• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.676-678
• /
• 2021

본 논문은 해상 및 산업용 IoT 서비스를 위한 에지 기기의 설계에 대해 설명한다. 에지 기기는 IoT 센싱 데이터를 수집하여 외부 망을 전달하는 역할만을 수행하도록 설계되었고, 통신 방식은 사용 LoRa와 LTE Cat.M1을 적용하였다.

• 대한기계학회논문집A
• /
• 제20권4호
• /
• pp.1202-1215
• /
• 1996

In this study, in order to achieve the uniformity of mechanical properties and microstructures of a hot-rolled coil in the transversal direction, the edge mask device is newly device is newly developed and installed at the upper laminar-flow cooling head in the run out table, which controls the transversal temperature of strip with enco panel and bar edge heater. The device that is transversally movable prevents the temperature drop of strip edge by blocking the cooling water into the strip edge. So, the pattern of edge mask set-up condition of the device was derived by analyzing the characteristics of strip temperature and mechanical properties according to the on-line application of edge mask.

• 대한임베디드공학회논문지
• /
• 제19권5호
• /
• pp.211-218
• /
• 2024

As computing technology advances, many services, including AI, that previously operated in the cloud will become usable on devices that users carry. The emergence of ultra-high-speed mobile networks like 5G dramatically increases the utility of numerous devices in the real world. In the future, with technologies like deviceless computing, the range of applications will diversify even further, and demand will continue to grow. Consequently, the importance of technology for monitoring vast amounts of device information and deploying AI services tailored to the functions and performance of each device is becoming increasingly evident. Therefore, this paper proposes a large-scale edge device monitoring technique necessary to leverage simple sensors and low-spec, low-resource devices in conjunction with Multi-access Edge Computing (MEC) to provide various AI functionalities.

• Journal of the Korean Physical Society
• /
• 제73권10호
• /
• pp.1473-1478
• /
• 2018

In this study, we have developed a simple and cost-effective method to prevent edge bead formation by covering the edge of a chip-level substrate with heat-resistant tape during patterning using SU-8. Edge beads are a fundamental problem in photoresists and are particularly notable in high-viscosity fluids and thick coatings. Edge beads can give rise to an air gap between the substrate and the patterning mask during UV exposure, which results in non-uniform patterns. Furthermore, the sample may break since the edge bead is in contact with the mask. In particular, the SU-8 coating thickness of the chip-level substrates used in MEMS or BioMEMS may not be properly controlled because of the presence of edge beads. The proposed method to solve the edge bead problem can be easily and economically utilized without the need for a special device or chemicals. This method is simple and prevents edge bead formation on the sample substrate. Despite the small loss in the taping area, the uniformity of the SU-8 coating is improved from 50.9% to 5.6%.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2019년도 춘계학술대회
• /
• pp.418-420
• /
• 2019

다양하게 요구되고 있는 해양 사물 인터넷 서비스 제공을 위하여 필요한 복합 센서 장치와 edge device를 제안하였다. 특히 통신 3사의 상용망 외에 폐쇄망을 통해 센싱 정보의 관리와 처리가 가능하도록 설계 제안하였다.

• Design & Manufacturing
• /
• 제14권4호
• /
• pp.25-39
• /
• 2020

In this study, an edge device that monitors the injection molding process by measuring the mold vibration(acceleration) signal and the mold surface temperature was developed and evaluated its performance. During injection molding, signals of the injection start, V/P switchover, and packing end sections were obtained through the measurement of the mold vibration and the injection time and packing time were calculated by using the difference between the times of the sections. Then, the mold closed and mold open signals were obtained using a magnetic hall sensor, and cycle time was calculated by using the time difference between the mold closed time each process. As a result of evaluating the performance by comparing the process data monitored by the edge device with the shot data recorded on the injection molding machine, the cycle time, injection time, and packing time showed very small error of 0.70±0.38%, 1.40±1.17%, and 0.69±0.82%, respectively, and the values close to the actual were monitored and the accuracy and reliability of the edge device were confirmed. In addition, it was confirmed that the mold surface temperature measured by the edge device was similar to the actual mold surface temperature.

• 대한임베디드공학회논문지
• /
• 제18권3호
• /
• 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.

• 한국정보통신학회논문지
• /
• 제24권12호
• /
• pp.1688-1696
• /
• 2020

기존 클라우드 기반 Internet-of-Things(IoT) 시스템의 네트워크 정체와 서버 과부하로 인한 지연, 데이터 이동으로 인한 보안 및 프라이버시 이슈를 해결하기 위하여 엣지 기반의 IoT 시스템으로 IoT의 패러다임이 움직이고 있다. 하지만 엣지 기반의 IoT 시스템은 여러 제약으로 인하여 처리 성능과 동작의 유연성이 부족한 치명적인 문제점을 가지고 있다. 처리 성능을 개선하기 위하여 응용 특화 하드웨어를 엣지 디바이스에 구현할 수 있지만, 고정된 기능으로 인하여 특정 응용 이외에는 성능 향상을 보여줄 수 없다. 본 논문은 엣지 디바이스의 제한된 하드웨어 자원에서 다양한 응용 특화 하드웨어를 주문형 부분 재구성을 통해 사용할 수 있고, 이를 통해 엣지 디바이스의 처리 성능과 동작의 유연성을 증가시킬 수 있는 엣지 중심의 Metamorphic IoT(mIoT) 플랫폼을 소개한다. 실험 결과에 따르면, 재구성 알고리즘을 엣지에서 실행하는 엣지 중심의 mIoT 플랫폼은 재구성 알고리즘을 서버에서 실행하는 이전 연구에 비해 엣지의 서버 접근 횟수를 최대 82.2% 줄일 수 있었다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 춘계학술발표대회
• /
• pp.79-80
• /
• 2023

CPU 와 GPU 의 성능이 지속적으로 발전함에 따라 객체 인식 인공지능의 정확도와 추론 속도는 점차 향상되고 있으나 이러한 성능을 Edge Device 와 같은 제한된 환경에서 구현하기에 아직 여러 한계점이 존재한다. 본 논문에서는 여러가지 Edge Device 에서 객체 인식을 위한 경량화 된 모델 중 하나인 SSD-Mobilenet-V2 를 활용하여 결과값을 통해 각 Device 간 경향성을 분석하였다. 본 결과를 바탕으로 다양한 환경에서의 객체인식 인공지능 모델의 성능 개선을 위한 연구에 활용할 수 있다.

• Journal of information and communication convergence engineering
• /
• 제20권3호
• /
• pp.166-173
• /
• 2022

Recently, studies have been conducted on intelligent transportation systems (ITS) that provide safety and convenience to humans. Systems that compose the ITS adopt architectures that applied the cloud computing which consists of a high-performance general-purpose processor or graphics processing unit. However, an architecture that only used the cloud computing requires a high network bandwidth and consumes much power. Therefore, applying edge computing to ITS is essential for solving these problems. In this paper, we propose an edge artificial intelligence (AI) device based ITS. Edge AI which is applicable to various systems in ITS has been applied to license plate recognition. We implemented edge AI on a field-programmable gate array (FPGA). The accuracy of the edge AI for license plate recognition was 0.94. Finally, we synthesized the edge AI logic with Magnachip/Hynix 180nm CMOS technology and the power consumption measured using the Synopsys's design compiler tool was 482.583mW.