• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.905-907
• /
• 2022

악성코드를 분석하는 기존 기법인 정적분석은 빠르고 효율적으로 악성코드를 탐지할 수 있지만 난독화된 파일에 취약한 반면,, 동적분석은 난독화된 파일에 적합하지만 느리고 비용이 많이 든다는 단점을 가진다. 본 연구에서는 두 분석 기법의 단점을 해결하기 위해 딥러닝 모델을 활용한 난독화에 강한 정적분석 모델을 제안하였다. 본 연구에서 제안한 방법은 원본 코드 및 난독화된 파일을 grayscale 이미지로 변환하여 데이터셋을 구축하고 AutoEncoder 를 사전학습시켜 encoder 가 원본 파일과 난독화된 파일로부터 원본 파일의 특징을 추출할 수 있도록 한 이후, encoder 의 output 을 fully connected layer 의 입력으로 넣고 전이학습시켜 악성코드를 탐지하도록 하였다. 본 연구에서는 제안한 방법론은 난독화된 파일에서 악성코드를 탐지하는 성능을 F1 score 기준 14.17% 포인트 향상시켰고, 난독화된 파일과 원본 파일을 전체를 합친 데이터셋에서도 악성코드 탐지 성능을 F1 score 기준 7.22% 포인트 향상시켰다.

• The Mathematical Education
• /
• v.44 no.4 s.111
• /
• pp.627-651
• /
• 2005

This study was conducted to attain an in-depth understanding of students' mathematical representations and to present the educational implications for teaching them. Twelve mathematical tasks were developed according to the six types of problems. A task performance was executed to 151 third graders from four classes in DaeJeon and GyeongGi. We analyzed the types and forms of representations generated by them. Then, qualitative case studies were conducted on two small-groups of five from two classes in GyeongGi. We analyzed how individuals' representations became elaborated into group representation and what patterns emerged during the collaborative small-group learning. From the results, most students used more than one representation in solving a problem, but they were not fluent enough to link them to successful problem solving or to transfer correctly among them. Students refined their representations into more meaningful group representation through peer interaction, self-reflection, etc.. Teachers need to give students opportunities to think through, and choose from, various representations in problem solving. We also need the in-depth understanding and great insights into students' representations for teaching.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.284-288
• /
• 2022

최근 다양한 언어모델의 구축 및 발전으로 개체명 인식 시스템의 성능은 최고 수준에 도달했다. 하지만 이와 관련된 대부분의 연구는 데이터가 충분한 언어에 대해서만 다루기 때문에, 양질의 지도학습 데이터의 존재를 가정한다. 대부분의 언어에서는 개체 유형에 대한 언어의 잠재적 특성을 충분히 학습할 수 있는 지도학습 데이터가 부족하기 때문에, 종종 자원 부족의 어려움에 직면한다. 본 논문에서는 Masked language modeling 기반 언어 간 전이학습을 이용한 개체명 인식 방법론에 대한 분석을 수행한다. 이를 위해 전이를 수행하는 소스 언어는 고자원 언어로 가정하며, 전이를 받는 타겟 언어는 저자원 언어로 가정한다. 본 논문에서는 언어모델의 토큰 사전에 언어 독립적인 가상의 자질인 개체 유형에 대한 프롬프트 토큰을 추가하고 이를 소스 언어로 학습한 뒤, 타겟 언어로 전이하는 상황에서 제안하는 방법론에 대한 평가를 수행한다. 실험 결과, 제안하는 방법론은 일반적인 미세조정 방법론보다 높은 성능을 보였으며, 한국어에서 가장 큰 영향을 받은 타겟 언어는 네덜란드어, 한국어로 전이할 때 가장 큰 영향을 준 소스 언어는 중국어인 결과를 보였다.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.53 no.6
• /
• pp.324-333
• /
• 2004

This paper discusses the development of an educational web-based power flow program for undergraduate students. The interaction between lectures and users can be much enhanced via the web-based programs which result in the student's learning effectiveness on the power flow problem. However the difficulties for developing web-based application programs are that there can be the numerous unspecified users to access the application programs. To overcome the aforementioned multi-users problem and to develope the educational web-based power flow program, we have revised the system architecture, the modeling of application programs, and database which efficiently and effectively manages the complex data sets related to the power flow analysis program. The developed application program is composed of the physical three tiers where the middle tier is logically divided into two kinds of application programs. The divided application programs are interconnected by using the Web-service based on XML (Extended Markup Technology) and HTTP (Hyper Text Transfer Protocol) which make it possible the distributed computing technology Also, this paper describes the method of database modeling to handle effectively when the numerous users change the parameters of the power system to compare the results of the base case.

• Research in Mathematical Education
• /
• v.22 no.4
• /
• pp.245-259
• /
• 2019

I examine the discussions of studies related to feminist mathematics education and the implications of mathematics education in South Korea. In particular, I attempt to answer the following questions through literature reviews on feminist mathematics: What is the epistemological background of feminist mathematics education? How is feminist mathematics education defined and implemented? What does feminist mathematics education suggest in South Korea's mathematics curriculum? From the analysis of the literatures, I found that feminist mathematics education reflects not just the rights of female's rights but also a paradigm shift in epistemology of mathematics and philosophy of mathematics education. In this regard, feminist mathematics questions the existing mathematics education related to the female students who were marginalized in the composition and delivery of mathematics. Feminist mathematics education points out that in the course of the transfer of mathematical knowledge in schools, female students understand unilateral information procedurally without understanding the concept. Mathematics educators should consider alternative curricula that reflect the views of female students regarding the nature of mathematics. Students should be able to receive equal mathematics education in a school regardless of their gender. In this case, equal mathematics education refers to education methods that are suitable for both male and female students. The existing mathematics content and its teaching methods were designed based on the learning experiences of male students, which made them relatively difficult for female students to understand.

• Journal of the Korean Society of Systems Engineering
• /
• v.16 no.2
• /
• pp.38-46
• /
• 2020

The accurate measurement of critical heat flux (CHF) in flow boiling is important for the safety requirement of the nuclear power plant to prevent sharp degradation of the convective heat transfer between the surface of the fuel rod cladding and the reactor coolant. In this paper, a System Engineering approach is used to develop a model that predicts the CHF using machine learning. The model is built using artificial neural network (ANN). The model is then trained, tested and validated using pre-existing database for different flow conditions. The Talos library is used to tune the model by optimizing the hyper parameters and selecting the best network architecture. Once developed, the ANN model can predict the CHF based solely on a set of input parameters (pressure, mass flux, quality and hydraulic diameter) without resorting to any physics-based model. It is intended to use the developed model to predict the DNBR under a large break loss of coolant accident (LBLOCA) in APR1400. The System Engineering approach proved very helpful in facilitating the planning and management of the current work both efficiently and effectively.

• Journal of Yeungnam Medical Science
• /
• v.34 no.1
• /
• pp.62-68
• /
• 2017

Background: This study was conducted to examine the academic achievements of first year medical students in one medical school based on their characteristics and student selection factors of admission. Methods: The admission scores of student selection factors (Medical Education Eligibility Test [MEET], grade point average [GPA], English test score and interview) and demographic information were obtained from 61 students who had interviewed (multiple mini interview [MMI]) for admission (38 graduate medical school students in 2014, 23 medical college-transfer students in 2015). T-tests and ANOVA were used to examine the differences in academic achievement according to the student characteristics. Correlations between admission criteria scores and academic achievements were examined. Results: MEET score was higher among graduate medical students than medical college transfer students among student selection factors for admission. There were no significant differences in academic achievement of first grade medical school between age, gender, region of high school, years after graduation and school system. The lowest interview score group showed significantly lower achievement in problem-based learning (PBL) (p=0.034). Undergraduate GPA score was positively correlated with first grade total score (r=0.446, p=0.001) among admission scores of student selection factors. Conclusion: Students with higher GPA scores tend to do better academically in their first year of medical school. In case of interview, academic achievement did not lead to differences except for PBL.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.5
• /
• pp.35-41
• /
• 2017

In this paper, we analyze the performance of the recently introduced Hint-knowledge distillation (KD) training approach based on the teacher-student framework for knowledge distillation and knowledge transfer. As a deep neural network (DNN) considered in this paper, the deep residual network (ResNet), which is currently regarded as the latest DNN, is used for the teacher-student framework. Therefore, when implementing the Hint-KD training, we investigate the impact on the weight of KD information based on the soften factor in terms of classification accuracy using the widely used open deep learning frameworks, Caffe. As a results, it can be seen that the recognition accuracy of the student model is improved when the fixed value of the KD information is maintained rather than the gradual decrease of the KD information during training.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.23 no.2
• /
• pp.115-124
• /
• 2020

Due to the increasing threats of submarines from North Korea and other countries, ROK Navy should improve the detection capability of submarines. There are two ways to detect submarines : acoustic detection and non-acoustic detection. Since the acoustic-detection way has limitations in spite of its usefulness, it should have the complementary way. The non-acoustic detection is the way to detect submarines which are operating mast sets such as periscopes and snorkels by non-acoustic sensors. So, this paper proposes a new submarine non-acoustic detection model using an ensemble of Convolutional Neural Network models in order to automate the non-acoustic detection. The proposed model is trained to classify targets as 4 classes which are submarines, flag buoys, lighted buoys, small boats. Based on the numerical study with 10,287 images, we confirm the proposed model can achieve 91.5 % test accuracy for the non-acoustic detection of submarines.

• Journal of the Korean Chemical Society
• /
• v.62 no.6
• /
• pp.427-432
• /
• 2018

The reaction of [$[Ni(L)]Cl_2{\cdot}2H_2O$ (L = 3,14-dimethyl-2,6,13,17-tetraazatricyclo[$14,4,0^{1.18},0^{7.12}$]docosane) with 1,1-cyclohexanediacetic acid ($H_2cda$) yields mononuclear nickel(II) complex, [$Ni(L)(Hcda^-)_2$] (1). This complex has been characterized by X-ray crystallography, electronic absorption, cyclic voltammetry and thermogravimetric analyzer. The crystal structure of 1 exhibits a distorted octahedral geometry with four nitrogen atoms of the macrocycle and two 1,1-cyclohexanediacetate ligands. It crystallizes in the triclinic system P-1 with a = 11.3918(7), b = 12.6196(8), $c=12.8700(8){\AA}$, $V=1579.9(2){\AA}^3$, Z = 2. Electronic spectrum of 1 also reveals a high-spin octahedral environment. Cyclic voltammetry of 1 undergoes one wave of a one-electron transfer corresponding to $Ni^{II}/Ni^{III}$ process. TGA curve for 1 shows three-step weight loss. The electronic spectra, electrochemical and TGA behavior of the complex are significantly affected by the nature of the axial $Hcda^-$ ligand.