• ETRI Journal
• /
• 제35권2호
• /
• pp.207-217
• /
• 2013

This paper introduces the modular cellular neural network (CNN), which is a new CNN structure constructed from nine one-layer modules with intercellular interactions between different modules. The new network is suitable for implementing many image processing operations. Inputting an image into the modules results in nine outputs. The topographic characteristic of the cell interactions allows the outputs to introduce new properties for image processing tasks. The stability of the system is proven and the performance is evaluated in several image processing applications. Experiment results on texture segmentation show the power of the proposed structure. The performance of the structure in a real edge detection application using the Berkeley dataset BSDS300 is also evaluated.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2020년도 제61차 동계학술대회논문집 28권1호
• /
• pp.63-64
• /
• 2020

본 논문에서는 딥러닝을 이용한 작업자 위험 행동 모니터링 선행 연구에 기반해, 엣지 컴퓨팅 기반 딥러닝을 사용하여 클라우드에 대한 의존성 문제를 해결하였다. 작업자는 IoT 안전벨트와 영상 전송 안전모를 통해 정보를 수집, 처리한다. 또한 LSTM 방식에서 개량된 필터를 통한 FFNN 딥러닝 방법을 사용하여 작업자 위험 행동 패턴 분석을 하며 선행 연구의 작업자 행동 모니터링 시스템을 엣지 컴퓨팅 기반 위에서 구현하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권11호
• /
• pp.3970-3990
• /
• 2021

In view of the problems of insufficient data collection and processing capability of multi-source heterogeneous equipment, and low visibility of equipment status at the ship block construction site. A data collection method for ship block construction equipment based on wireless sensor network (WSN) technology and a data processing method based on edge computing were proposed. Based on the Browser/Server (B/S) architecture and the OneNET platform, an online monitoring system for ship block construction equipment was designed and developed, which realized the visual online monitoring and management of the ship block construction equipment status. Not only that, the feasibility and reliability of the monitoring system were verified by using the intelligent tire frame system as the application object. The research of this project can lay the foundation for the ship block construction equipment management and the ship block intelligent construction, and ultimately improve the quality and efficiency of ship block construction.

• International Journal of Internet, Broadcasting and Communication
• /
• 제11권4호
• /
• pp.76-85
• /
• 2019

We introduce a vision-based object detection method for real-time video surveillance system in low-end edge computing environments. Recently, the accuracy of object detection has been improved due to the performance of approaches based on deep learning algorithm such as Region Convolutional Neural Network(R-CNN) which has two stage for inferencing. On the other hand, one stage detection algorithms such as single-shot detection (SSD) and you only look once (YOLO) have been developed at the expense of some accuracy and can be used for real-time systems. However, high-performance hardware such as General-Purpose computing on Graphics Processing Unit(GPGPU) is required to still achieve excellent object detection performance and speed. To address hardware requirement that is burdensome to low-end edge computing environments, We propose sub-frame analysis method for the object detection. In specific, We divide a whole image frame into smaller ones then inference them on Convolutional Neural Network (CNN) based image detection network, which is much faster than conventional network designed forfull frame image. We reduced its computationalrequirementsignificantly without losing throughput and object detection accuracy with the proposed method.

• 인터넷정보학회논문지
• /
• 제23권5호
• /
• pp.17-23
• /
• 2022

Network slicing is a promising paradigm and significant evolution for adjusting the heterogeneous services based on different requirements by placing dynamic virtual network functions (VNF) forwarding graph (VNFFG) and orchestrating service function chaining (SFC) based on criticalities of Quality of Service (QoS) classes. In system architecture, software-defined networks (SDN), network functions virtualization (NFV), and edge computing are used to provide resourceful data view, configurable virtual resources, and control interfaces for developing the modified deep reinforcement learning agent (MDRL-A). In this paper, task requests, tolerable delays, and required resources are differentiated for input state observations to identify the non-critical/critical classes, since each user equipment can execute different QoS application services. We design intelligent slicing for handing the cross-domain resource with MDRL-A in solving network problems and eliminating resource usage. The agent interacts with controllers and orchestrators to manage the flow rule installation and physical resource allocation in NFV infrastructure (NFVI) with the proposed formulation of completion time and criticality criteria. Simulation is conducted in SDN/NFV environment and capturing the QoS performances between conventional and MDRL-A approaches.

• Journal of Information Processing Systems
• /
• 제18권3호
• /
• pp.443-456
• /
• 2022

An efficient and reasonable resource allocation strategy can greatly improve the service quality of Internet of Vehicles (IoV). However, most of the current allocation methods have overestimation problem, and it is difficult to provide high-performance IoV network services. To solve this problem, this paper proposes a network resource allocation strategy based on deep learning network model DDQN. Firstly, the method implements the refined modeling of IoV model, including communication model, user layer computing model, edge layer offloading model, mobile model, etc., similar to the actual complex IoV application scenario. Then, the DDQN network model is used to calculate and solve the mathematical model of resource allocation. By decoupling the selection of target Q value action and the calculation of target Q value, the phenomenon of overestimation is avoided. It can provide higher-quality network services and ensure superior computing and processing performance in actual complex scenarios. Finally, simulation results show that the proposed method can maintain the network delay within 65 ms and show excellent network performance in high concurrency and complex scenes with task data volume of 500 kbits.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권8호
• /
• pp.2490-2506
• /
• 2022

In Mobile Edge Computing (MEC), attackers can speculate and mine sensitive user information by eavesdropping wireless channel status and offloading usage pattern, leading to user privacy leakage. To solve this problem, this paper proposes a Privacy-preserving and Energy-efficient Offloading Algorithm (PEOA) based on Lyapunov optimization. In this method, a continuous Markov process offloading model with a buffer queue strategy is built first. Then the amount of privacy of offloading usage pattern in wireless channel is defined. Finally, by introducing the Lyapunov optimization, the problem of minimum average energy consumption in continuous state transition process with privacy constraints in the infinite time domain is transformed into the minimum value problem of each timeslot, which reduces the complexity of algorithms and helps obtain the optimal solution while maintaining low energy consumption. The experimental results show that, compared with other methods, PEOA can maintain the amount of privacy accumulation in the system near zero, while sustaining low average energy consumption costs. This makes it difficult for attackers to infer sensitive user information through offloading usage patterns, thus effectively protecting user privacy and safety.

• Journal of Information Processing Systems
• /
• 제17권4호
• /
• pp.721-736
• /
• 2021

For the mobile edge computing (MEC) system supporting dense network, a joint allocation algorithm of computing and communication resources based on reinforcement learning is proposed. The energy consumption of task execution is defined as the maximum energy consumption of each user's task execution in the system. Considering the constraints of task unloading, power allocation, transmission rate and calculation resource allocation, the problem of joint task unloading and resource allocation is modeled as a problem of maximum task execution energy consumption minimization. As a mixed integer nonlinear programming problem, it is difficult to be directly solve by traditional optimization methods. This paper uses reinforcement learning algorithm to solve this problem. Then, the Markov decision-making process and the theoretical basis of reinforcement learning are introduced to provide a theoretical basis for the algorithm simulation experiment. Based on the algorithm of reinforcement learning and joint allocation of communication resources, the joint optimization of data task unloading and power control strategy is carried out for each terminal device, and the local computing model and task unloading model are built. The simulation results show that the total task computation cost of the proposed algorithm is 5%-10% less than that of the two comparison algorithms under the same task input. At the same time, the total task computation cost of the proposed algorithm is more than 5% less than that of the two new comparison algorithms.

• 융합보안논문지
• /
• 제22권1호
• /
• pp.71-79
• /
• 2022

정보기술과 전력 공급 시스템을 결합하여 전력 공급자와 소비자 간의 실시간 정보 교환을 통해 에너지 효율을 극대화하는 스마트 그리드 시스템이 등장했다. 중앙 클라우드 서버와 스마트 그리드 IoT 기기 사이에서 전력 관련 정보 수집 및 데이터저장 처리하는 엣지 서버를 활용하여 스마트 그리드 시스템을 위한 블록체인 기반의 사용자 인증 기법이 제안되고 있다. 최근, 스마트 그리드 환경에서 보안을 강화하기 위해 인증 방식이 제안되고 있지만 여전히 많은 취약점이 보고되고 있다. 본 논문은 블록체인을 이용한 엣지 컴퓨팅 기반의 스마트 그리드에서 사용자의 프라이버시와 익명성을 보장하기 위한 새로운 상호 인증 기법을 제시한다. 제안된 방식에서는 키 자료 업데이트 및 폐기와 같은 키 관리의 효율성을 위해 스마트 계약을 사용합니다. 마지막으로 제안하는 기법이 사용자의 스마트 그리드-IoT 기기와 에지 서버 간의 세션 키를 안전하게 설정함과 동시에 익명성을 보장함을 증명한다.

• 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.