Study of Use Cases for IOT Service Platforms Using AI/ML
Abstract
Many machine learning and artificial intelligence (AI) applications train their models using data gathered from IoT systems. The performance of AI models varies depending on the calibre and volume of data gathered for model training. The IoT platform serves as a hub for gathering and managing a variety of data, including text, photos, and sensory data. Building an effective AI/ML model requires excellent data management (DM). We examined current AI/ML technologies that can be included into an IoT platform in this article. We also look at possible applications for AI/ML services that make use of the information gathered by the IoT platform. In this study, oneM2M, a standardised IoT service layer platform, was used to analyse existing AI/ML technologies and application cases.
References
K. Gupta, N. Jiwani and N. Afreen, "Blood Pressure Detection Using CNN-LSTM Model," 2022 IEEE 11th International Conference on Communication Systems and Network Technologies (CSNT), 2022, pp. 262-366, doi: 10.1109/CSNT54456.2022.9787648.
K. C. A. Khanzode and R. D. Sarode, "Advantages and disadvantages of aie and ml: A literature review", International Journal of Library & Information Science (IJLIS), vol. 9, no. 1, pp. 30-36, 2020.
N. Dilshad, A. Ullah, J. Kim and J. Seo, "Locateuav: Unmanned aerial vehicle location estimation", IEEE Internet of Things Journal, 2022.
N. Jiwani, K. Gupta and N. Afreen, "Automated Seizure Detection using Theta Band," 2022 International Conference on Emerging Smart Computing and Informatics (ESCI), 2022, pp. 1-4, doi: 10.1109/ESCI53509.2022.9758331.
C. Gezer and E. Taskin, "An overview of onem2m standard", 2016 24th SIU, pp. 1705-1708, 2016.
D. Yacchirema and A. Belsapellicer, "OneM2M Based-Interworking Architecture for Heterogeneous Devices Interoperability in IoT", 2018 IEEE Conference on Standards for Communications and Networking CSCN 2018, pp. 1-6, 2018.
Gupta, K., & Jiwani, N. (2021). A systematic Overview of Fundamentals and Methods of Business Intelligence. International Journal of Sustainable Development in Computing Science, 3(3), 31-46.
S. K. Datta and Da Costa, "OneM2M architecture based IoT framework for mobile crowd sensing in smart cities", EUCNC 2016-European Conference on Networks and Communications, no. iii, pp. 168-173, 2016.
I. Senay Tuna and Mehmet, "Interopt: A new testing platform based on onem2m standards for iot systems", 2019 International Symposium on Networks Computers and Communications ISNCC 2019, pp. 1-6, 2019.
N. Jiwani, K. Gupta and N. Afreen, "A Convolutional Neural Network Approach for Diabetic Retinopathy Classification," 2022 IEEE 11th International Conference on Communication Systems and Network Technologies (CSNT), 2022, pp. 357-361, doi: 10.1109/CSNT54456.2022.9787577.