• Proceedings of the IEEK Conference
• /
• 2004.06b
• /
• pp.407-410
• /
• 2004

This paper describes an embedded system to put a SoC actuator IP in motion and linux drivers. The If that a embedded linux among embedded OS is ported is implemented as linux driver. The actuator IP is controlled by application programming. To make users use this easily, a QT is ported on the system. Application program can operate the actuator IP device driver on TFT LCD.

• Proceedings of the Materials Research Society of Korea Conference
• /
• 2005.05a
• /
• pp.110-110
• /
• 2005

• IEMEK Journal of Embedded Systems and Applications
• /
• v.7 no.3
• /
• pp.151-156
• /
• 2012

When mounting the sensor device in the way of Plug&Play, sensor device drivers need to be loaded and linked dynamically. Since a sensor node platform is based on small 8 bit MCU, dynamic loading and linking technique used in Windows and Linux can not be applied. In this paper, we present how to link and load dynamically sensor device drivers for sensor device Plug&Play. We implement a prototype and evaluate it to make sure that there is no performance degradation like sensor device driver connection speed and memory usage. Connection speed overhead increases to 0.2ms. Memory usage overhead increases to hundreds byte. It shows that there is no heavy influence in running the actual program.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.436-438
• /
• 2007

As the sensors and communication technology get advance, the remote health diagnosis for patients and senior persons at home are possible now without visiting doctors in hospitals. A low-power ubiquitous health check device was developed adapting Real-Time Embedded Linux is developed. This ubiquitous device is consisted of three sensors. The wrist type health checking terminal acquires periodically the health data by using a blood pressure sensor, a pulse sensor and a body temperature sensor. It transmits the health data to the access point located at the home center through the ZigBee wireless communication modem. This health data collector or access point device sends the data again to the main server operated in a hospital or health care organization. The health server control continuously the input data and sends an alarm signal to the assigned. doctor and responsible persons using cellular SMS when any dangerous events occur. This wrist type health check device has an embedded linux OS using Intel PAX255 MPU. The developed U-Health system is applicable for checking patients health in remote at home. And their family or related persons in remote site can check the patients health status at any time. They can be assured by receiving SMS record and alarm of emergency case which is transmitted from the health server.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.3
• /
• pp.362-367
• /
• 2010

In this paper, we describe implementation of FPGA-based Nios II embedded processor system and linux device driver for image monitoring system which is supplement weakness for fixed surveillance area of existing CCTV system and by manual operation of the camera's moving. Altera Nios II processor 8.0 is supported MMU which is stable and efficient managed memory. We designed the image monitoring and control system by using Altera Nios II soft-core processor system which is flexible in various application and excellent adaptability. By implementation of camera device driver and VGA decvice driver for Linux-based Nios II system, we implemented image serveillance system for Nios II embedded processor system.

• Journal of Welding and Joining
• /
• v.31 no.3
• /
• pp.84-88
• /
• 2013

These days embedded technology may be the most significant development in the electronics industry. The study focused on the development of active device embedding using flexible printed circuit in view of process and materials. The authors fabricated 30um thickness Si chip without any crack, chipping defects with a dicing before grinding process. In order to embed chips into flexible PCB, the chip pads on a chip are connected to bonding pad on flexible PCB using an ACF film. After packaging, all sample were tested by the O/S test and carried out the reliability test. All samples passed environmental reliability test. In the future, this technology will be applied to the wearable electronics and flexible display in the variety of electronics product.

• The KIPS Transactions:PartA
• /
• v.9A no.4
• /
• pp.451-458
• /
• 2002

In this article, we present, design, and implement a software and hardware for an embedded RAID system. The merits and drawbacks of our system are presented by performance evaluation. The proposed hardware system consists of three fibre channel controllers for the interface with fibre channel disks and hosts. Embedded Linux in which a RAID software is implemented is ported to the hardware. A SCSI target mode device driver and a target mode SCSI module are designed for that our RAID system is considered as a block device to a host computer. Linux Multi-device is used as RAID functions of this system. A data cache module is implemented for high performance and the interconnection between Linux Multi-device and the target mode SCSI module. The RAID 5 module of Multi-device is modified for improvement of read performance. The benchmark shows that the new RAID 5 module is superior to the original one in overall performance.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.33-35
• /
• 2004

In this paper, web based monitoring systems are implemented for multi-axis force control systems of an intelligent robot. Linux operating systems are ported to an embedded system which Include a Xscale processor to implement a web based monitoring system. A device driver is developed to receive data from multi-axis force sensors of intelligent robots. To control this device driver, a socket program for Labview is also developed.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.5
• /
• pp.205-214
• /
• 2020

With the recent development of hardware and software technology, interest in the development of wearable devices is increasing. In particular, wearable devices require algorithms suitable for low-power and low-capacity embedded devices. Among them, there is an increasing demand for a signal compression algorithm that reduces communication overhead, in order to increase the efficiency of storage and transmission of electrocardiogram (ECG) signals requiring long-time measurement. Because normal beats occupy most of the signal with similar shapes, a high rate of signal compression is possible if normal beats are represented by a template. In this paper, we propose an algorithm for determining the normal beat template using the template cluster and Pearson similarity. Also, the template is expressed effectively as a few vertices through linear approximation algorithm. In experiment of Datum 234 of MIT-BIH arrhythmia database (MIT-BIH ADB) provided by Physionet, a compression ratio was 33.44:1, and an average distribution of root mean square error (RMSE) was 1.55%.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.89-100
• /
• 2023

Recently, on-device artificial intelligence (AI) solutions using mobile devices and embedded edge devices have emerged in various fields, such as computer vision, to address network traffic burdens, low-energy operations, and security problems. Although vision transformer deep learning models have outperformed conventional convolutional neural network (CNN) models in computer vision, they require more computations and parameters than CNN models. Thus, they are not directly applicable to embedded edge devices with limited hardware resources. Many researchers have proposed various model compression methods or lightweight architectures for vision transformers; however, there are only a few studies evaluating the effects of model compression techniques of vision transformers on performance. Regarding this problem, this paper presents a performance evaluation of vision transformers on embedded platforms. We investigated the behaviors of three vision transformers: DeiT, LeViT, and MobileViT. Each model performance was evaluated by accuracy and inference time on edge devices using the ImageNet dataset. We assessed the effects of the quantization method applied to the models on latency enhancement and accuracy degradation by profiling the proportion of response time occupied by major operations. In addition, we evaluated the performance of each model on GPU and EdgeTPU-based edge devices. In our experimental results, LeViT showed the best performance in CPU-based edge devices, and DeiT-small showed the highest performance improvement in GPU-based edge devices. In addition, only MobileViT models showed performance improvement on EdgeTPU. Summarizing the analysis results through profiling, the degree of performance improvement of each vision transformer model was highly dependent on the proportion of parts that could be optimized in the target edge device. In summary, to apply vision transformers to on-device AI solutions, either proper operation composition and optimizations specific to target edge devices must be considered.