• ETRI Journal
• /
• v.33 no.2
• /
• pp.230-239
• /
• 2011

Dynamic memory allocators for real-time embedded systems need to fulfill three fundamental requirements: bounded worst-case execution time, fast average execution time, and minimal fragmentation. Since embedded systems generally run continuously during their whole lifetime, fragmentation is one of the most important factors in designing the memory allocator. This paper focuses on minimizing fragmentation while other requirements are still satisfied. To minimize fragmentation, a part of a memory region is segregated by the proposed budgeting method that exploits the memory profile of the given application. The budgeting method can be applied for any existing memory allocators. Experimental results show that the memory efficiency of allocators can be improved by up to 18.85% by using the budgeting method. Its worst-case execution time is analyzed to be bounded.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.3 no.1
• /
• pp.25-29
• /
• 2008

In this paper, we provide an adaptive power-aware checkpointing scheme for fixed priority-based DVS scheduling in dependable real-time systems. In the provided scheme, we analyze the minimum number of tolerable faults of a task and the optimal checkpointing interval in order to meet the deadline and guarantee its specified reliability. The energy-efficient voltage level at a fault arrival is also analyzed and used in the recovery of the faulty task.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.2
• /
• pp.100-104
• /
• 2020

Over the past several years, deep learning has been widely used for feature extraction in image and video for various applications such as object classification and facial recognition. This paper introduces an implantation of embedded Linux system for embossed digits recognition using CNN based deep learning methods. For this purpose, we implemented a coin recognition system based on deep learning with the Keras open source library on Raspberry PI. The performance evaluation has been made with the success rate of coin classification using the images captured with ultra-wide angle camera on Raspberry PI. The simulation result shows 98% of the success rate on average.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.725-728
• /
• 2006

본 논문에서는 Embedded 시스템에서 Windows CE 내에 사용되고 있는 불필요한 메모리를 최소화하고 메모리를 좀 더 효율적으로 관리하기 위한 방안으로 가비지컬렉터를 이용한 메모리관리 방법에 대한 연구이다. Embedded 시스템의 힙 메모리 내에 수집할 수 있는 방법 중 전체수집과, 부분수집에 대하여 살펴본다. 가비지컬렉터가 응용 프로그램에서 더 이상 사용하지 않는 힙 내에 개체가 있는지 확인하고, 힙에 대해 사용할 수 있는 메모리가 더 이상 없을 경우 새 연산자가 Out Of Memory Exception를 실행하게 된다. 실험부분에서 가비지컬렉터의 개체사용 여부를 실험한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06b
• /
• pp.129-133
• /
• 2007

임베디드SW에 대한 개발이 활발히 수행되고 다양한 플랫폼에서 다른 임베디드SW와 통합되고 제어하는 다양한 요구사항이 발생하고 있으나 HW와의 밀접한 관계 및 재사용성의 요구를 반영하고 있지 못하므로 제품계열 개념을 적용한 접근이 필요하다. 따라서 임베디드 시스템 수명주기 및 시스템, HW, SW간의 관계를 통해 임베디드SW 개발절차를 도출하며, 제품계열 개발방법론 중에서 마르미-EM, FORM, FAST 및 KobrA를 선정하고 도출된 임베디드SW 개발절차와 비교하여 각 개발방법론의 절차상의 차이점, 강점 및 보완 사항을 분석하고 방법론별 특징을 종합한다.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.3
• /
• pp.79-86
• /
• 2006

In this paper, we implement the ad ballon control system in which a built camera monitors using bluetooth wireless communication with ISM(Industrial. Scientific and Medical) band. In the proposed system. the driving time of ad ballon is increased by adopting the mercury battery and light weight. An ad ballon with camera is easily controlled by Graphic User Interface using Linux based embedded system.

• Journal of Broadcast Engineering
• /
• v.24 no.2
• /
• pp.357-360
• /
• 2019

We propose an efficient single convolutional neural network (CNN) for pedestrian detection on embedded GPUs. We first determine the optimal number of the convolutional layers and hyper-parameters for a lightweight CNN. Then, we employ a multi-scale approach to make the network robust to the sizes of the pedestrians in images. Experimental results demonstrate that the proposed algorithm is capable of real-time operation, while providing higher detection performance than conventional algorithms.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.1237-1239
• /
• 2007

This paper proposes a virtual storage system for smart home/office embedded devices by utilizing AoE and HyperSCSI protocols. It relies on current Ethernet infrastructures and aims to provide a low-cost solution for the storage limitation problem on embedded devices. We choose AoE (ATA over Ethernet) and HyperSCSI in our implementation because they are relatively lightweight compared to other network storage protocols such as NFS(Network File System), CIFS(Common Internet File System) and iSCSI(internet Small Computer System Interface). The design and architecture of our proposed virtual system as well as the prototype demonstration are presented in this paper.

• KSCI Review
• /
• v.12 no.1
• /
• pp.102-112
• /
• 2004

• Journal of Korea Multimedia Society
• /
• v.8 no.5
• /
• pp.721-728
• /
• 2005

A virtual machine is a conceptual computer with a logical system configuration, made of software unlike physical systems made of hardware. Virtual machine technology for embedded systems is a requisite software technology for download solutions such as mobile devices, digital TVs, etc. At present, a research of virtual machines for embedded systems named EVM(Embedded Virtual Machine) is in progress. As a part of the research, we define the EFF(Executable File Format) as a file format for embedded systems. We also prove completeness of EFF by structurally mapping class file widely used to EFF.