Resource Management in Healthcare IoT Networks Using Machine Learning for Accuracy Enhancement
DOI:
https://doi.org/10.21467/proceedings.7.6.31Keywords:
Internet of Things, machine learning, resource allocationAbstract
The objective of this paper was to improve the accuracy of resource management in IoT healthcare environments using machine learning models. A simulated dataset was created that considered client conditions, resource skills, and familiarity factors. Interactions were predicted using a Multiclass neural network and XGBoost decision tree models. The prediction model was trained and deployed using Azure ML Studio, which was integrated into the real-time framework of Azure IoT Hub. Results showed that predicted resource selection improved client satisfaction compared to random allocation. The study concluded that ML models are effective in resource optimization and can be deployed in real-time IoT environments. This instance involves an organization supplier managing IoT resources through machine learning. This might be a service provider, a business that fixes equipment, or a hospital where patients are the clients and the medical staff provides the service. The client rates the outcome of each encounter between a client and a resource on a three-point scale ('-1' for a poor interaction, '0' for a neutral interaction, and '+1' for a positive interaction). The score the following interaction with a certain resource, this collection of interactions is merged with the circumstances business keeps a note of these interactions as well as the conditions that led to them. To train a predictor for how the client would that led to the interactions. Resources are allocated to the highest-rated predictions to maximize client satisfaction.
References
[1] F. Hussain, Internet of Things; Building Blocks and Business Models. Springer, 2017[2] Fatima Hussain, Syed Ali Hassan, Rasheed Hussain, Ekram Hossain “Machine Learning for Resource Management in Cellular and IoT Networks: Potentials, Current Solutions, and Open Challenges,” arXiv:1907.08965v1 [cs.NI] 21 Jul 2019.
[2] D. B. J. Sen, “Internet of Things - Applications and Challenges in Technology and Standardization,” IEEE Transactions in Wireless Personal Communication, May 2011.
[3] D. Wang, D. Chen, B. Song, N. Guizani, X. Yu, X. Du “From IoT to 5G I-IoT: The next generation IoT-based intelligent algorithms and 5G technologies”, IEEE Commun. Mag. 56 (10) (2018) 114–120.
[4] U. S. Shanthamallu, A. Spanias, C. Tepedelenlioglu, and M. Stanley, “A Brief Survey of Machine Learning Methods and their Sensor and IoT Applications,” IEEE Conference on Information, Intelligence, Systems and Applications, March 2018.
[5] Q. et al., “Real-time multi-application network traffic identification based on machine learning,” in Springer, vol. 92, 2015, pp. 473– 480.
[6] Dan Wanga, Hao Qin, Bin Song, Ke Xu, Xiaojiang Du, Mohsen Guizani “Joint resource allocation and power control for D2D communication with deep reinforcement learning in MCC” Elsevier.
[7] Mark Eisen_ Clark Zhang_ Luiz F. O.Chamon_ Daniel D. Leey Alejandro Ribeiro_ “Learning Optimal Resource Allocations in Wireless Systems” 1053-587X (c) 2018 IEEE.
[8] T. et al., “Machine learning-based classification of encrypted internet traffic,” in Springer, 2017, p. 578592.
[9] Xiaolin Ma, Shiwen Ning, Xinhua Liu, Hailan Kuang, Youying Hong “Cooperative Spectrum Sensing using Extreme Learning Machine for Cognitive Radio Networks with Multiple Primary Users” IEEE 978-1-5386-4509-3
[10] P. Lynggaard, “Using machine learning for adaptive interference suppression in wireless sensor networks,” IEEE Sensors Journal, vol. 18, no. 21, pp. 8820–8826, Nov 2018
[11] Rathinaraja Jeyaraj, Anandkumar Balasubramaniam, Ajay Kumar M.A., Nadra Guizani, Anand Paul Authors Info & Claims “Resource Management in Cloud and Cloud-influenced Technologies for Internet of Things Applications” ACM Computing Surveys, Volume 55, Issue 12 Article No.: 242, Pages 1 – 37 March 2023
[12] Muhammad Fahimullah , Shohreh Ahvar, Mihir Agarwal & Maria Trocan “Machine learning-based solutions for resource management in fog computing” arXiv:2209.03066 volume 83, pages 23019-23045,(2024) https://doi.org/10.1145/3571729 Aug 2023
[13] Alhusein Almahjoub , Dongyu Qiu “A Grant-Free Random-Access Process for Low-End Distribution System Using Deep Neural Network” Appl. Sci. 2022, 12(14), 7070; https://doi.org/10.3390/app12147070.
[14] https://github.com/madsenmj/ml-iot-resource-allocation/blob/master/README.md
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
