• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.17-22
• /
• 2022

In this paper, we design a lightweight embedded device that can support intelligent edge computing, and show that the device quickly detects an object in an image input from a camera device in real time. The proposed system can be applied to environments without pre-installed infrastructure, such as an intelligent video control system for industrial sites or military areas, or video security systems mounted on autonomous vehicles such as drones. The On-Device AI(Artificial intelligence) technology is increasingly required for the widespread application of intelligent vision recognition systems. Computing offloading from an image data acquisition device to a nearby edge device enables fast service with less network and system resources than AI services performed in the cloud. In addition, it is expected to be safely applied to various industries as it can reduce the attack surface vulnerable to various hacking attacks and minimize the disclosure of sensitive data.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.244-245
• /
• 2022

최근에는 우수한 성능의 딥러닝 기술을 활용한 장비와 프로그램이 개발되고 있으나 기술의 특성상 모든 환경에서 우수한 성능을 보여주지 못하고 고 사양의 서버와 같은 환경에서의 성능만을 보장하고 있다. 따라서 이에 대한 개선으로 엣지 디바이스 독립적으로 혹은 클라우드 의존과 인터넷 연결을 최소화 할 수 있는 엣지 컴퓨팅 기술이 제안되고 있으며 경량 내장형 시스템에 적합한 인공지능 기술의 개발이 필요하다. 본 논문에서는 객체검출 모델을 적은 연산과 효율적인 구조로 설계하고 생성된 모델을 임베디드 보드에서 원활하게 실행할 수 있도록 중립 모델로 변환하고 경량화 하는 방법에 대해 소개한다. Qualcomm snapdragon 프로세서가 갖춰진 임베디드 보드를 목표로 하였고 편의를 위해 SNPE(snapdragon neural processing engine) SDK를 이용하여 실험을 진행하였다. 실험 결과 변환된 중립모델이 기존 모델과 비교하여 압축된 모델 크기 대비 미미한 성능 저하가 발생함을 확인할 수 있었다.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.2
• /
• pp.47-52
• /
• 2023

Mobile Edge Computing(MEC) is considered as a promising technology to effectively support the explosively increasing traffic demands. It can provide low-latency services and reduce network traffic by caching contents at the edge of networks such as Base Station(BS). Although users may associate with the nearest BSs, it is more beneficial to associate users to the BS where the requested content is cached to reduce content download latency. Therefore, in this paper, we propose a mobility-aware joint caching and user association algorithm to imporve the cache hit ratio. In particular, the proposed algorithm performs caching and user association based on sojourn time and content preferences. Simulation results show that the proposed scheme improves the performance in terms of cache hit ratio and latency as compared with existing schemes.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.4
• /
• pp.467-473
• /
• 2020

Recently, the number of traffic accidents has also increased with the increase in the penetration rate of cars in Korea. In particular, not only inter-vehicle accidents but also human accidents near crosswalks are increasing, so that more attention to traffic safety around crosswalks are required. In this paper, we propose a system for predicting the safety level around the crosswalk by recognizing an approaching vehicle and estimating the speed of the vehicle using NVIDIA Jetson Nano-class edge devices. To this end, various machine learning models are trained with the information obtained from deep learning-based vehicle detection to predict the degree of risk according to the speed of an approaching vehicle. Finally, based on experiments using actual driving images and web simulation, the performance and the feasibility of the proposed system are validated.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.33-40
• /
• 2023

As South Korea enters the realm of an super-aging society, the demand for elderly welfare services has been steadily rising. However, the current shortage of welfare personnel has emerged as a social issue. To address this challenge, there is active research underway on elderly care robots designed to mitigate the social isolation of the elderly and provide emergency contact capabilities in critical situations. Nonetheless, these functionalities require direct user contact, which represents a limitation of conventional elderly care robots. In this paper, we propose a solution to overcome these challenges by introducing a care robot system capable of interacting with users without the need for direct physical contact. This system leverages commercialized elderly care robots and cameras. We have equipped the care robot with an edge device that incorporates facial expression recognition and action recognition models. The models were trained and validated using public available data. Experimental results demonstrate high accuracy rates, with facial expression recognition achieving 96.5% accuracy and action recognition reaching 90.9%. Furthermore, the inference times for these processes are 50ms and 350ms, respectively. These findings affirm that our proposed system offers efficient and accurate facial and action recognition, enabling seamless interaction even in non-contact situations.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.92-93
• /
• 2022

As the importance of smart factories is emphasized, the use of industrial Ethernet-based devices is expected to increase to build smart factories. PROFINET is an industrial Ethernet protocol developed by SIEMENS, and a number of smart factories are currently being built as PROFINET-based products. Accordingly, in order to develop and utilize various industrial IoT-based services, an IIoT device capable of collecting various sensor data and information from PROFINET-based manufacturing equipment and transmitting data to an edge computer is required.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.2
• /
• pp.67-72
• /
• 2022

Recently, various intelligent application services using artificial intelligence are being actively developed. In particular, research on artificial intelligence-based real-time prediction services is being actively conducted in the manufacturing industry, and the demand for artificial intelligence services that can detect and predict fire and odors is very high. However, most of the existing detection and prediction systems do not predict the occurrence of fires and odors, but rather provide detection services after occurrence. This is because AI-based prediction service technology is not applied in existing systems. In addition, fire prediction, odor detection and odor level prediction services are services with ultra-low delay characteristics. Therefore, in order to provide ultra-low-latency prediction service, edge computing technology is combined with artificial intelligence models, so that faster inference results can be applied to the field faster than the cloud is being developed. Therefore, in this paper, we propose an LSTM algorithm-based learning model that can be used for fire prediction and odor detection/prediction, which are most required in the manufacturing industry. In addition, the proposed learning model is designed to be implemented in edge devices, and it is proposed to receive real-time sensor data from the IoT terminal and apply this data to the inference model to predict fire and odor conditions in real time. The proposed model evaluated the prediction accuracy of the learning model through three performance indicators, and the evaluation result showed an average performance of over 90%.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.11
• /
• pp.291-296
• /
• 2021

The development of the Internet of Things(IoT) requires large computational resources for tasks from numerous devices. Mobile Edge Computing(MEC) has attracted a lot of attention in the IoT environment because it provides computational resources geographically close to the devices. Task offloading to MEC servers is efficient for devices with limited battery life and computational capability. In this paper, we assumed an industrial IoT environment requiring high reliability. The complexity of optimization problem in industrial IoT environment with many devices and multiple MEC servers is very high. To solve this problem, the problem is divided into two. After selecting the MEC server considering the queue status of the MEC server, we propose an offloading decision algorithm that optimizes reliability and energy consumption using genetic algorithm. Through experiments, we analyze the performance of the proposed algorithm in terms of energy consumption and reliability.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.911-917
• /
• 2023

In today's world, we find ourselves facing energy crises due to factors such as war and climate crises. To prepare for these energy crises, many researchers continue to study systems related to energy monitoring and conservation, such as energy management systems, energy monitoring, and energy conservation. In line with these efforts, nations are making it mandatory for energy-consuming facilities to implement these systems. However, these facilities, limited by space and energy constraints, are exploring ways to improve. This research explores the operation of a data collection system using low-performance embedded devices. In this context, it proves that an optimized version of RocksDB, a Key-Value store, outperforms traditional databases when it comes to time-series data. Furthermore, a comprehensive database evaluation tool was employed to assess various databases, including optimized RocksDB and regular RocksDB. In addition, heterogeneous databases and evaluations are conducted using a UD Benchmark tool to evaluate them. As a result, we were able to see that on devices with low performance, the time required was up to 11 times shorter than that of other databases.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.85-87
• /
• 2018

Motivating by two promising technique of 5G, namely D2D and Edge computing, and the above mentioned problem of the current joint studies, We believe that more study is needed on the benefits of joining these two techniques in a single framework by more precisely taking into account the energy needed to computation, sending data, receiving data and as a result achieving more realistic energy efficiency in 5G cellular networks.