• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.676-678
• /
• 2021

This paper shows the design of edge device for marine and industry IoT sevice. Edge device gather IoT sensing data and then send these data into external network. For transmitting the gathered data, commercial LoRa and LTE Cat.M1 are applied into the edge device.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.20 no.4
• /
• 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.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.5
• /
• 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
• /
• v.73 no.10
• /
• 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%.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.418-420
• /
• 2019

Sensor node and edge device for multi-sensing of marine IoT service is proposed. Especially, the proposed devices are based on the management and data process through the closed network (i.e., private network) as well as the commercial public network provided by major communication service providers.

• Design & Manufacturing
• /
• v.14 no.4
• /
• 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.

• 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.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1688-1696
• /
• 2020

The paradigm of Internet-of-things(IoT) systems is changing from a cloud-based system to an edge-based system to solve delays caused by network congestion, server overload and security issues due to data transmission. However, edge-based IoT systems have fatal weaknesses such as lack of performance and flexibility due to various limitations. To improve performance, application-specific hardware can be implemented in the edge device, but performance cannot be improved except for specific applications due to a fixed function. This paper introduces a edge-centric metamorphic IoT(mIoT) platform that can use a variety of hardware through on-demand partial reconfiguration despite the limited hardware resources of the edge device, so we can increase the performance and flexibility of the edge device. According to the experimental results, the edge-centric mIoT platform that executes the reconfiguration algorithm at the edge was able to reduce the number of server accesses by up to 82.2% compared to previous studies in which the reconfiguration algorithm was executed on the server.

• Annual Conference of KIPS
• /
• 2023.05a
• /
• 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
• /
• v.20 no.3
• /
• 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.