• 한국멀티미디어학회논문지
• /
• 제24권7호
• /
• pp.860-867
• /
• 2021

Lane detection is important technology for implementing ADAS or autonomous driving. Although edge detection has been typically used for the lane detection however, false detections occur frequently. To improve this problem, a deep learning based lane detection algorithm is proposed in this paper. This algorithm is mounted on an ARM-based embedded system to implement a LDW(lane departure warning). Since the embedded environment lacks computing power, the VGG-11, a lightweight model based on VGG-13, has been proposed. In order to evaluate the performance of the LDW, the test was conducted according to the test scenario of NHTSA.

• 한국정보전자통신기술학회논문지
• /
• 제14권4호
• /
• pp.314-322
• /
• 2021

Skeleton-based action recognition has attracted considerable attention in human action recognition. Recent methods for skeleton-based action recognition employ spatiotemporal graph convolutional networks (GCNs) and have remarkable performance. However, most of them have heavy computational complexity for robust action recognition. To solve this problem, we propose a shuffle graph convolutional network (SGCN) which is a lightweight graph convolutional network using pointwise group convolution rather than pointwise convolution to reduce computational cost. Our SGCN is composed of spatial and temporal GCN. The spatial shuffle GCN contains pointwise group convolution and part shuffle module which enhances local and global information between correlated joints. In addition, the temporal shuffle GCN contains depthwise convolution to maintain a large receptive field. Our model achieves comparable performance with lowest computational cost and exceeds the performance of baseline at 0.3% and 1.2% on NTU RGB+D and NTU RGB+D 120 datasets, respectively.

• Computers and Concrete
• /
• 제12권3호
• /
• pp.319-335
• /
• 2013

In this paper, the properties of the cement mortar modified with styrene acrylic ester copolymer were investigated. Expanded vermiculite as lightweight aggregate was used for making the polymer modified mortar test specimens. To study the effect of polymer-cement ratio and vermiculite-cement ratio on various properties, specimens were prepared by varying the polymer-cement and vermiculite-cement ratios. Tests of physical properties such as density, water absorption, thermal conductivity, three-point flexure and compressive tests were made on the specimens. Furthermore, a coupled thermal-structural finite element model of an entire corner wall was modelled in order to study the best material configuration. The wall is composed by a total of 132 bricks of $120{\times}242{\times}54$ size, joined by means of a contact-bonded model. The use of advanced numerical methods allows us to obtain the optimum material properties. Finally, comparisons of polymer-cement and vermiculite-cement ratios on physical properties are given and the most important conclusions are exposed.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2007년도 추계학술대회논문집
• /
• pp.1284-1287
• /
• 2007

Recently, the need for slim type optical disk drive(ODD) has increased with popularization of lightweight notebook. Because of its lightweight and small structure, slim type ODD has low structural stiffness and it is weak to high-speed disk vibration. In this paper, Finite Element(FE) Model of slim type ODD is constructed and verified by experimental modal analysis. Additionally, sensitivity analysis is performed about structural parameters. As a result of sensitivity analysis, improved characteristic is verified by experiments using a sample of new model.

• Steel and Composite Structures
• /
• 제45권6호
• /
• pp.895-905
• /
• 2022

Composite flooring systems consisting of cold-formed steel joists and reinforced concrete slabs offer an efficient, lightweight solution. However, utilisation of composite action to achieve enhanced strength and economical design has been limited. In this study, finite element modelling was utilised to create a three-dimensional model which was then validated against experimental results for a composite flooring system consisting of cold-formed steel joists, reinforced concrete slab and steel bolt shear connectors. This validated numerical model was then utilised to perform parametric studies on the performance of the structural system. The results from the parametric study demonstrate that increased thickness of the concrete slab and increased thickness of the cold formed steel beam resulted in higher moment capacity and stiffness of the composite flooring system. In addition, reducing the spacing of bolts and spacing of the cold formed steel beams both resulted in enhanced load capacity of the composite system. Increasing the concrete grade was also found to increase the moment capacity of the composite flooring system. Overall, the results show that an efficient, lightweight composite flooring system can be achieved and optimised by selecting suitable concrete slab thickness, cold formed beam thickness, bolt spacing, cold formed beam spacing and concrete grade.

• 전기전자학회논문지
• /
• 제27권4호
• /
• pp.531-536
• /
• 2023

본 논문에서는 차량 내 네트워크에서 즉각적인 공격 탐지를 위해 프레임 피처 삽입이 적용된 슬라이딩 윈도우 기법을 제안한다. 이 방법은 현재 프레임의 공격 여부에 따라 라벨링을 진행하기 때문에 공격 탐지의 실시간성을 보장할 수 있다. 또한 이 방법이 CNN 연산에서 현재 프레임에 대한 가중치를 주어 성능을 향상시킬 수 있음을 실험을 통해 확인하였다. 제안하는 모델은 경량화된 LeNet-5 구조 기반으로 설계되었으며 DoS 공격 탐지 성능에서 100%를 달성하였다. 또한 기존 연구의 모델들과 복잡성을 비교했을 때 제안하는 모델이 ECU와 같이 리소스가 제한된 장치에 더 적합함을 확인하였다.

• Computers and Concrete
• /
• 제33권3호
• /
• pp.309-324
• /
• 2024

Internal curing, a widely used method for mitigating early-age shrinkage in concrete, also offers notable advantages for concrete durability. This paper explores the potential of internal curing by partial replacement of sand with fine lightweight aggregate for enhancing the behavior of high-performance concrete at elevated temperatures. Such a technique may prove economical and safe for the construction of skyscrapers, where explosive spalling of high-performance concrete in fire is a potential hazard. To reach this aim, the physico-mechanical features of internally cured high-strength concrete specimens, including mass loss, compressive strength, strain at peak stress, modulus of elasticity, stress-strain curve, toughness, and flexural strength, were investigated under different temperature exposures; and to predict some of these mechanical properties, a number of equations were proposed. Based on the experimental results, an advanced stress-strain model was proposed for internally cured high-performance concrete at different temperature levels, the results of which agreed well with the test data. It was observed that the replacement of 10% of sand with pre-wetted fine lightweight expanded clay aggregate (LECA) not only did not reduce the compressive strength at ambient temperature, but also prevented explosive spalling and could retain 20% of its ambient compressive strength after heating up to 800℃. It was then concluded that internal curing is an excellent method to enhance the performance of high-strength concrete at elevated temperatures.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 1997년도 봄 학술발표회 논문집
• /
• pp.383-391
• /
• 1997

The prediction of effective properties of heterogeneous material like concrete is of primary importance in design or analysis. This paper os about micromechanice-based evaluation of elastic moduli of concretes considering composite material behavior. In this study, micromechanixe-based schemes for the effective elastic modui of the lightweight foamed concrete and the normal concrete are proposed based on averaging techniques using a single-layered inclusion model and a multi-phase and multi-layered inclusion model. respectively, For the verification's sake, elastic moduli evaluated in this study are compared with experimental data and results by existing formula.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2009년도 춘계학술발표대회
• /
• pp.1264-1266
• /
• 2009

We introduce a location-based routing model applied for grid backbone nodes in wireless mesh network. The number of paths with nearest distance between two nodes is calculated and used as key parameter to execute routing algorithm. Node will increase the transmission range that makes a trade off with data rate to reach its neighbors when node itself is isolated. The routing model is lightweight and oriented thanks to the simple but efficient routing algorithm.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 춘계학술발표대회
• /
• pp.483-486
• /
• 2020

Age estimation and gender classification for human is a classic problem in computer vision. Almost research focus just only one task and the models are too heavy to run on low-cost system. In our research, we aim to apply multitasking learning to perform both task on a lightweight model which can achieve good precision on embedded system in the real time.