2020/03/18 by Mohammed S. Hadi, Ahmed Q. Lawey, Hadi, Mohammed S. +5 · 1 citation
Computer Science · Engineering · Social Sciences · #Advanced Computing and Algorithms #FOS: Computer and information sciences #FOS: Electrical engineering #IoT and Edge/Fog Computing #Networking and Internet Architecture (cs.NI) #Signal Processing (eess.SP) #Wireless Body Area Networks #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2003.08239
openalex publication_date 2020/03/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Having a cognitive and self-optimizing network that proactively adapts not\nonly to channel conditions, but also according to its users needs can be one of\nthe highest forthcoming priorities of future 6G Heterogeneous Networks\n(HetNets). In this paper, we introduce an interdisciplinary approach linking\nthe concepts of e-healthcare, priority, big data analytics (BDA) and radio\nresource optimization in a multi-tier 5G network. We employ three machine\nlearning (ML) algorithms, namely, naive Bayesian (NB) classifier, logistic\nregression (LR), and decision tree (DT), working as an ensemble system to\nanalyze historical medical records of stroke out-patients (OPs) and readings\nfrom body-attached internet-of-things (IoT) sensors to predict the likelihood\nof an imminent stroke. We convert the stroke likelihood into a risk factor\nfunctioning as a priority in a mixed integer linear programming (MILP)\noptimization model. Hence, the task is to optimally allocate physical resource\nblocks (PRBs) to HetNet users while prioritizing OPs by granting them high gain\nPRBs according to the severity of their medical state. Thus, empowering the OPs\nto send their critical data to their healthcare provider with minimized delay.\nTo that end, two optimization approaches are proposed, a weighted sum rate\nmaximization (WSRMax) approach and a proportional fairness (PF) approach. The\nproposed approaches increased the OPs average signal to interference plus noise\n(SINR) by 57% and 95%, respectively. The WSRMax approach increased the system\ntotal SINR to a level higher than that of the PF approach, nevertheless, the PF\napproach yielded higher SINRs for the OPs, better fairness and a lower margin\nof error.\n