Big data analytics is one of the state-of-the-art tools to optimize networks and transform them from merely being a blind tube that conveys data, into a cognitive, conscious, and self-optimizing entity that can intelligently adapt according to the needs of its users. This, in fact, can be regarded as one of the highest forthcoming priorities of future networks. In this paper, we propose a system for Out-Patient (OP) centric Long Term Evolution-Advanced (LTE-A) network optimization. Big data harvested from the OPs' medical records, along with current readings from their body sensors are processed and analyzed to predict the likelihood of a life-threatening medical condition, for instance, an imminent stroke. This prediction is used to ensure that the OP is assigned an optimal LTE-A Physical Resource Blocks (PRBs) to transmit their critical data to their healthcare provider with minimal delay. To the best of our knowledge, this is the first time big data analytics are utilized to optimize a cellular network in an OP-conscious manner. The PRBs assignment is optimized using Mixed Integer Linear Programming (MILP) and a real-time heuristic. Two approaches are proposed, the Weighted Sum Rate Maximization (WSRMax) approach and the Proportional Fairness (PF) approach. The approaches increased the OPs' average SINR by 26.6% and 40.5%, respectively. The WSRMax approach increased the system's total SINR to a level higher than that of the PF approach, however, the PF approach reported higher SINRs for the OPs, better fairness and a lower margin of error.
RIOR to the emergence of big data, decisions were made relying on data samples. Consequently, the decisions were semi-optimum [1]. Those ill-informed decisions spanned over different areas from marketing to law enforcement, sports, and healthcare. With the proliferation of social media applications, Internet of Things (IoT) sensors, and Global Positioning System (GPS)-based services, people may now be considered as walking generators of data. The powerful capability of big data analytics in analyzing massive amounts of data and inferring knowledge from it [2] has brought about better predictions paving the way for better decisions.
Healthcare is a vital subject due to its role in people’s lives. The continuous increase in the world population and other factors, like insufficient healthcare budgets, has resulted in crowded hospitals, over-worked medical staff, and extended queuing times for the patients. Given the global nature of the problem, researchers are developing new approaches to improve the level of care delivered by healthcare providers while ensuring a reduction in all previously-mentioned points. Big data can be used to ensure medical service is reaching those most in need, in a timely manner [3]. Big data analytics can provide accurate diagnosis by offering the ability to analyze and infer from the patient’s history, their daily routine, diet, allergies, and genetic information, etc. Such analyses can be time consuming and requires certain level of expertise to be carried out by medical personnel [4]. An example mentioned in [5] reports the use of big data analytics by Columbia University Medical Centre to diagnose complications in patients with bleeding stroke caused by raptured brain aneurysm. Based on physiological data, the diagnosis was reported 48 hours beforehand in patients with brain injuries, which gave the medical professionals a head start to address these complications.
In the healthcare sector, there are many sources of big data, for example; IoT medically-related sensors, smart watches, and smartphone medical applications. What the above-mentioned data generators have in common is their reliance on network connectivity. Maintaining this connectivity and ensuring its quality is a dilemma that many researchers tried to solve optimally. Here, the patient’s big data can play a double role. In addition to diagnosis, it can guide the network operator to the patients who have the highest and most urgent needs, and thus direct their network resources towards these patients. We believe that ensuring high quality connectivity between the patient-linked peripherals and their healthcare provider is an important step towards highly personalized e-healthcare services and applications.
A wireless connection is preferred over a wired one for what it has to offer in terms of mobility. Consequently, cellular and Wi-Fi are the most popular connectivity technologies. The level of freedom (mobility-wise) varies between wireless technologies, for example, Wi-Fi may provide an adequate data rate, nevertheless, it forces an Out-Patient (OP) that needs to keep his/her medical IoT sensor (e.g. IoT pacemaker) connected, to stay within a relatively-small coverage area (i.e., indoors mainly). Utilizing the already-existing cellular networks can provide a much-needed freedom to that OP. However, due to path loss and fading, this approach faces several problems because there might be some blind-spots, deeply-faded locations, where the Signal to Interference plus Noise Ratio (SINR) level is so low that the Patient-Centric Cellular Networks Optimization using Big Data Analytics Mohammed S. Hadi, Ahmed Q. Lawey, Taisir E. H. El-Gorashi and J. M. H Elmirghani P connection is unreliable or cannot be established. In a slow fading channel, this could mean that the signal level may not be adequate at the instant(s) when critical information relating to the OP’s health has to be conveyed immediately to the health care provider. Big data is portrayed in [6] as a next generation tool that can be used to find an optimal trade-off problem between resource sharing, allocation, and optimization in wireless networks. Nevertheless, optimizing cellular networks in a user-centric style is still underexplored. In this paper, we introduce for the first time two OP-conscious approaches optimizing the uplink side of a multi-cell Orthogonal Frequency Division Multiple Access (OFDMA) network. In both models, the objective function prioritizes the OPs by maximizing their SINR received at the Base Station (BS) while keeping the goal of maximizing the network’s overall SINR.
The models comprise an assignment scheme powered by big data analytics where OPs are assigned Physical Resource Blocks (PRBs) with powers proportional to their current medical situation. Fairness was incorporated to minimize the negative impact of such assignment on other users. The models are subject to several power and PRB assignment constrains that govern its
This content is AI-processed based on open access ArXiv data.
