2019/03/14 by Mohammed Hadi, Hadi, Mohammed, Ahmed Q. Lawey +5
Computer Science · Engineering · #Age of Information Optimization #Computers and Society (cs.CY) #FOS: Computer and information sciences #IoT and Edge/Fog Computing #Wireless Body Area Networks
paper · pdf · doi:10.48550/arxiv.1903.06045
openalex publication_date 2019/03/14 · openalex created_date 2022/07/29 · openalex updated_date 2026/07/28
In this paper, we introduce machine learning approaches that are used to\nprioritize outpatients (OP) according to their current health state, resulting\nin self-optimizing heterogeneous networks (HetNet) that intelligently adapt\naccording to users' needs. We use a na "ive Bayesian classifier to analyze data\nacquired from OPs' medical records, alongside data from medical Internet of\nThings (IoT) sensors that provide the current state of the OP. We use this\nmachine learning algorithm to calculate the likelihood of a life-threatening\nmedical condition, in this case an imminent stroke. An OP is assigned\nhigh-powered resource blocks (RBs) according to the seriousness of their\ncurrent health state, enabling them to remain connected and send their critical\ndata to the designated medical facility with minimal delay. Using a mixed\ninteger linear programming formulation (MILP), we present two approaches to\noptimizing the uplink side of a HetNet in terms of user-RB assignment: a\nWeighted Sum Rate Maximization (WSRMax) approach and a Proportional Fairness\n(PF) approach. Using these approaches, we illustrate the utility of the\nproposed system in terms of providing reliable connectivity to medical IoT\nsensors, enabling the OPs to maintain the quality and speed of their\nconnection. Moreover, we demonstrate how system response can change according\nto alterations in the OPs' medical conditions.\n