduce and improve the operating cost of image acquisition, we constructed the 'Defective Railroad Surface Regeneration Model' by applying the methods presented in the related studies of the Generative Adversarial Network (GAN). Thus, we aimed to detect defects on railroad surface even without a dedicated database. This constructed model is designed to learn to generate the railroad surface combining the different railroad surface textures and the original surface, considering the ground truth of the railroad defects. The generated images of the railroad surface were used as training data in defect detection network, which is based on Fully Convolutional Network (FCN). To validate its performance, we clustered and divided the railroad data into three subsets, one subset as original railroad texture images and the remaining two subsets as another railroad surface texture images. In the first experiment, we used only original texture images for training sets in the defect detection model. And in the second experiment, we trained the generated images that were generated by combining the original images with a few railroad textures of the other images. Each defect detection model was evaluated in terms of 'intersection of union(IoU)' and F1-score measures with ground truths. As a result, the scores increased by about 10~15% when the generated images were used, compared to the case that only the original images were used. This proves that it is possible to detect defects by using the existing data and a few different texture images, even for the railroad surface images in which dedicated training database is not constructed.

• Convergence Security Journal
• /
• v.21 no.2
• /
• pp.57-66
• /
• 2021

Deep neural networks (DNNs) provide excellent performance for image, speech, and pattern recognition. However, DNNs sometimes misrecognize certain adversarial examples. An adversarial example is a sample that adds optimized noise to the original data, which makes the DNN erroneously misclassified, although there is nothing wrong with the human eye. Therefore studies on defense against adversarial example attacks are required. In this paper, we have experimentally analyzed the success rate of detection for adversarial examples by adjusting various parameters. The performance of the ensemble defense method was analyzed using fast gradient sign method, DeepFool method, Carlini & Wanger method, which are adversarial example attack methods. Moreover, we used MNIST as experimental data and Tensorflow as a machine learning library. As an experimental method, we carried out performance analysis based on three adversarial example attack methods, threshold, number of models, and random noise. As a result, when there were 7 models and a threshold of 1, the detection rate for adversarial example is 98.3%, and the accuracy of 99.2% of the original sample is maintained.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.4
• /
• pp.31-39
• /
• 2012

On rainy days, water films form on wet road surfaces and reduce the braking force of vehicles, which often ends up in accidents. For safe driving, the road information signage provides information on road and weather conditions warning drivers of wet road conditions. Still, current information on road conditions is neither localized nor detailed but universal. The present study used the images on CCTVs installed on roads to compare the images of road surfaces in an attempt to suggest a mechanism determining factors that hamper safe driving based on the images. In the image comparison, a normal road image taken on a sunny day is used as an original image, against which road conditions occurring on rainy days are categorized and determined on a case-by-case basis to provide drivers with early warning for the sake of safe driving.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.6
• /
• pp.1293-1308
• /
• 2014

The cause of privacy extrusion in credit card company at 2014 is usage of the original data in test system. By Electronic banking supervision regulations of the Financial Supervisory Service and Information Security business best practices of Finance information technology (IT) sector, the data to identify the customer in the test system should be used to convert. Following this guidelines, Financial firms use converted customer identificaion data by loading in test system. However, there is some risks that may be introduced unintentionally by user mistake or lack of administrative or technical security in the process of testing. also control and risk management processes for those risks did not studied. These situations are conducive to increasing the compliance violation possibility of supervisory institution. So in this paper, we present and prove the process to eliminate the compliance violation possibility of supervisory institution by controlling and managing the unidentified conversion customer identification data and check the effectiveness of the process.

• Journal of Internet Computing and Services
• /
• v.20 no.5
• /
• pp.1-8
• /
• 2019

This paper carried out a study to reduce damage from jellyfish whose population has increased due to global warming. The emergence of jellyfish on the beach could result in casualties from jellyfish stings and economic losses from closures. This paper confirmed from the preceding studies that the pattern of jellyfish's appearance is predictable through machine learning. This paper is an extension of The prediction model of emergence of Busan coastal jellyfish using SVM. In this paper, we used deep neural network to expand from the existing methods of predicting the existence of jellyfish to the classification by index. Due to the limitations of the small amount of data collected, the 84.57% prediction accuracy limit was sought to be resolved through data expansion using bootstraping. The expanded data showed about 7% higher performance than the original data, and about 6% better performance compared to the transfer learning. Finally, we used the test data to confirm the prediction performance of jellyfish appearance. As a result, although it has been confirmed that jellyfish emergence binary classification can be predicted with high accuracy, predictions through indexation have not produced meaningful results.