• Journal of Korea Multimedia Society
• /
• v.6 no.7
• /
• pp.1302-1311
• /
• 2003

This paper presents a more stable method of multiresolution editing for a triangular mesh. The basic idea of our paper is to embed an editing area of a mesh onto a 2D region and to produce 3D surfaces which interpolate the editing-information. In this paper, we adopt the extended convex combination approach based on the shape-preserving parameterization for the embedding, which guarantees no self-intersection on the 2D embedded mesh. That is, the result of the embedding is stable. Moreover, we adopt the multi-level B-spline approach to generate the surface containing all of 3D editing-information, which can make us control the editing area in several levels. Hence, this method supports interactive editing and thus can produce intuitive editing results.

• Journal of Astronomy and Space Sciences
• /
• v.18 no.2
• /
• pp.119-128
• /
• 2001

The oscillation frequency tuning range of waveguide Gunn oscillator and its stability depend sensitively on the dimensions of the resonator. Therefore the embedding impedances with the various dimensions of the resonator for Q-band (33 ∼ 50 GHz) Gunn oscillator are calculated by using HFSS (High Frequency Structure Simulator). In this paper the comparisons between theoretical results of embedding impedances as a function of frequency and that of experimental results are described. And the oscillation frequency range could be predicted by using the theoretical evaluation methods which were proposed in this paper It shows that post size has an effect on the frequency tuning characteristics of Gunn oscillator.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.447-453
• /
• 2020

In this paper, we propose a system to extract effective speaker representations from a speech signal using a deep learning method. Based on the fact that speech signal contains identity unrelated information such as text content, emotion, background noise, and so on, we perform a training such that the extracted features only represent speaker-related information but do not represent speaker-unrelated information. Specifically, we propose an auto-encoder based disentanglement method that outputs both speaker-related and speaker-unrelated embeddings using effective loss functions. To further improve the reconstruction performance in the decoding process, we also introduce a discriminator popularly used in Generative Adversarial Network (GAN) structure. Since improving the decoding capability is helpful for preserving speaker information and disentanglement, it results in the improvement of speaker verification performance. Experimental results demonstrate the effectiveness of our proposed method by improving Equal Error Rate (EER) on benchmark dataset, Voxceleb1.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.377-380
• /
• 2024

최근 악성코드 제작 기술의 고도화에 따라 악성코드의 변종이 전세계적으로 급격히 증가하고 있다. 이러한 대량의 악성코드를 신속하고 정확하게 탐지하기 위한 새로운 악성코드 탐지 기술에 관한 연구가 절실히 필요하다. 본 연구는 기존의 정적 분석과 동적 분석 방법의 한계를 극복하기 위한 방법을 제안한다. 신속한 데이터 수집을 위하여 정적 분석을 이용하여 사용자 정의 함수의 어셈블리어 데이터를 수집하고 BERT 로 임베딩하고 LSTM 으로 악성코드를 분류하는 모델을 제안한다. 분류 데이터는 행위가 정확한 랜섬웨어를 사용하였고 총 세 종류의 랜섬웨어를 분류하였고 다중 분류의 결과로 85.5%의 분류 정확도를 달성하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.108-111
• /
• 2022

Applying deep learning to machine vision systems for defect detection of products requires vast amounts of training data about various defect cases. However, since data imbalance occurs according to the type of defect in the actual manufacturing industry, it takes a lot of time to collect product images enough to generalize defect cases. In this paper, we apply a Siamese neural network that can be learned with even a small amount of data to product defect detection, and modify the image pairing method and contrastive loss function by properties the situation of product defect image data. We indirectly evaluated the embedding performance of Siamese neural networks using AUC-ROC, and it showed good performance when the images only paired among same products, not paired among defective products, and learned with exponential contrastive loss.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.1
• /
• pp.17-24
• /
• 2020

In this paper, we present a movie rating prediction architecture based on a convolutional neural network (CNN). Our prediction architecture extends TextCNN, a popular CNN-based architecture for sentence classification, in three aspects. First, character embeddings are utilized to cover many variants of words since reviews are short and not well-written linguistically. Second, the attention mechanism (i.e., squeeze-and-excitation) is adopted to focus on important features. Third, a scoring function is proposed to convert the output of an activation function to a review score in a certain range (1-10). We evaluated our prediction architecture on a movie review dataset and achieved a low MSE (e.g., 3.3841) compared with an existing method. It showed the superiority of our movie rating prediction architecture.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.1
• /
• pp.189-194
• /
• 2017

The reversibility of a quantum logic circuit can be realized when two reversible conditions of information reversible and energy reversible circuits are satisfied. In this paper, we have modeled the computation cycle required to recover the information reversibility from the multivalued quantum logic to the original state. For modeling, we used a function embedding method that uses a unitary switch as an arithmetic exponentiation switch. In the quantum logic circuit, if the adjoint gate pair is symmetric, the unitary switch function shows the balance function characteristic, and it takes 1 cycle operation to recover the original information reversibility. Conversely, if it is an asymmetric structure, it takes two cycle operations by the constant function. In this paper, we show that the problem of 2-cycle restoration according to the asymmetric structure when the hybrid MCT gate is realized with the ternary M-S gate can be solved by equivalent conversion of the asymmetric gate to the gate of the symmetric structure.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.05a
• /
• pp.652-655
• /
• 2002

The embedded atom method based on the density functional theory is used for calculating ground state properties of realistic metal systems. In this paper, we had corrected constitutive formulae and parameters on the palladium for the purpose of doing Embedded Atom Method analysis. And then we have computed the properties of the palladium on the fundamental scale of the atomic structure. In result, simulated ground state properties, such as the lattice constant, elastics constants and the sublimation energy, show good agreement with Daw's simulation data and with experimental data.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2000.11a
• /
• pp.267-275
• /
• 2000

최근 전자상거래가 활성화되면서, 거래 인증서와 같은 온라인 증명서가 광범위하게 사용되고 있다. 그리고 증명서의 위/변조기술이 발전함에 따라서 온라인 거래에 사용되는 증명서의 인증과 위조/변조를 방지하는 기술이 필요하게 되었다. 본 연구는 증명서의 인증에 필요한 기술로서, 메시지 인증함수가 가지는 성질을 포함하고 있다. 본 연구에서 개발한 알고리즘은 증명서에 포함된 텍스트문서가 위조/변조되었을 경우 그 변동 상황을 알아내며, 부정적으로 위조/변조된 부분을 검출하며, 변동상황 검출과 함께 원 증명서의 문서를 복원할 수 있는 기술이다. 만일 이 증명서에 대하여 변동이 진행된 흔적이 발견될 경우, 증명서를 인증하지 않으며, 삽입한 텍스트 데이터를 추출하고 변동을 확인하는 것과 함께 필요한 정보를 복원한다. 본 논문의 시험결과에 근거하면 256$\times$256BMP file Format 이미지에 3만2천자 정도의 텍스트문서를 삽입할 수 있었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.106-108
• /
• 2022

이미지 기반 3D 형상 복원에 있어서, 이미지에 보이지 않는 폐색(Occlusion) 영역 부분에 대한 정보가 손실되므로 완전한 복원에 어려움이 있으며, 세밀한 텍스쳐(Texture) 표현이 이루어지지 않고 심한 평활화(Smoothing)나 고립된 노이즈 메쉬(Isolated Noise Mesh) 등 구조적 훼손이 발생한다. 주로 깊은 신경망을 이용하여, 음함수(Implicit Function) 기반 방법은 사전훈련이 완료된 보조 신경망들을 전면부에 배치하거나, Hourglass 등 임베딩(Embedding) 아키텍처를 추가하거나, 또는 표면 법선(Surface Normal)과 같은 환시(Hallucination)를 생성하여 신경망에 입력하기도 한다. 이 논문에서는, 인물의 이미지를 입력받아 색상, 머리카락 및 의상을 포함하는 완전 3D 인간 복원 기술들을 조망해본다.