• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1103-1110
• /
• 2022

Due to the rapid development of AI-related industries, countless edge devices are working in the real world. Since data generated within the smart space consisted of these devices is beyond imagination, it is becoming increasingly difficult for edge devices to process. To solve this issue, EdgeCPS has appeared. EdgeCPS is a technology to support harmonious execution of various application services including AI applications through interworking between edge devices and edge servers, and augmenting resources/functions. Therefore, we propose a knowledge-sharing graph-based componentized AI application support system applicable to the EdgeCPS platform. The graph is designed to effectively store information which are essential elements for creating AI applications. In order to easily change resource/function augmentation under the support of the EdgeCPS platform, AI applications are operated as components. The application support system is linked with the knowledge graph so that users can easily create and test applications, and visualizes the execution aspect of the application to users as a pipeline.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.8
• /
• pp.2772-2786
• /
• 2022

We had researched an automatic authentication-supported medical information platform[6]. The proposed automatic authentication consists of user authentication and mobile terminal authentication, and the authentications are performed simultaneously in patients' emergency conditions. In this paper, we studied on finding emergency conditions for the automatic authentication by applying big data processing and AI mechanism on the extended medical information platform with an added edge computing system. We used big data processing, SVM, and 1-Dimension CNN of AI mechanism to find emergency conditions as authentication means considering patients' underlying diseases such as hypertension, diabetes mellitus, and arrhythmia. To quickly determine a patient's emergency conditions, we placed edge computing at the end of the platform. The medical information server derives patients' emergency conditions decision values using big data processing and AI mechanism and transmits the values to an edge node. If the edge node determines the patient emergency conditions, the edge node notifies the emergency conditions to the medical information server. The medical server transmits an emergency message to the patient's charge medical staff. The medical staff performs the automatic authentication using a mobile terminal. After the automatic authentication is completed, the medical staff can access the patient's upper medical information that was not seen in the normal condition.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.3
• /
• pp.549-559
• /
• 2023

As mobile edge computing (MEC) is gaining attention as a core technology of 5G networks, edge AI technology of 5G network environment based on mobile user data is recently being used in various fields. However, as in traditional AI security, there is a possibility of adversarial interference of standard 5G network functions within the core network responsible for edge AI core functions. In addition, research on data poisoning attacks that can occur in the MEC environment of standalone mode defined in 5G standards by 3GPP is currently insufficient compared to existing LTE networks. In this study, we explore the threat model for the MEC environment using NWDAF, a network function that is responsible for the core function of edge AI in 5G, and propose a feature selection method to improve the performance of detecting data poisoning attacks for Leaf NWDAF as some proof of concept. Through the proposed methodology, we achieved a maximum detection rate of 94.9% for Slowloris attack-based data poisoning attacks in NWDAF.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.1-8
• /
• 2024

On-device AI technology, which can operate AI models at the edge devices to support real-time processing and privacy enhancement, is attracting attention. As intelligent IoT is applied to various industries, services utilizing the on-device AI technology are increasing significantly. However, general deep learning models require a lot of computational resources for inference and learning. Therefore, various lightweighting methods such as quantization and pruning have been suggested to operate deep learning models in embedded edge devices. Among the lightweighting methods, we analyze how to lightweight and apply deep learning models to edge computing devices, focusing on pruning technology in this paper. In particular, we utilize dynamic and static pruning techniques to evaluate the inference speed, accuracy, and memory usage of a lightweight AI vision model. The content analyzed in this paper can be used for intelligent video control systems or video security systems in autonomous vehicles, where real-time processing are highly required. In addition, it is expected that the content can be used more effectively in various IoT services and industries.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.107-116
• /
• 2024

In this paper, we analyze the performance of MicroVM when running AI applications on an edge computing environment and whether it can replace current container technology and traditional virtual machines. To achieve this, we set up Docker container, Firecracker MicroVM and KVM virtual machine environments on a Raspberry Pi 4 and executed representative AI applications in each environment. We analyze the inference time, total CPU usage and trends over time and file I/O performance on each environment. The results show that there is no significant performance difference between MicroVM and container when running AI applications. Moreover, on average, a stable inference time over multiple trials was observed on MicroVM. Therefore, we can confirm that executing AI applications using MicroVM instead of container or heavy-weight virtual machine is suitable for an edge computing.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.4
• /
• pp.257-270
• /
• 2022

In this paper, we design a smart factory risk improvement system and risk improvement method using AI edge devices. The smart factory risk improvement system collects, analyzes, prevents, and promptly responds to the worker's work performance process in the smart factory using AI edge devices, and can reduce the risk that may occur during work with improving the defect rate when workers perfom jobs. In particular, based on worker image information, worker biometric information, equipment operation information, and quality information of manufactured products, it is possible to set an abnormal risk condition, and it is possible to improve the risk so that the work is efficient and for the accurate performance. In addition, all data collected from cameras and IoT sensors inside the smart factory are processed by the AI edge device instead of all data being sent to the cloud, and only necessary data can be transmitted to the cloud, so the processing speed is fast and it has the advantage that security problems are low. Additionally, the use of AI edge devices has the advantage of reducing of data communication costs and the costs of data transmission bandwidth acquisition due to decrease of the amount of data transmission to the cloud.

• KNOM Review
• /
• v.22 no.3
• /
• pp.1-12
• /
• 2019

Recently, researching using big data and AI has emerged as a major issue in the ICT field. But, the size of big data for research is growing exponentially. In addition, users of data transmission of existing network method suggest that the problem the time taken to send and receive big data is slower than the time to copy and send the hard disk. Accordingly, researchers require dynamic and flexible network technology that can transmit data at high speed and accommodate various network structures. SDN/NFV technologies can be programming a network to provide a network suitable for the needs of users. It can easily solve the network's flexibility and security problems. Also, the problem with performing AI is that centralized data processing cannot guarantee real-time, and network delay occur when traffic increases. In order to solve this problem, the edge-computing technology, should be used which has moved away from the centralized method. In this paper, we investigate the concept and research trend of SDN, NFV, and edge-computing technologies, and analyze the trends of data central network technologies used by combining these three technologies.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.2
• /
• pp.79-88
• /
• 2024

We used actual field data to analyze from a traffic engineering perspective how AI and edge computing technologies affect the reduction of traffic accidents. By providing object information from 20m behind with AI object recognition, the driver secures a response time of about 3.6 seconds, and with edge technology, information is displayed in 0.5 to 0.8 seconds, giving the driver time to respond to intersection situations. In addition, it was analyzed that stopping before entering the intersection is possible when speed is controlled at 11-12km at the 10m point of the intersection approach and 20km/h at the 20m point. As a result, it was shown that traffic accidents can be reduced when the high object recognition rate of AI technology, provision of real-time information by edge technology, and the appropriate speed management at intersection approaches are executed simultaneously.

• 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.