• Smart Media Journal
• /
• 제12권4호
• /
• pp.19-26
• /
• 2023

IoT edge services utilizing neuromorphic hardware architectures are suitable for autonomous IoT applications as they perform intelligent processing on the device itself. However, spiking neural networks applied to neuromorphic hardware are difficult for IoT developers to comprehend due to their complex structures and various hyper-parameters. In this paper, we propose a method for generating spiking neural network (SNN) models that satisfy user performance requirements while considering the constraints of neuromorphic hardware. Our proposed method utilizes previously trained models from pre-processed data to find optimal SNN model parameters from profiling data. Comparing our method to a naive search method, both methods satisfy user requirements, but our proposed method shows better performance in terms of runtime. Additionally, even if the constraints of new hardware are not clearly known, the proposed method can provide high scalability by utilizing the profiled data of the hardware.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• 제15권4호
• /
• 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.

• Smart Media Journal
• /
• 제12권7호
• /
• pp.27-42
• /
• 2023

The development of cloud services and IoT technology has radically changed the cloud environment, and has evolved into a new concept called fog computing and F2C (fog-to-cloud). However, as heterogeneous cloud/fog layers are integrated, problems of access control and security management for end users and edge devices may occur. In this paper, an F2C-based IoT smart health monitoring system architecture was designed to operate a medical information service that can quickly respond to medical emergencies. In addition, a role-based service access control technology was proposed to enhance the security of user's personal health information and sensor information during service interoperability. Through simulation, it was shown that role-based access control is achieved by sharing role registration and user role token issuance information through blockchain. End users can receive services from the device with the fastest response time, and by performing service access control according to roles, direct access to data can be minimized and security for personal information can be enhanced.

• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2019년도 추계학술발표대회
• /
• pp.60-62
• /
• 2019

지능형 IoT 애플리케이션들을 효과적으로 사용하기 위해서는 추론 엔진을 Edge device로 포팅하는 것이 필수적이다. 그러나 컴퓨팅 자원이 제한적인 Edge 환경에서 computational cost가 상당히 큰 CNN 추론을 실시간으로 하는 것은 쉽지 않다. 이에, CNN 추론의 하드웨어 가속화의 필요성이 제기되어 활발한 연구가 진행되고 있으며, Xilinx, Intel 등에서도 하드웨어 가속화를 도와주는 툴을 개발하여 지속적으로 업그레이드하고 있다. 본 연구에서는 CIFAR-10 데이터베이스의 테스트 이미지 10,000개를 Xilinx 사의 CNN 추론 엔진인 DPU를 사용하여 Zynq UltraScale+ 보드에서 추론해보고, DPU 아키텍처에 따른 결과를 비교·분석했다. 병렬처리 수준을 높게 한 DPU는 그렇지 않은 DPU보다 소비전력 및 자원 사용량이 3배 이상 높았지만, 1.65배 좋은 성능을 보여 Trade-off 관계를 확인할 수 있었다.

• Electronics and Telecommunications Trends
• /
• 제34권5호
• /
• pp.58-70
• /
• 2019

In this paper, we present the R&D status of ETRI's Trusted Reality (TR) project and its core technologies. ETRI's TR project focuses on the next-generation paradigm of smart phones, ETRI-TR Smart Glasses, which aims to provide the same features as those of smart phones without the involvement of any handheld device. Furthermore, they are characterized by additional features enabled by trustworthy VR/AR/MR/XR, such as privacy masking/unmasking, distributed structure of thin-client computing/networking among TR-Glasses, TR-LocalEdge, and TR-RemoteEdge, with novel see-through eyes-direct communication between IoT real/virtual objects and human eyes. Based on these core technologies of the ETRI's TR project, the human-held ETRI-TR Smart Glasses is expected to aid in the realization of XR vision with particularly more XR's safe_privacy on social life in the near future.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권10호
• /
• pp.2732-2749
• /
• 2023

Device-to-Device (D2D) communication has received increasing attention and been studied extensively thanks to its advantages in improving spectral efficiency and energy efficiency of cellular networks. This paper proposes a novel relay selection algorithm for multi-hop full-duplex D2D communications underlaying cellular networks. By selecting the relay of each hop in a reverse manner, the proposed algorithm reduces the heavy signaling overhead that traditional relay selection algorithms introduce. In addition, the social domain information of mobile terminals is taken into consideration and its influence on the performance of D2D communications studied, which is found significant enough not to be overlooked. Moreover, simulations show that the proposed algorithm, in absence of social relationship information, improves data throughput by around 70% and 7% and energy efficiency by 64% and 6%, compared with two benchmark algorithms, when D2D distance is 260 meters. In a more practical implementation considering social relationship information, although the proposed algorithm naturally achieves less throughput, it substantially increases the energy efficiency than the benchmarks.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제26권1호
• /
• pp.1-6
• /
• 2022

Recently, IoT sensors are often used to produce stream data locally and they are provided for edge computing applications. Mass-produced data are stored in the mobile device's database for real-time processing and then synchronized with the server when needed. Many mobile databases are developed to support those applications. They are CloudScape, DB2 Everyplace, ASA, PointBase Mobile, etc, and the most widely used database is SQLite3 on Linux. In this paper, we focused on the performance required for synchronization with the server. The search performance required to retrieve SQLite3 was compared and analyzed according to the type of each Linux file system in which the database is stored. Thus, performance differences were checked for each file system according to various search query types, and criteria for applying the more appropriate Linux file system according to the index use environment and table scan environment were prepared and presented.

• ETRI Journal
• /
• 제39권2호
• /
• pp.202-212
• /
• 2017

With the advent of the Internet-of-Things paradigm, the amount of data production has grown exponentially and the user demand for responsive consumption of data has increased significantly. Herein, we present DART, a fast and lightweight stream processing framework for the IoT environment. Because the DART framework targets a geospatially distributed environment of heterogeneous devices, the framework provides (1) an end-user tool for device registration and application authoring, (2) automatic worker node monitoring and task allocations, and (3) runtime management of user applications with fault tolerance. To maximize performance, the DART framework adopts an actor model in which applications are segmented into microtasks and assigned to an actor following a single responsibility. To prove the feasibility of the proposed framework, we implemented the DART system. We also conducted experiments to show that the system can significantly reduce computing burdens and alleviate network load by utilizing the idle resources of intermediate edge devices.

• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2018년도 추계학술발표대회
• /
• pp.139-142
• /
• 2018

최근, Industry과 IoT 기기의 보급으로 인하여 수많은 센서와 액추에이터, 모바일 기기 등이 Cyber-Physical System을 통해 네트워크와 연결되며, 더 효율적인 시스템을 요규한다. 이를 위하여, EdgeX와 SDN을 활용하여 빠르고 효율적인 네트워크 서비스를 제공한다. 따라서 본 논문에서는 CPS 기반의 Reinforcement Learning을 활용한 Rotary Inverted Pendulum System을 통해 실시간으로 빠르고 안전한 네트워크 서비스를 제공할 수 CPS 아키텍처를 구현한다.

• KIPS Transactions on Computer and Communication Systems
• /
• 제11권7호
• /
• pp.217-224
• /
• 2022

Today, with the development of technology and industry, fire accidents in special buildings are increasing as special buildings increase. However, despite the rapid development of information and communication technology, human casualties are steadily occurring due to the underdeveloped and ineffective indoor fire alarm system. In this study, we confirmed that the existing indoor fire alarm system using acoustic alarm could not deliver a sufficiently large alarm to the in-room personnel. To improve this, we designed and implemented a fire alarm system using edge computing and beacons. The proposed improved fire alarm system consists of terminal sensor nodes, edge nodes, a user application, and a server. The terminal sensor nodes collect indoor environment data and send it to the edge node, and the edge node monitors whether a fire occurs through the transmitted sensor value. In addition, the edge node continuously generate beacon signals to collect information of smart devices with user applications installed within the signal range, store them in a server database, and send application push-type fire alarms to all in-room personnel based on the collected user information. As a result of conducting a signal valid range measurement experiment in a university building with dense lecture rooms, it was confirmed that device information was normally collected within the beacon signal range of the edge node and a fire alarm was quickly sent to specific users. Through this, it was confirmed that the "blind spot problem of the alarm" was solved by flexibly collecting information of visitors that changes time to time and sending the alarm to a smart device very adjacent to the people. In addition, through the analysis of the experimental results, a plan to effectively apply the proposed fire alarm system according to the characteristics of the indoor space was proposed.