• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.39 no.3
• /
• pp.283-289
• /
• 2015

In this study, the lightweight design of a brake bracket for a composite bogie was studied by considering two brake bracket models with thicknesses of 12t and 9t, respectively. For achieving this goal, finite element analysis and topology optimization were conducted. Firstly, the largest cross-sectional areas of the vertical and horizontal plates of the brake bracket were selected as the design variables. As the constraint, the Z-axis displacement of the brake bracket was increased by 2.5 units from the initial displacement value. The minimum volume fraction of the design regions was chosen as the objective function. The full model comprised a composite bogie frame and brackets attached together. However, to reduce the analysis time, 1D beam elements were used instead of the composite bogie frame by ensuring its equivalence with the full model. The result revealed that the weights of the 12t and 9t models of the brake bracket were reduced to 60 kg and 31 kg, respectively.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.04a
• /
• pp.230-233
• /
• 2010

최근 분산된 노드들 간의 자료를 송수신하는 임베디드 어플리케이션들이 증가함에 따라 이를 지원하기 위한 분산 미들웨어도 함께 발전하고 있다. 분산미들웨어는 원격 객체 관리를 위한 클라이언트-서버 모델, 큐를 이용한 메시지 전송을 목적으로 하는 메시지 패싱 모델, 분산 컴퓨팅 환경에서 자료의 전송을 목적으로 하는 출판-구독 모델이라는 3가지 모델로 분류 된다. 본 논문에서는 3가지 분산 미들웨어 모델들에 대하여 살펴보고 출판-구독 모델의 대표적 분산미들웨어인 Data Distribution Service를 소개한다. 또한 출판-구독 모델이 단말 간 P2P를 지원함에 따라 생기는 문제점인 과다한 트래픽을 해결하기 위해 자료들을 그룹화 시켜 전송하거나 특정 토픽에 관련된 자료들을 미리 예약된 채널을 통해 전송하는 기법들을 제안하고 일반 DDS와 비교를 통해 그 효과를 예측해본다.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.59-68
• /
• 2021

As artificial intelligence(AI) technologies, which have made rapid growth recently, began to be applied to the marine environment such as ships, there have been active researches on the application of CNN-based models specialized for digital videos. In E-Navigation service, which is combined with various technologies to detect floating objects of clash risk to reduce human errors and prevent fires inside ships, real-time processing is of huge importance. More functions added, however, mean a need for high-performance processes, which raises prices and poses a cost burden on shipowners. This study thus set out to propose a method capable of processing information at a high rate while maintaining the accuracy by applying Quantization techniques of a deep learning model. First, videos were pre-processed fit for the detection of floating matters in the sea to ensure the efficient transmission of video data to the deep learning entry. Secondly, the quantization technique, one of lightweight techniques for a deep learning model, was applied to reduce the usage rate of memory and increase the processing speed. Finally, the proposed deep learning model to which video pre-processing and quantization were applied was applied to various embedded boards to measure its accuracy and processing speed and test its performance. The proposed method was able to reduce the usage of memory capacity four times and improve the processing speed about four to five times while maintaining the old accuracy of recognition.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.531-536
• /
• 2023

This paper proposes a sliding window method with frame feature insertion for immediate attack detection on in-vehicle networks. This method guarantees real-time attack detection by labeling based on the attack status of the current frame. Experiments show that the proposed method improves detection performance by giving more weight to the current frame in CNN computation. The proposed model was designed based on a lightweight LeNet-5 architecture and it achieves 100% detection for DoS attacks. Additionally, by comparing the complexity with conventional models, the proposed model has been proven to be more suitable for resource-constrained devices like ECUs.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.10
• /
• pp.29-41
• /
• 2022

Recently, with the development of deep learning technology, a variety of huge models with excellent performance have been devised by pre-training massive amounts of text data. However, in order for such a model to be applied to real-life services, the inference speed must be fast and the amount of computation must be low, so the technology for model compression is attracting attention. Knowledge distillation, a representative model compression, is attracting attention as it can be used in a variety of ways as a method of transferring the knowledge already learned by the teacher model to a relatively small-sized student model. However, knowledge distillation has a limitation in that it is difficult to solve problems with low similarity to previously learned data because only knowledge necessary for solving a given problem is learned in a teacher model and knowledge distillation to a student model is performed from the same point of view. Therefore, we propose a heterogeneous knowledge distillation method in which the teacher model learns a higher-level concept rather than the knowledge required for the task that the student model needs to solve, and the teacher model distills this knowledge to the student model. In addition, through classification experiments on about 18,000 documents, we confirmed that the heterogeneous knowledge distillation method showed superior performance in all aspects of learning efficiency and accuracy compared to the traditional knowledge distillation.

• Bulletin of the Society of Naval Architects of Korea
• /
• v.31 no.3
• /
• pp.25-27
• /
• 1994

선박의 고속화, 경량화, 전문화 및 대형화의 촉진과 더불어 신형식 선박의 출현으로 기존의 해 석방법과 같은 개념으로는 새로운 문제점에 대한 해결이 불가능하다. 따라서 이와 같은 새로운 외력환경에 대한 신형식 선박에 구애받지 않고 범용으로 이용이 가능할 수 있게 하기 위해서는 하중의 공간적 분포와 시간적 변화에 대한 정보를 정도 높게 추정할 수 있는 방법이 바람직하 다고 본다. 이를 해결할 수 있는 유일한 방법은 우리가 지금까지 소흘하여 왔던 반복적 실험이 뒷받침되어, 수치이론의 모델화 과정에서나 물리현상 설정과정에서 내재하게 되는random한 불확실성을 정량적으로 파악해 두어야 신형식 선박 개발에 신뢰할 수 있는 동적 응답해석이 가 능해질 것이다.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.3 s.35
• /
• pp.237-247
• /
• 2005

Ubiquitous Sensor Network(USN) is the very core of a technology for the Ubiquitous environments. There is the weakness from various security attacks such that tapping of sensor informations, flowing of abnormal packets, data modification and Denial of Service(DoS) etc. And it's required counterplan with them. Especially it's restricted by the capacity of battery and computing. By reasons of theses. positively, USN security technology needs the lightweighted design for the low electric energy and the minimum computing. In this paper, we propose lightweight USN mutual authentication methology based on trust model to solve above problems. The proposed authentication model can minimize the measure of computing because it authenticates the sensor nodes based on trust information represented by subjective logic model. So it can economize battery consumption and resultingly increse the lifetime of sensor nodes.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.604-606
• /
• 2024

컴퓨터 비전 응용은 우리 생활에서 중요한 역할을 한다. 현재, 대규모 모델의 등장으로 딥 러닝의 훈련 및 운행 비용이 급격히 상승하고 있다. 자원이 제한된 환경에서는 일부 AI 프로그램을 실행할 수 없게 되므로, 경량화 연구가 필요하다. YOLOv8 은 현재 주요 목표 검출 모델 중 하나이며, 본 논문은 다중 스케일 Ghost 컨볼루션 모듈을 사용하여 구축된 새로운 YOLOv8-pose-msg 키포인트 검출 모델을 제안한다. 다양한 사양에서 새 모델의 매개변수 양은 최소 34% 감소할 수 있으며, 최대 59%까지 감소할 수 있다. 종합적인 검출 성능은 비교적 대규모 데이터셋에서 원래의 수준을 유지할 수 있으며, 소규모 데이터셋에서의 키포인트 검출은 30% 이상 증가할 수 있다. 동시에 최대 25%의 훈련 및 추론 시간을 절약할 수 있다.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.31 no.6
• /
• pp.353-358
• /
• 2018

In this study, it is describe to an optimization analysis process for the weight reduction of the voltage converter in the electric vehicle charging systems. The optimization design is a technique that finds the optimal material distribution under a given material quantity constraint by combining the design sensitivity with the material properties and the mathematical optimization. Among the topology optimization, a lightweight design is performed by a solid isotropic material with penalization with simple formula and well-convergence. The lightweight design consists of three steps. As a first step, a finite element model for the basic design of the on-board voltage converter was constructed and static analysis was performed on the load. In the second step, the optimum shape is obtained for the lightweight by performing the topology optimization using the solid isotropic material with penalization applying the stiffness coefficient of the isotropic material to the static analysis result. As a final step, impact analysis was performed by applying a half-sinusoidal pulse shape impact load which satisfies the impact test standard of the vehicle-mounted part with respect to the optimum shape. In the topology optimization, the design domain was defined as the mounting bracket area, and the design technology was finally achieved by optimizing the mounting bracket to achieve a weight reduction of 20% over the basic design.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.129-132
• /
• 2020

최근 모바일 기기에서 딥러닝 모델을 사용하기 위한 경량화 연구가 진행되고 있다. 그중 모델의 가중치 표현 bit를 줄이는 양자화와 사용하기 위한 다양한 압축 알고리즘이 개발되었다. 하지만 대부분의 양자화 및 압축 알고리즘들은 한 번 이상의 Fine-tuning을 거쳐야 하는데 이 과정은 모바일 환경에서 수행하기에는 연산복잡도가 너무 높다. 따라서 본 논문은 양자화된 가중치를 High Efficiency Video Coding(HEVC)을 통해 압축하는 방법을 제안하고 정확도와 압축률을 실험한다. 실험결과는 양자화만 실시한 경우 대비 크기는 25%의 감소했지만, 정확도는 0.7% 감소했다. 따라서 이런 결과는 모바일 기기에 가중치를 전송하는 과정에 적용될 수 있다.