머신러닝 기반의 IoB 리소스 분석 모델 설계 = Design of IoB Resource Analysis Model Based on Machine Learning

국문 초록 (Abstract)

최근 IoT 기술이 발달하면서 IoT 기술은 다양한 지능형 장치를 통해 실시간으로 데이터를 지속적으로 처리할 수 있는 클라우드 환경에 사용되고 있다. 특히, IoT 기술은 AI, 분산 컴퓨팅, 사용자의 단순/복잡한 인터넷 활동 등에서 수집된 정보를 활용한 IoB 분야가 최근 각광을 받고 있다. 그러나, IoB 정보를 활용하는 여러 분야에서 IoB 정보의 정확성 및 효율성을 향상하는 방안들이 현재 부족한 상황이다. 본 논문에서는 머신러닝 기반의 IoB 리소스를 효과적으로 분석할 수 있는 분석 모델을 제안한다. 제안 모델은 IoB 리소스를 클라우드 환경에 있는 서버로 전송할 때 머신러닝을 통해 IoB 리소스를 분석하고 특정 정보들을 추출할 수 있도록 IoB 데이터 셋을 생성한다. 제안 모델은 IoB 리소스가 클라우드 환경에서 지속적으로 교환이 유지할 수 있도록 블록체인으로 IoB 리소스를 계층적으로 묶어 처리한다. 제안 모델은 IoB 리소스를 블록체인에 추가함으로써 네트워크에 연결된 장치에 대한 안정적인 상호 연결이 가능하도록 네트워를 메시 네트워크로 구성한다 이 같은 네트워크 구성은 IoB의 분산 접근이 가능하고 단일 장애 지점을 효과적으로 방지하고 탄력적으로 운영할 수 있다. 또한, 제안 모델은 저 비용으로 효율적인 IoB 연속 학습을 수행하기 때문에 IoB 정보의 병목 현상, IoB 처리 리소스의 지연, 네트워크 오버헤드를 최소화하였다.

다국어 초록 (Multilingual Abstract)

With the recent development of IoT technology, IoT technology is being used in a cloud environment that can continuously process data in real time through various intelligent devices. In particular, IoT technology has recently attracted attention in the field of IoB using information collected from AI, distributed computing, and simple/complex Internet activities of users. However, measures to improve the accuracy and efficiency of IoB information in various fields using IoB information are currently lacking. In this paper, we propose an analysis model that can effectively analyze machine learning-based IoB resources. The proposed model creates an IoB dataset to allow machine learning to analyze IoB resources and extract specific information when transferring IoB resources to servers in a cloud environment. The proposed model combines and processes IoB resources hierarchically in a blockchain so that IoB resources can be continuously exchanged in a cloud environment. The proposed model configures the network as a mesh network to enable stable interconnections to devices connected to the network by adding IoB resources to the blockchain. Such a network configuration allows IoB distributed access, effectively prevents a single point of failure, and operates flexibly. In addition, the proposed model minimizes bottlenecks in IoB information, delays in IoB processing resources, and network overhead because it performs efficient IoB continuous learning at low cost.

참고문헌 (Reference)

• 1 정윤수, "행동 인터넷 기반 생산성 향상을 위한 산업 현장의 효율적인 데이터 처리 모델" 융복합지식학회 11 (11): 39-47, 2023
• 2 Boddington, G., "The Internet of Bodies-alive, Connected, and Collective : the Virtual Physical Future of Our Bodies and Our Senses" 38 (38): 1-17, 2021
• 3 Mäkitalo, N., "The Internet of Bodies Needs a Human Data Model" 24 (24): 28-37, 2020
• 4 Celik, A., "The Internet of Bodies : Asystematic Survey on Propagation Characterization and Channel Modeling" 9 (9): 321-345, 2022
• 5 Gao, M., "Power Generation for Wearable Systems" 14 (14): 2114-2157, 2021
• 6 Liu, Y., "Optimization Strategy Based on Deep Reinforcement Learning for Home Energy Management" 6 (6): 572-582, 2020
• 7 Albon, C., "Machine Learning with Python Cookbook" Hanbit Media, Inc. 2019
• 8 Iob, E., "Levels of Severity of Depressive Symptoms among At-risk Groups in the UK during the COVID-19 Pandemic" 3 (3): e2026064-, 2020
• 9 Muller, A., "Introduction to Machine Learning with Python" Hanbit Media, Inc 2017
• 10 Taylor, M. C., "Intervolution" Columbia University Press 2021
• 11 Blake, M. B., "Internet of Bodies/Internet of Sports" 24 (24): 8-9, 2020
• 12 O’Driscoll, R., "Improving Energy Expenditure Estimates from Wearable Devices : a Machine Learning Approach" 38 (38): 1496-1505, 2020
• 13 Syed, D., "Household-level Energy Forecasting in Smart Buildings using a Novel Hybrid Deep Learning Model" 9 : 33498-33511, 2021
• 14 Wei, K., "Health Monitoring based on the Internet of Medical Things : Architecture, Enabling Technologies, and Applications" 8 : 27468-27478, 2020
• 15 Khan, S., "Health Informatics: A Computational Perspective in Healthcare" Springer Nature 2021
• 16 El-Khoury, M., "From the Internet of Things Toward the Internet of Bodies : Ethical and Legal Considerations" 30 (30): 307-314, 2021
• 17 Indrakumari, R., "Emergence of Pharmaceutical Industry Growth with Industrial IoT Approachs" Elsevier, Academic Press, India 2020
• 18 Chung, H. -M., "Distributed Deep Reinforcement Learning for Intelligent Load Scheduling in Residential Smart Grids" 17 (17): 2752-2763, 2020
• 19 Li, X., "Building the Internet of Things Platform for Smart Maternal Healthcare Services with Wearable Devices and Cloud Computing" 118 : 282-296, 2021
• 20 Kazansky, B., "Bodies not Templates : Contesting Dominant Algorithmic Imaginaries" 23 (23): 363-381, 2021
• 21 Kim, S. -H., "An Accelerated Edge Cloud System for Energy Data Stream Processing based on Adaptive Incremental Deep Learning Scheme" 8 : 195341-195358, 2020
• 22 Aileni, R. M., "Advances in Cyber Security Analytics and Decision Systems" Springer 2020
• 23 Poongodi, T., "A Handbook of Internet of Things in a Biomedical and Cyber Physical System" Springer 2020