• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.5
• /
• pp.871-879
• /
• 2020

Perceptual Ad-Blocking is a new advertising blocking technique that detects online advertising by using an artificial intelligence-based advertising image classification model. A recent study has shown that these Perceptual Ad-Blocking models are vulnerable to adversarial attacks using adversarial examples to add noise to images that cause them to be misclassified. In this paper, we prove that existing perceptual Ad-Blocking technique has a weakness for several adversarial example and that Defense-GAN and MagNet who performed well for MNIST dataset and CIFAR-10 dataset are good to advertising dataset. Through this, using Defense-GAN and MagNet techniques, it presents a robust new advertising image classification model for adversarial attacks. According to the results of experiments using various existing adversarial attack techniques, the techniques proposed in this paper were able to secure the accuracy and performance through the robust image classification techniques, and furthermore, they were able to defend a certain level against white-box attacks by attackers who knew the details of defense techniques.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.10 no.6
• /
• pp.87-94
• /
• 2006

Estimating moving vehicle loads is important in modeling design loads for bridge design and construction. The paper proposes a moving force identification algorithm using moment influence lines measured at multi-axes. Density estimation function was applied to estimate more than two wheel loads when estimated load values fluctuated severely. The algorithm has been examined through simulation studies on a simple-span plate-girder bridge. Influences of measurement noise and error in velocity on the identification results were investigated in the simulation study. Also, laboratory experiments were carried out to examine the algorithm. The load identification capability was dependent on the type and speed of moving loads, but the developed algorithm could identify loads within 10% error in maximum.

• Journal of Korea Multimedia Society
• /
• v.16 no.3
• /
• pp.375-387
• /
• 2013

Advanced internet service and smart equipment have caused an environment supporting various online learning anytime and anywhere, which requires learning contents optimized on a new media. Among various on/off line education related to IT, most part if it is office SW. Many oh them cannot make a good education for effective training in practical because many instructors are tend to focus on teaching simple function and use examples of formality repeatedly. In this paper we propose a new office SW education system that make use of LET(Live EduTainer) based on RTE(Real Training Environment) which maximize the effect of learning and it is integrated with GBL(Game Based Learning) which gives rise to interesting in a knowledge as well as simple teaching so that learners are absorbed on it. We'll elaborate a method for teaching and learning required in this system, design and configuration of the system.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.2 no.1
• /
• pp.95-111
• /
• 1998

In this study, the concepts and procedures of the seismic damage analysis methods are examined for both the element-level and the system-level. The seismic damage analysis at the element-level is performed for several example structures using existing method for structural elements or single-degree-of-freedom (SDOF) systems such as the Park and Ang method. In order to analyze seismic damage at the system-level, two types of procedures are used. In the first type of procedure, the system-level seismic responses can be estimated by using the system representative response method(SRRM), or the equivalent SDOF system response method (ESDOF-SRM). Then, the system-level seismic damage is analyzed from the system-level seismic responses using existing method for structural elements or SDOF systems. IN the second type of procedure, the system-level seismic damages are analyzed using the element damage combination method (EDCM) combing the element-level damage indices determined by existing method. To compare tendency of the seismic damage analysis using each methods, example analysis is accomplished for several cases of different structures and different earthquake excitation.

• Convergence Security Journal
• /
• v.18 no.2
• /
• pp.59-67
• /
• 2018

The programming language is a core education area of software that is becoming increasingly important in the age of the fourth industrial revolution, but it requires mathematical knowledge and logical thinking skills, so that many local private university and college students with low basic skills are having difficulties learning it. This problem occasionally causes SW-major students to lose interest and confidence in their majors during the introductory course of programming languages; making them change their majors, or give up their studies. In this study, we designed an instructional model using Scratch for educating C-language which is a typical programming introductory language. To do this, we analyzed the concepts that can be trained by Scratch among the programming concepts supported by C-language, and developed the examples of Scratch for exercising the concepts. In addition, we designed an instructional model, by which the programming concepts are first learned through Scratch and then C-language is taught, and conducted an experiment on the SW-major freshman students of a local private university to verify the effectiveness of the model. In the situation where SW education is becoming common, we expect that this study will help programming language education of security IT students.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.34 no.1
• /
• pp.35-42
• /
• 2021

This paper presents an on-line finite element model updating method for in-service structures using measured data. Conventional updating methods, which are based on numerical optimization, are not efficient for on-line updating because they generally require repeated eigenvalue analyses until convergence criteria are met. The proposed method enables fully automated on-line finite element model updating, almost simultaneously with vibration measurement, without any user intervention or off-line procedures. The automated covariance-driven stochastic subspace identification (Cov-SSI) method is utilized to identify modal frequencies and vectors, and the identified modal data is fed to the neural network of the inverse eigenvalue function to produce the updated finite element model parameters. Numerical examples for a wind excited 20-story building structure shows that the proposed method can update the series of finite element model parameters automatically. It is also shown that sudden changes in the structural parameters can be detected and traced successfully.

• Journal of the Korea Society for Simulation
• /
• v.19 no.2
• /
• pp.91-98
• /
• 2010

Conventional path-finding has focused on finding short collision-free paths. However, as computer games become more sophisticated, it is required to take tactical information like ambush points or lines of enemy sight into account. One way to make this information have an effect on path-finding is to represent a heuristic function of a search algorithm as a weighted sum of tactics. In this paper we consider the problem of learning heuristic to optimize path-finding based on given tactical information. What is meant by learning is to produce a good weight vector for a heuristic function. Training examples for learning are given by a game level-designer and will be compared with search results in every search level to update weights. This paper proposes a learning algorithm integrated with search for tactical path-finding. The perceptron-like method for updating weights is described and a simulation tool for implementing these is presented. A level-designer can mark desired paths according to characters' properties in the heuristic learning tool and then it uses them as training examples to learn weights and shows traces of paths changing along with weight learning.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.3A
• /
• pp.243-250
• /
• 2009

The purpose of this study is to investigate several strategies that can be used to extend the span of conventional PSC girder bridge and to propose a systematic procedure to evaluate the effect of each strategy on the span. In the preceding companion paper, fundamental equations were derived which constitute the assessment graphs and a possible domain for the design. Quantitative evaluation for extension of the span follows here by adopting a sample PSC girder bridge. It apparently shows a number of advantages of the proposed scheme in finding out why and how each strategy contributes to the span extension and in suggesting further improvement for a longer span. The results imply that increasing the strength of a girder, the multistage prestressing with the secondary tendons prestressed before composite action with a deck, and Decked PSC girder are very effective among the strategies examined. It is expected that the span of the PSC girder bridge can be well extended up to 50 m to 70 m which corresponds to a span of the conventional box girder bridges.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.3A
• /
• pp.485-496
• /
• 2006

Practical stability design method of main members of cable-stayed bridges is proposed and discussed through a design example. For this purpose, initial tensions of stay cables and axial forces of main members are firstly determined using initial shaping analysis of bridges under dead loads. And then the effective buckling length using system elastic/inelastic buckling analysis and bending moments considering $P-{\delta}-{\Delta}$ effect by second-order elastic analysis are calculated for main girder and pylon members subjected to both axial forces and moments, respectively. Particularly, three load combinations of dead and live loads, in which maximum load effects due to live loads are obtained, are taken into account and effects of live loads on effective buckling lengths are investigated.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.6A
• /
• pp.577-585
• /
• 2009

A 9-node degenerated shell finite element(FE), which has been developed for assessment of ultimate pressure capacity and nonlinear analysis for nuclear containment building is described in this paper. Reissner-Midnlin(RM) assumptions are adopted to develop the shell FE so that transverse shear deformation effects is considered. Material model for concrete prior to cracking is constructed based on the equivalent stress-equivalent strain relationship. Tension stiffening model, shear transfer mechanism and compressive strength reduction model are used to model the material behavior of concrete after cracking. Niwa and Aoyagi-Yamada failure criteria have been adapted to find initial cracking point in compression-tension and tension-tension region, respectively. Finally, the performance of the developed program is tested and demonstrated with several examples. From the numerical tests, the present results show a good agreement with experimental data or other numerical results.